diff --git "a/experiment/rwkv-x-exp/v5-memory/v5-L96-D1024-E1e-1-ctx4k-part5.ipynb" "b/experiment/rwkv-x-exp/v5-memory/v5-L96-D1024-E1e-1-ctx4k-part5.ipynb" --- "a/experiment/rwkv-x-exp/v5-memory/v5-L96-D1024-E1e-1-ctx4k-part5.ipynb" +++ "b/experiment/rwkv-x-exp/v5-memory/v5-L96-D1024-E1e-1-ctx4k-part5.ipynb" @@ -3,13 +3,13 @@ { "attachments": {}, "cell_type": "markdown", - "id": "46576376", + "id": "f1d7ccda", "metadata": { "papermill": { - "duration": 0.00263, - "end_time": "2023-09-02T08:41:08.904462", + "duration": 0.002567, + "end_time": "2023-09-02T06:16:28.958047", "exception": false, - "start_time": "2023-09-02T08:41:08.901832", + "start_time": "2023-09-02T06:16:28.955480", "status": "completed" }, "tags": [] @@ -28,13 +28,13 @@ { "attachments": {}, "cell_type": "markdown", - "id": "85f150d0", + "id": "54efc4fa", "metadata": { "papermill": { - "duration": 0.001681, - "end_time": "2023-09-02T08:41:08.908102", + "duration": 0.001679, + "end_time": "2023-09-02T06:16:28.961787", "exception": false, - "start_time": "2023-09-02T08:41:08.906421", + "start_time": "2023-09-02T06:16:28.960108", "status": "completed" }, "tags": [] @@ -46,19 +46,19 @@ { "cell_type": "code", "execution_count": 1, - "id": "f904d7f9", + "id": "8b4caf1b", "metadata": { "execution": { - "iopub.execute_input": "2023-09-02T08:41:08.912507Z", - "iopub.status.busy": "2023-09-02T08:41:08.912330Z", - "iopub.status.idle": "2023-09-02T08:41:09.629380Z", - "shell.execute_reply": "2023-09-02T08:41:09.628542Z" + "iopub.execute_input": "2023-09-02T06:16:28.967200Z", + "iopub.status.busy": "2023-09-02T06:16:28.966328Z", + "iopub.status.idle": "2023-09-02T06:16:29.684585Z", + "shell.execute_reply": "2023-09-02T06:16:29.683732Z" }, "papermill": { - "duration": 0.721494, - "end_time": "2023-09-02T08:41:09.631404", + "duration": 0.722814, + "end_time": "2023-09-02T06:16:29.686619", "exception": false, - "start_time": "2023-09-02T08:41:08.909910", + "start_time": "2023-09-02T06:16:28.963805", "status": "completed" }, "tags": [] @@ -74,19 +74,19 @@ { "cell_type": "code", "execution_count": 2, - "id": "222e5b4f", + "id": "6cc3a721", "metadata": { "execution": { - "iopub.execute_input": "2023-09-02T08:41:09.636778Z", - "iopub.status.busy": "2023-09-02T08:41:09.636579Z", - "iopub.status.idle": "2023-09-02T08:41:12.546148Z", - "shell.execute_reply": "2023-09-02T08:41:12.545350Z" + "iopub.execute_input": "2023-09-02T06:16:29.691742Z", + "iopub.status.busy": "2023-09-02T06:16:29.691539Z", + "iopub.status.idle": "2023-09-02T06:16:32.527158Z", + "shell.execute_reply": "2023-09-02T06:16:32.526387Z" }, "papermill": { - "duration": 2.914378, - "end_time": "2023-09-02T08:41:12.548071", + "duration": 2.840419, + "end_time": "2023-09-02T06:16:32.529061", "exception": false, - "start_time": "2023-09-02T08:41:09.633693", + "start_time": "2023-09-02T06:16:29.688642", "status": "completed" }, "tags": [] @@ -118,19 +118,19 @@ { "cell_type": "code", "execution_count": 3, - "id": "52f966a7", + "id": "6c3b0fbe", "metadata": { "execution": { - "iopub.execute_input": "2023-09-02T08:41:12.553617Z", - "iopub.status.busy": "2023-09-02T08:41:12.553422Z", - "iopub.status.idle": "2023-09-02T08:41:12.560017Z", - "shell.execute_reply": "2023-09-02T08:41:12.559418Z" + "iopub.execute_input": "2023-09-02T06:16:32.534904Z", + "iopub.status.busy": "2023-09-02T06:16:32.534704Z", + "iopub.status.idle": "2023-09-02T06:16:32.541251Z", + "shell.execute_reply": "2023-09-02T06:16:32.540683Z" }, "papermill": { - "duration": 0.010711, - "end_time": "2023-09-02T08:41:12.561162", + "duration": 0.010568, + "end_time": "2023-09-02T06:16:32.542402", "exception": false, - "start_time": "2023-09-02T08:41:12.550451", + "start_time": "2023-09-02T06:16:32.531834", "status": "completed" }, "tags": [] @@ -193,19 +193,19 @@ { "cell_type": "code", "execution_count": 4, - "id": "5969a736", + "id": "2bb9275c", "metadata": { "execution": { - "iopub.execute_input": "2023-09-02T08:41:12.566119Z", - "iopub.status.busy": "2023-09-02T08:41:12.565958Z", - "iopub.status.idle": "2023-09-02T08:41:46.796618Z", - "shell.execute_reply": "2023-09-02T08:41:46.795641Z" + "iopub.execute_input": "2023-09-02T06:16:32.547321Z", + "iopub.status.busy": "2023-09-02T06:16:32.547162Z", + "iopub.status.idle": "2023-09-02T06:17:41.766730Z", + "shell.execute_reply": "2023-09-02T06:17:41.765728Z" }, "papermill": { - "duration": 34.234865, - "end_time": "2023-09-02T08:41:46.798178", + "duration": 69.223979, + "end_time": "2023-09-02T06:17:41.768492", "exception": false, - "start_time": "2023-09-02T08:41:12.563313", + "start_time": "2023-09-02T06:16:32.544513", "status": "completed" }, "tags": [] @@ -215,7 +215,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "--2023-09-02 08:41:12-- https://huggingface.co/rwkv-x-dev/rwkv-x-playground/resolve/main/experiment/rwkv-x-exp/v5-memory/v5-L96-D1024-E0_1-mem-ctx-4k.pth\r\n", + "--2023-09-02 06:16:32-- https://huggingface.co/rwkv-x-dev/rwkv-x-playground/resolve/main/experiment/rwkv-x-exp/v5-memory/v5-L96-D1024-E0_1-mem-ctx-4k.pth\r\n", "Resolving huggingface.co (huggingface.co)... " ] }, @@ -223,8 +223,8 @@ "name": "stdout", "output_type": "stream", "text": [ - "18.165.122.11, 18.165.122.30, 18.165.122.101, ...\r\n", - "Connecting to huggingface.co (huggingface.co)|18.165.122.11|:443... connected.\r\n", + "18.165.122.101, 18.165.122.11, 18.165.122.120, ...\r\n", + "Connecting to huggingface.co (huggingface.co)|18.165.122.101|:443... connected.\r\n", "HTTP request sent, awaiting response... " ] }, @@ -233,8 +233,8 @@ "output_type": "stream", "text": [ "302 Found\r\n", - "Location: https://cdn-lfs.huggingface.co/repos/2e/f7/2ef78555202aa92abdbdf476ce3d0fd5a8b15f7245edf0b80d4d30572355f30d/20fb328bd798a1e23967f80661a0b6a277f1d45ed2d90760cec68d32dfcbd516?response-content-disposition=attachment%3B+filename*%3DUTF-8%27%27v5-L96-D1024-E0_1-mem-ctx-4k.pth%3B+filename%3D%22v5-L96-D1024-E0_1-mem-ctx-4k.pth%22%3B&Expires=1693903272&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTY5MzkwMzI3Mn19LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy5odWdnaW5nZmFjZS5jby9yZXBvcy8yZS9mNy8yZWY3ODU1NTIwMmFhOTJhYmRiZGY0NzZjZTNkMGZkNWE4YjE1ZjcyNDVlZGYwYjgwZDRkMzA1NzIzNTVmMzBkLzIwZmIzMjhiZDc5OGExZTIzOTY3ZjgwNjYxYTBiNmEyNzdmMWQ0NWVkMmQ5MDc2MGNlYzY4ZDMyZGZjYmQ1MTY%7EcmVzcG9uc2UtY29udGVudC1kaXNwb3NpdGlvbj0qIn1dfQ__&Signature=XYUEm5rWRl8TZW2GseMQ7CZsoQWK%7ExizTrnu71lLngQQTBmQGTJGqqKHVXkB3N%7E-l3HrQnY-2UE1xVGJAqeSSkvBLsQO84qIhPYkt2sOJKLMFYyidxXiI%7EPdnW9XJw38lLiZWkBFo4HJEaU-L4Wa%7Ej2zz19V19fUHN01xqokVHF7EJgvgltH7R9MrBIW16GVNkX5GPy16UdOOykn12Eag5OerEkjigfYVxOtHy5cEOSjXjRZHLm8bFzUFe9K7jGNCdddmNebAQwCl%7E1dLXeCQya6rDrNtjse52R5tzuPCKM8dcyaR5vv2ZznDl3Njk1Lo7KbFZ3O3XYmE9XeAYId%7Eg__&Key-Pair-Id=KVTP0A1DKRTAX [following]\r\n", - "--2023-09-02 08:41:12-- https://cdn-lfs.huggingface.co/repos/2e/f7/2ef78555202aa92abdbdf476ce3d0fd5a8b15f7245edf0b80d4d30572355f30d/20fb328bd798a1e23967f80661a0b6a277f1d45ed2d90760cec68d32dfcbd516?response-content-disposition=attachment%3B+filename*%3DUTF-8%27%27v5-L96-D1024-E0_1-mem-ctx-4k.pth%3B+filename%3D%22v5-L96-D1024-E0_1-mem-ctx-4k.pth%22%3B&Expires=1693903272&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTY5MzkwMzI3Mn19LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy5odWdnaW5nZmFjZS5jby9yZXBvcy8yZS9mNy8yZWY3ODU1NTIwMmFhOTJhYmRiZGY0NzZjZTNkMGZkNWE4YjE1ZjcyNDVlZGYwYjgwZDRkMzA1NzIzNTVmMzBkLzIwZmIzMjhiZDc5OGExZTIzOTY3ZjgwNjYxYTBiNmEyNzdmMWQ0NWVkMmQ5MDc2MGNlYzY4ZDMyZGZjYmQ1MTY%7EcmVzcG9uc2UtY29udGVudC1kaXNwb3NpdGlvbj0qIn1dfQ__&Signature=XYUEm5rWRl8TZW2GseMQ7CZsoQWK%7ExizTrnu71lLngQQTBmQGTJGqqKHVXkB3N%7E-l3HrQnY-2UE1xVGJAqeSSkvBLsQO84qIhPYkt2sOJKLMFYyidxXiI%7EPdnW9XJw38lLiZWkBFo4HJEaU-L4Wa%7Ej2zz19V19fUHN01xqokVHF7EJgvgltH7R9MrBIW16GVNkX5GPy16UdOOykn12Eag5OerEkjigfYVxOtHy5cEOSjXjRZHLm8bFzUFe9K7jGNCdddmNebAQwCl%7E1dLXeCQya6rDrNtjse52R5tzuPCKM8dcyaR5vv2ZznDl3Njk1Lo7KbFZ3O3XYmE9XeAYId%7Eg__&Key-Pair-Id=KVTP0A1DKRTAX\r\n", + "Location: https://cdn-lfs.huggingface.co/repos/2e/f7/2ef78555202aa92abdbdf476ce3d0fd5a8b15f7245edf0b80d4d30572355f30d/20fb328bd798a1e23967f80661a0b6a277f1d45ed2d90760cec68d32dfcbd516?response-content-disposition=attachment%3B+filename*%3DUTF-8%27%27v5-L96-D1024-E0_1-mem-ctx-4k.pth%3B+filename%3D%22v5-L96-D1024-E0_1-mem-ctx-4k.pth%22%3B&Expires=1693894592&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTY5Mzg5NDU5Mn19LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy5odWdnaW5nZmFjZS5jby9yZXBvcy8yZS9mNy8yZWY3ODU1NTIwMmFhOTJhYmRiZGY0NzZjZTNkMGZkNWE4YjE1ZjcyNDVlZGYwYjgwZDRkMzA1NzIzNTVmMzBkLzIwZmIzMjhiZDc5OGExZTIzOTY3ZjgwNjYxYTBiNmEyNzdmMWQ0NWVkMmQ5MDc2MGNlYzY4ZDMyZGZjYmQ1MTY%7EcmVzcG9uc2UtY29udGVudC1kaXNwb3NpdGlvbj0qIn1dfQ__&Signature=0lvghwVju7ugxwlMlvj%7EIeK4lhVAMO1bcdYQsP0FxGPt5AK88smuTfGJvprL1l1HiQVj4a7f6U8yvc97nQxIdWdTF0RC8s4SAyFcZoupxdMbzOQ7kEr7OgXQPIdUhXWFAQN8Jrd-gkTfbl1ZAR2HjikcsW0MZI2do5UoTezTx6aBHfDhSwsx0SOCKOXHdWmyvofJts71OggEykKwEqY0AH3CHBro5v88luav9avT6Ha3nrtoJQKwKBxYLkC5RVwbsw7L6Br%7EV14-DYVOr1EIrDRifwMfNjtbDrx5eoJiXJF4mpngng5zcaDIofe1LUprJ8oOglZbD8IwmUJyW6JiRw__&Key-Pair-Id=KVTP0A1DKRTAX [following]\r\n", + "--2023-09-02 06:16:32-- https://cdn-lfs.huggingface.co/repos/2e/f7/2ef78555202aa92abdbdf476ce3d0fd5a8b15f7245edf0b80d4d30572355f30d/20fb328bd798a1e23967f80661a0b6a277f1d45ed2d90760cec68d32dfcbd516?response-content-disposition=attachment%3B+filename*%3DUTF-8%27%27v5-L96-D1024-E0_1-mem-ctx-4k.pth%3B+filename%3D%22v5-L96-D1024-E0_1-mem-ctx-4k.pth%22%3B&Expires=1693894592&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTY5Mzg5NDU5Mn19LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy5odWdnaW5nZmFjZS5jby9yZXBvcy8yZS9mNy8yZWY3ODU1NTIwMmFhOTJhYmRiZGY0NzZjZTNkMGZkNWE4YjE1ZjcyNDVlZGYwYjgwZDRkMzA1NzIzNTVmMzBkLzIwZmIzMjhiZDc5OGExZTIzOTY3ZjgwNjYxYTBiNmEyNzdmMWQ0NWVkMmQ5MDc2MGNlYzY4ZDMyZGZjYmQ1MTY%7EcmVzcG9uc2UtY29udGVudC1kaXNwb3NpdGlvbj0qIn1dfQ__&Signature=0lvghwVju7ugxwlMlvj%7EIeK4lhVAMO1bcdYQsP0FxGPt5AK88smuTfGJvprL1l1HiQVj4a7f6U8yvc97nQxIdWdTF0RC8s4SAyFcZoupxdMbzOQ7kEr7OgXQPIdUhXWFAQN8Jrd-gkTfbl1ZAR2HjikcsW0MZI2do5UoTezTx6aBHfDhSwsx0SOCKOXHdWmyvofJts71OggEykKwEqY0AH3CHBro5v88luav9avT6Ha3nrtoJQKwKBxYLkC5RVwbsw7L6Br%7EV14-DYVOr1EIrDRifwMfNjtbDrx5eoJiXJF4mpngng5zcaDIofe1LUprJ8oOglZbD8IwmUJyW6JiRw__&Key-Pair-Id=KVTP0A1DKRTAX\r\n", "Resolving cdn-lfs.huggingface.co (cdn-lfs.huggingface.co)... " ] }, @@ -242,15 +242,16 @@ "name": "stdout", "output_type": "stream", "text": [ - "108.156.22.119, 108.156.22.7, 108.156.22.58, ...\r\n", - "Connecting to cdn-lfs.huggingface.co (cdn-lfs.huggingface.co)|108.156.22.119|:443... connected.\r\n" + "108.156.22.119, 108.156.22.58, 108.156.22.7, ...\r\n", + "Connecting to cdn-lfs.huggingface.co (cdn-lfs.huggingface.co)|108.156.22.119|:443... connected.\r\n", + "HTTP request sent, awaiting response... " ] }, { "name": "stdout", "output_type": "stream", "text": [ - "HTTP request sent, awaiting response... 200 OK\r\n", + "200 OK\r\n", "Length: 2825976699 (2.6G) [binary/octet-stream]\r\n", "Saving to: ‘v5-L96-D1024-E0_1-mem-ctx-4k.pth’\r\n", "\r\n", @@ -263,7 +264,343 @@ "output_type": "stream", "text": [ "\r", - " v5-L96-D10 0%[ ] 13.31M 66.4MB/s " + " v5-L96-D10 0%[ ] 128.27K 472KB/s " + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r", + " v5-L96-D102 0%[ ] 1.18M 2.49MB/s " + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r", + " v5-L96-D1024 0%[ ] 3.65M 5.41MB/s " + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r", + " v5-L96-D1024- 0%[ ] 10.10M 11.5MB/s " + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r", + " v5-L96-D1024-E 0%[ ] 20.48M 18.5MB/s " + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r", + " v5-L96-D1024-E0 1%[ ] 28.53M 21.6MB/s " + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r", + " v5-L96-D1024-E0_ 1%[ ] 38.20M 25.0MB/s " + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r", + " v5-L96-D1024-E0_1 1%[ ] 45.14M 26.1MB/s " + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r", + " v5-L96-D1024-E0_1- 1%[ ] 53.31M 27.3MB/s " + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r", + "v5-L96-D1024-E0_1-m 2%[ ] 61.80M 28.7MB/s " + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r", + "5-L96-D1024-E0_1-me 2%[ ] 68.40M 29.1MB/s " + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r", + "-L96-D1024-E0_1-mem 2%[ ] 78.76M 30.8MB/s " + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r", + "L96-D1024-E0_1-mem- 3%[ ] 85.85M 31.1MB/s " + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r", + "96-D1024-E0_1-mem-c 3%[ ] 95.06M 31.9MB/s " + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r", + "6-D1024-E0_1-mem-ct 3%[ ] 103.00M 32.3MB/s eta 80s " + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r", + "-D1024-E0_1-mem-ctx 4%[ ] 110.60M 32.4MB/s eta 80s " + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r", + "D1024-E0_1-mem-ctx- 4%[ ] 121.50M 36.9MB/s eta 80s " + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r", + "1024-E0_1-mem-ctx-4 4%[ ] 130.07M 39.0MB/s eta 80s " + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r", + "024-E0_1-mem-ctx-4k 5%[> ] 137.57M 39.9MB/s eta 80s " + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r", + "24-E0_1-mem-ctx-4k. 5%[> ] 147.07M 40.5MB/s eta 74s " + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r", + "4-E0_1-mem-ctx-4k.p 5%[> ] 156.38M 40.1MB/s eta 74s " + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r", + "-E0_1-mem-ctx-4k.pt 6%[> ] 164.59M 40.0MB/s eta 74s " + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r", + "E0_1-mem-ctx-4k.pth 6%[> ] 171.63M 39.2MB/s eta 74s " + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r", + "0_1-mem-ctx-4k.pth 6%[> ] 180.27M 40.0MB/s eta 74s " + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r", + "_1-mem-ctx-4k.pth 6%[> ] 187.18M 39.2MB/s eta 71s " + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r", + "1-mem-ctx-4k.pth 7%[> ] 193.83M 39.0MB/s eta 71s " + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r", + "-mem-ctx-4k.pth 7%[> ] 202.32M 39.3MB/s eta 71s " + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r", + "mem-ctx-4k.pth 7%[> ] 210.41M 39.0MB/s eta 71s " + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r", + "em-ctx-4k.pth 8%[> ] 219.40M 39.4MB/s eta 71s " + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r", + "m-ctx-4k.pth 8%[> ] 226.92M 39.2MB/s eta 69s " + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r", + "-ctx-4k.pth 8%[> ] 235.87M 39.2MB/s eta 69s " + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r", + "ctx-4k.pth 9%[> ] 244.37M 39.2MB/s eta 69s " + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r", + "tx-4k.pth 9%[> ] 252.94M 39.4MB/s eta 69s " + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r", + "x-4k.pth 9%[> ] 260.46M 39.1MB/s eta 69s " + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r", + "-4k.pth 9%[> ] 268.38M 39.0MB/s eta 67s " + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r", + "4k.pth 10%[=> ] 278.50M 39.2MB/s eta 67s " + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r", + "k.pth 10%[=> ] 286.82M 39.2MB/s eta 67s " + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r", + ".pth 10%[=> ] 294.98M 39.1MB/s eta 67s " + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r", + "pth 11%[=> ] 303.99M 40.1MB/s eta 67s " + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r", + "th 11%[=> ] 312.18M 39.9MB/s eta 64s " + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r", + "h 11%[=> ] 320.37M 40.7MB/s eta 64s " + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r", + " 12%[=> ] 327.41M 40.2MB/s eta 64s " + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r", + " v 12%[=> ] 334.85M 40.1MB/s eta 64s " ] }, { @@ -271,7 +608,7 @@ "output_type": "stream", "text": [ "\r", - " v5-L96-D102 1%[ ] 28.83M 72.0MB/s " + " v5 12%[=> ] 343.29M 40.2MB/s eta 64s " ] }, { @@ -279,7 +616,7 @@ "output_type": "stream", "text": [ "\r", - " v5-L96-D1024 1%[ ] 46.59M 77.6MB/s " + " v5- 12%[=> ] 350.02M 39.8MB/s eta 63s " ] }, { @@ -287,7 +624,7 @@ "output_type": "stream", "text": [ "\r", - " v5-L96-D1024- 2%[ ] 64.08M 80.0MB/s " + " v5-L 13%[=> ] 359.43M 40.0MB/s eta 63s " ] }, { @@ -295,7 +632,7 @@ "output_type": "stream", "text": [ "\r", - " v5-L96-D1024-E 3%[ ] 81.49M 81.4MB/s " + " v5-L9 13%[=> ] 366.85M 39.7MB/s eta 63s " ] }, { @@ -303,7 +640,7 @@ "output_type": "stream", "text": [ "\r", - " v5-L96-D1024-E0 3%[ ] 96.12M 79.1MB/s " + " v5-L96 13%[=> ] 374.94M 39.6MB/s eta 63s " ] }, { @@ -311,7 +648,7 @@ "output_type": "stream", "text": [ "\r", - " v5-L96-D1024-E0_ 4%[ ] 111.73M 78.9MB/s " + " v5-L96- 14%[=> ] 383.94M 39.8MB/s eta 63s " ] }, { @@ -319,7 +656,7 @@ "output_type": "stream", "text": [ "\r", - " v5-L96-D1024-E0_1 4%[ ] 128.42M 79.5MB/s " + " v5-L96-D 14%[=> ] 389.22M 39.0MB/s eta 62s " ] }, { @@ -327,7 +664,7 @@ "output_type": "stream", "text": [ "\r", - " v5-L96-D1024-E0_1- 5%[> ] 147.05M 81.0MB/s " + " v5-L96-D1 14%[=> ] 399.01M 39.5MB/s eta 62s " ] }, { @@ -335,7 +672,7 @@ "output_type": "stream", "text": [ "\r", - "v5-L96-D1024-E0_1-m 6%[> ] 162.80M 80.7MB/s " + " v5-L96-D10 14%[=> ] 400.87M 37.2MB/s eta 62s " ] }, { @@ -343,7 +680,7 @@ "output_type": "stream", "text": [ "\r", - "5-L96-D1024-E0_1-me 6%[> ] 180.14M 81.3MB/s " + " v5-L96-D102 15%[==> ] 409.16M 37.3MB/s eta 62s " ] }, { @@ -351,7 +688,7 @@ "output_type": "stream", "text": [ "\r", - "-L96-D1024-E0_1-mem 7%[> ] 196.70M 81.4MB/s " + " v5-L96-D1024 15%[==> ] 422.11M 38.5MB/s eta 62s " ] }, { @@ -359,7 +696,7 @@ "output_type": "stream", "text": [ "\r", - "L96-D1024-E0_1-mem- 7%[> ] 212.43M 81.2MB/s " + " v5-L96-D1024- 15%[==> ] 430.96M 38.8MB/s eta 60s " ] }, { @@ -367,7 +704,7 @@ "output_type": "stream", "text": [ "\r", - "96-D1024-E0_1-mem-c 8%[> ] 230.28M 81.7MB/s " + " v5-L96-D1024-E 16%[==> ] 438.90M 38.4MB/s eta 60s " ] }, { @@ -375,7 +712,7 @@ "output_type": "stream", "text": [ "\r", - "6-D1024-E0_1-mem-ct 9%[> ] 248.08M 82.2MB/s eta 30s " + " v5-L96-D1024-E0 16%[==> ] 448.99M 39.2MB/s eta 60s " ] }, { @@ -383,7 +720,7 @@ "output_type": "stream", "text": [ "\r", - "-D1024-E0_1-mem-ctx 9%[> ] 263.31M 82.6MB/s eta 30s " + " v5-L96-D1024-E0_ 16%[==> ] 454.42M 38.5MB/s eta 60s " ] }, { @@ -391,7 +728,7 @@ "output_type": "stream", "text": [ "\r", - "D1024-E0_1-mem-ctx- 10%[=> ] 280.14M 83.0MB/s eta 30s " + " v5-L96-D1024-E0_1 17%[==> ] 463.45M 39.3MB/s eta 60s " ] }, { @@ -399,7 +736,7 @@ "output_type": "stream", "text": [ "\r", - "1024-E0_1-mem-ctx-4 11%[=> ] 297.06M 83.3MB/s eta 30s " + " v5-L96-D1024-E0_1- 17%[==> ] 472.14M 39.5MB/s eta 59s " ] }, { @@ -407,7 +744,7 @@ "output_type": "stream", "text": [ "\r", - "024-E0_1-mem-ctx-4k 11%[=> ] 313.79M 82.9MB/s eta 30s " + "v5-L96-D1024-E0_1-m 17%[==> ] 480.86M 39.7MB/s eta 59s " ] }, { @@ -415,7 +752,7 @@ "output_type": "stream", "text": [ "\r", - "24-E0_1-mem-ctx-4k. 12%[=> ] 331.17M 82.9MB/s eta 29s " + "5-L96-D1024-E0_1-me 18%[==> ] 488.78M 39.6MB/s eta 59s " ] }, { @@ -423,7 +760,7 @@ "output_type": "stream", "text": [ "\r", - "4-E0_1-mem-ctx-4k.p 12%[=> ] 346.16M 82.7MB/s eta 29s " + "-L96-D1024-E0_1-mem 18%[==> ] 498.34M 40.4MB/s eta 59s " ] }, { @@ -431,7 +768,7 @@ "output_type": "stream", "text": [ "\r", - "-E0_1-mem-ctx-4k.pt 13%[=> ] 364.67M 83.4MB/s eta 29s " + "L96-D1024-E0_1-mem- 18%[==> ] 507.16M 40.0MB/s eta 59s " ] }, { @@ -439,7 +776,7 @@ "output_type": "stream", "text": [ "\r", - "E0_1-mem-ctx-4k.pth 14%[=> ] 382.49M 83.9MB/s eta 29s " + "96-D1024-E0_1-mem-c 19%[==> ] 515.72M 40.0MB/s eta 57s " ] }, { @@ -447,7 +784,7 @@ "output_type": "stream", "text": [ "\r", - "0_1-mem-ctx-4k.pth 14%[=> ] 399.47M 83.7MB/s eta 29s " + "6-D1024-E0_1-mem-ct 19%[==> ] 523.23M 40.3MB/s eta 57s " ] }, { @@ -455,7 +792,7 @@ "output_type": "stream", "text": [ "\r", - "_1-mem-ctx-4k.pth 15%[==> ] 413.53M 82.3MB/s eta 28s " + "-D1024-E0_1-mem-ctx 19%[==> ] 530.88M 40.2MB/s eta 57s " ] }, { @@ -463,7 +800,7 @@ "output_type": "stream", "text": [ "\r", - "1-mem-ctx-4k.pth 15%[==> ] 430.24M 82.7MB/s eta 28s " + "D1024-E0_1-mem-ctx- 20%[===> ] 541.15M 42.6MB/s eta 57s " ] }, { @@ -471,7 +808,7 @@ "output_type": "stream", "text": [ "\r", - "-mem-ctx-4k.pth 16%[==> ] 440.09M 79.6MB/s eta 28s " + "1024-E0_1-mem-ctx-4 20%[===> ] 549.61M 40.9MB/s eta 57s " ] }, { @@ -479,7 +816,7 @@ "output_type": "stream", "text": [ "\r", - "mem-ctx-4k.pth 16%[==> ] 451.39M 78.5MB/s eta 28s " + "024-E0_1-mem-ctx-4k 20%[===> ] 557.83M 40.4MB/s eta 56s " ] }, { @@ -487,7 +824,7 @@ "output_type": "stream", "text": [ "\r", - "em-ctx-4k.pth 17%[==> ] 468.42M 78.4MB/s eta 28s " + "24-E0_1-mem-ctx-4k. 21%[===> ] 566.19M 40.5MB/s eta 56s " ] }, { @@ -495,7 +832,7 @@ "output_type": "stream", "text": [ "\r", - "m-ctx-4k.pth 17%[==> ] 485.02M 76.8MB/s eta 28s " + "4-E0_1-mem-ctx-4k.p 21%[===> ] 576.30M 40.9MB/s eta 56s " ] }, { @@ -503,7 +840,7 @@ "output_type": "stream", "text": [ "\r", - "-ctx-4k.pth 18%[==> ] 497.70M 75.9MB/s eta 28s " + "-E0_1-mem-ctx-4k.pt 21%[===> ] 584.55M 40.6MB/s eta 56s " ] }, { @@ -511,7 +848,7 @@ "output_type": "stream", "text": [ "\r", - "ctx-4k.pth 19%[==> ] 517.39M 76.9MB/s eta 28s " + "E0_1-mem-ctx-4k.pth 22%[===> ] 593.19M 40.8MB/s eta 56s " ] }, { @@ -519,7 +856,7 @@ "output_type": "stream", "text": [ "\r", - "tx-4k.pth 19%[==> ] 532.44M 76.4MB/s eta 28s " + "0_1-mem-ctx-4k.pth 22%[===> ] 601.02M 41.2MB/s eta 55s " ] }, { @@ -527,7 +864,7 @@ "output_type": "stream", "text": [ "\r", - "x-4k.pth 20%[===> ] 546.53M 75.4MB/s eta 28s " + "_1-mem-ctx-4k.pth 22%[===> ] 607.94M 40.3MB/s eta 55s " ] }, { @@ -535,7 +872,7 @@ "output_type": "stream", "text": [ "\r", - "-4k.pth 20%[===> ] 563.48M 75.1MB/s eta 27s " + "1-mem-ctx-4k.pth 22%[===> ] 617.53M 40.9MB/s eta 55s " ] }, { @@ -543,7 +880,7 @@ "output_type": "stream", "text": [ "\r", - "4k.pth 21%[===> ] 582.10M 75.1MB/s eta 27s " + "-mem-ctx-4k.pth 23%[===> ] 626.19M 41.1MB/s eta 55s " ] }, { @@ -551,7 +888,7 @@ "output_type": "stream", "text": [ "\r", - "k.pth 22%[===> ] 599.29M 75.2MB/s eta 27s " + "mem-ctx-4k.pth 23%[===> ] 631.94M 40.2MB/s eta 55s " ] }, { @@ -559,7 +896,7 @@ "output_type": "stream", "text": [ "\r", - ".pth 22%[===> ] 617.27M 75.5MB/s eta 27s " + "em-ctx-4k.pth 23%[===> ] 642.25M 40.8MB/s eta 53s " ] }, { @@ -567,7 +904,7 @@ "output_type": "stream", "text": [ "\r", - "pth 23%[===> ] 632.54M 74.8MB/s eta 27s " + "m-ctx-4k.pth 24%[===> ] 650.46M 40.2MB/s eta 53s " ] }, { @@ -575,7 +912,7 @@ "output_type": "stream", "text": [ "\r", - "th 24%[===> ] 650.42M 75.1MB/s eta 26s " + "-ctx-4k.pth 24%[===> ] 660.40M 41.1MB/s eta 53s " ] }, { @@ -583,7 +920,7 @@ "output_type": "stream", "text": [ "\r", - "h 24%[===> ] 665.16M 74.5MB/s eta 26s " + "ctx-4k.pth 24%[===> ] 669.04M 41.3MB/s eta 53s " ] }, { @@ -591,7 +928,7 @@ "output_type": "stream", "text": [ "\r", - " 25%[====> ] 680.40M 75.1MB/s eta 26s " + "tx-4k.pth 25%[====> ] 677.22M 40.6MB/s eta 53s " ] }, { @@ -599,7 +936,7 @@ "output_type": "stream", "text": [ "\r", - " v 25%[====> ] 696.57M 77.9MB/s eta 26s " + "x-4k.pth 25%[====> ] 685.40M 40.8MB/s eta 52s " ] }, { @@ -607,7 +944,7 @@ "output_type": "stream", "text": [ "\r", - " v5 26%[====> ] 715.45M 79.1MB/s eta 26s " + "-4k.pth 25%[====> ] 692.90M 40.2MB/s eta 52s " ] }, { @@ -615,7 +952,7 @@ "output_type": "stream", "text": [ "\r", - " v5- 27%[====> ] 732.12M 79.5MB/s eta 25s " + "4k.pth 26%[====> ] 701.72M 40.5MB/s eta 52s " ] }, { @@ -623,7 +960,7 @@ "output_type": "stream", "text": [ "\r", - " v5-L 27%[====> ] 748.81M 81.2MB/s eta 25s " + "k.pth 26%[====> ] 710.47M 40.8MB/s eta 52s " ] }, { @@ -631,7 +968,7 @@ "output_type": "stream", "text": [ "\r", - " v5-L9 28%[====> ] 765.59M 80.9MB/s eta 25s " + ".pth 26%[====> ] 719.50M 40.4MB/s eta 52s " ] }, { @@ -639,7 +976,7 @@ "output_type": "stream", "text": [ "\r", - " v5-L96 29%[====> ] 783.92M 81.8MB/s eta 25s " + "pth 26%[====> ] 727.67M 40.6MB/s eta 51s " ] }, { @@ -647,7 +984,7 @@ "output_type": "stream", "text": [ "\r", - " v5-L96- 29%[====> ] 799.27M 81.9MB/s eta 25s " + "th 27%[====> ] 735.40M 40.5MB/s eta 51s " ] }, { @@ -655,7 +992,7 @@ "output_type": "stream", "text": [ "\r", - " v5-L96-D 30%[=====> ] 815.27M 81.7MB/s eta 24s " + "h 27%[====> ] 745.58M 41.2MB/s eta 51s " ] }, { @@ -663,7 +1000,7 @@ "output_type": "stream", "text": [ "\r", - " v5-L96-D1 30%[=====> ] 831.37M 81.9MB/s eta 24s " + " 27%[====> ] 754.27M 41.0MB/s eta 51s " ] }, { @@ -671,7 +1008,7 @@ "output_type": "stream", "text": [ "\r", - " v5-L96-D10 31%[=====> ] 848.57M 81.6MB/s eta 24s " + " v 28%[====> ] 762.58M 40.9MB/s eta 51s " ] }, { @@ -679,7 +1016,7 @@ "output_type": "stream", "text": [ "\r", - " v5-L96-D102 32%[=====> ] 868.14M 82.7MB/s eta 24s " + " v5 28%[====> ] 770.36M 40.8MB/s eta 50s " ] }, { @@ -687,7 +1024,7 @@ "output_type": "stream", "text": [ "\r", - " v5-L96-D1024 32%[=====> ] 884.10M 82.3MB/s eta 24s " + " v5- 28%[====> ] 778.11M 40.5MB/s eta 50s " ] }, { @@ -695,7 +1032,7 @@ "output_type": "stream", "text": [ "\r", - " v5-L96-D1024- 33%[=====> ] 896.71M 80.2MB/s eta 23s " + " v5-L 29%[====> ] 787.60M 40.9MB/s eta 50s " ] }, { @@ -703,7 +1040,7 @@ "output_type": "stream", "text": [ "\r", - " v5-L96-D1024-E 33%[=====> ] 913.93M 81.2MB/s eta 23s " + " v5-L9 29%[====> ] 795.51M 40.5MB/s eta 50s " ] }, { @@ -711,7 +1048,7 @@ "output_type": "stream", "text": [ "\r", - " v5-L96-D1024-E0 34%[=====> ] 926.25M 80.5MB/s eta 23s " + " v5-L96 29%[====> ] 804.15M 40.9MB/s eta 50s " ] }, { @@ -719,7 +1056,7 @@ "output_type": "stream", "text": [ "\r", - " v5-L96-D1024-E0_ 34%[=====> ] 942.73M 80.4MB/s eta 23s " + " v5-L96- 30%[=====> ] 811.94M 40.2MB/s eta 48s " ] }, { @@ -727,7 +1064,7 @@ "output_type": "stream", "text": [ "\r", - " v5-L96-D1024-E0_1 35%[======> ] 959.37M 80.3MB/s eta 23s " + " v5-L96-D 30%[=====> ] 819.92M 40.3MB/s eta 48s " ] }, { @@ -735,7 +1072,7 @@ "output_type": "stream", "text": [ "\r", - " v5-L96-D1024-E0_1- 36%[======> ] 976.46M 80.6MB/s eta 22s " + " v5-L96-D1 30%[=====> ] 828.12M 40.4MB/s eta 48s " ] }, { @@ -743,7 +1080,7 @@ "output_type": "stream", "text": [ "\r", - "v5-L96-D1024-E0_1-m 36%[======> ] 991.58M 79.6MB/s eta 22s " + " v5-L96-D10 31%[=====> ] 837.98M 40.4MB/s eta 48s " ] }, { @@ -751,7 +1088,7 @@ "output_type": "stream", "text": [ "\r", - "5-L96-D1024-E0_1-me 37%[======> ] 1007M 79.3MB/s eta 22s " + " v5-L96-D102 31%[=====> ] 846.44M 40.3MB/s eta 48s " ] }, { @@ -759,7 +1096,7 @@ "output_type": "stream", "text": [ "\r", - "-L96-D1024-E0_1-mem 38%[======> ] 1.00G 79.8MB/s eta 22s " + " v5-L96-D1024 31%[=====> ] 855.32M 40.7MB/s eta 47s " ] }, { @@ -767,7 +1104,7 @@ "output_type": "stream", "text": [ "\r", - "L96-D1024-E0_1-mem- 38%[======> ] 1.02G 79.6MB/s eta 22s " + " v5-L96-D1024- 32%[=====> ] 863.40M 40.7MB/s eta 47s " ] }, { @@ -775,7 +1112,7 @@ "output_type": "stream", "text": [ "\r", - "96-D1024-E0_1-mem-c 39%[======> ] 1.03G 79.4MB/s eta 21s " + " v5-L96-D1024-E 32%[=====> ] 871.21M 40.2MB/s eta 47s " ] }, { @@ -783,7 +1120,7 @@ "output_type": "stream", "text": [ "\r", - "6-D1024-E0_1-mem-ct 39%[======> ] 1.03G 73.8MB/s eta 21s " + " v5-L96-D1024-E0 32%[=====> ] 880.97M 41.1MB/s eta 47s " ] }, { @@ -791,7 +1128,7 @@ "output_type": "stream", "text": [ "\r", - "-D1024-E0_1-mem-ctx 39%[======> ] 1.05G 74.1MB/s eta 21s " + " v5-L96-D1024-E0_ 32%[=====> ] 889.22M 40.5MB/s eta 47s " ] }, { @@ -799,7 +1136,7 @@ "output_type": "stream", "text": [ "\r", - "D1024-E0_1-mem-ctx- 40%[=======> ] 1.07G 73.3MB/s eta 21s " + " v5-L96-D1024-E0_1 33%[=====> ] 897.03M 40.2MB/s eta 46s " ] }, { @@ -807,7 +1144,7 @@ "output_type": "stream", "text": [ "\r", - "1024-E0_1-mem-ctx-4 41%[=======> ] 1.08G 74.0MB/s eta 21s " + " v5-L96-D1024-E0_1- 33%[=====> ] 898.93M 38.4MB/s eta 46s " ] }, { @@ -815,7 +1152,7 @@ "output_type": "stream", "text": [ "\r", - "024-E0_1-mem-ctx-4k 41%[=======> ] 1.10G 74.6MB/s eta 20s " + "v5-L96-D1024-E0_1-m 33%[=====> ] 915.07M 40.6MB/s eta 46s " ] }, { @@ -823,7 +1160,7 @@ "output_type": "stream", "text": [ "\r", - "24-E0_1-mem-ctx-4k. 42%[=======> ] 1.11G 75.3MB/s eta 20s " + "5-L96-D1024-E0_1-me 34%[=====> ] 924.14M 40.6MB/s eta 46s " ] }, { @@ -831,7 +1168,7 @@ "output_type": "stream", "text": [ "\r", - "4-E0_1-mem-ctx-4k.p 42%[=======> ] 1.13G 75.1MB/s eta 20s " + "-L96-D1024-E0_1-mem 34%[=====> ] 932.36M 40.8MB/s eta 46s " ] }, { @@ -839,7 +1176,7 @@ "output_type": "stream", "text": [ "\r", - "-E0_1-mem-ctx-4k.pt 43%[=======> ] 1.15G 76.2MB/s eta 20s " + "L96-D1024-E0_1-mem- 34%[=====> ] 941.37M 40.7MB/s eta 45s " ] }, { @@ -847,7 +1184,7 @@ "output_type": "stream", "text": [ "\r", - "E0_1-mem-ctx-4k.pth 44%[=======> ] 1.17G 77.2MB/s eta 20s " + "96-D1024-E0_1-mem-c 35%[======> ] 949.66M 40.9MB/s eta 45s " ] }, { @@ -855,7 +1192,7 @@ "output_type": "stream", "text": [ "\r", - "0_1-mem-ctx-4k.pth 44%[=======> ] 1.18G 77.7MB/s eta 19s " + "6-D1024-E0_1-mem-ct 35%[======> ] 958.50M 40.8MB/s eta 45s " ] }, { @@ -863,7 +1200,7 @@ "output_type": "stream", "text": [ "\r", - "_1-mem-ctx-4k.pth 45%[========> ] 1.20G 78.5MB/s eta 19s " + "-D1024-E0_1-mem-ctx 35%[======> ] 966.79M 40.7MB/s eta 45s " ] }, { @@ -871,7 +1208,7 @@ "output_type": "stream", "text": [ "\r", - "1-mem-ctx-4k.pth 46%[========> ] 1.22G 78.6MB/s eta 19s " + "D1024-E0_1-mem-ctx- 36%[======> ] 976.33M 41.2MB/s eta 45s " ] }, { @@ -879,7 +1216,7 @@ "output_type": "stream", "text": [ "\r", - "-mem-ctx-4k.pth 46%[========> ] 1.23G 77.9MB/s eta 19s " + "1024-E0_1-mem-ctx-4 36%[======> ] 985.30M 41.5MB/s eta 44s " ] }, { @@ -887,7 +1224,7 @@ "output_type": "stream", "text": [ "\r", - "mem-ctx-4k.pth 47%[========> ] 1.25G 77.8MB/s eta 19s " + "024-E0_1-mem-ctx-4k 36%[======> ] 993.33M 41.0MB/s eta 44s " ] }, { @@ -895,7 +1232,7 @@ "output_type": "stream", "text": [ "\r", - "em-ctx-4k.pth 48%[========> ] 1.27G 78.0MB/s eta 18s " + "24-E0_1-mem-ctx-4k. 37%[======> ] 1002M 41.1MB/s eta 44s " ] }, { @@ -903,7 +1240,7 @@ "output_type": "stream", "text": [ "\r", - "m-ctx-4k.pth 48%[========> ] 1.28G 81.0MB/s eta 18s " + "4-E0_1-mem-ctx-4k.p 37%[======> ] 1011M 41.0MB/s eta 44s " ] }, { @@ -911,7 +1248,7 @@ "output_type": "stream", "text": [ "\r", - "-ctx-4k.pth 49%[========> ] 1.30G 82.9MB/s eta 18s " + "-E0_1-mem-ctx-4k.pt 37%[======> ] 1019M 40.9MB/s eta 44s " ] }, { @@ -919,7 +1256,7 @@ "output_type": "stream", "text": [ "\r", - "ctx-4k.pth 50%[=========> ] 1.32G 83.3MB/s eta 18s " + "E0_1-mem-ctx-4k.pth 38%[======> ] 1.00G 40.9MB/s eta 42s " ] }, { @@ -927,7 +1264,7 @@ "output_type": "stream", "text": [ "\r", - "tx-4k.pth 50%[=========> ] 1.33G 84.6MB/s eta 18s " + "0_1-mem-ctx-4k.pth 38%[======> ] 1.01G 42.5MB/s eta 42s " ] }, { @@ -935,7 +1272,7 @@ "output_type": "stream", "text": [ "\r", - "x-4k.pth 51%[=========> ] 1.35G 84.7MB/s eta 16s " + "_1-mem-ctx-4k.pth 38%[======> ] 1.02G 41.9MB/s eta 42s " ] }, { @@ -943,7 +1280,7 @@ "output_type": "stream", "text": [ "\r", - "-4k.pth 52%[=========> ] 1.37G 85.0MB/s eta 16s " + "1-mem-ctx-4k.pth 39%[======> ] 1.03G 40.6MB/s eta 42s " ] }, { @@ -951,7 +1288,7 @@ "output_type": "stream", "text": [ "\r", - "4k.pth 52%[=========> ] 1.38G 85.2MB/s eta 16s " + "-mem-ctx-4k.pth 39%[======> ] 1.04G 40.4MB/s eta 42s " ] }, { @@ -959,7 +1296,7 @@ "output_type": "stream", "text": [ "\r", - "k.pth 53%[=========> ] 1.40G 84.9MB/s eta 16s " + "mem-ctx-4k.pth 39%[======> ] 1.04G 39.5MB/s eta 41s " ] }, { @@ -967,7 +1304,7 @@ "output_type": "stream", "text": [ "\r", - ".pth 53%[=========> ] 1.42G 84.1MB/s eta 16s " + "em-ctx-4k.pth 40%[=======> ] 1.05G 40.4MB/s eta 41s " ] }, { @@ -975,7 +1312,7 @@ "output_type": "stream", "text": [ "\r", - "pth 54%[=========> ] 1.43G 84.1MB/s eta 15s " + "m-ctx-4k.pth 40%[=======> ] 1.06G 40.0MB/s eta 41s " ] }, { @@ -983,7 +1320,7 @@ "output_type": "stream", "text": [ "\r", - "th 55%[==========> ] 1.45G 84.2MB/s eta 15s " + "-ctx-4k.pth 40%[=======> ] 1.07G 40.5MB/s eta 41s " ] }, { @@ -991,7 +1328,7 @@ "output_type": "stream", "text": [ "\r", - "h 55%[==========> ] 1.47G 84.2MB/s eta 15s " + "ctx-4k.pth 40%[=======> ] 1.08G 40.1MB/s eta 41s " ] }, { @@ -999,7 +1336,7 @@ "output_type": "stream", "text": [ "\r", - " 56%[==========> ] 1.48G 84.1MB/s eta 15s " + "tx-4k.pth 41%[=======> ] 1.09G 40.8MB/s eta 40s " ] }, { @@ -1007,7 +1344,7 @@ "output_type": "stream", "text": [ "\r", - " v 56%[==========> ] 1.50G 83.5MB/s eta 15s " + "x-4k.pth 41%[=======> ] 1.09G 40.6MB/s eta 40s " ] }, { @@ -1015,7 +1352,7 @@ "output_type": "stream", "text": [ "\r", - " v5 57%[==========> ] 1.52G 83.5MB/s eta 14s " + "-4k.pth 41%[=======> ] 1.10G 40.2MB/s eta 40s " ] }, { @@ -1023,7 +1360,7 @@ "output_type": "stream", "text": [ "\r", - " v5- 58%[==========> ] 1.53G 82.6MB/s eta 14s " + "4k.pth 42%[=======> ] 1.11G 40.0MB/s eta 40s " ] }, { @@ -1031,7 +1368,7 @@ "output_type": "stream", "text": [ "\r", - " v5-L 58%[==========> ] 1.55G 82.9MB/s eta 14s " + "k.pth 42%[=======> ] 1.12G 39.8MB/s eta 40s " ] }, { @@ -1039,7 +1376,7 @@ "output_type": "stream", "text": [ "\r", - " v5-L9 59%[==========> ] 1.56G 83.4MB/s eta 14s " + ".pth 42%[=======> ] 1.12G 39.2MB/s eta 39s " ] }, { @@ -1047,7 +1384,7 @@ "output_type": "stream", "text": [ "\r", - " v5-L96 60%[===========> ] 1.58G 83.6MB/s eta 14s " + "pth 43%[=======> ] 1.13G 39.1MB/s eta 39s " ] }, { @@ -1055,7 +1392,7 @@ "output_type": "stream", "text": [ "\r", - " v5-L96- 60%[===========> ] 1.59G 82.9MB/s eta 13s " + "th 43%[=======> ] 1.14G 38.9MB/s eta 39s " ] }, { @@ -1063,7 +1400,7 @@ "output_type": "stream", "text": [ "\r", - " v5-L96-D 60%[===========> ] 1.60G 79.3MB/s eta 13s " + "h 43%[=======> ] 1.15G 39.3MB/s eta 39s " ] }, { @@ -1071,7 +1408,7 @@ "output_type": "stream", "text": [ "\r", - " v5-L96-D1 61%[===========> ] 1.62G 79.4MB/s eta 13s " + " 44%[=======> ] 1.16G 38.9MB/s eta 39s " ] }, { @@ -1079,7 +1416,7 @@ "output_type": "stream", "text": [ "\r", - " v5-L96-D10 62%[===========> ] 1.63G 78.9MB/s eta 13s " + " v 44%[=======> ] 1.17G 39.4MB/s eta 38s " ] }, { @@ -1087,7 +1424,7 @@ "output_type": "stream", "text": [ "\r", - " v5-L96-D102 62%[===========> ] 1.65G 78.9MB/s eta 13s " + " v5 44%[=======> ] 1.17G 39.8MB/s eta 38s " ] }, { @@ -1095,7 +1432,7 @@ "output_type": "stream", "text": [ "\r", - " v5-L96-D1024 63%[===========> ] 1.67G 78.8MB/s eta 12s " + " v5- 44%[=======> ] 1.18G 39.8MB/s eta 38s " ] }, { @@ -1103,7 +1440,7 @@ "output_type": "stream", "text": [ "\r", - " v5-L96-D1024- 63%[===========> ] 1.68G 79.5MB/s eta 12s " + " v5-L 45%[========> ] 1.19G 39.6MB/s eta 38s " ] }, { @@ -1111,7 +1448,7 @@ "output_type": "stream", "text": [ "\r", - " v5-L96-D1024-E 64%[===========> ] 1.70G 79.1MB/s eta 12s " + " v5-L9 45%[========> ] 1.20G 39.7MB/s eta 38s " ] }, { @@ -1119,7 +1456,7 @@ "output_type": "stream", "text": [ "\r", - " v5-L96-D1024-E0 65%[============> ] 1.72G 78.9MB/s eta 12s " + " v5-L96 45%[========> ] 1.21G 39.9MB/s eta 37s " ] }, { @@ -1127,7 +1464,7 @@ "output_type": "stream", "text": [ "\r", - " v5-L96-D1024-E0_ 65%[============> ] 1.73G 79.4MB/s eta 12s " + " v5-L96- 46%[========> ] 1.22G 39.7MB/s eta 37s " ] }, { @@ -1135,7 +1472,7 @@ "output_type": "stream", "text": [ "\r", - " v5-L96-D1024-E0_1 66%[============> ] 1.75G 79.3MB/s eta 11s " + " v5-L96-D 46%[========> ] 1.23G 39.2MB/s eta 37s " ] }, { @@ -1143,7 +1480,7 @@ "output_type": "stream", "text": [ "\r", - " v5-L96-D1024-E0_1- 67%[============> ] 1.77G 79.3MB/s eta 11s " + " v5-L96-D1 46%[========> ] 1.23G 39.5MB/s eta 37s " ] }, { @@ -1151,7 +1488,7 @@ "output_type": "stream", "text": [ "\r", - "v5-L96-D1024-E0_1-m 67%[============> ] 1.78G 79.4MB/s eta 11s " + " v5-L96-D10 47%[========> ] 1.24G 39.9MB/s eta 37s " ] }, { @@ -1159,7 +1496,7 @@ "output_type": "stream", "text": [ "\r", - "5-L96-D1024-E0_1-me 68%[============> ] 1.80G 79.6MB/s eta 11s " + " v5-L96-D102 47%[========> ] 1.25G 39.6MB/s eta 36s " ] }, { @@ -1167,7 +1504,7 @@ "output_type": "stream", "text": [ "\r", - "-L96-D1024-E0_1-mem 68%[============> ] 1.81G 79.1MB/s eta 11s " + " v5-L96-D1024 47%[========> ] 1.26G 39.9MB/s eta 36s " ] }, { @@ -1175,7 +1512,7 @@ "output_type": "stream", "text": [ "\r", - "L96-D1024-E0_1-mem- 69%[============> ] 1.83G 79.1MB/s eta 10s " + " v5-L96-D1024- 48%[========> ] 1.27G 40.6MB/s eta 36s " ] }, { @@ -1183,7 +1520,7 @@ "output_type": "stream", "text": [ "\r", - "96-D1024-E0_1-mem-c 70%[=============> ] 1.85G 78.6MB/s eta 10s " + " v5-L96-D1024-E 48%[========> ] 1.27G 40.1MB/s eta 36s " ] }, { @@ -1191,7 +1528,7 @@ "output_type": "stream", "text": [ "\r", - "6-D1024-E0_1-mem-ct 70%[=============> ] 1.86G 82.6MB/s eta 10s " + " v5-L96-D1024-E0 48%[========> ] 1.28G 40.5MB/s eta 36s " ] }, { @@ -1199,7 +1536,7 @@ "output_type": "stream", "text": [ "\r", - "-D1024-E0_1-mem-ctx 71%[=============> ] 1.88G 83.3MB/s eta 10s " + " v5-L96-D1024-E0_ 49%[========> ] 1.29G 40.5MB/s eta 35s " ] }, { @@ -1207,7 +1544,7 @@ "output_type": "stream", "text": [ "\r", - "D1024-E0_1-mem-ctx- 71%[=============> ] 1.89G 82.3MB/s eta 10s " + " v5-L96-D1024-E0_1 49%[========> ] 1.30G 40.6MB/s eta 35s " ] }, { @@ -1215,7 +1552,7 @@ "output_type": "stream", "text": [ "\r", - "1024-E0_1-mem-ctx-4 72%[=============> ] 1.90G 78.4MB/s eta 9s " + " v5-L96-D1024-E0_1- 49%[========> ] 1.31G 40.0MB/s eta 35s " ] }, { @@ -1223,7 +1560,7 @@ "output_type": "stream", "text": [ "\r", - "024-E0_1-mem-ctx-4k 72%[=============> ] 1.91G 76.3MB/s eta 9s " + "v5-L96-D1024-E0_1-m 49%[========> ] 1.31G 37.9MB/s eta 35s " ] }, { @@ -1231,7 +1568,7 @@ "output_type": "stream", "text": [ "\r", - "24-E0_1-mem-ctx-4k. 73%[=============> ] 1.93G 76.6MB/s eta 9s " + "5-L96-D1024-E0_1-me 49%[========> ] 1.31G 37.3MB/s eta 35s " ] }, { @@ -1239,7 +1576,7 @@ "output_type": "stream", "text": [ "\r", - "4-E0_1-mem-ctx-4k.p 73%[=============> ] 1.94G 76.0MB/s eta 9s " + "-L96-D1024-E0_1-mem 50%[=========> ] 1.33G 39.3MB/s eta 34s " ] }, { @@ -1247,7 +1584,7 @@ "output_type": "stream", "text": [ "\r", - "-E0_1-mem-ctx-4k.pt 74%[=============> ] 1.96G 74.8MB/s eta 9s " + "L96-D1024-E0_1-mem- 50%[=========> ] 1.34G 38.9MB/s eta 34s " ] }, { @@ -1255,7 +1592,7 @@ "output_type": "stream", "text": [ "\r", - "E0_1-mem-ctx-4k.pth 74%[=============> ] 1.97G 74.9MB/s eta 8s " + "96-D1024-E0_1-mem-c 51%[=========> ] 1.34G 38.8MB/s eta 34s " ] }, { @@ -1263,7 +1600,7 @@ "output_type": "stream", "text": [ "\r", - "0_1-mem-ctx-4k.pth 75%[==============> ] 1.99G 73.7MB/s eta 8s " + "6-D1024-E0_1-mem-ct 51%[=========> ] 1.35G 39.0MB/s eta 34s " ] }, { @@ -1271,7 +1608,7 @@ "output_type": "stream", "text": [ "\r", - "_1-mem-ctx-4k.pth 76%[==============> ] 2.01G 74.2MB/s eta 8s " + "-D1024-E0_1-mem-ctx 51%[=========> ] 1.36G 39.1MB/s eta 34s " ] }, { @@ -1279,7 +1616,7 @@ "output_type": "stream", "text": [ "\r", - "1-mem-ctx-4k.pth 76%[==============> ] 2.02G 74.1MB/s eta 8s " + "D1024-E0_1-mem-ctx- 52%[=========> ] 1.37G 38.5MB/s eta 33s " ] }, { @@ -1287,7 +1624,7 @@ "output_type": "stream", "text": [ "\r", - "-mem-ctx-4k.pth 77%[==============> ] 2.04G 75.3MB/s eta 8s " + "1024-E0_1-mem-ctx-4 52%[=========> ] 1.38G 39.2MB/s eta 33s " ] }, { @@ -1295,7 +1632,7 @@ "output_type": "stream", "text": [ "\r", - "mem-ctx-4k.pth 78%[==============> ] 2.06G 74.3MB/s eta 7s " + "024-E0_1-mem-ctx-4k 52%[=========> ] 1.39G 39.4MB/s eta 33s " ] }, { @@ -1303,7 +1640,7 @@ "output_type": "stream", "text": [ "\r", - "em-ctx-4k.pth 78%[==============> ] 2.07G 75.5MB/s eta 7s " + "24-E0_1-mem-ctx-4k. 53%[=========> ] 1.40G 39.5MB/s eta 33s " ] }, { @@ -1311,7 +1648,7 @@ "output_type": "stream", "text": [ "\r", - "m-ctx-4k.pth 79%[==============> ] 2.09G 74.4MB/s eta 7s " + "4-E0_1-mem-ctx-4k.p 53%[=========> ] 1.40G 39.4MB/s eta 33s " ] }, { @@ -1319,7 +1656,7 @@ "output_type": "stream", "text": [ "\r", - "-ctx-4k.pth 80%[===============> ] 2.11G 74.8MB/s eta 7s " + "-E0_1-mem-ctx-4k.pt 53%[=========> ] 1.41G 39.4MB/s eta 32s " ] }, { @@ -1327,7 +1664,7 @@ "output_type": "stream", "text": [ "\r", - "ctx-4k.pth 80%[===============> ] 2.12G 75.1MB/s eta 7s " + "E0_1-mem-ctx-4k.pth 53%[=========> ] 1.42G 39.0MB/s eta 32s " ] }, { @@ -1335,7 +1672,7 @@ "output_type": "stream", "text": [ "\r", - "tx-4k.pth 81%[===============> ] 2.14G 77.3MB/s eta 6s " + "0_1-mem-ctx-4k.pth 54%[=========> ] 1.43G 40.3MB/s eta 32s " ] }, { @@ -1343,7 +1680,7 @@ "output_type": "stream", "text": [ "\r", - "x-4k.pth 81%[===============> ] 2.16G 81.6MB/s eta 6s " + "_1-mem-ctx-4k.pth 54%[=========> ] 1.44G 40.6MB/s eta 32s " ] }, { @@ -1351,7 +1688,7 @@ "output_type": "stream", "text": [ "\r", - "-4k.pth 82%[===============> ] 2.17G 81.8MB/s eta 6s " + "1-mem-ctx-4k.pth 54%[=========> ] 1.44G 42.8MB/s eta 32s " ] }, { @@ -1359,7 +1696,7 @@ "output_type": "stream", "text": [ "\r", - "4k.pth 83%[===============> ] 2.19G 82.7MB/s eta 6s " + "-mem-ctx-4k.pth 55%[==========> ] 1.45G 42.5MB/s eta 31s " ] }, { @@ -1367,7 +1704,7 @@ "output_type": "stream", "text": [ "\r", - "k.pth 83%[===============> ] 2.21G 83.5MB/s eta 6s " + "mem-ctx-4k.pth 55%[==========> ] 1.46G 40.5MB/s eta 31s " ] }, { @@ -1375,7 +1712,7 @@ "output_type": "stream", "text": [ "\r", - ".pth 84%[===============> ] 2.22G 82.8MB/s eta 5s " + "em-ctx-4k.pth 55%[==========> ] 1.47G 40.7MB/s eta 31s " ] }, { @@ -1383,7 +1720,7 @@ "output_type": "stream", "text": [ "\r", - "pth 85%[================> ] 2.24G 82.6MB/s eta 5s " + "m-ctx-4k.pth 56%[==========> ] 1.48G 40.5MB/s eta 31s " ] }, { @@ -1391,7 +1728,7 @@ "output_type": "stream", "text": [ "\r", - "th 85%[================> ] 2.26G 84.6MB/s eta 5s " + "-ctx-4k.pth 56%[==========> ] 1.48G 39.5MB/s eta 31s " ] }, { @@ -1399,7 +1736,7 @@ "output_type": "stream", "text": [ "\r", - "h 86%[================> ] 2.28G 84.4MB/s eta 5s " + "ctx-4k.pth 56%[==========> ] 1.49G 39.4MB/s eta 30s " ] }, { @@ -1407,7 +1744,7 @@ "output_type": "stream", "text": [ "\r", - " 87%[================> ] 2.29G 84.7MB/s eta 5s " + "tx-4k.pth 57%[==========> ] 1.50G 40.0MB/s eta 30s " ] }, { @@ -1415,7 +1752,7 @@ "output_type": "stream", "text": [ "\r", - " v 87%[================> ] 2.31G 84.6MB/s eta 4s " + "x-4k.pth 57%[==========> ] 1.51G 39.8MB/s eta 30s " ] }, { @@ -1423,7 +1760,7 @@ "output_type": "stream", "text": [ "\r", - " v5 88%[================> ] 2.33G 84.7MB/s eta 4s " + "-4k.pth 57%[==========> ] 1.52G 39.9MB/s eta 30s " ] }, { @@ -1431,7 +1768,7 @@ "output_type": "stream", "text": [ "\r", - " v5- 88%[================> ] 2.34G 84.0MB/s eta 4s " + "4k.pth 57%[==========> ] 1.53G 39.6MB/s eta 30s " ] }, { @@ -1439,7 +1776,7 @@ "output_type": "stream", "text": [ "\r", - " v5-L 89%[================> ] 2.36G 85.4MB/s eta 4s " + "k.pth 58%[==========> ] 1.54G 40.3MB/s eta 28s " ] }, { @@ -1447,7 +1784,7 @@ "output_type": "stream", "text": [ "\r", - " v5-L9 90%[=================> ] 2.37G 84.9MB/s eta 4s " + ".pth 58%[==========> ] 1.54G 39.8MB/s eta 28s " ] }, { @@ -1455,7 +1792,7 @@ "output_type": "stream", "text": [ "\r", - " v5-L96 90%[=================> ] 2.39G 85.9MB/s eta 3s " + "pth 58%[==========> ] 1.55G 40.0MB/s eta 28s " ] }, { @@ -1463,7 +1800,7 @@ "output_type": "stream", "text": [ "\r", - " v5-L96- 91%[=================> ] 2.41G 85.4MB/s eta 3s " + "th 59%[==========> ] 1.56G 39.6MB/s eta 28s " ] }, { @@ -1471,7 +1808,7 @@ "output_type": "stream", "text": [ "\r", - " v5-L96-D 92%[=================> ] 2.42G 85.3MB/s eta 3s " + "h 59%[==========> ] 1.57G 39.9MB/s eta 28s " ] }, { @@ -1479,7 +1816,7 @@ "output_type": "stream", "text": [ "\r", - " v5-L96-D1 92%[=================> ] 2.44G 84.5MB/s eta 3s " + " 59%[==========> ] 1.58G 39.5MB/s eta 27s " ] }, { @@ -1487,7 +1824,7 @@ "output_type": "stream", "text": [ "\r", - " v5-L96-D10 93%[=================> ] 2.46G 85.1MB/s eta 3s " + " v 60%[===========> ] 1.58G 39.8MB/s eta 27s " ] }, { @@ -1495,7 +1832,7 @@ "output_type": "stream", "text": [ "\r", - " v5-L96-D102 94%[=================> ] 2.47G 84.5MB/s eta 2s " + " v5 60%[===========> ] 1.59G 39.8MB/s eta 27s " ] }, { @@ -1503,7 +1840,7 @@ "output_type": "stream", "text": [ "\r", - " v5-L96-D1024 94%[=================> ] 2.49G 84.9MB/s eta 2s " + " v5- 60%[===========> ] 1.60G 39.9MB/s eta 27s " ] }, { @@ -1511,7 +1848,7 @@ "output_type": "stream", "text": [ "\r", - " v5-L96-D1024- 95%[==================> ] 2.51G 85.3MB/s eta 2s " + " v5-L 61%[===========> ] 1.61G 40.0MB/s eta 27s " ] }, { @@ -1519,7 +1856,7 @@ "output_type": "stream", "text": [ "\r", - " v5-L96-D1024-E 95%[==================> ] 2.53G 84.6MB/s eta 2s " + " v5-L9 61%[===========> ] 1.62G 40.5MB/s eta 26s " ] }, { @@ -1527,7 +1864,7 @@ "output_type": "stream", "text": [ "\r", - " v5-L96-D1024-E0 96%[==================> ] 2.54G 85.4MB/s eta 2s " + " v5-L96 61%[===========> ] 1.63G 40.7MB/s eta 26s " ] }, { @@ -1535,7 +1872,7 @@ "output_type": "stream", "text": [ "\r", - " v5-L96-D1024-E0_ 97%[==================> ] 2.56G 84.5MB/s eta 1s " + " v5-L96- 62%[===========> ] 1.63G 40.6MB/s eta 26s " ] }, { @@ -1543,7 +1880,7 @@ "output_type": "stream", "text": [ "\r", - " v5-L96-D1024-E0_1 97%[==================> ] 2.58G 84.1MB/s eta 1s " + " v5-L96-D 62%[===========> ] 1.64G 41.2MB/s eta 26s " ] }, { @@ -1551,7 +1888,7 @@ "output_type": "stream", "text": [ "\r", - " v5-L96-D1024-E0_1- 98%[==================> ] 2.60G 85.3MB/s eta 1s " + " v5-L96-D1 62%[===========> ] 1.65G 41.0MB/s eta 26s " ] }, { @@ -1559,7 +1896,7 @@ "output_type": "stream", "text": [ "\r", - "v5-L96-D1024-E0_1-m 99%[==================> ] 2.61G 85.9MB/s eta 1s " + " v5-L96-D10 63%[===========> ] 1.66G 40.7MB/s eta 25s " ] }, { @@ -1567,100348 +1904,7 @@ "output_type": "stream", "text": [ "\r", - "5-L96-D1024-E0_1-me 99%[==================> ] 2.63G 84.7MB/s eta 1s \r", - "v5-L96-D1024-E0_1-m 100%[===================>] 2.63G 84.9MB/s in 33s \r\n", - "\r\n", - "2023-09-02 08:41:46 (80.6 MB/s) - ‘v5-L96-D1024-E0_1-mem-ctx-4k.pth’ saved [2825976699/2825976699]\r\n", - "\r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "total 2.7G\r\n", - "drwxr-xr-x 2 root root 54 Sep 2 08:41 .\r\n", - "drwxr-xr-x 19 root root 4.0K Sep 2 08:41 ..\r\n", - "-rw-r--r-- 1 root root 2.7G Sep 2 05:37 v5-L96-D1024-E0_1-mem-ctx-4k.pth\r\n" - ] - } - ], - "source": [ - "# Download the model directly (stop gap till HF sync issues is resolved)\n", - "!cd \"{TRAINER_DIR}\" && cd \"../model/\" && \\\n", - " wget -nc \"https://huggingface.co/rwkv-x-dev/rwkv-x-playground/resolve/main/experiment/rwkv-x-exp/v5-memory/{FILENAME_PREFIX}-mem-ctx-4k.pth\"\n", - "\n", - "!cd \"{TRAINER_DIR}\" && cd \"../model/\" && \\\n", - " ls -alh ." - ] - }, - { - "cell_type": "markdown", - "id": "eafbdbb6", - "metadata": { - "papermill": { - "duration": 0.010117, - "end_time": "2023-09-02T08:41:46.820211", - "exception": false, - "start_time": "2023-09-02T08:41:46.810094", - "status": "completed" - }, - "tags": [] - }, - "source": [ - "## Tune 6 : Ramping up the ctx size (8192), memory training\n", - "\n", - "- Tune 6: Large ctx size (8192), Scaling up!" - ] - }, - { - "cell_type": "code", - "execution_count": 5, - "id": "7a3deb9d", - "metadata": { - "execution": { - "iopub.execute_input": "2023-09-02T08:41:46.844105Z", - "iopub.status.busy": "2023-09-02T08:41:46.843909Z", - "iopub.status.idle": "2023-09-02T08:41:53.856857Z", - "shell.execute_reply": "2023-09-02T08:41:53.856017Z" - }, - "papermill": { - "duration": 7.084423, - "end_time": "2023-09-02T08:41:53.914741", - "exception": false, - "start_time": "2023-09-02T08:41:46.830318", - "status": "completed" - }, - "tags": [] - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "## Generating word reptition dataset ##\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 40 max words, 50 samples - at ../dataset/gen-word-40-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 130 samples (1 token repeat) - 20 max words - at ../dataset/shuffle-word-20-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 45 max words, 50 samples - at ../dataset/gen-word-45-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 25 max words, 50 samples - at ../dataset/gen-word-25-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 5 max words, 50 samples - at ../dataset/gen-word-5-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 89 samples (1 token repeat) - 30 max words - at ../dataset/shuffle-word-30-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 30 max words, 50 samples - at ../dataset/gen-word-30-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 50 max words, 50 samples - at ../dataset/gen-word-50-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 179 samples (1 token repeat) - 15 max words - at ../dataset/shuffle-word-15-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 65 max words, 50 samples - at ../dataset/gen-word-65-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 34 samples (1 token repeat) - 80 max words - at ../dataset/shuffle-word-80-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 75 samples (1 token repeat) - 35 max words - at ../dataset/shuffle-word-35-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 60 max words, 50 samples - at ../dataset/gen-word-60-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 263 samples (1 token repeat) - 10 max words - at ../dataset/shuffle-word-10-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 20 max words, 50 samples - at ../dataset/gen-word-20-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 103 samples (1 token repeat) - 25 max words - at ../dataset/shuffle-word-25-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 55 max words, 50 samples - at ../dataset/gen-word-55-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 61 samples (1 token repeat) - 45 max words - at ../dataset/shuffle-word-45-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 38 samples (1 token repeat) - 70 max words - at ../dataset/shuffle-word-70-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 554 samples (1 token repeat) - 5 max words - at ../dataset/shuffle-word-5-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 55 samples (1 token repeat) - 50 max words - at ../dataset/shuffle-word-50-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 95 max words, 50 samples - at ../dataset/gen-word-95-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 43 samples (1 token repeat) - 60 max words - at ../dataset/shuffle-word-60-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 70 max words, 50 samples - at ../dataset/gen-word-70-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 175 max words, 50 samples - at ../dataset/gen-word-175-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 75 max words, 50 samples - at ../dataset/gen-word-75-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 48 samples (1 token repeat) - 55 max words - at ../dataset/shuffle-word-55-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 29 samples (1 token repeat) - 90 max words - at ../dataset/shuffle-word-90-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 17 samples (1 token repeat) - 135 max words - at ../dataset/shuffle-word-135-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 29 samples (1 token repeat) - 95 max words - at ../dataset/shuffle-word-95-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 25 samples (1 token repeat) - 100 max words - at ../dataset/shuffle-word-100-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 15 max words, 50 samples - at ../dataset/gen-word-15-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 2 max words, 50 samples - at ../dataset/word-2-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 110 max words, 50 samples - at ../dataset/gen-word-110-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 90 max words, 50 samples - at ../dataset/gen-word-90-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 85 max words, 50 samples - at ../dataset/gen-word-85-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 68 samples (1 token repeat) - 40 max words - at ../dataset/shuffle-word-40-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 34 samples (1 token repeat) - 75 max words - at ../dataset/shuffle-word-75-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 130 max words, 50 samples - at ../dataset/gen-word-130-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 125 max words, 50 samples - at ../dataset/gen-word-125-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 140 max words, 50 samples - at ../dataset/gen-word-140-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 21 samples (1 token repeat) - 105 max words - at ../dataset/shuffle-word-105-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 10 max words, 50 samples - at ../dataset/gen-word-10-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 7 samples (1 token repeat) - 315 max words - at ../dataset/shuffle-word-315-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 10 samples (1 token repeat) - 215 max words - at ../dataset/shuffle-word-215-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 18 samples (1 token repeat) - 120 max words - at ../dataset/shuffle-word-120-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 7 samples (1 token repeat) - 305 max words - at ../dataset/shuffle-word-305-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 335 max words, 50 samples - at ../dataset/gen-word-335-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 10 samples (1 token repeat) - 240 max words - at ../dataset/shuffle-word-240-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 20 samples (1 token repeat) - 115 max words - at ../dataset/shuffle-word-115-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 16 samples (1 token repeat) - 145 max words - at ../dataset/shuffle-word-145-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 15 samples (1 token repeat) - 150 max words - at ../dataset/shuffle-word-150-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 180 max words, 50 samples - at ../dataset/gen-word-180-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 16 samples (1 token repeat) - 140 max words - at ../dataset/shuffle-word-140-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 120 max words, 50 samples - at ../dataset/gen-word-120-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 7 samples (1 token repeat) - 335 max words - at ../dataset/shuffle-word-335-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 115 max words, 50 samples - at ../dataset/gen-word-115-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 7 samples (1 token repeat) - 325 max words - at ../dataset/shuffle-word-325-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 195 max words, 50 samples - at ../dataset/gen-word-195-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 35 max words, 50 samples - at ../dataset/gen-word-35-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 18 samples (1 token repeat) - 125 max words - at ../dataset/shuffle-word-125-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 21 samples (1 token repeat) - 110 max words - at ../dataset/shuffle-word-110-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 9 samples (1 token repeat) - 285 max words - at ../dataset/shuffle-word-285-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 10 samples (1 token repeat) - 275 max words - at ../dataset/shuffle-word-275-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 10 samples (1 token repeat) - 220 max words - at ../dataset/shuffle-word-220-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 190 max words, 50 samples - at ../dataset/gen-word-190-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 14 samples (1 token repeat) - 190 max words - at ../dataset/shuffle-word-190-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 215 max words, 50 samples - at ../dataset/gen-word-215-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 370 max words, 50 samples - at ../dataset/gen-word-370-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 7 samples (1 token repeat) - 355 max words - at ../dataset/shuffle-word-355-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 41 samples (1 token repeat) - 65 max words - at ../dataset/shuffle-word-65-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 270 max words, 50 samples - at ../dataset/gen-word-270-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 450 max words, 50 samples - at ../dataset/gen-word-450-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 7 samples (1 token repeat) - 400 max words - at ../dataset/shuffle-word-400-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 13 samples (1 token repeat) - 195 max words - at ../dataset/shuffle-word-195-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 275 max words, 50 samples - at ../dataset/gen-word-275-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 350 max words, 50 samples - at ../dataset/gen-word-350-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 535 max words, 50 samples - at ../dataset/gen-word-535-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 100 max words, 50 samples - at ../dataset/gen-word-100-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 33 samples (1 token repeat) - 85 max words - at ../dataset/shuffle-word-85-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 5 samples (1 token repeat) - 525 max words - at ../dataset/shuffle-word-525-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 210 max words, 50 samples - at ../dataset/gen-word-210-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 155 max words, 50 samples - at ../dataset/gen-word-155-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 13 samples (1 token repeat) - 200 max words - at ../dataset/shuffle-word-200-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 145 max words, 50 samples - at ../dataset/gen-word-145-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 355 max words, 50 samples - at ../dataset/gen-word-355-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 10 samples (1 token repeat) - 230 max words - at ../dataset/shuffle-word-230-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 17 samples (1 token repeat) - 130 max words - at ../dataset/shuffle-word-130-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 240 max words, 50 samples - at ../dataset/gen-word-240-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 15 samples (1 token repeat) - 155 max words - at ../dataset/shuffle-word-155-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 330 max words, 50 samples - at ../dataset/gen-word-330-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 185 max words, 50 samples - at ../dataset/gen-word-185-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 5 samples (1 token repeat) - 570 max words - at ../dataset/shuffle-word-570-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 265 max words, 50 samples - at ../dataset/gen-word-265-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 15 samples (1 token repeat) - 160 max words - at ../dataset/shuffle-word-160-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 225 max words, 50 samples - at ../dataset/gen-word-225-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 430 max words, 50 samples - at ../dataset/gen-word-430-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 14 samples (1 token repeat) - 165 max words - at ../dataset/shuffle-word-165-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 14 samples (1 token repeat) - 170 max words - at ../dataset/shuffle-word-170-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 11 samples (1 token repeat) - 205 max words - at ../dataset/shuffle-word-205-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 460 max words, 50 samples - at ../dataset/gen-word-460-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 465 max words, 50 samples - at ../dataset/gen-word-465-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 400 max words, 50 samples - at ../dataset/gen-word-400-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 415 max words, 50 samples - at ../dataset/gen-word-415-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 3 samples (1 token repeat) - 960 max words - at ../dataset/shuffle-word-960-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 160 max words, 50 samples - at ../dataset/gen-word-160-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 3 samples (1 token repeat) - 825 max words - at ../dataset/shuffle-word-825-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 3 samples (1 token repeat) - 915 max words - at ../dataset/shuffle-word-915-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 4 samples (1 token repeat) - 710 max words - at ../dataset/shuffle-word-710-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 710 max words, 50 samples - at ../dataset/gen-word-710-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 5 samples (1 token repeat) - 510 max words - at ../dataset/shuffle-word-510-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 5 samples (1 token repeat) - 585 max words - at ../dataset/shuffle-word-585-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 850 max words, 50 samples - at ../dataset/gen-word-850-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 385 max words, 50 samples - at ../dataset/gen-word-385-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 10 samples (1 token repeat) - 225 max words - at ../dataset/shuffle-word-225-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 3 samples (1 token repeat) - 955 max words - at ../dataset/shuffle-word-955-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 5 samples (1 token repeat) - 520 max words - at ../dataset/shuffle-word-520-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 9 samples (1 token repeat) - 290 max words - at ../dataset/shuffle-word-290-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 755 max words, 50 samples - at ../dataset/gen-word-755-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 800 max words, 50 samples - at ../dataset/gen-word-800-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 6 samples (1 token repeat) - 460 max words - at ../dataset/shuffle-word-460-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 3 samples (1 token repeat) - 830 max words - at ../dataset/shuffle-word-830-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 3 samples (1 token repeat) - 965 max words - at ../dataset/shuffle-word-965-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 6 samples (1 token repeat) - 475 max words - at ../dataset/shuffle-word-475-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 3 samples (1 token repeat) - 910 max words - at ../dataset/shuffle-word-910-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 3 samples (1 token repeat) - 885 max words - at ../dataset/shuffle-word-885-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 590 max words, 50 samples - at ../dataset/gen-word-590-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 750 max words, 50 samples - at ../dataset/gen-word-750-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 5000 max words - at ../dataset/shuffle-word-5000-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 7 samples (1 token repeat) - 395 max words - at ../dataset/shuffle-word-395-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 635 max words, 50 samples - at ../dataset/gen-word-635-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 790 max words, 50 samples - at ../dataset/gen-word-790-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 940 max words, 50 samples - at ../dataset/gen-word-940-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 3 samples (1 token repeat) - 820 max words - at ../dataset/shuffle-word-820-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 935 max words, 50 samples - at ../dataset/gen-word-935-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 7 samples (1 token repeat) - 390 max words - at ../dataset/shuffle-word-390-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 4800 max words - at ../dataset/shuffle-word-4800-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 13 samples (1 token repeat) - 185 max words - at ../dataset/shuffle-word-185-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 3 samples (1 token repeat) - 975 max words - at ../dataset/shuffle-word-975-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 250 max words, 50 samples - at ../dataset/gen-word-250-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 4 samples (1 token repeat) - 685 max words - at ../dataset/shuffle-word-685-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 105 max words, 50 samples - at ../dataset/gen-word-105-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 205 max words, 50 samples - at ../dataset/gen-word-205-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 80 max words, 50 samples - at ../dataset/gen-word-80-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 390 max words, 50 samples - at ../dataset/gen-word-390-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 830 max words, 50 samples - at ../dataset/gen-word-830-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 4500 max words - at ../dataset/shuffle-word-4500-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 4400 max words - at ../dataset/shuffle-word-4400-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 420 max words, 50 samples - at ../dataset/gen-word-420-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 405 max words, 50 samples - at ../dataset/gen-word-405-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 490 max words, 50 samples - at ../dataset/gen-word-490-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 3 samples (1 token repeat) - 865 max words - at ../dataset/shuffle-word-865-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 4 samples (1 token repeat) - 800 max words - at ../dataset/shuffle-word-800-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 3 samples (1 token repeat) - 875 max words - at ../dataset/shuffle-word-875-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 860 max words, 50 samples - at ../dataset/gen-word-860-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 15 samples (1 token repeat) - 175 max words - at ../dataset/shuffle-word-175-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 3 samples (1 token repeat) - 905 max words - at ../dataset/shuffle-word-905-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 4 samples (1 token repeat) - 765 max words - at ../dataset/shuffle-word-765-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 8 samples (1 token repeat) - 310 max words - at ../dataset/shuffle-word-310-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 7 samples (1 token repeat) - 350 max words - at ../dataset/shuffle-word-350-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 3 samples (1 token repeat) - 985 max words - at ../dataset/shuffle-word-985-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 9 samples (1 token repeat) - 260 max words - at ../dataset/shuffle-word-260-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 4 samples (1 token repeat) - 655 max words - at ../dataset/shuffle-word-655-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 815 max words, 50 samples - at ../dataset/gen-word-815-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 5 samples (1 token repeat) - 545 max words - at ../dataset/shuffle-word-545-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 4 samples (1 token repeat) - 750 max words - at ../dataset/shuffle-word-750-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 3 samples (1 token repeat) - 950 max words - at ../dataset/shuffle-word-950-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 7 samples (1 token repeat) - 360 max words - at ../dataset/shuffle-word-360-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 4 samples (1 token repeat) - 760 max words - at ../dataset/shuffle-word-760-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 14 samples (1 token repeat) - 180 max words - at ../dataset/shuffle-word-180-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 9 samples (1 token repeat) - 255 max words - at ../dataset/shuffle-word-255-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 5 samples (1 token repeat) - 530 max words - at ../dataset/shuffle-word-530-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 7 samples (1 token repeat) - 340 max words - at ../dataset/shuffle-word-340-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 37 samples (20 token repeat) - 2500 max words - at ../dataset/shuffle-word-2500-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 3 samples (1 token repeat) - 890 max words - at ../dataset/shuffle-word-890-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 320 max words, 50 samples - at ../dataset/gen-word-320-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 3 samples (1 token repeat) - 995 max words - at ../dataset/shuffle-word-995-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 7 samples (1 token repeat) - 330 max words - at ../dataset/shuffle-word-330-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 3 samples (1 token repeat) - 900 max words - at ../dataset/shuffle-word-900-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 6 samples (1 token repeat) - 405 max words - at ../dataset/shuffle-word-405-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 4 samples (1 token repeat) - 670 max words - at ../dataset/shuffle-word-670-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 3 samples (1 token repeat) - 990 max words - at ../dataset/shuffle-word-990-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 3 samples (1 token repeat) - 870 max words - at ../dataset/shuffle-word-870-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 900 max words, 50 samples - at ../dataset/gen-word-900-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 5 samples (1 token repeat) - 595 max words - at ../dataset/shuffle-word-595-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 480 max words, 50 samples - at ../dataset/gen-word-480-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 3 samples (1 token repeat) - 980 max words - at ../dataset/shuffle-word-980-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 235 max words, 50 samples - at ../dataset/gen-word-235-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 6 samples (1 token repeat) - 425 max words - at ../dataset/shuffle-word-425-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 6 samples (1 token repeat) - 455 max words - at ../dataset/shuffle-word-455-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 610 max words, 50 samples - at ../dataset/gen-word-610-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 150 max words, 50 samples - at ../dataset/gen-word-150-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 200 max words, 50 samples - at ../dataset/gen-word-200-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 3 samples (1 token repeat) - 970 max words - at ../dataset/shuffle-word-970-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 7600 max words - at ../dataset/shuffle-word-7600-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 3 samples (1 token repeat) - 895 max words - at ../dataset/shuffle-word-895-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 440 max words, 50 samples - at ../dataset/gen-word-440-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 955 max words, 50 samples - at ../dataset/gen-word-955-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 280 max words, 50 samples - at ../dataset/gen-word-280-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 7 samples (1 token repeat) - 375 max words - at ../dataset/shuffle-word-375-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 920 max words, 50 samples - at ../dataset/gen-word-920-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 600 max words, 50 samples - at ../dataset/gen-word-600-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 4000 max words - at ../dataset/shuffle-word-4000-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 445 max words, 50 samples - at ../dataset/gen-word-445-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 510 max words, 50 samples - at ../dataset/gen-word-510-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 3200 max words - at ../dataset/shuffle-word-3200-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 6900 max words - at ../dataset/shuffle-word-6900-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 895 max words, 50 samples - at ../dataset/gen-word-895-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 4 samples (1 token repeat) - 630 max words - at ../dataset/shuffle-word-630-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 8000 max words - at ../dataset/shuffle-word-8000-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 3 samples (1 token repeat) - 860 max words - at ../dataset/shuffle-word-860-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 3 samples (1 token repeat) - 935 max words - at ../dataset/shuffle-word-935-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 4 samples (1 token repeat) - 625 max words - at ../dataset/shuffle-word-625-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 6 samples (1 token repeat) - 495 max words - at ../dataset/shuffle-word-495-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 905 max words, 50 samples - at ../dataset/gen-word-905-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 290 max words, 50 samples - at ../dataset/gen-word-290-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 325 max words, 50 samples - at ../dataset/gen-word-325-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 5 samples (1 token repeat) - 560 max words - at ../dataset/shuffle-word-560-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 4 samples (1 token repeat) - 640 max words - at ../dataset/shuffle-word-640-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 875 max words, 50 samples - at ../dataset/gen-word-875-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 5 samples (1 token repeat) - 540 max words - at ../dataset/shuffle-word-540-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 4 samples (1 token repeat) - 720 max words - at ../dataset/shuffle-word-720-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 5 samples (1 token repeat) - 485 max words - at ../dataset/shuffle-word-485-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 340 max words, 50 samples - at ../dataset/gen-word-340-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 7 samples (1 token repeat) - 320 max words - at ../dataset/shuffle-word-320-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 4 samples (1 token repeat) - 705 max words - at ../dataset/shuffle-word-705-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 865 max words, 50 samples - at ../dataset/gen-word-865-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 310 max words, 50 samples - at ../dataset/gen-word-310-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 425 max words, 50 samples - at ../dataset/gen-word-425-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 990 max words, 50 samples - at ../dataset/gen-word-990-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 6400 max words - at ../dataset/shuffle-word-6400-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 7 samples (1 token repeat) - 365 max words - at ../dataset/shuffle-word-365-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 6 samples (1 token repeat) - 450 max words - at ../dataset/shuffle-word-450-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 5 samples (1 token repeat) - 580 max words - at ../dataset/shuffle-word-580-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 820 max words, 50 samples - at ../dataset/gen-word-820-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 5 samples (1 token repeat) - 565 max words - at ../dataset/shuffle-word-565-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 7100 max words - at ../dataset/shuffle-word-7100-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 9 samples (1 token repeat) - 270 max words - at ../dataset/shuffle-word-270-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 4 samples (1 token repeat) - 730 max words - at ../dataset/shuffle-word-730-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 795 max words, 50 samples - at ../dataset/gen-word-795-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 7 samples (1 token repeat) - 385 max words - at ../dataset/shuffle-word-385-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 5 samples (1 token repeat) - 505 max words - at ../dataset/shuffle-word-505-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 3 samples (1 token repeat) - 925 max words - at ../dataset/shuffle-word-925-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 4 samples (1 token repeat) - 615 max words - at ../dataset/shuffle-word-615-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 6 samples (1 token repeat) - 440 max words - at ../dataset/shuffle-word-440-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 9 samples (1 token repeat) - 245 max words - at ../dataset/shuffle-word-245-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 6 samples (1 token repeat) - 435 max words - at ../dataset/shuffle-word-435-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 720 max words, 50 samples - at ../dataset/gen-word-720-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 805 max words, 50 samples - at ../dataset/gen-word-805-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 5 samples (1 token repeat) - 590 max words - at ../dataset/shuffle-word-590-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 260 max words, 50 samples - at ../dataset/gen-word-260-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 3 samples (1 token repeat) - 835 max words - at ../dataset/shuffle-word-835-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 375 max words, 50 samples - at ../dataset/gen-word-375-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 29 samples (20 token repeat) - 2600 max words - at ../dataset/shuffle-word-2600-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 495 max words, 50 samples - at ../dataset/gen-word-495-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 380 max words, 50 samples - at ../dataset/gen-word-380-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 565 max words, 50 samples - at ../dataset/gen-word-565-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 6 samples (1 token repeat) - 470 max words - at ../dataset/shuffle-word-470-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 745 max words, 50 samples - at ../dataset/gen-word-745-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 4 samples (1 token repeat) - 785 max words - at ../dataset/shuffle-word-785-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 9 samples (1 token repeat) - 300 max words - at ../dataset/shuffle-word-300-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 475 max words, 50 samples - at ../dataset/gen-word-475-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 135 max words, 50 samples - at ../dataset/gen-word-135-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 4900 max words - at ../dataset/shuffle-word-4900-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 7500 max words - at ../dataset/shuffle-word-7500-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 775 max words, 50 samples - at ../dataset/gen-word-775-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 470 max words, 50 samples - at ../dataset/gen-word-470-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 6 samples (1 token repeat) - 500 max words - at ../dataset/shuffle-word-500-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 500 max words, 50 samples - at ../dataset/gen-word-500-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 885 max words, 50 samples - at ../dataset/gen-word-885-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 525 max words, 50 samples - at ../dataset/gen-word-525-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 165 max words, 50 samples - at ../dataset/gen-word-165-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 770 max words, 50 samples - at ../dataset/gen-word-770-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 40 samples (20 token repeat) - 2100 max words - at ../dataset/shuffle-word-2100-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 3300 max words - at ../dataset/shuffle-word-3300-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 6800 max words - at ../dataset/shuffle-word-6800-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 625 max words, 50 samples - at ../dataset/gen-word-625-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 5400 max words - at ../dataset/shuffle-word-5400-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 540 max words, 50 samples - at ../dataset/gen-word-540-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 7000 max words - at ../dataset/shuffle-word-7000-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 4600 max words - at ../dataset/shuffle-word-4600-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 345 max words, 50 samples - at ../dataset/gen-word-345-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 665 max words, 50 samples - at ../dataset/gen-word-665-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 40 samples (20 token repeat) - 1900 max words - at ../dataset/shuffle-word-1900-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 170 max words, 50 samples - at ../dataset/gen-word-170-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 60 samples (20 token repeat) - 1100 max words - at ../dataset/shuffle-word-1100-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 640 max words, 50 samples - at ../dataset/gen-word-640-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 51 samples (20 token repeat) - 1300 max words - at ../dataset/shuffle-word-1300-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 6100 max words - at ../dataset/shuffle-word-6100-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 985 max words, 50 samples - at ../dataset/gen-word-985-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 7800 max words - at ../dataset/shuffle-word-7800-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 395 max words, 50 samples - at ../dataset/gen-word-395-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 7200 max words - at ../dataset/shuffle-word-7200-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 6500 max words - at ../dataset/shuffle-word-6500-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 975 max words, 50 samples - at ../dataset/gen-word-975-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 315 max words, 50 samples - at ../dataset/gen-word-315-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 655 max words, 50 samples - at ../dataset/gen-word-655-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 3700 max words - at ../dataset/shuffle-word-3700-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 7400 max words - at ../dataset/shuffle-word-7400-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 555 max words, 50 samples - at ../dataset/gen-word-555-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 3600 max words - at ../dataset/shuffle-word-3600-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 6 samples (1 token repeat) - 465 max words - at ../dataset/shuffle-word-465-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 7 samples (1 token repeat) - 370 max words - at ../dataset/shuffle-word-370-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 3000 max words - at ../dataset/shuffle-word-3000-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 4 samples (1 token repeat) - 715 max words - at ../dataset/shuffle-word-715-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 11 samples (1 token repeat) - 210 max words - at ../dataset/shuffle-word-210-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 9 samples (1 token repeat) - 280 max words - at ../dataset/shuffle-word-280-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 220 max words, 50 samples - at ../dataset/gen-word-220-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 230 max words, 50 samples - at ../dataset/gen-word-230-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 7 samples (1 token repeat) - 380 max words - at ../dataset/shuffle-word-380-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 4 samples (1 token repeat) - 780 max words - at ../dataset/shuffle-word-780-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 3 samples (1 token repeat) - 850 max words - at ../dataset/shuffle-word-850-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 5 samples (1 token repeat) - 535 max words - at ../dataset/shuffle-word-535-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 435 max words, 50 samples - at ../dataset/gen-word-435-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 4 samples (1 token repeat) - 690 max words - at ../dataset/shuffle-word-690-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 4 samples (1 token repeat) - 645 max words - at ../dataset/shuffle-word-645-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 9 samples (1 token repeat) - 250 max words - at ../dataset/shuffle-word-250-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 5 samples (1 token repeat) - 600 max words - at ../dataset/shuffle-word-600-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 580 max words, 50 samples - at ../dataset/gen-word-580-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 285 max words, 50 samples - at ../dataset/gen-word-285-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 595 max words, 50 samples - at ../dataset/gen-word-595-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 695 max words, 50 samples - at ../dataset/gen-word-695-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 4 samples (1 token repeat) - 735 max words - at ../dataset/shuffle-word-735-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 255 max words, 50 samples - at ../dataset/gen-word-255-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 855 max words, 50 samples - at ../dataset/gen-word-855-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 5 samples (1 token repeat) - 415 max words - at ../dataset/shuffle-word-415-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 4 samples (1 token repeat) - 610 max words - at ../dataset/shuffle-word-610-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 5 samples (1 token repeat) - 420 max words - at ../dataset/shuffle-word-420-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 3 samples (1 token repeat) - 945 max words - at ../dataset/shuffle-word-945-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 530 max words, 50 samples - at ../dataset/gen-word-530-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 545 max words, 50 samples - at ../dataset/gen-word-545-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 690 max words, 50 samples - at ../dataset/gen-word-690-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 615 max words, 50 samples - at ../dataset/gen-word-615-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 4 samples (1 token repeat) - 620 max words - at ../dataset/shuffle-word-620-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 6300 max words - at ../dataset/shuffle-word-6300-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 575 max words, 50 samples - at ../dataset/gen-word-575-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 7 samples (1 token repeat) - 345 max words - at ../dataset/shuffle-word-345-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 3 samples (1 token repeat) - 930 max words - at ../dataset/shuffle-word-930-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 845 max words, 50 samples - at ../dataset/gen-word-845-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 3 samples (1 token repeat) - 1000 max words - at ../dataset/shuffle-word-1000-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 7300 max words - at ../dataset/shuffle-word-7300-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 4 samples (1 token repeat) - 725 max words - at ../dataset/shuffle-word-725-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 23 samples (20 token repeat) - 2800 max words - at ../dataset/shuffle-word-2800-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 6700 max words - at ../dataset/shuffle-word-6700-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 735 max words, 50 samples - at ../dataset/gen-word-735-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 4 samples (1 token repeat) - 745 max words - at ../dataset/shuffle-word-745-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 4 samples (1 token repeat) - 695 max words - at ../dataset/shuffle-word-695-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 9 samples (1 token repeat) - 295 max words - at ../dataset/shuffle-word-295-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 5200 max words - at ../dataset/shuffle-word-5200-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 5900 max words - at ../dataset/shuffle-word-5900-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 3 samples (1 token repeat) - 880 max words - at ../dataset/shuffle-word-880-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 4 samples (1 token repeat) - 605 max words - at ../dataset/shuffle-word-605-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 915 max words, 50 samples - at ../dataset/gen-word-915-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 585 max words, 50 samples - at ../dataset/gen-word-585-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 4 samples (1 token repeat) - 675 max words - at ../dataset/shuffle-word-675-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 3 samples (1 token repeat) - 815 max words - at ../dataset/shuffle-word-815-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 715 max words, 50 samples - at ../dataset/gen-word-715-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 515 max words, 50 samples - at ../dataset/gen-word-515-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 645 max words, 50 samples - at ../dataset/gen-word-645-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 5 samples (1 token repeat) - 555 max words - at ../dataset/shuffle-word-555-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 4 samples (1 token repeat) - 635 max words - at ../dataset/shuffle-word-635-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 9 samples (1 token repeat) - 265 max words - at ../dataset/shuffle-word-265-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 6 samples (1 token repeat) - 430 max words - at ../dataset/shuffle-word-430-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 6 samples (1 token repeat) - 410 max words - at ../dataset/shuffle-word-410-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 3 samples (1 token repeat) - 940 max words - at ../dataset/shuffle-word-940-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 485 max words, 50 samples - at ../dataset/gen-word-485-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 305 max words, 50 samples - at ../dataset/gen-word-305-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 3 samples (1 token repeat) - 840 max words - at ../dataset/shuffle-word-840-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 4 samples (1 token repeat) - 770 max words - at ../dataset/shuffle-word-770-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 780 max words, 50 samples - at ../dataset/gen-word-780-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 950 max words, 50 samples - at ../dataset/gen-word-950-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 4 samples (1 token repeat) - 755 max words - at ../dataset/shuffle-word-755-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 4 samples (1 token repeat) - 660 max words - at ../dataset/shuffle-word-660-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 650 max words, 50 samples - at ../dataset/gen-word-650-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 5 samples (1 token repeat) - 515 max words - at ../dataset/shuffle-word-515-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 10 samples (1 token repeat) - 235 max words - at ../dataset/shuffle-word-235-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 725 max words, 50 samples - at ../dataset/gen-word-725-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 5 samples (1 token repeat) - 575 max words - at ../dataset/shuffle-word-575-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 4 samples (1 token repeat) - 700 max words - at ../dataset/shuffle-word-700-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 3 samples (1 token repeat) - 845 max words - at ../dataset/shuffle-word-845-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 700 max words, 50 samples - at ../dataset/gen-word-700-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 880 max words, 50 samples - at ../dataset/gen-word-880-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 505 max words, 50 samples - at ../dataset/gen-word-505-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 910 max words, 50 samples - at ../dataset/gen-word-910-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 300 max words, 50 samples - at ../dataset/gen-word-300-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 4100 max words - at ../dataset/shuffle-word-4100-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 4300 max words - at ../dataset/shuffle-word-4300-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 705 max words, 50 samples - at ../dataset/gen-word-705-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 4 samples (1 token repeat) - 665 max words - at ../dataset/shuffle-word-665-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 365 max words, 50 samples - at ../dataset/gen-word-365-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 4 samples (1 token repeat) - 775 max words - at ../dataset/shuffle-word-775-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 965 max words, 50 samples - at ../dataset/gen-word-965-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 23 samples (20 token repeat) - 2700 max words - at ../dataset/shuffle-word-2700-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 3400 max words - at ../dataset/shuffle-word-3400-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 3800 max words - at ../dataset/shuffle-word-3800-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 810 max words, 50 samples - at ../dataset/gen-word-810-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 4 samples (1 token repeat) - 790 max words - at ../dataset/shuffle-word-790-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 605 max words, 50 samples - at ../dataset/gen-word-605-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 560 max words, 50 samples - at ../dataset/gen-word-560-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 410 max words, 50 samples - at ../dataset/gen-word-410-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 520 max words, 50 samples - at ../dataset/gen-word-520-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 41 samples (20 token repeat) - 1400 max words - at ../dataset/shuffle-word-1400-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 660 max words, 50 samples - at ../dataset/gen-word-660-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 295 max words, 50 samples - at ../dataset/gen-word-295-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 360 max words, 50 samples - at ../dataset/gen-word-360-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 840 max words, 50 samples - at ../dataset/gen-word-840-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 945 max words, 50 samples - at ../dataset/gen-word-945-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 680 max words, 50 samples - at ../dataset/gen-word-680-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 925 max words, 50 samples - at ../dataset/gen-word-925-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 40 samples (20 token repeat) - 2300 max words - at ../dataset/shuffle-word-2300-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 5100 max words - at ../dataset/shuffle-word-5100-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 6 samples (1 token repeat) - 480 max words - at ../dataset/shuffle-word-480-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 40 samples (20 token repeat) - 1500 max words - at ../dataset/shuffle-word-1500-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 550 max words, 50 samples - at ../dataset/gen-word-550-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 765 max words, 50 samples - at ../dataset/gen-word-765-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 4200 max words - at ../dataset/shuffle-word-4200-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 6000 max words - at ../dataset/shuffle-word-6000-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 685 max words, 50 samples - at ../dataset/gen-word-685-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 7900 max words - at ../dataset/shuffle-word-7900-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 4 samples (1 token repeat) - 650 max words - at ../dataset/shuffle-word-650-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 4700 max words - at ../dataset/shuffle-word-4700-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 7700 max words - at ../dataset/shuffle-word-7700-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 40 samples (20 token repeat) - 1700 max words - at ../dataset/shuffle-word-1700-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 980 max words, 50 samples - at ../dataset/gen-word-980-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 5300 max words - at ../dataset/shuffle-word-5300-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 3500 max words - at ../dataset/shuffle-word-3500-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 5 samples (1 token repeat) - 550 max words - at ../dataset/shuffle-word-550-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 4 samples (1 token repeat) - 680 max words - at ../dataset/shuffle-word-680-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 3 samples (1 token repeat) - 855 max words - at ../dataset/shuffle-word-855-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 570 max words, 50 samples - at ../dataset/gen-word-570-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 740 max words, 50 samples - at ../dataset/gen-word-740-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 5600 max words - at ../dataset/shuffle-word-5600-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 4 samples (1 token repeat) - 740 max words - at ../dataset/shuffle-word-740-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 630 max words, 50 samples - at ../dataset/gen-word-630-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 675 max words, 50 samples - at ../dataset/gen-word-675-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 245 max words, 50 samples - at ../dataset/gen-word-245-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 785 max words, 50 samples - at ../dataset/gen-word-785-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 3 samples (1 token repeat) - 810 max words - at ../dataset/shuffle-word-810-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 960 max words, 50 samples - at ../dataset/gen-word-960-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 3100 max words - at ../dataset/shuffle-word-3100-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 4 samples (1 token repeat) - 795 max words - at ../dataset/shuffle-word-795-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 3 samples (1 token repeat) - 920 max words - at ../dataset/shuffle-word-920-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 455 max words, 50 samples - at ../dataset/gen-word-455-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 890 max words, 50 samples - at ../dataset/gen-word-890-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 1000 max words, 50 samples - at ../dataset/gen-word-1000-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 835 max words, 50 samples - at ../dataset/gen-word-835-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 760 max words, 50 samples - at ../dataset/gen-word-760-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 40 samples (20 token repeat) - 2000 max words - at ../dataset/shuffle-word-2000-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 870 max words, 50 samples - at ../dataset/gen-word-870-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 825 max words, 50 samples - at ../dataset/gen-word-825-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 5500 max words - at ../dataset/shuffle-word-5500-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 2900 max words - at ../dataset/shuffle-word-2900-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 5800 max words - at ../dataset/shuffle-word-5800-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 6200 max words - at ../dataset/shuffle-word-6200-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 930 max words, 50 samples - at ../dataset/gen-word-930-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 6 samples (1 token repeat) - 490 max words - at ../dataset/shuffle-word-490-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 730 max words, 50 samples - at ../dataset/gen-word-730-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 40 samples (20 token repeat) - 2400 max words - at ../dataset/shuffle-word-2400-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 3900 max words - at ../dataset/shuffle-word-3900-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 6 samples (1 token repeat) - 445 max words - at ../dataset/shuffle-word-445-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 995 max words, 50 samples - at ../dataset/gen-word-995-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 60 samples (20 token repeat) - 1200 max words - at ../dataset/shuffle-word-1200-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 3 samples (1 token repeat) - 805 max words - at ../dataset/shuffle-word-805-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 620 max words, 50 samples - at ../dataset/gen-word-620-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 40 samples (20 token repeat) - 1600 max words - at ../dataset/shuffle-word-1600-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 970 max words, 50 samples - at ../dataset/gen-word-970-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 5700 max words - at ../dataset/shuffle-word-5700-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 40 samples (20 token repeat) - 1800 max words - at ../dataset/shuffle-word-1800-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 6600 max words - at ../dataset/shuffle-word-6600-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 670 max words, 50 samples - at ../dataset/gen-word-670-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 40 samples (20 token repeat) - 2200 max words - at ../dataset/shuffle-word-2200-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 1100 max words, 2000 samples - at ../dataset/gen-word-1100-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 1500 max words, 2000 samples - at ../dataset/gen-word-1500-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 1200 max words, 2000 samples - at ../dataset/gen-word-1200-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 1600 max words, 2000 samples - at ../dataset/gen-word-1600-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 1300 max words, 2000 samples - at ../dataset/gen-word-1300-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 1700 max words, 2000 samples - at ../dataset/gen-word-1700-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 1900 max words, 2000 samples - at ../dataset/gen-word-1900-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 2000 max words, 2000 samples - at ../dataset/gen-word-2000-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 1800 max words, 2000 samples - at ../dataset/gen-word-1800-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 1400 max words, 2000 samples - at ../dataset/gen-word-1400-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 2100 max words, 2000 samples - at ../dataset/gen-word-2100-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 2200 max words, 2000 samples - at ../dataset/gen-word-2200-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 2500 max words, 2000 samples - at ../dataset/gen-word-2500-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 2300 max words, 2000 samples - at ../dataset/gen-word-2300-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 2700 max words, 2000 samples - at ../dataset/gen-word-2700-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 2600 max words, 2000 samples - at ../dataset/gen-word-2600-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 2400 max words, 2000 samples - at ../dataset/gen-word-2400-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 2800 max words, 2000 samples - at ../dataset/gen-word-2800-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 2900 max words, 2000 samples - at ../dataset/gen-word-2900-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 3300 max words, 2000 samples - at ../dataset/gen-word-3300-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 3200 max words, 2000 samples - at ../dataset/gen-word-3200-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 3100 max words, 2000 samples - at ../dataset/gen-word-3100-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 3400 max words, 2000 samples - at ../dataset/gen-word-3400-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 3700 max words, 2000 samples - at ../dataset/gen-word-3700-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 4100 max words, 2000 samples - at ../dataset/gen-word-4100-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 3000 max words, 2000 samples - at ../dataset/gen-word-3000-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 3600 max words, 2000 samples - at ../dataset/gen-word-3600-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 3500 max words, 2000 samples - at ../dataset/gen-word-3500-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 4000 max words, 2000 samples - at ../dataset/gen-word-4000-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 3900 max words, 2000 samples - at ../dataset/gen-word-3900-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 4700 max words, 2000 samples - at ../dataset/gen-word-4700-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 3800 max words, 2000 samples - at ../dataset/gen-word-3800-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 4200 max words, 2000 samples - at ../dataset/gen-word-4200-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 4500 max words, 2000 samples - at ../dataset/gen-word-4500-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 4400 max words, 2000 samples - at ../dataset/gen-word-4400-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 5000 max words, 2000 samples - at ../dataset/gen-word-5000-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 5200 max words, 2000 samples - at ../dataset/gen-word-5200-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 4300 max words, 2000 samples - at ../dataset/gen-word-4300-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 5400 max words, 2000 samples - at ../dataset/gen-word-5400-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 4900 max words, 2000 samples - at ../dataset/gen-word-4900-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 5300 max words, 2000 samples - at ../dataset/gen-word-5300-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 4600 max words, 2000 samples - at ../dataset/gen-word-4600-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 4800 max words, 2000 samples - at ../dataset/gen-word-4800-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 5100 max words, 2000 samples - at ../dataset/gen-word-5100-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 6000 max words, 2000 samples - at ../dataset/gen-word-6000-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 6200 max words, 2000 samples - at ../dataset/gen-word-6200-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 7500 max words, 2000 samples - at ../dataset/gen-word-7500-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 6500 max words, 2000 samples - at ../dataset/gen-word-6500-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 5900 max words, 2000 samples - at ../dataset/gen-word-5900-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 5500 max words, 2000 samples - at ../dataset/gen-word-5500-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 5600 max words, 2000 samples - at ../dataset/gen-word-5600-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 6100 max words, 2000 samples - at ../dataset/gen-word-6100-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 6600 max words, 2000 samples - at ../dataset/gen-word-6600-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 6400 max words, 2000 samples - at ../dataset/gen-word-6400-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 6300 max words, 2000 samples - at ../dataset/gen-word-6300-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 5700 max words, 2000 samples - at ../dataset/gen-word-5700-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 5800 max words, 2000 samples - at ../dataset/gen-word-5800-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 6900 max words, 2000 samples - at ../dataset/gen-word-6900-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 6800 max words, 2000 samples - at ../dataset/gen-word-6800-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 7100 max words, 2000 samples - at ../dataset/gen-word-7100-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 6700 max words, 2000 samples - at ../dataset/gen-word-6700-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 7400 max words, 2000 samples - at ../dataset/gen-word-7400-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 7000 max words, 2000 samples - at ../dataset/gen-word-7000-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 7300 max words, 2000 samples - at ../dataset/gen-word-7300-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 7600 max words, 2000 samples - at ../dataset/gen-word-7600-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 7900 max words, 2000 samples - at ../dataset/gen-word-7900-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 7800 max words, 2000 samples - at ../dataset/gen-word-7800-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 7200 max words, 2000 samples - at ../dataset/gen-word-7200-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 8000 max words, 2000 samples - at ../dataset/gen-word-8000-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 7700 max words, 2000 samples - at ../dataset/gen-word-7700-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "## Done ##\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "total 6.1G\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 10K Sep 2 08:41 gen-word-10-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 54K Sep 2 08:41 gen-word-100-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 494K Sep 2 08:41 gen-word-1000-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 56K Sep 2 08:41 gen-word-105-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 60K Sep 2 08:41 gen-word-110-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 22M Sep 2 08:41 gen-word-1100-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 64K Sep 2 08:41 gen-word-115-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 63K Sep 2 08:41 gen-word-120-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 23M Sep 2 08:41 gen-word-1200-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 69K Sep 2 08:41 gen-word-125-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 71K Sep 2 08:41 gen-word-130-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 25M Sep 2 08:41 gen-word-1300-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 68K Sep 2 08:41 gen-word-135-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 70K Sep 2 08:41 gen-word-140-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27M Sep 2 08:41 gen-word-1400-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 78K Sep 2 08:41 gen-word-145-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 13K Sep 2 08:41 gen-word-15-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 79K Sep 2 08:41 gen-word-150-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 29M Sep 2 08:41 gen-word-1500-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 82K Sep 2 08:41 gen-word-155-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 83K Sep 2 08:41 gen-word-160-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 31M Sep 2 08:41 gen-word-1600-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 86K Sep 2 08:41 gen-word-165-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 85K Sep 2 08:41 gen-word-170-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 33M Sep 2 08:41 gen-word-1700-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 93K Sep 2 08:41 gen-word-175-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 90K Sep 2 08:41 gen-word-180-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 35M Sep 2 08:41 gen-word-1800-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 98K Sep 2 08:41 gen-word-185-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 100K Sep 2 08:41 gen-word-190-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 37M Sep 2 08:41 gen-word-1900-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 95K Sep 2 08:41 gen-word-195-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 14K Sep 2 08:41 gen-word-20-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 104K Sep 2 08:41 gen-word-200-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 39M Sep 2 08:41 gen-word-2000-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 108K Sep 2 08:41 gen-word-205-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 109K Sep 2 08:41 gen-word-210-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 41M Sep 2 08:41 gen-word-2100-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 109K Sep 2 08:41 gen-word-215-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 111K Sep 2 08:41 gen-word-220-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 42M Sep 2 08:41 gen-word-2200-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 117K Sep 2 08:41 gen-word-225-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 118K Sep 2 08:41 gen-word-230-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 44M Sep 2 08:41 gen-word-2300-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 120K Sep 2 08:41 gen-word-235-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 122K Sep 2 08:41 gen-word-240-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 46M Sep 2 08:41 gen-word-2400-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 127K Sep 2 08:41 gen-word-245-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 17K Sep 2 08:41 gen-word-25-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 129K Sep 2 08:41 gen-word-250-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 48M Sep 2 08:41 gen-word-2500-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 131K Sep 2 08:41 gen-word-255-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 130K Sep 2 08:41 gen-word-260-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 50M Sep 2 08:41 gen-word-2600-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 136K Sep 2 08:41 gen-word-265-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 141K Sep 2 08:41 gen-word-270-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 52M Sep 2 08:41 gen-word-2700-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 137K Sep 2 08:41 gen-word-275-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 140K Sep 2 08:41 gen-word-280-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 54M Sep 2 08:41 gen-word-2800-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 144K Sep 2 08:41 gen-word-285-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 149K Sep 2 08:41 gen-word-290-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 56M Sep 2 08:41 gen-word-2900-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 148K Sep 2 08:41 gen-word-295-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 20K Sep 2 08:41 gen-word-30-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 153K Sep 2 08:41 gen-word-300-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 58M Sep 2 08:41 gen-word-3000-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 156K Sep 2 08:41 gen-word-305-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 158K Sep 2 08:41 gen-word-310-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 60M Sep 2 08:41 gen-word-3100-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 161K Sep 2 08:41 gen-word-315-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 160K Sep 2 08:41 gen-word-320-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 61M Sep 2 08:41 gen-word-3200-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 162K Sep 2 08:41 gen-word-325-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 168K Sep 2 08:41 gen-word-330-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 63M Sep 2 08:41 gen-word-3300-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 167K Sep 2 08:41 gen-word-335-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 169K Sep 2 08:41 gen-word-340-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 65M Sep 2 08:41 gen-word-3400-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 171K Sep 2 08:41 gen-word-345-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 22K Sep 2 08:41 gen-word-35-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 178K Sep 2 08:41 gen-word-350-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 67M Sep 2 08:41 gen-word-3500-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 176K Sep 2 08:41 gen-word-355-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 180K Sep 2 08:41 gen-word-360-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 69M Sep 2 08:41 gen-word-3600-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 181K Sep 2 08:41 gen-word-365-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 184K Sep 2 08:41 gen-word-370-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 71M Sep 2 08:41 gen-word-3700-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 184K Sep 2 08:41 gen-word-375-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 188K Sep 2 08:41 gen-word-380-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 73M Sep 2 08:41 gen-word-3800-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 195K Sep 2 08:41 gen-word-385-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 195K Sep 2 08:41 gen-word-390-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 75M Sep 2 08:41 gen-word-3900-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 197K Sep 2 08:41 gen-word-395-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 24K Sep 2 08:41 gen-word-40-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 201K Sep 2 08:41 gen-word-400-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 77M Sep 2 08:41 gen-word-4000-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 202K Sep 2 08:41 gen-word-405-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 206K Sep 2 08:41 gen-word-410-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 79M Sep 2 08:41 gen-word-4100-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 211K Sep 2 08:41 gen-word-415-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 213K Sep 2 08:41 gen-word-420-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 80M Sep 2 08:41 gen-word-4200-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 209K Sep 2 08:41 gen-word-425-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 214K Sep 2 08:41 gen-word-430-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 82M Sep 2 08:41 gen-word-4300-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 216K Sep 2 08:41 gen-word-435-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 218K Sep 2 08:41 gen-word-440-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 84M Sep 2 08:41 gen-word-4400-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 221K Sep 2 08:41 gen-word-445-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 28K Sep 2 08:41 gen-word-45-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 225K Sep 2 08:41 gen-word-450-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 86M Sep 2 08:41 gen-word-4500-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 230K Sep 2 08:41 gen-word-455-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 228K Sep 2 08:41 gen-word-460-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 88M Sep 2 08:41 gen-word-4600-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 232K Sep 2 08:41 gen-word-465-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 241K Sep 2 08:41 gen-word-470-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 90M Sep 2 08:41 gen-word-4700-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 237K Sep 2 08:41 gen-word-475-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 239K Sep 2 08:41 gen-word-480-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 92M Sep 2 08:41 gen-word-4800-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 242K Sep 2 08:41 gen-word-485-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 247K Sep 2 08:41 gen-word-490-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 94M Sep 2 08:41 gen-word-4900-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 244K Sep 2 08:41 gen-word-495-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 7.3K Sep 2 08:41 gen-word-5-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 28K Sep 2 08:41 gen-word-50-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 252K Sep 2 08:41 gen-word-500-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 96M Sep 2 08:41 gen-word-5000-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 249K Sep 2 08:41 gen-word-505-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 250K Sep 2 08:41 gen-word-510-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 98M Sep 2 08:41 gen-word-5100-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 253K Sep 2 08:41 gen-word-515-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 258K Sep 2 08:41 gen-word-520-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 100M Sep 2 08:41 gen-word-5200-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 262K Sep 2 08:41 gen-word-525-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 265K Sep 2 08:41 gen-word-530-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 101M Sep 2 08:41 gen-word-5300-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 263K Sep 2 08:41 gen-word-535-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 267K Sep 2 08:41 gen-word-540-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 103M Sep 2 08:41 gen-word-5400-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 268K Sep 2 08:41 gen-word-545-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 33K Sep 2 08:41 gen-word-55-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 274K Sep 2 08:41 gen-word-550-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 105M Sep 2 08:41 gen-word-5500-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 273K Sep 2 08:41 gen-word-555-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 279K Sep 2 08:41 gen-word-560-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 107M Sep 2 08:41 gen-word-5600-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 282K Sep 2 08:41 gen-word-565-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 281K Sep 2 08:41 gen-word-570-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 109M Sep 2 08:41 gen-word-5700-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 283K Sep 2 08:41 gen-word-575-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 286K Sep 2 08:41 gen-word-580-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 111M Sep 2 08:41 gen-word-5800-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 288K Sep 2 08:41 gen-word-585-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 291K Sep 2 08:41 gen-word-590-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 113M Sep 2 08:41 gen-word-5900-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 296K Sep 2 08:41 gen-word-595-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 34K Sep 2 08:41 gen-word-60-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 300K Sep 2 08:41 gen-word-600-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 115M Sep 2 08:41 gen-word-6000-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 300K Sep 2 08:41 gen-word-605-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 296K Sep 2 08:41 gen-word-610-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 117M Sep 2 08:41 gen-word-6100-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 303K Sep 2 08:41 gen-word-615-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 309K Sep 2 08:41 gen-word-620-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 119M Sep 2 08:41 gen-word-6200-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 311K Sep 2 08:41 gen-word-625-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 312K Sep 2 08:41 gen-word-630-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 120M Sep 2 08:41 gen-word-6300-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 316K Sep 2 08:41 gen-word-635-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 319K Sep 2 08:41 gen-word-640-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 122M Sep 2 08:41 gen-word-6400-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 313K Sep 2 08:41 gen-word-645-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 37K Sep 2 08:41 gen-word-65-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 316K Sep 2 08:41 gen-word-650-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 124M Sep 2 08:41 gen-word-6500-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 323K Sep 2 08:41 gen-word-655-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 330K Sep 2 08:41 gen-word-660-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 126M Sep 2 08:41 gen-word-6600-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 328K Sep 2 08:41 gen-word-665-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 332K Sep 2 08:41 gen-word-670-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 128M Sep 2 08:41 gen-word-6700-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 336K Sep 2 08:41 gen-word-675-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 335K Sep 2 08:41 gen-word-680-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 130M Sep 2 08:41 gen-word-6800-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 338K Sep 2 08:41 gen-word-685-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 345K Sep 2 08:41 gen-word-690-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 132M Sep 2 08:41 gen-word-6900-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 340K Sep 2 08:41 gen-word-695-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 39K Sep 2 08:41 gen-word-70-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 346K Sep 2 08:41 gen-word-700-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 134M Sep 2 08:41 gen-word-7000-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 345K Sep 2 08:41 gen-word-705-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 354K Sep 2 08:41 gen-word-710-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 135M Sep 2 08:41 gen-word-7100-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 350K Sep 2 08:41 gen-word-715-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 358K Sep 2 08:41 gen-word-720-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 137M Sep 2 08:41 gen-word-7200-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 357K Sep 2 08:41 gen-word-725-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 363K Sep 2 08:41 gen-word-730-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 139M Sep 2 08:41 gen-word-7300-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 361K Sep 2 08:41 gen-word-735-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 364K Sep 2 08:41 gen-word-740-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 141M Sep 2 08:41 gen-word-7400-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 366K Sep 2 08:41 gen-word-745-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 39K Sep 2 08:41 gen-word-75-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 365K Sep 2 08:41 gen-word-750-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 143M Sep 2 08:41 gen-word-7500-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 368K Sep 2 08:41 gen-word-755-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 375K Sep 2 08:41 gen-word-760-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 145M Sep 2 08:41 gen-word-7600-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 378K Sep 2 08:41 gen-word-765-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 377K Sep 2 08:41 gen-word-770-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 147M Sep 2 08:41 gen-word-7700-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 381K Sep 2 08:41 gen-word-775-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 379K Sep 2 08:41 gen-word-780-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 149M Sep 2 08:41 gen-word-7800-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 387K Sep 2 08:41 gen-word-785-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 391K Sep 2 08:41 gen-word-790-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 151M Sep 2 08:41 gen-word-7900-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 389K Sep 2 08:41 gen-word-795-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 45K Sep 2 08:41 gen-word-80-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 387K Sep 2 08:41 gen-word-800-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 153M Sep 2 08:41 gen-word-8000-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 395K Sep 2 08:41 gen-word-805-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 403K Sep 2 08:41 gen-word-810-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 399K Sep 2 08:41 gen-word-815-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 404K Sep 2 08:41 gen-word-820-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 407K Sep 2 08:41 gen-word-825-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 406K Sep 2 08:41 gen-word-830-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 414K Sep 2 08:41 gen-word-835-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 421K Sep 2 08:41 gen-word-840-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 415K Sep 2 08:41 gen-word-845-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 47K Sep 2 08:41 gen-word-85-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 416K Sep 2 08:41 gen-word-850-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 420K Sep 2 08:41 gen-word-855-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 428K Sep 2 08:41 gen-word-860-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 427K Sep 2 08:41 gen-word-865-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 425K Sep 2 08:41 gen-word-870-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 430K Sep 2 08:41 gen-word-875-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 434K Sep 2 08:41 gen-word-880-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 435K Sep 2 08:41 gen-word-885-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 441K Sep 2 08:41 gen-word-890-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 442K Sep 2 08:41 gen-word-895-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 46K Sep 2 08:41 gen-word-90-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 440K Sep 2 08:41 gen-word-900-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 454K Sep 2 08:41 gen-word-905-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 451K Sep 2 08:41 gen-word-910-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 447K Sep 2 08:41 gen-word-915-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 451K Sep 2 08:41 gen-word-920-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 460K Sep 2 08:41 gen-word-925-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 456K Sep 2 08:41 gen-word-930-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 458K Sep 2 08:41 gen-word-935-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 457K Sep 2 08:41 gen-word-940-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 465K Sep 2 08:41 gen-word-945-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 52K Sep 2 08:41 gen-word-95-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 466K Sep 2 08:41 gen-word-950-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 465K Sep 2 08:41 gen-word-955-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 468K Sep 2 08:41 gen-word-960-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 471K Sep 2 08:41 gen-word-965-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 481K Sep 2 08:41 gen-word-970-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 477K Sep 2 08:41 gen-word-975-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 482K Sep 2 08:41 gen-word-980-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 483K Sep 2 08:41 gen-word-985-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 492K Sep 2 08:41 gen-word-990-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 491K Sep 2 08:41 gen-word-995-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 51K Sep 2 08:41 shuffle-word-10-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 30K Sep 2 08:41 shuffle-word-100-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-1000-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 28K Sep 2 08:41 shuffle-word-105-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 28K Sep 2 08:41 shuffle-word-110-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 523K Sep 2 08:41 shuffle-word-1100-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 29K Sep 2 08:41 shuffle-word-115-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-120-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 523K Sep 2 08:41 shuffle-word-1200-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 29K Sep 2 08:41 shuffle-word-125-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 29K Sep 2 08:41 shuffle-word-130-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 521K Sep 2 08:41 shuffle-word-1300-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 28K Sep 2 08:41 shuffle-word-135-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 28K Sep 2 08:41 shuffle-word-140-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 523K Sep 2 08:41 shuffle-word-1400-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 28K Sep 2 08:41 shuffle-word-145-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 40K Sep 2 08:41 shuffle-word-15-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 28K Sep 2 08:41 shuffle-word-150-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 520K Sep 2 08:41 shuffle-word-1500-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-155-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 28K Sep 2 08:41 shuffle-word-160-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 519K Sep 2 08:41 shuffle-word-1600-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 28K Sep 2 08:41 shuffle-word-165-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 28K Sep 2 08:41 shuffle-word-170-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 520K Sep 2 08:41 shuffle-word-1700-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 28K Sep 2 08:41 shuffle-word-175-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-180-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 518K Sep 2 08:41 shuffle-word-1800-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 28K Sep 2 08:41 shuffle-word-185-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-190-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 521K Sep 2 08:41 shuffle-word-1900-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-195-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 41K Sep 2 08:41 shuffle-word-20-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-200-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 520K Sep 2 08:41 shuffle-word-2000-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-205-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 28K Sep 2 08:41 shuffle-word-210-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 520K Sep 2 08:41 shuffle-word-2100-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 26K Sep 2 08:41 shuffle-word-215-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-220-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 520K Sep 2 08:41 shuffle-word-2200-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-225-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-230-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 520K Sep 2 08:41 shuffle-word-2300-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-235-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 28K Sep 2 08:41 shuffle-word-240-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 521K Sep 2 08:41 shuffle-word-2400-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-245-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 36K Sep 2 08:41 shuffle-word-25-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-250-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 519K Sep 2 08:41 shuffle-word-2500-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-255-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 28K Sep 2 08:41 shuffle-word-260-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 515K Sep 2 08:41 shuffle-word-2600-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-265-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-270-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 511K Sep 2 08:41 shuffle-word-2700-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 26K Sep 2 08:41 shuffle-word-275-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-280-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 511K Sep 2 08:41 shuffle-word-2800-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-285-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 28K Sep 2 08:41 shuffle-word-290-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 509K Sep 2 08:41 shuffle-word-2900-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-295-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 34K Sep 2 08:41 shuffle-word-30-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-300-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 508K Sep 2 08:41 shuffle-word-3000-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 26K Sep 2 08:41 shuffle-word-305-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-310-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 509K Sep 2 08:41 shuffle-word-3100-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-315-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 28K Sep 2 08:41 shuffle-word-320-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 508K Sep 2 08:41 shuffle-word-3200-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 26K Sep 2 08:41 shuffle-word-325-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-330-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 509K Sep 2 08:41 shuffle-word-3300-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 28K Sep 2 08:41 shuffle-word-335-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-340-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 509K Sep 2 08:41 shuffle-word-3400-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-345-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 33K Sep 2 08:41 shuffle-word-35-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 28K Sep 2 08:41 shuffle-word-350-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 508K Sep 2 08:41 shuffle-word-3500-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-355-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 26K Sep 2 08:41 shuffle-word-360-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 509K Sep 2 08:41 shuffle-word-3600-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-365-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 26K Sep 2 08:41 shuffle-word-370-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 509K Sep 2 08:41 shuffle-word-3700-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-375-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-380-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 509K Sep 2 08:41 shuffle-word-3800-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-385-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 26K Sep 2 08:41 shuffle-word-390-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 509K Sep 2 08:41 shuffle-word-3900-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 28K Sep 2 08:41 shuffle-word-395-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 34K Sep 2 08:41 shuffle-word-40-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-400-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 509K Sep 2 08:41 shuffle-word-4000-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-405-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 26K Sep 2 08:41 shuffle-word-410-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 509K Sep 2 08:41 shuffle-word-4100-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 26K Sep 2 08:41 shuffle-word-415-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 26K Sep 2 08:41 shuffle-word-420-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 509K Sep 2 08:41 shuffle-word-4200-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-425-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 28K Sep 2 08:41 shuffle-word-430-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 509K Sep 2 08:41 shuffle-word-4300-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 26K Sep 2 08:41 shuffle-word-435-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-440-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 508K Sep 2 08:41 shuffle-word-4400-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-445-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 32K Sep 2 08:41 shuffle-word-45-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-450-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 508K Sep 2 08:41 shuffle-word-4500-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-455-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-460-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 509K Sep 2 08:41 shuffle-word-4600-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 26K Sep 2 08:41 shuffle-word-465-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-470-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 509K Sep 2 08:41 shuffle-word-4700-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 26K Sep 2 08:41 shuffle-word-475-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 26K Sep 2 08:41 shuffle-word-480-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 508K Sep 2 08:41 shuffle-word-4800-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-485-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 26K Sep 2 08:41 shuffle-word-490-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 509K Sep 2 08:41 shuffle-word-4900-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 26K Sep 2 08:41 shuffle-word-495-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 80K Sep 2 08:41 shuffle-word-5-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 29K Sep 2 08:41 shuffle-word-50-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-500-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 509K Sep 2 08:41 shuffle-word-5000-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-505-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-510-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 509K Sep 2 08:41 shuffle-word-5100-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-515-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 26K Sep 2 08:41 shuffle-word-520-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 508K Sep 2 08:41 shuffle-word-5200-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-525-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 26K Sep 2 08:41 shuffle-word-530-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 509K Sep 2 08:41 shuffle-word-5300-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-535-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 26K Sep 2 08:41 shuffle-word-540-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 509K Sep 2 08:41 shuffle-word-5400-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 26K Sep 2 08:41 shuffle-word-545-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 29K Sep 2 08:41 shuffle-word-55-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-550-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 508K Sep 2 08:41 shuffle-word-5500-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-555-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 26K Sep 2 08:41 shuffle-word-560-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 509K Sep 2 08:41 shuffle-word-5600-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 28K Sep 2 08:41 shuffle-word-565-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 26K Sep 2 08:41 shuffle-word-570-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 509K Sep 2 08:41 shuffle-word-5700-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-575-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 26K Sep 2 08:41 shuffle-word-580-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 509K Sep 2 08:41 shuffle-word-5800-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 26K Sep 2 08:41 shuffle-word-585-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 26K Sep 2 08:41 shuffle-word-590-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 509K Sep 2 08:41 shuffle-word-5900-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-595-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 29K Sep 2 08:41 shuffle-word-60-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-600-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 509K Sep 2 08:41 shuffle-word-6000-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-605-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-610-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 509K Sep 2 08:41 shuffle-word-6100-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-615-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-620-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 509K Sep 2 08:41 shuffle-word-6200-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 26K Sep 2 08:41 shuffle-word-625-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-630-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 509K Sep 2 08:41 shuffle-word-6300-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 26K Sep 2 08:41 shuffle-word-635-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-640-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 509K Sep 2 08:41 shuffle-word-6400-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-645-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 31K Sep 2 08:41 shuffle-word-65-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 26K Sep 2 08:41 shuffle-word-650-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 509K Sep 2 08:41 shuffle-word-6500-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 26K Sep 2 08:41 shuffle-word-655-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 26K Sep 2 08:41 shuffle-word-660-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 509K Sep 2 08:41 shuffle-word-6600-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-665-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 26K Sep 2 08:41 shuffle-word-670-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 508K Sep 2 08:41 shuffle-word-6700-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-675-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-680-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 509K Sep 2 08:41 shuffle-word-6800-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 26K Sep 2 08:41 shuffle-word-685-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-690-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 508K Sep 2 08:41 shuffle-word-6900-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-695-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 30K Sep 2 08:41 shuffle-word-70-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-700-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 508K Sep 2 08:41 shuffle-word-7000-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 26K Sep 2 08:41 shuffle-word-705-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-710-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 509K Sep 2 08:41 shuffle-word-7100-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 26K Sep 2 08:41 shuffle-word-715-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 26K Sep 2 08:41 shuffle-word-720-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 509K Sep 2 08:41 shuffle-word-7200-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-725-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-730-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 509K Sep 2 08:41 shuffle-word-7300-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-735-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-740-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 509K Sep 2 08:41 shuffle-word-7400-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-745-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 28K Sep 2 08:41 shuffle-word-75-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-750-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 508K Sep 2 08:41 shuffle-word-7500-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 26K Sep 2 08:41 shuffle-word-755-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-760-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 509K Sep 2 08:41 shuffle-word-7600-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-765-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-770-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 509K Sep 2 08:41 shuffle-word-7700-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 26K Sep 2 08:41 shuffle-word-775-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 26K Sep 2 08:41 shuffle-word-780-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 509K Sep 2 08:41 shuffle-word-7800-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 26K Sep 2 08:41 shuffle-word-785-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 26K Sep 2 08:41 shuffle-word-790-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 509K Sep 2 08:41 shuffle-word-7900-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-795-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 28K Sep 2 08:41 shuffle-word-80-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-800-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 509K Sep 2 08:41 shuffle-word-8000-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 26K Sep 2 08:41 shuffle-word-805-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-810-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-815-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-820-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-825-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 26K Sep 2 08:41 shuffle-word-830-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 26K Sep 2 08:41 shuffle-word-835-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 26K Sep 2 08:41 shuffle-word-840-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-845-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 28K Sep 2 08:41 shuffle-word-85-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-850-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 26K Sep 2 08:41 shuffle-word-855-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-860-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 26K Sep 2 08:41 shuffle-word-865-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-870-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 26K Sep 2 08:41 shuffle-word-875-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-880-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 26K Sep 2 08:41 shuffle-word-885-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 26K Sep 2 08:41 shuffle-word-890-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-895-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 30K Sep 2 08:41 shuffle-word-90-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 26K Sep 2 08:41 shuffle-word-900-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-905-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-910-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-915-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-920-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-925-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-930-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-935-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 26K Sep 2 08:41 shuffle-word-940-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-945-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 30K Sep 2 08:41 shuffle-word-95-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-950-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-955-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 26K Sep 2 08:41 shuffle-word-960-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 26K Sep 2 08:41 shuffle-word-965-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-970-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-975-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 26K Sep 2 08:41 shuffle-word-980-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 26K Sep 2 08:41 shuffle-word-985-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 26K Sep 2 08:41 shuffle-word-990-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 27K Sep 2 08:41 shuffle-word-995-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 5.9K Sep 2 08:41 word-2-count.jsonl\n" - ] - } - ], - "source": [ - "%%script bash\n", - "\n", - "########################################\n", - "# Generate the required jsonl dataset\n", - "########################################\n", - "\n", - "# Reset the dataset dir\n", - "mkdir -p ../dataset\n", - "rm -rf ../dataset/*.jsonl\n", - "\n", - "# Generate the various datasets\n", - "echo \"## Generating word reptition dataset ##\"\n", - "\n", - "#\n", - "# We reduce the training set for < 50 words - and shift the focus upwards\n", - "# (aka 50-100 token * 2 : ~100 - 250 token ctx len)\n", - "#\n", - "python ../memory_script/gen_limited_prompt_completion_jsonl.py ../dataset/word-2-count.jsonl 2 50 &\n", - "for i in {5..1000..5} \n", - "do\n", - " python ../memory_script/gen_limited_prompt_completion_jsonl.py ../dataset/gen-word-$i-count.jsonl $i 50 & \n", - " python ../memory_script/shuffle_limited_prompt_completion_jsonl.py ../dataset/shuffle-word-$i-count.jsonl $i 1 & \n", - "done\n", - "\n", - "#\n", - "# Ramping up the 50+ - 4200 words dataset\n", - "# \n", - "for i in {1100..8000..100} \n", - "do\n", - " python ../memory_script/gen_limited_prompt_completion_jsonl.py ../dataset/gen-word-$i-count.jsonl $i 2000 & \n", - " python ../memory_script/shuffle_limited_prompt_completion_jsonl.py ../dataset/shuffle-word-$i-count.jsonl $i 20 & \n", - "done\n", - "\n", - "wait\n", - "echo \"## Done ##\"\n", - "\n", - "ls -lh ../dataset/" - ] - }, - { - "cell_type": "code", - "execution_count": 6, - "id": "15e03154", - "metadata": { - "execution": { - "iopub.execute_input": "2023-09-02T08:41:54.110558Z", - "iopub.status.busy": "2023-09-02T08:41:54.110363Z", - "iopub.status.idle": "2023-09-03T06:13:05.260832Z", - "shell.execute_reply": "2023-09-03T06:13:05.259129Z" - }, - "papermill": { - "duration": 77471.213932, - "end_time": "2023-09-03T06:13:05.263168", - "exception": false, - "start_time": "2023-09-02T08:41:54.049236", - "status": "completed" - }, - "tags": [] - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Setting ds_accelerator to cuda (auto detect)\r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "[RWKV.model] Running RWKV model using 'torch-jit' with torch '2.0.1+cu118'\r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "/usr/local/lib/python3.11/dist-packages/lightning/pytorch/cli.py:484: UserWarning: LightningCLI's args parameter is intended to run from within Python like if it were from the command line. To prevent mistakes it is not recommended to provide both args and command line arguments, got: sys.argv[1:]=['fit', '-c', '/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/notebook/experiment/rwkv-x-exp/v5-memory/config-mem-template.yaml', '--trainer.logger.init_args.name=v5-L96-D1024-E0.1 - Mem-Tune ctx-8k (train-ctx=4k, deepspeed_stage_1)', '--trainer.strategy=deepspeed_stage_1', '--trainer.devices=auto', '--trainer.callbacks.init_args.dirpath=../checkpoint/v5-L96-D1024-E0_1-mem-ctx-8k/', '--model.lr_init=1e-4', '--model.lr_final=1e-4', '--data.max_token_size=8192', '--model.ctx_len=4096', '--model.bptt_learning_range=2', '--model.load_model=../model/v5-L96-D1024-E0_1-mem-ctx-4k.pth'], args=['fit', '-c', '/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/notebook/experiment/rwkv-x-exp/v5-memory/config-mem-template.yaml', '--trainer.logger.init_args.name=v5-L96-D1024-E0.1 - Mem-Tune ctx-8k (train-ctx=4k, deepspeed_stage_1)', '--trainer.strategy=deepspeed_stage_1', '--trainer.devices=auto', '--trainer.callbacks.init_args.dirpath=../checkpoint/v5-L96-D1024-E0_1-mem-ctx-8k/', '--model.lr_init=1e-4', '--model.lr_final=1e-4', '--data.max_token_size=8192', '--model.ctx_len=4096', '--model.bptt_learning_range=2', '--model.load_model=../model/v5-L96-D1024-E0_1-mem-ctx-4k.pth'].\r\n", - " rank_zero_warn(\r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "/usr/local/lib/python3.11/dist-packages/lightning/fabric/utilities/seed.py:39: UserWarning: No seed found, seed set to 3809433325\r\n", - " rank_zero_warn(f\"No seed found, seed set to {seed}\")\r\n", - "Global seed set to 3809433325\r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\u001b[34m\u001b[1mwandb\u001b[0m: Currently logged in as: \u001b[33mpicocreator\u001b[0m (\u001b[33mrwkv-x-dev\u001b[0m). Use \u001b[1m`wandb login --relogin`\u001b[0m to force relogin\r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\u001b[34m\u001b[1mwandb\u001b[0m: Tracking run with wandb version 0.15.9\r\n", - "\u001b[34m\u001b[1mwandb\u001b[0m: Run data is saved locally in \u001b[35m\u001b[1m./wandb/run-20230902_084200-42tne4xv\u001b[0m\r\n", - "\u001b[34m\u001b[1mwandb\u001b[0m: Run \u001b[1m`wandb offline`\u001b[0m to turn off syncing.\r\n", - "\u001b[34m\u001b[1mwandb\u001b[0m: Syncing run \u001b[33mv5-L96-D1024-E0.1 - Mem-Tune ctx-8k (train-ctx=4k, deepspeed_stage_1)\u001b[0m\r\n", - "\u001b[34m\u001b[1mwandb\u001b[0m: ⭐️ View project at \u001b[34m\u001b[4mhttps://wandb.ai/rwkv-x-dev/RWKV-X-Experiments\u001b[0m\r\n", - "\u001b[34m\u001b[1mwandb\u001b[0m: 🚀 View run at \u001b[34m\u001b[4mhttps://wandb.ai/rwkv-x-dev/RWKV-X-Experiments/runs/42tne4xv\u001b[0m\r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "/usr/local/lib/python3.11/dist-packages/lightning/fabric/connector.py:562: UserWarning: bf16 is supported for historical reasons but its usage is discouraged. Please set your precision to bf16-mixed instead!\r\n", - " rank_zero_warn(\r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "GPU available: True (cuda), used: True\r\n", - "TPU available: False, using: 0 TPU cores\r\n", - "IPU available: False, using: 0 IPUs\r\n", - "HPU available: False, using: 0 HPUs\r\n", - "\r\n", - "\r\n", - "[RWKV.Trainer] Applying 'target_batch_size' with the following:\r\n", - " - target_batch_size: 256\r\n", - " - num_nodes: 1\r\n", - " - num_devices: 8\r\n", - " - accumulate_grad_batches: 32\r\n", - " - effective_batch_size: 256\r\n", - "\r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "Resolving data files: 0%| | 0/541 [00:00=12.1), as this is known to have freeze issues\r\n", - "# - The terms used in wandb / the progress bar can be confusing, see the github README.md for beter clarifications\r\n", - "# - When resuming from checkpoint, the estimated time is inaccurate\r\n", - "#\r\n", - "\r\n", - "[RWKV.model] Configuring optimizer with\r\n", - " - lr_init: 1.000e-04 (0.0001)\r\n", - " - lr_final: 1.000e-04 (0.0001)\r\n", - "\r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Detected CUDA files, patching ldflags\r\n", - "Emitting ninja build file /root/.cache/torch_extensions/py311_cu118/fused_adam/build.ninja...\r\n", - "Building extension module fused_adam...\r\n", - "Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)\r\n", - "ninja: no work to do.\r\n", - "Loading extension module fused_adam...\r\n", - "Time to load fused_adam op: 0.0724024772644043 seconds\r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Loading extension module fused_adam...\r\n", - "Loading extension module fused_adam...\r\n", - "Loading extension module fused_adam...\r\n", - "Loading extension module fused_adam...\r\n", - "Time to load fused_adam op: 0.10135412216186523 seconds\r\n", - "Time to load fused_adam op: 0.1016843318939209 seconds\r\n", - "Loading extension module fused_adam...\r\n", - "Time to load fused_adam op: 0.10171890258789062 seconds\r\n", - "Time to load fused_adam op: 0.10201501846313477 seconds\r\n", - "Time to load fused_adam op: 0.10342574119567871 seconds\r\n", - "Loading extension module fused_adam...\r\n", - "Loading extension module fused_adam...\r\n", - "Time to load fused_adam op: 0.11149120330810547 seconds\r\n", - "Time to load fused_adam op: 0.1042928695678711 seconds\r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "Emitting ninja build file /root/.cache/torch_extensions/py311_cu118/utils/build.ninja...\r\n", - "Building extension module utils...\r\n", - "Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)\r\n", - "ninja: no work to do.\r\n", - "Loading extension module utils...\r\n", - "Time to load utils op: 0.0709686279296875 seconds\r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Loading extension module utils...\r\n", - "Time to load utils op: 0.10201740264892578 seconds\r\n", - "Loading extension module utils...\r\n", - "Loading extension module utils...\r\n", - "Time to load utils op: 0.10213279724121094 seconds\r\n", - "Time to load utils op: 0.10248398780822754 seconds\r\n", - "Loading extension module utils...\r\n", - "Loading extension module utils...\r\n", - "Time to load utils op: 0.10281991958618164 seconds\r\n", - "Loading extension module utils...\r\n", - "Time to load utils op: 0.10238265991210938 seconds\r\n", - "Time to load utils op: 0.10246157646179199 seconds\r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Loading extension module utils...\r\n", - "Time to load utils op: 0.10242843627929688 seconds\r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Rank: 3 partition count [8, 8] and sizes[(176584448, False), (384, False)] \r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Rank: 5 partition count [8, 8] and sizes[(176584448, False), (384, False)] " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Rank: 4 partition count [8, 8] and sizes[(176584448, False), (384, False)] \r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Rank: 6 partition count [8, 8] and sizes[(176584448, False), (384, False)] \r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Rank: 2 partition count [8, 8] and sizes[(176584448, False), (384, False)] \r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Rank: 7 partition count [8, 8] and sizes[(176584448, False), (384, False)] \r\n", - "Rank: 1 partition count [8, 8] and sizes[(176584448, False), (384, False)] \r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Rank: 0 partition count [8, 8] and sizes[(176584448, False), (384, False)] \r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "No modifications detected for re-loaded extension module utils, skipping build step...\r\n", - "Loading extension module utils...\r\n", - "No modifications detected for re-loaded extension module utils, skipping build step...\r\n", - "No modifications detected for re-loaded extension module utils, skipping build step...\r\n", - "Loading extension module utils...\r\n", - "Loading extension module utils...\r\n", - "Time to load utils op: 0.0006196498870849609 seconds\r\n", - "Time to load utils op: 0.0006136894226074219 seconds\r\n", - "Time to load utils op: 0.0007157325744628906 seconds\r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "No modifications detected for re-loaded extension module utils, skipping build step...\r\n", - "Loading extension module utils...\r\n", - "Time to load utils op: 0.0006725788116455078 seconds\r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "No modifications detected for re-loaded extension module utils, skipping build step...\r\n", - "Loading extension module utils...\r\n", - "Time to load utils op: 0.0008366107940673828 seconds\r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "No modifications detected for re-loaded extension module utils, skipping build step...\r\n", - "Loading extension module utils...\r\n", - "Time to load utils op: 0.0011620521545410156 seconds\r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "No modifications detected for re-loaded extension module utils, skipping build step...\r\n", - "Loading extension module utils...\r\n", - "Time to load utils op: 0.0012750625610351562 seconds\r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "No modifications detected for re-loaded extension module utils, skipping build step...\r\n", - "Loading extension module utils...\r\n", - "Time to load utils op: 0.0009191036224365234 seconds\r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r\n", - " | Name | Type | Params\r\n", - "--------------------------------------\r\n", - "0 | emb | Embedding | 51.5 M\r\n", - "1 | blocks | ModuleList | 1.3 B \r\n", - "2 | ln_out | LayerNorm | 2.0 K \r\n", - "3 | head | Linear | 51.5 M\r\n", - "--------------------------------------\r\n", - "1.4 B Trainable params\r\n", - "0 Non-trainable params\r\n", - "1.4 B Total params\r\n", - "5,650.715 Total estimated model params size (MB)\r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "Training: 0it [00:00, ?it/s]\r", - "Training: 0%| | 0/12318 [00:00 ] 1.67G 40.7MB/s eta 25s " ] }, { @@ -101916,8 +1912,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8466/12318 [14:39:05<6:39:58, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8466/12318 [14:39:05<6:39:58, 6.23s/it, v_num=e4xv, train/loss" + " v5-L96-D1024 63%[===========> ] 1.67G 40.2MB/s eta 25s " ] }, { @@ -101925,8 +1920,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8467/12318 [14:39:11<6:39:52, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8467/12318 [14:39:11<6:39:52, 6.23s/it, v_num=e4xv, train/loss" + " v5-L96-D1024- 63%[===========> ] 1.68G 40.6MB/s eta 25s " ] }, { @@ -101934,7 +1928,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8468/12318 [14:39:18<6:39:46, 6.23s/it, v_num=e4xv, train/loss" + " v5-L96-D1024-E 64%[===========> ] 1.69G 40.3MB/s eta 25s " ] }, { @@ -101942,7 +1936,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8468/12318 [14:39:18<6:39:46, 6.23s/it, v_num=e4xv, train/loss" + " v5-L96-D1024-E0 64%[===========> ] 1.70G 40.5MB/s eta 24s " ] }, { @@ -101950,8 +1944,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8469/12318 [14:39:23<6:39:40, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8469/12318 [14:39:23<6:39:40, 6.23s/it, v_num=e4xv, train/loss" + " v5-L96-D1024-E0_ 64%[===========> ] 1.71G 40.5MB/s eta 24s " ] }, { @@ -101959,8 +1952,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8470/12318 [14:39:29<6:39:33, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8470/12318 [14:39:29<6:39:33, 6.23s/it, v_num=e4xv, train/loss" + " v5-L96-D1024-E0_1 65%[============> ] 1.72G 40.9MB/s eta 24s " ] }, { @@ -101968,8 +1960,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8471/12318 [14:39:34<6:39:27, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8471/12318 [14:39:34<6:39:27, 6.23s/it, v_num=e4xv, train/loss" + " v5-L96-D1024-E0_1- 65%[============> ] 1.73G 40.6MB/s eta 24s " ] }, { @@ -101977,8 +1968,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8472/12318 [14:39:40<6:39:20, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8472/12318 [14:39:40<6:39:20, 6.23s/it, v_num=e4xv, train/loss" + "v5-L96-D1024-E0_1-m 65%[============> ] 1.73G 40.4MB/s eta 24s " ] }, { @@ -101986,8 +1976,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8473/12318 [14:39:45<6:39:13, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8473/12318 [14:39:45<6:39:13, 6.23s/it, v_num=e4xv, train/loss" + "5-L96-D1024-E0_1-me 66%[============> ] 1.74G 39.9MB/s eta 23s " ] }, { @@ -101995,8 +1984,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8474/12318 [14:39:50<6:39:06, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8474/12318 [14:39:50<6:39:06, 6.23s/it, v_num=e4xv, train/loss" + "-L96-D1024-E0_1-mem 66%[============> ] 1.75G 39.8MB/s eta 23s " ] }, { @@ -102004,8 +1992,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8475/12318 [14:39:56<6:39:00, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8475/12318 [14:39:56<6:39:00, 6.23s/it, v_num=e4xv, train/loss" + "L96-D1024-E0_1-mem- 66%[============> ] 1.75G 37.0MB/s eta 23s " ] }, { @@ -102013,8 +2000,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8476/12318 [14:40:03<6:38:54, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8476/12318 [14:40:03<6:38:54, 6.23s/it, v_num=e4xv, train/loss" + "96-D1024-E0_1-mem-c 67%[============> ] 1.76G 39.3MB/s eta 23s " ] }, { @@ -102022,8 +2008,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8477/12318 [14:40:09<6:38:48, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8477/12318 [14:40:09<6:38:48, 6.23s/it, v_num=e4xv, train/loss" + "6-D1024-E0_1-mem-ct 67%[============> ] 1.77G 39.7MB/s eta 23s " ] }, { @@ -102031,8 +2016,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8478/12318 [14:40:12<6:38:40, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8478/12318 [14:40:12<6:38:40, 6.23s/it, v_num=e4xv, train/loss" + "-D1024-E0_1-mem-ctx 67%[============> ] 1.78G 38.8MB/s eta 22s " ] }, { @@ -102040,8 +2024,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8479/12318 [14:40:16<6:38:33, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8479/12318 [14:40:16<6:38:33, 6.23s/it, v_num=e4xv, train/loss" + "D1024-E0_1-mem-ctx- 67%[============> ] 1.79G 38.9MB/s eta 22s " ] }, { @@ -102049,8 +2032,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8480/12318 [14:40:55<6:38:42, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8480/12318 [14:40:55<6:38:42, 6.23s/it, v_num=e4xv, train/loss" + "1024-E0_1-mem-ctx-4 68%[============> ] 1.79G 38.7MB/s eta 22s " ] }, { @@ -102058,8 +2040,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8481/12318 [14:40:59<6:38:34, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8481/12318 [14:40:59<6:38:34, 6.23s/it, v_num=e4xv, train/loss" + "024-E0_1-mem-ctx-4k 68%[============> ] 1.81G 39.0MB/s eta 22s " ] }, { @@ -102067,8 +2048,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8482/12318 [14:41:07<6:38:29, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8482/12318 [14:41:07<6:38:29, 6.23s/it, v_num=e4xv, train/loss" + "24-E0_1-mem-ctx-4k. 68%[============> ] 1.81G 39.4MB/s eta 22s " ] }, { @@ -102076,8 +2056,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8483/12318 [14:41:14<6:38:23, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8483/12318 [14:41:14<6:38:23, 6.23s/it, v_num=e4xv, train/loss" + "4-E0_1-mem-ctx-4k.p 69%[============> ] 1.82G 39.3MB/s eta 21s " ] }, { @@ -102085,8 +2064,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8484/12318 [14:41:17<6:38:15, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8484/12318 [14:41:17<6:38:15, 6.23s/it, v_num=e4xv, train/loss" + "-E0_1-mem-ctx-4k.pt 69%[============> ] 1.83G 38.9MB/s eta 21s " ] }, { @@ -102094,8 +2072,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8485/12318 [14:41:25<6:38:10, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8485/12318 [14:41:25<6:38:10, 6.23s/it, v_num=e4xv, train/loss" + "E0_1-mem-ctx-4k.pth 69%[============> ] 1.84G 39.5MB/s eta 21s " ] }, { @@ -102103,8 +2080,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8486/12318 [14:41:32<6:38:04, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8486/12318 [14:41:32<6:38:04, 6.23s/it, v_num=e4xv, train/loss" + "0_1-mem-ctx-4k.pth 70%[=============> ] 1.85G 38.9MB/s eta 21s " ] }, { @@ -102112,8 +2088,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8487/12318 [14:41:39<6:37:58, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8487/12318 [14:41:39<6:37:58, 6.23s/it, v_num=e4xv, train/loss" + "_1-mem-ctx-4k.pth 70%[=============> ] 1.85G 39.1MB/s eta 21s " ] }, { @@ -102121,8 +2096,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8488/12318 [14:41:46<6:37:52, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8488/12318 [14:41:46<6:37:52, 6.23s/it, v_num=e4xv, train/loss" + "1-mem-ctx-4k.pth 70%[=============> ] 1.86G 38.3MB/s eta 20s " ] }, { @@ -102130,8 +2104,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8489/12318 [14:41:51<6:37:45, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8489/12318 [14:41:51<6:37:45, 6.23s/it, v_num=e4xv, train/loss" + "-mem-ctx-4k.pth 70%[=============> ] 1.87G 38.7MB/s eta 20s " ] }, { @@ -102139,8 +2112,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8490/12318 [14:41:56<6:37:38, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8490/12318 [14:41:56<6:37:38, 6.23s/it, v_num=e4xv, train/loss" + "mem-ctx-4k.pth 71%[=============> ] 1.87G 38.1MB/s eta 20s " ] }, { @@ -102148,8 +2120,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8491/12318 [14:42:04<6:37:33, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8491/12318 [14:42:04<6:37:33, 6.23s/it, v_num=e4xv, train/loss" + "em-ctx-4k.pth 71%[=============> ] 1.88G 38.3MB/s eta 20s " ] }, { @@ -102157,8 +2128,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8492/12318 [14:42:13<6:37:28, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8492/12318 [14:42:13<6:37:28, 6.23s/it, v_num=e4xv, train/loss" + "m-ctx-4k.pth 71%[=============> ] 1.89G 39.9MB/s eta 20s " ] }, { @@ -102166,8 +2136,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8493/12318 [14:42:18<6:37:21, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8493/12318 [14:42:18<6:37:21, 6.23s/it, v_num=e4xv, train/loss" + "-ctx-4k.pth 72%[=============> ] 1.90G 38.3MB/s eta 19s " ] }, { @@ -102175,8 +2144,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8494/12318 [14:42:25<6:37:16, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8494/12318 [14:42:25<6:37:16, 6.23s/it, v_num=e4xv, train/loss" + "ctx-4k.pth 72%[=============> ] 1.91G 38.7MB/s eta 19s " ] }, { @@ -102184,8 +2152,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8495/12318 [14:42:32<6:37:10, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8495/12318 [14:42:32<6:37:10, 6.23s/it, v_num=e4xv, train/loss" + "tx-4k.pth 72%[=============> ] 1.91G 38.6MB/s eta 19s " ] }, { @@ -102193,8 +2160,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8496/12318 [14:42:35<6:37:02, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8496/12318 [14:42:35<6:37:02, 6.23s/it, v_num=e4xv, train/loss" + "x-4k.pth 73%[=============> ] 1.92G 39.5MB/s eta 19s " ] }, { @@ -102202,8 +2168,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8497/12318 [14:42:40<6:36:55, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8497/12318 [14:42:40<6:36:55, 6.23s/it, v_num=e4xv, train/loss" + "-4k.pth 73%[=============> ] 1.93G 39.2MB/s eta 19s " ] }, { @@ -102211,8 +2176,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8498/12318 [14:42:47<6:36:49, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8498/12318 [14:42:47<6:36:49, 6.23s/it, v_num=e4xv, train/loss" + "4k.pth 73%[=============> ] 1.94G 38.9MB/s eta 18s " ] }, { @@ -102220,8 +2184,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8499/12318 [14:42:51<6:36:42, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8499/12318 [14:42:51<6:36:42, 6.23s/it, v_num=e4xv, train/loss" + "k.pth 74%[=============> ] 1.95G 39.1MB/s eta 18s " ] }, { @@ -102229,8 +2192,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8500/12318 [14:42:53<6:36:34, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8500/12318 [14:42:53<6:36:34, 6.23s/it, v_num=e4xv, train/loss" + ".pth 74%[=============> ] 1.96G 39.1MB/s eta 18s " ] }, { @@ -102238,8 +2200,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8501/12318 [14:42:59<6:36:28, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8501/12318 [14:42:59<6:36:28, 6.23s/it, v_num=e4xv, train/loss" + "pth 74%[=============> ] 1.97G 39.4MB/s eta 18s " ] }, { @@ -102247,8 +2208,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8502/12318 [14:43:06<6:36:22, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8502/12318 [14:43:06<6:36:22, 6.23s/it, v_num=e4xv, train/loss" + "th 75%[==============> ] 1.97G 38.7MB/s eta 18s " ] }, { @@ -102256,8 +2216,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8503/12318 [14:43:07<6:36:13, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8503/12318 [14:43:07<6:36:13, 6.23s/it, v_num=e4xv, train/loss" + "h 75%[==============> ] 1.98G 39.3MB/s eta 17s " ] }, { @@ -102265,8 +2224,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8504/12318 [14:43:16<6:36:08, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8504/12318 [14:43:16<6:36:08, 6.23s/it, v_num=e4xv, train/loss" + " 75%[==============> ] 1.99G 40.3MB/s eta 17s " ] }, { @@ -102274,8 +2232,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8505/12318 [14:43:20<6:36:01, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8505/12318 [14:43:20<6:36:01, 6.23s/it, v_num=e4xv, train/loss" + " v 76%[==============> ] 2.00G 40.0MB/s eta 17s " ] }, { @@ -102283,8 +2240,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8506/12318 [14:43:23<6:35:53, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8506/12318 [14:43:23<6:35:53, 6.23s/it, v_num=e4xv, train/loss" + " v5 76%[==============> ] 2.01G 40.8MB/s eta 17s " ] }, { @@ -102292,8 +2248,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8507/12318 [14:43:31<6:35:48, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8507/12318 [14:43:31<6:35:48, 6.23s/it, v_num=e4xv, train/loss" + " v5- 76%[==============> ] 2.02G 40.8MB/s eta 17s " ] }, { @@ -102301,8 +2256,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8508/12318 [14:43:36<6:35:41, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8508/12318 [14:43:36<6:35:41, 6.23s/it, v_num=e4xv, train/loss" + " v5-L 77%[==============> ] 2.03G 40.8MB/s eta 16s " ] }, { @@ -102310,8 +2264,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8509/12318 [14:43:38<6:35:33, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8509/12318 [14:43:38<6:35:33, 6.23s/it, v_num=e4xv, train/loss" + " v5-L9 77%[==============> ] 2.03G 41.2MB/s eta 16s " ] }, { @@ -102319,8 +2272,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8510/12318 [14:43:42<6:35:26, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8510/12318 [14:43:42<6:35:26, 6.23s/it, v_num=e4xv, train/loss" + " v5-L96 77%[==============> ] 2.04G 41.2MB/s eta 16s " ] }, { @@ -102328,8 +2280,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8511/12318 [14:43:49<6:35:20, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8511/12318 [14:43:49<6:35:20, 6.23s/it, v_num=e4xv, train/loss" + " v5-L96- 77%[==============> ] 2.05G 41.8MB/s eta 16s " ] }, { @@ -102337,8 +2288,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8512/12318 [14:44:06<6:35:18, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8512/12318 [14:44:06<6:35:18, 6.23s/it, v_num=e4xv, train/loss" + " v5-L96-D 78%[==============> ] 2.06G 40.4MB/s eta 16s " ] }, { @@ -102346,8 +2296,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8513/12318 [14:44:15<6:35:13, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8513/12318 [14:44:15<6:35:13, 6.23s/it, v_num=e4xv, train/loss" + " v5-L96-D1 78%[==============> ] 2.06G 39.9MB/s eta 15s " ] }, { @@ -102355,8 +2304,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8514/12318 [14:44:21<6:35:07, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8514/12318 [14:44:21<6:35:07, 6.23s/it, v_num=e4xv, train/loss" + " v5-L96-D10 78%[==============> ] 2.08G 41.5MB/s eta 15s " ] }, { @@ -102364,8 +2312,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8515/12318 [14:44:26<6:35:00, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8515/12318 [14:44:26<6:35:00, 6.23s/it, v_num=e4xv, train/loss" + " v5-L96-D102 79%[==============> ] 2.08G 40.8MB/s eta 15s " ] }, { @@ -102373,8 +2320,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8516/12318 [14:44:31<6:34:53, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8516/12318 [14:44:31<6:34:53, 6.23s/it, v_num=e4xv, train/loss" + " v5-L96-D1024 79%[==============> ] 2.09G 40.5MB/s eta 15s " ] }, { @@ -102382,8 +2328,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8517/12318 [14:44:36<6:34:47, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8517/12318 [14:44:36<6:34:47, 6.23s/it, v_num=e4xv, train/loss" + " v5-L96-D1024- 79%[==============> ] 2.10G 39.8MB/s eta 15s " ] }, { @@ -102391,8 +2336,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8518/12318 [14:44:44<6:34:41, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8518/12318 [14:44:44<6:34:41, 6.23s/it, v_num=e4xv, train/loss" + " v5-L96-D1024-E 80%[===============> ] 2.11G 40.0MB/s eta 14s " ] }, { @@ -102400,8 +2344,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8519/12318 [14:44:47<6:34:34, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8519/12318 [14:44:47<6:34:34, 6.23s/it, v_num=e4xv, train/loss" + " v5-L96-D1024-E0 80%[===============> ] 2.12G 39.9MB/s eta 14s " ] }, { @@ -102409,8 +2352,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8520/12318 [14:44:56<6:34:28, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8520/12318 [14:44:56<6:34:28, 6.23s/it, v_num=e4xv, train/loss" + " v5-L96-D1024-E0_ 80%[===============> ] 2.12G 40.2MB/s eta 14s " ] }, { @@ -102418,8 +2360,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8521/12318 [14:45:03<6:34:23, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8521/12318 [14:45:03<6:34:23, 6.23s/it, v_num=e4xv, train/loss" + " v5-L96-D1024-E0_1 81%[===============> ] 2.13G 39.1MB/s eta 14s " ] }, { @@ -102427,8 +2368,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8522/12318 [14:45:05<6:34:14, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8522/12318 [14:45:05<6:34:14, 6.23s/it, v_num=e4xv, train/loss" + " v5-L96-D1024-E0_1- 81%[===============> ] 2.14G 39.9MB/s eta 14s " ] }, { @@ -102436,7 +2376,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8523/12318 [14:45:10<6:34:08, 6.23s/it, v_num=e4xv, train/loss" + "v5-L96-D1024-E0_1-m 81%[===============> ] 2.15G 39.5MB/s eta 13s " ] }, { @@ -102444,7 +2384,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8523/12318 [14:45:10<6:34:08, 6.23s/it, v_num=e4xv, train/loss" + "5-L96-D1024-E0_1-me 82%[===============> ] 2.16G 39.8MB/s eta 13s " ] }, { @@ -102452,8 +2392,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8524/12318 [14:45:11<6:33:59, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8524/12318 [14:45:11<6:33:59, 6.23s/it, v_num=e4xv, train/loss" + "-L96-D1024-E0_1-mem 82%[===============> ] 2.17G 39.3MB/s eta 13s " ] }, { @@ -102461,8 +2400,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8525/12318 [14:45:20<6:33:54, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8525/12318 [14:45:20<6:33:54, 6.23s/it, v_num=e4xv, train/loss" + "L96-D1024-E0_1-mem- 82%[===============> ] 2.17G 39.2MB/s eta 13s " ] }, { @@ -102470,8 +2408,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8526/12318 [14:45:29<6:33:49, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8526/12318 [14:45:29<6:33:49, 6.23s/it, v_num=e4xv, train/loss" + "96-D1024-E0_1-mem-c 82%[===============> ] 2.18G 39.5MB/s eta 13s " ] }, { @@ -102479,8 +2416,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8527/12318 [14:45:33<6:33:42, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8527/12318 [14:45:33<6:33:42, 6.23s/it, v_num=e4xv, train/loss" + "6-D1024-E0_1-mem-ct 83%[===============> ] 2.19G 39.7MB/s eta 11s " ] }, { @@ -102488,8 +2424,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8528/12318 [14:45:41<6:33:37, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8528/12318 [14:45:41<6:33:37, 6.23s/it, v_num=e4xv, train/loss" + "-D1024-E0_1-mem-ctx 83%[===============> ] 2.20G 40.6MB/s eta 11s " ] }, { @@ -102497,8 +2432,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8529/12318 [14:45:46<6:33:30, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8529/12318 [14:45:46<6:33:30, 6.23s/it, v_num=e4xv, train/loss" + "D1024-E0_1-mem-ctx- 83%[===============> ] 2.21G 39.8MB/s eta 11s " ] }, { @@ -102506,8 +2440,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8530/12318 [14:45:49<6:33:22, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8530/12318 [14:45:49<6:33:22, 6.23s/it, v_num=e4xv, train/loss" + "1024-E0_1-mem-ctx-4 84%[===============> ] 2.21G 39.9MB/s eta 11s " ] }, { @@ -102515,8 +2448,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8531/12318 [14:45:50<6:33:14, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8531/12318 [14:45:50<6:33:14, 6.23s/it, v_num=e4xv, train/loss" + "024-E0_1-mem-ctx-4k 84%[===============> ] 2.22G 40.4MB/s eta 11s " ] }, { @@ -102524,8 +2456,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8532/12318 [14:45:56<6:33:07, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8532/12318 [14:45:56<6:33:07, 6.23s/it, v_num=e4xv, train/loss" + "24-E0_1-mem-ctx-4k. 84%[===============> ] 2.23G 40.4MB/s eta 10s " ] }, { @@ -102533,8 +2464,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8533/12318 [14:46:05<6:33:02, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8533/12318 [14:46:05<6:33:02, 6.23s/it, v_num=e4xv, train/loss" + "4-E0_1-mem-ctx-4k.p 85%[================> ] 2.24G 40.8MB/s eta 10s " ] }, { @@ -102542,8 +2472,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8534/12318 [14:46:09<6:32:55, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8534/12318 [14:46:09<6:32:55, 6.23s/it, v_num=e4xv, train/loss" + "-E0_1-mem-ctx-4k.pt 85%[================> ] 2.25G 40.5MB/s eta 10s " ] }, { @@ -102551,8 +2480,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8535/12318 [14:46:15<6:32:49, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8535/12318 [14:46:15<6:32:49, 6.23s/it, v_num=e4xv, train/loss" + "E0_1-mem-ctx-4k.pth 85%[================> ] 2.26G 40.4MB/s eta 10s " ] }, { @@ -102560,8 +2488,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8536/12318 [14:46:21<6:32:43, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8536/12318 [14:46:21<6:32:43, 6.23s/it, v_num=e4xv, train/loss" + "0_1-mem-ctx-4k.pth 86%[================> ] 2.27G 40.8MB/s eta 10s " ] }, { @@ -102569,8 +2496,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8537/12318 [14:46:23<6:32:34, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8537/12318 [14:46:23<6:32:34, 6.23s/it, v_num=e4xv, train/loss" + "_1-mem-ctx-4k.pth 86%[================> ] 2.27G 41.0MB/s eta 9s " ] }, { @@ -102578,8 +2504,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8538/12318 [14:46:31<6:32:29, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8538/12318 [14:46:31<6:32:29, 6.23s/it, v_num=e4xv, train/loss" + "1-mem-ctx-4k.pth 86%[================> ] 2.28G 40.1MB/s eta 9s " ] }, { @@ -102587,8 +2512,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8539/12318 [14:46:36<6:32:22, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8539/12318 [14:46:36<6:32:22, 6.23s/it, v_num=e4xv, train/loss" + "-mem-ctx-4k.pth 87%[================> ] 2.29G 40.1MB/s eta 9s " ] }, { @@ -102596,8 +2520,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8540/12318 [14:46:41<6:32:15, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8540/12318 [14:46:41<6:32:15, 6.23s/it, v_num=e4xv, train/loss" + "mem-ctx-4k.pth 87%[================> ] 2.30G 40.0MB/s eta 9s " ] }, { @@ -102605,8 +2528,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8541/12318 [14:46:45<6:32:08, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8541/12318 [14:46:45<6:32:08, 6.23s/it, v_num=e4xv, train/loss" + "em-ctx-4k.pth 87%[================> ] 2.31G 40.4MB/s eta 9s " ] }, { @@ -102614,8 +2536,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8542/12318 [14:46:53<6:32:02, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8542/12318 [14:46:53<6:32:02, 6.23s/it, v_num=e4xv, train/loss" + "m-ctx-4k.pth 87%[================> ] 2.31G 40.1MB/s eta 8s " ] }, { @@ -102623,7 +2544,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8543/12318 [14:46:54<6:31:54, 6.23s/it, v_num=e4xv, train/loss" + "-ctx-4k.pth 88%[================> ] 2.32G 39.9MB/s eta 8s " ] }, { @@ -102631,7 +2552,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8543/12318 [14:46:54<6:31:54, 6.23s/it, v_num=e4xv, train/loss" + "ctx-4k.pth 88%[================> ] 2.33G 40.0MB/s eta 8s " ] }, { @@ -102639,8 +2560,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8544/12318 [14:47:16<6:31:55, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8544/12318 [14:47:16<6:31:55, 6.23s/it, v_num=e4xv, train/loss" + "tx-4k.pth 88%[================> ] 2.34G 39.2MB/s eta 8s " ] }, { @@ -102648,8 +2568,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8545/12318 [14:47:19<6:31:47, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8545/12318 [14:47:19<6:31:47, 6.23s/it, v_num=e4xv, train/loss" + "x-4k.pth 89%[================> ] 2.35G 39.7MB/s eta 8s " ] }, { @@ -102657,8 +2576,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8546/12318 [14:47:23<6:31:40, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8546/12318 [14:47:23<6:31:40, 6.23s/it, v_num=e4xv, train/loss" + "-4k.pth 89%[================> ] 2.36G 39.4MB/s eta 7s " ] }, { @@ -102666,8 +2584,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8547/12318 [14:47:30<6:31:34, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8547/12318 [14:47:30<6:31:34, 6.23s/it, v_num=e4xv, train/loss" + "4k.pth 89%[================> ] 2.36G 39.4MB/s eta 7s " ] }, { @@ -102675,8 +2592,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8548/12318 [14:47:35<6:31:27, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8548/12318 [14:47:35<6:31:27, 6.23s/it, v_num=e4xv, train/loss" + "k.pth 90%[=================> ] 2.37G 39.6MB/s eta 7s " ] }, { @@ -102684,8 +2600,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8549/12318 [14:47:38<6:31:20, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8549/12318 [14:47:38<6:31:20, 6.23s/it, v_num=e4xv, train/loss" + ".pth 90%[=================> ] 2.38G 39.4MB/s eta 7s " ] }, { @@ -102693,8 +2608,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8550/12318 [14:47:43<6:31:13, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8550/12318 [14:47:43<6:31:13, 6.23s/it, v_num=e4xv, train/loss" + "pth 90%[=================> ] 2.39G 39.2MB/s eta 7s " ] }, { @@ -102702,8 +2616,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8551/12318 [14:47:51<6:31:07, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8551/12318 [14:47:51<6:31:07, 6.23s/it, v_num=e4xv, train/loss" + "th 91%[=================> ] 2.40G 39.2MB/s eta 6s " ] }, { @@ -102711,8 +2624,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8552/12318 [14:47:56<6:31:00, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8552/12318 [14:47:56<6:31:00, 6.23s/it, v_num=e4xv, train/loss" + "h 91%[=================> ] 2.41G 39.4MB/s eta 6s " ] }, { @@ -102720,8 +2632,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8553/12318 [14:48:03<6:30:55, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8553/12318 [14:48:03<6:30:55, 6.23s/it, v_num=e4xv, train/loss" + " 91%[=================> ] 2.41G 40.0MB/s eta 6s " ] }, { @@ -102729,8 +2640,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8554/12318 [14:48:11<6:30:49, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8554/12318 [14:48:11<6:30:49, 6.23s/it, v_num=e4xv, train/loss" + " v 92%[=================> ] 2.42G 39.8MB/s eta 6s " ] }, { @@ -102738,8 +2648,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8555/12318 [14:48:14<6:30:42, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8555/12318 [14:48:14<6:30:42, 6.23s/it, v_num=e4xv, train/loss" + " v5 92%[=================> ] 2.43G 39.7MB/s eta 6s " ] }, { @@ -102747,8 +2656,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8556/12318 [14:48:21<6:30:36, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8556/12318 [14:48:21<6:30:36, 6.23s/it, v_num=e4xv, train/loss" + " v5- 92%[=================> ] 2.44G 39.5MB/s eta 5s " ] }, { @@ -102756,8 +2664,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8557/12318 [14:48:27<6:30:29, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8557/12318 [14:48:27<6:30:29, 6.23s/it, v_num=e4xv, train/loss" + " v5-L 92%[=================> ] 2.45G 40.6MB/s eta 5s " ] }, { @@ -102765,8 +2672,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8558/12318 [14:48:36<6:30:24, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8558/12318 [14:48:36<6:30:24, 6.23s/it, v_num=e4xv, train/loss" + " v5-L9 93%[=================> ] 2.45G 39.8MB/s eta 5s " ] }, { @@ -102774,8 +2680,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8559/12318 [14:48:39<6:30:17, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8559/12318 [14:48:39<6:30:17, 6.23s/it, v_num=e4xv, train/loss" + " v5-L96 93%[=================> ] 2.46G 39.0MB/s eta 5s " ] }, { @@ -102783,8 +2688,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8560/12318 [14:48:46<6:30:11, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8560/12318 [14:48:46<6:30:11, 6.23s/it, v_num=e4xv, train/loss" + " v5-L96- 93%[=================> ] 2.46G 37.8MB/s eta 5s " ] }, { @@ -102792,8 +2696,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 69%|▋| 8561/12318 [14:48:50<6:30:03, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 69%|▋| 8561/12318 [14:48:50<6:30:03, 6.23s/it, v_num=e4xv, train/loss" + " v5-L96-D 94%[=================> ] 2.48G 40.1MB/s eta 4s " ] }, { @@ -102801,8 +2704,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 70%|▋| 8562/12318 [14:48:55<6:29:57, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8562/12318 [14:48:55<6:29:57, 6.23s/it, v_num=e4xv, train/loss" + " v5-L96-D1 94%[=================> ] 2.49G 40.3MB/s eta 4s " ] }, { @@ -102810,8 +2712,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 70%|▋| 8563/12318 [14:48:58<6:29:49, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8563/12318 [14:48:58<6:29:49, 6.23s/it, v_num=e4xv, train/loss" + " v5-L96-D10 94%[=================> ] 2.50G 40.4MB/s eta 4s " ] }, { @@ -102819,8 +2720,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 70%|▋| 8564/12318 [14:49:06<6:29:44, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8564/12318 [14:49:06<6:29:44, 6.23s/it, v_num=e4xv, train/loss" + " v5-L96-D102 95%[==================> ] 2.51G 40.3MB/s eta 4s " ] }, { @@ -102828,8 +2728,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 70%|▋| 8565/12318 [14:49:15<6:29:39, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8565/12318 [14:49:15<6:29:39, 6.23s/it, v_num=e4xv, train/loss" + " v5-L96-D1024 95%[==================> ] 2.51G 40.4MB/s eta 4s " ] }, { @@ -102837,8 +2736,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 70%|▋| 8566/12318 [14:49:22<6:29:33, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8566/12318 [14:49:22<6:29:33, 6.23s/it, v_num=e4xv, train/loss" + " v5-L96-D1024- 95%[==================> ] 2.52G 41.1MB/s eta 3s " ] }, { @@ -102846,8 +2744,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 70%|▋| 8567/12318 [14:49:27<6:29:26, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8567/12318 [14:49:27<6:29:26, 6.23s/it, v_num=e4xv, train/loss" + " v5-L96-D1024-E 96%[==================> ] 2.53G 40.8MB/s eta 3s " ] }, { @@ -102855,8 +2752,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 70%|▋| 8568/12318 [14:49:32<6:29:19, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8568/12318 [14:49:32<6:29:19, 6.23s/it, v_num=e4xv, train/loss" + " v5-L96-D1024-E0 96%[==================> ] 2.54G 40.5MB/s eta 3s " ] }, { @@ -102864,8 +2760,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 70%|▋| 8569/12318 [14:49:35<6:29:12, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8569/12318 [14:49:35<6:29:12, 6.23s/it, v_num=e4xv, train/loss" + " v5-L96-D1024-E0_ 96%[==================> ] 2.55G 40.5MB/s eta 3s " ] }, { @@ -102873,8 +2768,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 70%|▋| 8570/12318 [14:49:41<6:29:05, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8570/12318 [14:49:41<6:29:05, 6.23s/it, v_num=e4xv, train/loss" + " v5-L96-D1024-E0_1 97%[==================> ] 2.55G 40.3MB/s eta 3s " ] }, { @@ -102882,8 +2776,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 70%|▋| 8571/12318 [14:49:45<6:28:58, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8571/12318 [14:49:45<6:28:58, 6.23s/it, v_num=e4xv, train/loss" + " v5-L96-D1024-E0_1- 97%[==================> ] 2.56G 40.3MB/s eta 2s " ] }, { @@ -102891,8 +2784,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 70%|▋| 8572/12318 [14:49:46<6:28:50, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8572/12318 [14:49:46<6:28:50, 6.23s/it, v_num=e4xv, train/loss" + "v5-L96-D1024-E0_1-m 97%[==================> ] 2.57G 40.5MB/s eta 2s " ] }, { @@ -102900,8 +2792,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 70%|▋| 8573/12318 [14:49:52<6:28:43, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8573/12318 [14:49:52<6:28:43, 6.23s/it, v_num=e4xv, train/loss" + "5-L96-D1024-E0_1-me 98%[==================> ] 2.58G 40.9MB/s eta 2s " ] }, { @@ -102909,8 +2800,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 70%|▋| 8574/12318 [14:49:59<6:28:37, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8574/12318 [14:49:59<6:28:37, 6.23s/it, v_num=e4xv, train/loss" + "-L96-D1024-E0_1-mem 98%[==================> ] 2.59G 40.8MB/s eta 2s " ] }, { @@ -102918,8 +2808,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 70%|▋| 8575/12318 [14:50:06<6:28:31, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8575/12318 [14:50:06<6:28:31, 6.23s/it, v_num=e4xv, train/loss" + "L96-D1024-E0_1-mem- 98%[==================> ] 2.60G 42.5MB/s eta 2s " ] }, { @@ -102927,8 +2816,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 70%|▋| 8576/12318 [14:50:40<6:28:37, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8576/12318 [14:50:40<6:28:37, 6.23s/it, v_num=e4xv, train/loss" + "96-D1024-E0_1-mem-c 99%[==================> ] 2.61G 42.8MB/s eta 1s " ] }, { @@ -102936,8 +2824,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 70%|▋| 8577/12318 [14:50:48<6:28:32, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8577/12318 [14:50:48<6:28:32, 6.23s/it, v_num=e4xv, train/loss" + "6-D1024-E0_1-mem-ct 99%[==================> ] 2.61G 40.8MB/s eta 1s " ] }, { @@ -102945,8 +2832,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 70%|▋| 8578/12318 [14:50:55<6:28:26, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8578/12318 [14:50:55<6:28:26, 6.23s/it, v_num=e4xv, train/loss" + "-D1024-E0_1-mem-ctx 99%[==================> ] 2.62G 40.9MB/s eta 1s " ] }, { @@ -102954,8 +2840,7 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 70%|▋| 8579/12318 [14:51:03<6:28:21, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8579/12318 [14:51:03<6:28:21, 6.23s/it, v_num=e4xv, train/loss" + "D1024-E0_1-mem-ctx- 99%[==================> ] 2.63G 40.8MB/s eta 1s " ] }, { @@ -102963,9843 +2848,7796 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 70%|▋| 8580/12318 [14:51:09<6:28:14, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8580/12318 [14:51:09<6:28:14, 6.23s/it, v_num=e4xv, train/loss" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "Epoch 0: 70%|▋| 8581/12318 [14:51:18<6:28:09, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8581/12318 [14:51:18<6:28:09, 6.23s/it, v_num=e4xv, train/loss" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "Epoch 0: 70%|▋| 8582/12318 [14:51:22<6:28:02, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8582/12318 [14:51:22<6:28:02, 6.23s/it, v_num=e4xv, train/loss" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "Epoch 0: 70%|▋| 8583/12318 [14:51:30<6:27:56, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8583/12318 [14:51:30<6:27:56, 6.23s/it, v_num=e4xv, train/loss" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "Epoch 0: 70%|▋| 8584/12318 [14:51:36<6:27:50, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8584/12318 [14:51:36<6:27:50, 6.23s/it, v_num=e4xv, train/loss" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "Epoch 0: 70%|▋| 8585/12318 [14:51:41<6:27:43, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8585/12318 [14:51:41<6:27:43, 6.23s/it, v_num=e4xv, train/loss" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "Epoch 0: 70%|▋| 8586/12318 [14:51:48<6:27:38, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8586/12318 [14:51:48<6:27:38, 6.23s/it, v_num=e4xv, train/loss" + "v5-L96-D1024-E0_1-m 100%[===================>] 2.63G 41.1MB/s in 68s \r\n", + "\r\n", + "2023-09-02 06:17:41 (39.7 MB/s) - ‘v5-L96-D1024-E0_1-mem-ctx-4k.pth’ saved [2825976699/2825976699]\r\n", + "\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8587/12318 [14:51:52<6:27:30, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8587/12318 [14:51:52<6:27:30, 6.23s/it, v_num=e4xv, train/loss" + "total 2.7G\r\n", + "drwxr-xr-x 2 root root 54 Sep 2 06:16 .\r\n", + "drwxr-xr-x 19 root root 4.0K Sep 2 06:16 ..\r\n", + "-rw-r--r-- 1 root root 2.7G Sep 2 05:37 v5-L96-D1024-E0_1-mem-ctx-4k.pth\r\n" ] + } + ], + "source": [ + "# Download the model directly (stop gap till HF sync issues is resolved)\n", + "!cd \"{TRAINER_DIR}\" && cd \"../model/\" && \\\n", + " wget -nc \"https://huggingface.co/rwkv-x-dev/rwkv-x-playground/resolve/main/experiment/rwkv-x-exp/v5-memory/{FILENAME_PREFIX}-mem-ctx-4k.pth\"\n", + "\n", + "!cd \"{TRAINER_DIR}\" && cd \"../model/\" && \\\n", + " ls -alh ." + ] + }, + { + "cell_type": "markdown", + "id": "adf68d89", + "metadata": { + "papermill": { + "duration": 0.01742, + "end_time": "2023-09-02T06:17:41.804733", + "exception": false, + "start_time": "2023-09-02T06:17:41.787313", + "status": "completed" }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "Epoch 0: 70%|▋| 8588/12318 [14:52:01<6:27:25, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8588/12318 [14:52:01<6:27:25, 6.23s/it, v_num=e4xv, train/loss" - ] + "tags": [] + }, + "source": [ + "## Tune 6 : Ramping up the ctx size (8192), memory training\n", + "\n", + "- Tune 6: Large ctx size (8192), Scaling up!" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "id": "51c58e54", + "metadata": { + "execution": { + "iopub.execute_input": "2023-09-02T06:17:41.841382Z", + "iopub.status.busy": "2023-09-02T06:17:41.841191Z", + "iopub.status.idle": "2023-09-02T06:17:48.969203Z", + "shell.execute_reply": "2023-09-02T06:17:48.967550Z" }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "Epoch 0: 70%|▋| 8589/12318 [14:52:09<6:27:20, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8589/12318 [14:52:09<6:27:20, 6.23s/it, v_num=e4xv, train/loss" - ] + "papermill": { + "duration": 7.217868, + "end_time": "2023-09-02T06:17:49.040024", + "exception": false, + "start_time": "2023-09-02T06:17:41.822156", + "status": "completed" }, + "tags": [] + }, + "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8590/12318 [14:52:17<6:27:14, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8590/12318 [14:52:17<6:27:14, 6.23s/it, v_num=e4xv, train/loss" + "## Generating word reptition dataset ##\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8591/12318 [14:52:22<6:27:08, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8591/12318 [14:52:22<6:27:08, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 2 max words, 50 samples - at ../dataset/word-2-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8592/12318 [14:52:29<6:27:02, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8592/12318 [14:52:29<6:27:02, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 10 max words, 50 samples - at ../dataset/gen-word-10-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8593/12318 [14:52:37<6:26:56, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8593/12318 [14:52:37<6:26:56, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 35 max words, 50 samples - at ../dataset/gen-word-35-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8594/12318 [14:52:41<6:26:49, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8594/12318 [14:52:41<6:26:49, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 566 samples (1 token repeat) - 5 max words - at ../dataset/shuffle-word-5-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8595/12318 [14:52:47<6:26:43, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8595/12318 [14:52:47<6:26:43, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 5 max words, 50 samples - at ../dataset/gen-word-5-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8596/12318 [14:52:54<6:26:37, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8596/12318 [14:52:54<6:26:37, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 60 max words, 50 samples - at ../dataset/gen-word-60-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8597/12318 [14:53:01<6:26:31, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8597/12318 [14:53:01<6:26:31, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 30 max words, 50 samples - at ../dataset/gen-word-30-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8598/12318 [14:53:07<6:26:24, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8598/12318 [14:53:07<6:26:24, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 84 samples (1 token repeat) - 30 max words - at ../dataset/shuffle-word-30-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8599/12318 [14:53:12<6:26:18, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8599/12318 [14:53:12<6:26:18, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 77 samples (1 token repeat) - 35 max words - at ../dataset/shuffle-word-35-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8600/12318 [14:53:21<6:26:13, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8600/12318 [14:53:21<6:26:13, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 25 max words, 50 samples - at ../dataset/gen-word-25-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8601/12318 [14:53:26<6:26:06, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8601/12318 [14:53:26<6:26:06, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 45 max words, 50 samples - at ../dataset/gen-word-45-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8602/12318 [14:53:28<6:25:58, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8602/12318 [14:53:28<6:25:58, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 63 samples (1 token repeat) - 40 max words - at ../dataset/shuffle-word-40-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8603/12318 [14:53:31<6:25:50, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8603/12318 [14:53:31<6:25:50, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 50 max words, 50 samples - at ../dataset/gen-word-50-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8604/12318 [14:53:40<6:25:45, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 55 max words, 50 samples - at ../dataset/gen-word-55-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8604/12318 [14:53:40<6:25:45, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 15 max words, 50 samples - at ../dataset/gen-word-15-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8605/12318 [14:53:47<6:25:39, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8605/12318 [14:53:47<6:25:39, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 120 max words, 50 samples - at ../dataset/gen-word-120-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8606/12318 [14:53:48<6:25:31, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8606/12318 [14:53:48<6:25:31, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 129 samples (1 token repeat) - 20 max words - at ../dataset/shuffle-word-20-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8607/12318 [14:53:51<6:25:23, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 56 samples (1 token repeat) - 50 max words - at ../dataset/shuffle-word-50-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8607/12318 [14:53:51<6:25:23, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 264 samples (1 token repeat) - 10 max words - at ../dataset/shuffle-word-10-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8608/12318 [14:54:06<6:25:21, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8608/12318 [14:54:06<6:25:21, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 40 max words, 50 samples - at ../dataset/gen-word-40-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8609/12318 [14:54:14<6:25:15, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8609/12318 [14:54:14<6:25:15, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 189 samples (1 token repeat) - 15 max words - at ../dataset/shuffle-word-15-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8610/12318 [14:54:17<6:25:08, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8610/12318 [14:54:17<6:25:08, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 19 samples (1 token repeat) - 115 max words - at ../dataset/shuffle-word-115-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8611/12318 [14:54:23<6:25:01, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8611/12318 [14:54:23<6:25:01, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 58 samples (1 token repeat) - 45 max words - at ../dataset/shuffle-word-45-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8612/12318 [14:54:31<6:24:56, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8612/12318 [14:54:31<6:24:56, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 20 max words, 50 samples - at ../dataset/gen-word-20-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8613/12318 [14:54:37<6:24:49, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8613/12318 [14:54:37<6:24:49, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 20 samples (1 token repeat) - 110 max words - at ../dataset/shuffle-word-110-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8614/12318 [14:54:39<6:24:41, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8614/12318 [14:54:39<6:24:41, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 10 samples (1 token repeat) - 220 max words - at ../dataset/shuffle-word-220-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8615/12318 [14:54:40<6:24:33, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8615/12318 [14:54:40<6:24:33, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 110 max words, 50 samples - at ../dataset/gen-word-110-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8616/12318 [14:54:45<6:24:27, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8616/12318 [14:54:45<6:24:27, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 50 samples (1 token repeat) - 55 max words - at ../dataset/shuffle-word-55-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8617/12318 [14:54:48<6:24:19, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8617/12318 [14:54:48<6:24:19, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 105 max words, 50 samples - at ../dataset/gen-word-105-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8618/12318 [14:54:57<6:24:14, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8618/12318 [14:54:57<6:24:14, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 85 max words, 50 samples - at ../dataset/gen-word-85-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8619/12318 [14:55:04<6:24:08, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8619/12318 [14:55:04<6:24:08, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 100 max words, 50 samples - at ../dataset/gen-word-100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8620/12318 [14:55:09<6:24:01, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8620/12318 [14:55:09<6:24:01, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 235 max words, 50 samples - at ../dataset/gen-word-235-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8621/12318 [14:55:15<6:23:55, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8621/12318 [14:55:15<6:23:55, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 19 samples (1 token repeat) - 120 max words - at ../dataset/shuffle-word-120-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8622/12318 [14:55:17<6:23:47, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8622/12318 [14:55:17<6:23:47, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 140 max words, 50 samples - at ../dataset/gen-word-140-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8623/12318 [14:55:25<6:23:41, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8623/12318 [14:55:25<6:23:41, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 125 max words, 50 samples - at ../dataset/gen-word-125-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8624/12318 [14:55:28<6:23:33, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8624/12318 [14:55:28<6:23:33, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 80 max words, 50 samples - at ../dataset/gen-word-80-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8625/12318 [14:55:31<6:23:26, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8625/12318 [14:55:31<6:23:26, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 95 max words, 50 samples - at ../dataset/gen-word-95-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8626/12318 [14:55:36<6:23:19, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8626/12318 [14:55:36<6:23:19, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 105 samples (1 token repeat) - 25 max words - at ../dataset/shuffle-word-25-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8627/12318 [14:55:43<6:23:13, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8627/12318 [14:55:43<6:23:13, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 10 samples (1 token repeat) - 215 max words - at ../dataset/shuffle-word-215-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8628/12318 [14:55:46<6:23:06, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8628/12318 [14:55:46<6:23:06, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 10 samples (1 token repeat) - 265 max words - at ../dataset/shuffle-word-265-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8629/12318 [14:55:49<6:22:58, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 21 samples (1 token repeat) - 105 max words - at ../dataset/shuffle-word-105-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8629/12318 [14:55:49<6:22:58, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 310 max words, 50 samples - at ../dataset/gen-word-310-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8630/12318 [14:55:57<6:22:53, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8630/12318 [14:55:57<6:22:53, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 70 max words, 50 samples - at ../dataset/gen-word-70-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8631/12318 [14:56:02<6:22:46, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8631/12318 [14:56:02<6:22:46, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 115 max words, 50 samples - at ../dataset/gen-word-115-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8632/12318 [14:56:05<6:22:38, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8632/12318 [14:56:05<6:22:38, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 5 samples (1 token repeat) - 590 max words - at ../dataset/shuffle-word-590-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8633/12318 [14:56:12<6:22:32, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8633/12318 [14:56:12<6:22:32, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 200 max words, 50 samples - at ../dataset/gen-word-200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8634/12318 [14:56:17<6:22:26, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8634/12318 [14:56:17<6:22:26, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 5 samples (1 token repeat) - 595 max words - at ../dataset/shuffle-word-595-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8635/12318 [14:56:26<6:22:21, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8635/12318 [14:56:26<6:22:21, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 9 samples (1 token repeat) - 255 max words - at ../dataset/shuffle-word-255-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8636/12318 [14:56:31<6:22:14, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8636/12318 [14:56:31<6:22:14, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 175 max words, 50 samples - at ../dataset/gen-word-175-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8637/12318 [14:56:40<6:22:09, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8637/12318 [14:56:40<6:22:09, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 26 samples (1 token repeat) - 95 max words - at ../dataset/shuffle-word-95-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8638/12318 [14:56:47<6:22:03, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8638/12318 [14:56:47<6:22:03, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 6 samples (1 token repeat) - 450 max words - at ../dataset/shuffle-word-450-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8639/12318 [14:56:52<6:21:56, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8639/12318 [14:56:52<6:21:56, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 270 max words, 50 samples - at ../dataset/gen-word-270-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8640/12318 [14:57:18<6:21:58, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8640/12318 [14:57:18<6:21:58, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 44 samples (1 token repeat) - 60 max words - at ../dataset/shuffle-word-60-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8641/12318 [14:57:23<6:21:51, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8641/12318 [14:57:23<6:21:51, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 415 max words, 50 samples - at ../dataset/gen-word-415-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8642/12318 [14:57:27<6:21:45, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 585 max words, 50 samples - at ../dataset/gen-word-585-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8642/12318 [14:57:27<6:21:45, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 7 samples (1 token repeat) - 350 max words - at ../dataset/shuffle-word-350-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8643/12318 [14:57:32<6:21:38, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8643/12318 [14:57:32<6:21:38, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 430 max words, 50 samples - at ../dataset/gen-word-430-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8644/12318 [14:57:37<6:21:31, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8644/12318 [14:57:37<6:21:31, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 17 samples (1 token repeat) - 135 max words - at ../dataset/shuffle-word-135-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8645/12318 [14:57:42<6:21:24, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8645/12318 [14:57:42<6:21:24, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 5 samples (1 token repeat) - 525 max words - at ../dataset/shuffle-word-525-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8646/12318 [14:57:47<6:21:17, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8646/12318 [14:57:47<6:21:17, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 5 samples (1 token repeat) - 530 max words - at ../dataset/shuffle-word-530-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8647/12318 [14:57:50<6:21:10, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8647/12318 [14:57:50<6:21:10, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 8 samples (1 token repeat) - 305 max words - at ../dataset/shuffle-word-305-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8648/12318 [14:57:55<6:21:03, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8648/12318 [14:57:55<6:21:03, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 11 samples (1 token repeat) - 210 max words - at ../dataset/shuffle-word-210-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8649/12318 [14:58:01<6:20:57, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8649/12318 [14:58:01<6:20:57, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 285 max words, 50 samples - at ../dataset/gen-word-285-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8650/12318 [14:58:07<6:20:50, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8650/12318 [14:58:07<6:20:50, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 330 max words, 50 samples - at ../dataset/gen-word-330-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8651/12318 [14:58:12<6:20:43, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8651/12318 [14:58:12<6:20:43, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 6 samples (1 token repeat) - 495 max words - at ../dataset/shuffle-word-495-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8652/12318 [14:58:17<6:20:37, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8652/12318 [14:58:17<6:20:37, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 400 max words, 50 samples - at ../dataset/gen-word-400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8653/12318 [14:58:22<6:20:30, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8653/12318 [14:58:22<6:20:30, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 9 samples (1 token repeat) - 240 max words - at ../dataset/shuffle-word-240-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8654/12318 [14:58:28<6:20:24, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8654/12318 [14:58:28<6:20:24, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 5 samples (1 token repeat) - 580 max words - at ../dataset/shuffle-word-580-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8655/12318 [14:58:32<6:20:17, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8655/12318 [14:58:32<6:20:17, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 520 max words, 50 samples - at ../dataset/gen-word-520-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8656/12318 [14:58:39<6:20:11, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8656/12318 [14:58:39<6:20:11, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 370 max words, 50 samples - at ../dataset/gen-word-370-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8657/12318 [14:58:47<6:20:05, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 425 max words, 50 samples - at ../dataset/gen-word-425-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8657/12318 [14:58:47<6:20:05, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 7 samples (1 token repeat) - 365 max words - at ../dataset/shuffle-word-365-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8658/12318 [14:58:52<6:19:58, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8658/12318 [14:58:52<6:19:58, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 10 samples (1 token repeat) - 225 max words - at ../dataset/shuffle-word-225-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8659/12318 [14:58:54<6:19:50, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8659/12318 [14:58:54<6:19:50, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 10 samples (1 token repeat) - 230 max words - at ../dataset/shuffle-word-230-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8660/12318 [14:59:02<6:19:45, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8660/12318 [14:59:02<6:19:45, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 290 max words, 50 samples - at ../dataset/gen-word-290-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8661/12318 [14:59:07<6:19:38, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8661/12318 [14:59:07<6:19:38, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 7 samples (1 token repeat) - 400 max words - at ../dataset/shuffle-word-400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8662/12318 [14:59:10<6:19:31, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 6 samples (1 token repeat) - 445 max words - at ../dataset/shuffle-word-445-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8662/12318 [14:59:10<6:19:31, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 180 max words, 50 samples - at ../dataset/gen-word-180-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8663/12318 [14:59:16<6:19:24, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8663/12318 [14:59:16<6:19:24, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 65 max words, 50 samples - at ../dataset/gen-word-65-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8664/12318 [14:59:24<6:19:19, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8664/12318 [14:59:24<6:19:19, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 5 samples (1 token repeat) - 545 max words - at ../dataset/shuffle-word-545-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8665/12318 [14:59:28<6:19:12, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8665/12318 [14:59:28<6:19:12, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 18 samples (1 token repeat) - 130 max words - at ../dataset/shuffle-word-130-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8666/12318 [14:59:35<6:19:06, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8666/12318 [14:59:35<6:19:06, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 560 max words, 50 samples - at ../dataset/gen-word-560-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8667/12318 [14:59:43<6:19:00, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8667/12318 [14:59:43<6:19:00, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 480 max words, 50 samples - at ../dataset/gen-word-480-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8668/12318 [14:59:48<6:18:53, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8668/12318 [14:59:48<6:18:53, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 32 samples (1 token repeat) - 85 max words - at ../dataset/shuffle-word-85-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8669/12318 [14:59:52<6:18:46, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8669/12318 [14:59:52<6:18:46, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 36 samples (1 token repeat) - 75 max words - at ../dataset/shuffle-word-75-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8670/12318 [15:00:01<6:18:41, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8670/12318 [15:00:01<6:18:41, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 15 samples (1 token repeat) - 155 max words - at ../dataset/shuffle-word-155-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8671/12318 [15:00:08<6:18:35, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8671/12318 [15:00:08<6:18:35, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 4 samples (1 token repeat) - 800 max words - at ../dataset/shuffle-word-800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8672/12318 [15:00:36<6:18:38, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8672/12318 [15:00:36<6:18:38, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 365 max words, 50 samples - at ../dataset/gen-word-365-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8673/12318 [15:00:38<6:18:30, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8673/12318 [15:00:38<6:18:30, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 5 samples (1 token repeat) - 600 max words - at ../dataset/shuffle-word-600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8674/12318 [15:00:47<6:18:25, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8674/12318 [15:00:47<6:18:25, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 18 samples (1 token repeat) - 125 max words - at ../dataset/shuffle-word-125-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8675/12318 [15:00:48<6:18:17, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8675/12318 [15:00:48<6:18:17, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 16 samples (1 token repeat) - 140 max words - at ../dataset/shuffle-word-140-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8676/12318 [15:00:57<6:18:12, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8676/12318 [15:00:57<6:18:12, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 155 max words, 50 samples - at ../dataset/gen-word-155-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8677/12318 [15:01:04<6:18:06, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8677/12318 [15:01:04<6:18:06, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 130 max words, 50 samples - at ../dataset/gen-word-130-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8678/12318 [15:01:12<6:18:00, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 445 max words, 50 samples - at ../dataset/gen-word-445-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8678/12318 [15:01:12<6:18:00, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 6 samples (1 token repeat) - 470 max words - at ../dataset/shuffle-word-470-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8679/12318 [15:01:15<6:17:53, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8679/12318 [15:01:15<6:17:53, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 580 max words, 50 samples - at ../dataset/gen-word-580-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8680/12318 [15:01:22<6:17:47, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8680/12318 [15:01:22<6:17:47, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 4 samples (1 token repeat) - 610 max words - at ../dataset/shuffle-word-610-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8681/12318 [15:01:28<6:17:40, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8681/12318 [15:01:28<6:17:40, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 405 max words, 50 samples - at ../dataset/gen-word-405-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8682/12318 [15:01:34<6:17:34, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8682/12318 [15:01:34<6:17:34, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 6 samples (1 token repeat) - 490 max words - at ../dataset/shuffle-word-490-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8683/12318 [15:01:39<6:17:27, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8683/12318 [15:01:39<6:17:27, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 4 samples (1 token repeat) - 630 max words - at ../dataset/shuffle-word-630-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 70%|▋| 8684/12318 [15:01:45<6:17:21, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 70%|▋| 8684/12318 [15:01:45<6:17:21, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 755 max words, 50 samples - at ../dataset/gen-word-755-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8685/12318 [15:01:46<6:17:13, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8685/12318 [15:01:46<6:17:13, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 255 max words, 50 samples - at ../dataset/gen-word-255-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8686/12318 [15:01:51<6:17:06, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8686/12318 [15:01:51<6:17:06, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 4 samples (1 token repeat) - 745 max words - at ../dataset/shuffle-word-745-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8687/12318 [15:02:00<6:17:01, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8687/12318 [15:02:00<6:17:01, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 9 samples (1 token repeat) - 280 max words - at ../dataset/shuffle-word-280-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8688/12318 [15:02:01<6:16:52, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8688/12318 [15:02:01<6:16:52, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 4 samples (1 token repeat) - 690 max words - at ../dataset/shuffle-word-690-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8689/12318 [15:02:06<6:16:46, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8689/12318 [15:02:06<6:16:46, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 15 samples (1 token repeat) - 160 max words - at ../dataset/shuffle-word-160-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8690/12318 [15:02:10<6:16:39, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8690/12318 [15:02:10<6:16:39, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 740 max words, 50 samples - at ../dataset/gen-word-740-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8691/12318 [15:02:17<6:16:33, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8691/12318 [15:02:17<6:16:33, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 145 max words, 50 samples - at ../dataset/gen-word-145-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8692/12318 [15:02:20<6:16:25, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8692/12318 [15:02:20<6:16:25, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 7 samples (1 token repeat) - 360 max words - at ../dataset/shuffle-word-360-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8693/12318 [15:02:26<6:16:19, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8693/12318 [15:02:26<6:16:19, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 3 samples (1 token repeat) - 835 max words - at ../dataset/shuffle-word-835-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8694/12318 [15:02:31<6:16:12, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8694/12318 [15:02:31<6:16:12, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 210 max words, 50 samples - at ../dataset/gen-word-210-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8695/12318 [15:02:33<6:16:04, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 5 samples (1 token repeat) - 585 max words - at ../dataset/shuffle-word-585-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8695/12318 [15:02:33<6:16:04, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 39 samples (1 token repeat) - 65 max words - at ../dataset/shuffle-word-65-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8696/12318 [15:02:41<6:15:58, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8696/12318 [15:02:41<6:15:58, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 9 samples (1 token repeat) - 250 max words - at ../dataset/shuffle-word-250-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8697/12318 [15:02:44<6:15:51, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8697/12318 [15:02:44<6:15:51, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 450 max words, 50 samples - at ../dataset/gen-word-450-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8698/12318 [15:02:50<6:15:45, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8698/12318 [15:02:50<6:15:45, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 5 samples (1 token repeat) - 550 max words - at ../dataset/shuffle-word-550-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8699/12318 [15:02:59<6:15:39, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 455 max words, 50 samples - at ../dataset/gen-word-455-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8699/12318 [15:02:59<6:15:39, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 435 max words, 50 samples - at ../dataset/gen-word-435-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8700/12318 [15:03:00<6:15:31, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8700/12318 [15:03:00<6:15:31, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 4 samples (1 token repeat) - 760 max words - at ../dataset/shuffle-word-760-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8701/12318 [15:03:02<6:15:23, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8701/12318 [15:03:02<6:15:23, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 165 max words, 50 samples - at ../dataset/gen-word-165-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8702/12318 [15:03:06<6:15:16, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8702/12318 [15:03:06<6:15:16, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 14 samples (1 token repeat) - 170 max words - at ../dataset/shuffle-word-170-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8703/12318 [15:03:08<6:15:08, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8703/12318 [15:03:08<6:15:08, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 15 samples (1 token repeat) - 180 max words - at ../dataset/shuffle-word-180-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8704/12318 [15:03:55<6:15:19, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8704/12318 [15:03:55<6:15:19, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 75 max words, 50 samples - at ../dataset/gen-word-75-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8705/12318 [15:04:01<6:15:12, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8705/12318 [15:04:01<6:15:12, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 28 samples (1 token repeat) - 100 max words - at ../dataset/shuffle-word-100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8706/12318 [15:04:06<6:15:06, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8706/12318 [15:04:06<6:15:06, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 39 samples (1 token repeat) - 70 max words - at ../dataset/shuffle-word-70-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8707/12318 [15:04:12<6:14:59, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8707/12318 [15:04:12<6:14:59, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 550 max words, 50 samples - at ../dataset/gen-word-550-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8708/12318 [15:04:16<6:14:52, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8708/12318 [15:04:16<6:14:52, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 3 samples (1 token repeat) - 955 max words - at ../dataset/shuffle-word-955-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8709/12318 [15:04:23<6:14:46, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8709/12318 [15:04:23<6:14:46, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 355 max words, 50 samples - at ../dataset/gen-word-355-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8710/12318 [15:04:26<6:14:39, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8710/12318 [15:04:26<6:14:39, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 9 samples (1 token repeat) - 295 max words - at ../dataset/shuffle-word-295-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8711/12318 [15:04:28<6:14:31, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8711/12318 [15:04:28<6:14:31, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 4 samples (1 token repeat) - 830 max words - at ../dataset/shuffle-word-830-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8712/12318 [15:04:30<6:14:23, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8712/12318 [15:04:30<6:14:23, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 4 samples (1 token repeat) - 770 max words - at ../dataset/shuffle-word-770-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8713/12318 [15:04:34<6:14:16, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8713/12318 [15:04:34<6:14:16, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 9 samples (1 token repeat) - 285 max words - at ../dataset/shuffle-word-285-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8714/12318 [15:04:38<6:14:08, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8714/12318 [15:04:38<6:14:08, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 470 max words, 50 samples - at ../dataset/gen-word-470-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8715/12318 [15:04:46<6:14:03, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8715/12318 [15:04:46<6:14:03, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 345 max words, 50 samples - at ../dataset/gen-word-345-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8716/12318 [15:04:50<6:13:56, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8716/12318 [15:04:50<6:13:56, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 7 samples (1 token repeat) - 355 max words - at ../dataset/shuffle-word-355-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8717/12318 [15:04:55<6:13:49, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8717/12318 [15:04:55<6:13:49, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 410 max words, 50 samples - at ../dataset/gen-word-410-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8718/12318 [15:05:03<6:13:44, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8718/12318 [15:05:03<6:13:44, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 5 samples (1 token repeat) - 535 max words - at ../dataset/shuffle-word-535-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8719/12318 [15:05:12<6:13:38, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8719/12318 [15:05:12<6:13:38, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 15 samples (1 token repeat) - 165 max words - at ../dataset/shuffle-word-165-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8720/12318 [15:05:17<6:13:32, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8720/12318 [15:05:17<6:13:32, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 995 max words, 50 samples - at ../dataset/gen-word-995-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8721/12318 [15:05:20<6:13:24, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8721/12318 [15:05:20<6:13:24, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 60 samples (20 token repeat) - 1100 max words - at ../dataset/shuffle-word-1100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8722/12318 [15:05:28<6:13:19, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8722/12318 [15:05:28<6:13:19, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 225 max words, 50 samples - at ../dataset/gen-word-225-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8723/12318 [15:05:32<6:13:12, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8723/12318 [15:05:32<6:13:12, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 245 max words, 50 samples - at ../dataset/gen-word-245-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8724/12318 [15:05:41<6:13:06, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8724/12318 [15:05:41<6:13:06, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 13 samples (1 token repeat) - 190 max words - at ../dataset/shuffle-word-190-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8725/12318 [15:05:44<6:12:59, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8725/12318 [15:05:44<6:12:59, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 13 samples (1 token repeat) - 200 max words - at ../dataset/shuffle-word-200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8726/12318 [15:05:46<6:12:51, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8726/12318 [15:05:46<6:12:51, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 7 samples (1 token repeat) - 310 max words - at ../dataset/shuffle-word-310-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8727/12318 [15:05:48<6:12:43, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8727/12318 [15:05:48<6:12:43, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 230 max words, 50 samples - at ../dataset/gen-word-230-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8728/12318 [15:05:54<6:12:37, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8728/12318 [15:05:54<6:12:37, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 59 samples (20 token repeat) - 1200 max words - at ../dataset/shuffle-word-1200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8729/12318 [15:06:00<6:12:30, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8729/12318 [15:06:00<6:12:30, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 390 max words, 50 samples - at ../dataset/gen-word-390-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8730/12318 [15:06:01<6:12:22, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8730/12318 [15:06:01<6:12:22, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 5 samples (1 token repeat) - 500 max words - at ../dataset/shuffle-word-500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8731/12318 [15:06:10<6:12:17, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8731/12318 [15:06:10<6:12:17, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 685 max words, 50 samples - at ../dataset/gen-word-685-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8732/12318 [15:06:15<6:12:10, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8732/12318 [15:06:15<6:12:10, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 635 max words, 50 samples - at ../dataset/gen-word-635-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8733/12318 [15:06:20<6:12:03, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8733/12318 [15:06:20<6:12:03, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 545 max words, 50 samples - at ../dataset/gen-word-545-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8734/12318 [15:06:24<6:11:56, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8734/12318 [15:06:24<6:11:56, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 20 samples (20 token repeat) - 4200 max words - at ../dataset/shuffle-word-4200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8735/12318 [15:06:29<6:11:50, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8735/12318 [15:06:29<6:11:50, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 4 samples (1 token repeat) - 715 max words - at ../dataset/shuffle-word-715-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8736/12318 [15:07:14<6:11:59, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8736/12318 [15:07:14<6:11:59, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 625 max words, 50 samples - at ../dataset/gen-word-625-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8737/12318 [15:07:20<6:11:53, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8737/12318 [15:07:20<6:11:53, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 4 samples (1 token repeat) - 795 max words - at ../dataset/shuffle-word-795-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8738/12318 [15:07:25<6:11:46, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8738/12318 [15:07:25<6:11:46, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 4 samples (1 token repeat) - 705 max words - at ../dataset/shuffle-word-705-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8739/12318 [15:07:29<6:11:39, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8739/12318 [15:07:29<6:11:39, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 33 samples (1 token repeat) - 80 max words - at ../dataset/shuffle-word-80-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8740/12318 [15:07:36<6:11:33, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8740/12318 [15:07:36<6:11:33, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 905 max words, 50 samples - at ../dataset/gen-word-905-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8741/12318 [15:07:43<6:11:27, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8741/12318 [15:07:43<6:11:27, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 4 samples (1 token repeat) - 780 max words - at ../dataset/shuffle-word-780-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8742/12318 [15:07:45<6:11:19, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8742/12318 [15:07:45<6:11:19, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 5 samples (1 token repeat) - 520 max words - at ../dataset/shuffle-word-520-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8743/12318 [15:07:51<6:11:13, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8743/12318 [15:07:51<6:11:13, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 375 max words, 50 samples - at ../dataset/gen-word-375-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8744/12318 [15:07:59<6:11:07, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8744/12318 [15:07:59<6:11:07, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 3 samples (1 token repeat) - 940 max words - at ../dataset/shuffle-word-940-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8745/12318 [15:08:06<6:11:01, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8745/12318 [15:08:06<6:11:01, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 150 max words, 50 samples - at ../dataset/gen-word-150-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8746/12318 [15:08:12<6:10:55, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8746/12318 [15:08:12<6:10:55, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 7 samples (1 token repeat) - 345 max words - at ../dataset/shuffle-word-345-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8747/12318 [15:08:21<6:10:50, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8747/12318 [15:08:21<6:10:50, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 275 max words, 50 samples - at ../dataset/gen-word-275-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8748/12318 [15:08:29<6:10:45, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8748/12318 [15:08:29<6:10:45, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 6 samples (1 token repeat) - 425 max words - at ../dataset/shuffle-word-425-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8749/12318 [15:08:32<6:10:37, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8749/12318 [15:08:32<6:10:37, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 3 samples (1 token repeat) - 945 max words - at ../dataset/shuffle-word-945-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8750/12318 [15:08:33<6:10:29, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8750/12318 [15:08:33<6:10:29, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 3 samples (1 token repeat) - 815 max words - at ../dataset/shuffle-word-815-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8751/12318 [15:08:37<6:10:21, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8751/12318 [15:08:37<6:10:21, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 3 samples (1 token repeat) - 960 max words - at ../dataset/shuffle-word-960-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8752/12318 [15:08:41<6:10:14, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8752/12318 [15:08:41<6:10:14, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 14 samples (1 token repeat) - 195 max words - at ../dataset/shuffle-word-195-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8753/12318 [15:08:46<6:10:08, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8753/12318 [15:08:46<6:10:08, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 3 samples (1 token repeat) - 825 max words - at ../dataset/shuffle-word-825-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8754/12318 [15:08:51<6:10:01, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8754/12318 [15:08:51<6:10:01, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 3 samples (1 token repeat) - 980 max words - at ../dataset/shuffle-word-980-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8755/12318 [15:08:54<6:09:53, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8755/12318 [15:08:54<6:09:53, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 7 samples (1 token repeat) - 335 max words - at ../dataset/shuffle-word-335-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8756/12318 [15:08:55<6:09:45, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8756/12318 [15:08:55<6:09:45, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 830 max words, 50 samples - at ../dataset/gen-word-830-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8757/12318 [15:08:57<6:09:37, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8757/12318 [15:08:57<6:09:37, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 3 samples (1 token repeat) - 810 max words - at ../dataset/shuffle-word-810-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8758/12318 [15:08:58<6:09:29, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8758/12318 [15:08:58<6:09:29, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 3 samples (1 token repeat) - 820 max words - at ../dataset/shuffle-word-820-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8759/12318 [15:08:59<6:09:20, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8759/12318 [15:08:59<6:09:20, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 3 samples (1 token repeat) - 990 max words - at ../dataset/shuffle-word-990-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8760/12318 [15:09:03<6:09:13, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8760/12318 [15:09:03<6:09:13, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 725 max words, 50 samples - at ../dataset/gen-word-725-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8761/12318 [15:09:08<6:09:06, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8761/12318 [15:09:08<6:09:06, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 3 samples (1 token repeat) - 975 max words - at ../dataset/shuffle-word-975-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8762/12318 [15:09:15<6:09:01, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8762/12318 [15:09:15<6:09:01, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 7 samples (1 token repeat) - 315 max words - at ../dataset/shuffle-word-315-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8763/12318 [15:09:18<6:08:53, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8763/12318 [15:09:18<6:08:53, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 4 samples (1 token repeat) - 680 max words - at ../dataset/shuffle-word-680-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8764/12318 [15:09:23<6:08:46, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8764/12318 [15:09:23<6:08:46, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 20 samples (20 token repeat) - 5400 max words - at ../dataset/shuffle-word-5400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8765/12318 [15:09:32<6:08:41, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8765/12318 [15:09:32<6:08:41, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 525 max words, 50 samples - at ../dataset/gen-word-525-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8766/12318 [15:09:36<6:08:34, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8766/12318 [15:09:36<6:08:34, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 20 samples (20 token repeat) - 7300 max words - at ../dataset/shuffle-word-7300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8767/12318 [15:09:41<6:08:27, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 170 max words, 50 samples - at ../dataset/gen-word-170-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8767/12318 [15:09:41<6:08:27, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 250 max words, 50 samples - at ../dataset/gen-word-250-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8768/12318 [15:10:33<6:08:40, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8768/12318 [15:10:33<6:08:40, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 380 max words, 50 samples - at ../dataset/gen-word-380-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8769/12318 [15:10:36<6:08:32, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8769/12318 [15:10:36<6:08:32, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 4 samples (1 token repeat) - 740 max words - at ../dataset/shuffle-word-740-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8770/12318 [15:10:45<6:08:27, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8770/12318 [15:10:45<6:08:27, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 4 samples (1 token repeat) - 725 max words - at ../dataset/shuffle-word-725-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8771/12318 [15:10:50<6:08:20, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8771/12318 [15:10:50<6:08:20, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 715 max words, 50 samples - at ../dataset/gen-word-715-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8772/12318 [15:10:55<6:08:13, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8772/12318 [15:10:55<6:08:13, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 760 max words, 50 samples - at ../dataset/gen-word-760-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8773/12318 [15:10:56<6:08:05, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8773/12318 [15:10:56<6:08:05, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 5 samples (1 token repeat) - 510 max words - at ../dataset/shuffle-word-510-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8774/12318 [15:11:04<6:08:00, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8774/12318 [15:11:04<6:08:00, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 7 samples (1 token repeat) - 375 max words - at ../dataset/shuffle-word-375-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8775/12318 [15:11:11<6:07:54, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8775/12318 [15:11:11<6:07:54, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 3 samples (1 token repeat) - 860 max words - at ../dataset/shuffle-word-860-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8776/12318 [15:11:16<6:07:47, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8776/12318 [15:11:16<6:07:47, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 7 samples (1 token repeat) - 330 max words - at ../dataset/shuffle-word-330-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8777/12318 [15:11:19<6:07:40, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8777/12318 [15:11:19<6:07:40, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 4 samples (1 token repeat) - 755 max words - at ../dataset/shuffle-word-755-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8778/12318 [15:11:24<6:07:33, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8778/12318 [15:11:24<6:07:33, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 3 samples (1 token repeat) - 905 max words - at ../dataset/shuffle-word-905-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8779/12318 [15:11:32<6:07:27, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8779/12318 [15:11:32<6:07:27, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 915 max words, 50 samples - at ../dataset/gen-word-915-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8780/12318 [15:11:35<6:07:20, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8780/12318 [15:11:35<6:07:20, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 4 samples (1 token repeat) - 660 max words - at ../dataset/shuffle-word-660-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8781/12318 [15:11:39<6:07:12, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8781/12318 [15:11:39<6:07:12, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 20 samples (20 token repeat) - 4000 max words - at ../dataset/shuffle-word-4000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8782/12318 [15:11:40<6:07:04, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8782/12318 [15:11:40<6:07:04, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 315 max words, 50 samples - at ../dataset/gen-word-315-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8783/12318 [15:11:44<6:06:57, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8783/12318 [15:11:44<6:06:57, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 880 max words, 50 samples - at ../dataset/gen-word-880-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8784/12318 [15:11:47<6:06:50, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8784/12318 [15:11:47<6:06:50, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 195 max words, 50 samples - at ../dataset/gen-word-195-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8785/12318 [15:11:56<6:06:44, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8785/12318 [15:11:56<6:06:44, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 4 samples (1 token repeat) - 625 max words - at ../dataset/shuffle-word-625-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8786/12318 [15:12:02<6:06:38, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8786/12318 [15:12:02<6:06:38, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 40 samples (20 token repeat) - 2100 max words - at ../dataset/shuffle-word-2100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8787/12318 [15:12:07<6:06:32, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8787/12318 [15:12:07<6:06:32, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 325 max words, 50 samples - at ../dataset/gen-word-325-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8788/12318 [15:12:11<6:06:24, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8788/12318 [15:12:11<6:06:24, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 4 samples (1 token repeat) - 735 max words - at ../dataset/shuffle-word-735-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8789/12318 [15:12:19<6:06:19, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8789/12318 [15:12:19<6:06:19, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 795 max words, 50 samples - at ../dataset/gen-word-795-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8790/12318 [15:12:24<6:06:12, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8790/12318 [15:12:24<6:06:12, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 890 max words, 50 samples - at ../dataset/gen-word-890-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8791/12318 [15:12:33<6:06:07, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 4 samples (1 token repeat) - 685 max words - at ../dataset/shuffle-word-685-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8791/12318 [15:12:33<6:06:07, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 4 samples (1 token repeat) - 620 max words - at ../dataset/shuffle-word-620-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8792/12318 [15:12:36<6:05:59, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8792/12318 [15:12:36<6:05:59, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 4 samples (1 token repeat) - 785 max words - at ../dataset/shuffle-word-785-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8793/12318 [15:12:37<6:05:51, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8793/12318 [15:12:37<6:05:51, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 9 samples (1 token repeat) - 275 max words - at ../dataset/shuffle-word-275-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8794/12318 [15:12:41<6:05:44, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8794/12318 [15:12:41<6:05:44, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 4 samples (1 token repeat) - 655 max words - at ../dataset/shuffle-word-655-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8795/12318 [15:12:48<6:05:38, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8795/12318 [15:12:48<6:05:38, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 340 max words, 50 samples - at ../dataset/gen-word-340-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8796/12318 [15:12:51<6:05:31, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8796/12318 [15:12:51<6:05:31, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 3 samples (1 token repeat) - 920 max words - at ../dataset/shuffle-word-920-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8797/12318 [15:12:59<6:05:25, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8797/12318 [15:12:59<6:05:25, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 20 samples (20 token repeat) - 7100 max words - at ../dataset/shuffle-word-7100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8798/12318 [15:13:00<6:05:17, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8798/12318 [15:13:00<6:05:17, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 655 max words, 50 samples - at ../dataset/gen-word-655-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8799/12318 [15:13:06<6:05:10, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8799/12318 [15:13:06<6:05:10, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 4 samples (1 token repeat) - 720 max words - at ../dataset/shuffle-word-720-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8800/12318 [15:13:51<6:05:20, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8800/12318 [15:13:51<6:05:20, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 3 samples (1 token repeat) - 970 max words - at ../dataset/shuffle-word-970-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8801/12318 [15:14:18<6:05:22, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8801/12318 [15:14:18<6:05:22, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 845 max words, 50 samples - at ../dataset/gen-word-845-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8802/12318 [15:14:27<6:05:16, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8802/12318 [15:14:27<6:05:16, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 20 samples (20 token repeat) - 3000 max words - at ../dataset/shuffle-word-3000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8803/12318 [15:14:30<6:05:09, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8803/12318 [15:14:30<6:05:09, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 6 samples (1 token repeat) - 430 max words - at ../dataset/shuffle-word-430-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8804/12318 [15:14:32<6:05:01, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8804/12318 [15:14:32<6:05:01, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 14 samples (1 token repeat) - 175 max words - at ../dataset/shuffle-word-175-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8805/12318 [15:14:36<6:04:54, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8805/12318 [15:14:36<6:04:54, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 4 samples (1 token repeat) - 790 max words - at ../dataset/shuffle-word-790-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8806/12318 [15:14:42<6:04:48, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8806/12318 [15:14:42<6:04:48, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 90 max words, 50 samples - at ../dataset/gen-word-90-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 71%|▋| 8807/12318 [15:14:49<6:04:42, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 71%|▋| 8807/12318 [15:14:49<6:04:42, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 3 samples (1 token repeat) - 895 max words - at ../dataset/shuffle-word-895-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8808/12318 [15:14:56<6:04:36, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8808/12318 [15:14:56<6:04:36, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 37 samples (20 token repeat) - 2500 max words - at ../dataset/shuffle-word-2500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8809/12318 [15:15:00<6:04:29, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8809/12318 [15:15:00<6:04:29, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 3 samples (1 token repeat) - 865 max words - at ../dataset/shuffle-word-865-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8810/12318 [15:15:09<6:04:23, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8810/12318 [15:15:09<6:04:23, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 51 samples (20 token repeat) - 1300 max words - at ../dataset/shuffle-word-1300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8811/12318 [15:15:14<6:04:17, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8811/12318 [15:15:14<6:04:17, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 660 max words, 50 samples - at ../dataset/gen-word-660-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8812/12318 [15:15:20<6:04:11, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8812/12318 [15:15:20<6:04:11, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 220 max words, 50 samples - at ../dataset/gen-word-220-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8813/12318 [15:15:22<6:04:03, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8813/12318 [15:15:22<6:04:03, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 6 samples (1 token repeat) - 485 max words - at ../dataset/shuffle-word-485-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8814/12318 [15:15:24<6:03:55, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8814/12318 [15:15:24<6:03:55, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 695 max words, 50 samples - at ../dataset/gen-word-695-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8815/12318 [15:15:32<6:03:49, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8815/12318 [15:15:32<6:03:49, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 840 max words, 50 samples - at ../dataset/gen-word-840-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8816/12318 [15:15:39<6:03:43, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8816/12318 [15:15:39<6:03:43, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 745 max words, 50 samples - at ../dataset/gen-word-745-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8817/12318 [15:15:44<6:03:37, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8817/12318 [15:15:44<6:03:37, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 600 max words, 50 samples - at ../dataset/gen-word-600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8818/12318 [15:15:48<6:03:29, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8818/12318 [15:15:48<6:03:29, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 790 max words, 50 samples - at ../dataset/gen-word-790-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8819/12318 [15:15:51<6:03:22, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8819/12318 [15:15:51<6:03:22, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 540 max words, 50 samples - at ../dataset/gen-word-540-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8820/12318 [15:15:59<6:03:16, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8820/12318 [15:15:59<6:03:16, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 420 max words, 50 samples - at ../dataset/gen-word-420-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8821/12318 [15:16:07<6:03:11, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8821/12318 [15:16:07<6:03:11, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 825 max words, 50 samples - at ../dataset/gen-word-825-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8822/12318 [15:16:11<6:03:04, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8822/12318 [15:16:11<6:03:04, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 805 max words, 50 samples - at ../dataset/gen-word-805-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8823/12318 [15:16:17<6:02:58, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8823/12318 [15:16:17<6:02:58, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 765 max words, 50 samples - at ../dataset/gen-word-765-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8824/12318 [15:16:25<6:02:52, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8824/12318 [15:16:25<6:02:52, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 4 samples (1 token repeat) - 855 max words - at ../dataset/shuffle-word-855-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8825/12318 [15:16:28<6:02:44, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8825/12318 [15:16:28<6:02:44, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 965 max words, 50 samples - at ../dataset/gen-word-965-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8826/12318 [15:16:30<6:02:36, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8826/12318 [15:16:30<6:02:36, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 20 samples (20 token repeat) - 5900 max words - at ../dataset/shuffle-word-5900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8827/12318 [15:16:34<6:02:29, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8827/12318 [15:16:34<6:02:29, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 40 samples (20 token repeat) - 1700 max words - at ../dataset/shuffle-word-1700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8828/12318 [15:16:38<6:02:22, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8828/12318 [15:16:38<6:02:22, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 705 max words, 50 samples - at ../dataset/gen-word-705-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8829/12318 [15:16:43<6:02:15, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8829/12318 [15:16:43<6:02:15, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 20 samples (20 token repeat) - 7900 max words - at ../dataset/shuffle-word-7900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8830/12318 [15:16:46<6:02:08, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8830/12318 [15:16:46<6:02:08, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 40 samples (20 token repeat) - 2300 max words - at ../dataset/shuffle-word-2300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8831/12318 [15:16:53<6:02:02, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8831/12318 [15:16:53<6:02:02, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 385 max words, 50 samples - at ../dataset/gen-word-385-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8832/12318 [15:17:20<6:02:04, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8832/12318 [15:17:20<6:02:04, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 990 max words, 50 samples - at ../dataset/gen-word-990-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8833/12318 [15:17:28<6:01:59, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8833/12318 [15:17:28<6:01:59, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 515 max words, 50 samples - at ../dataset/gen-word-515-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8834/12318 [15:17:35<6:01:53, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8834/12318 [15:17:35<6:01:53, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 640 max words, 50 samples - at ../dataset/gen-word-640-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8835/12318 [15:17:40<6:01:46, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8835/12318 [15:17:40<6:01:46, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 730 max words, 50 samples - at ../dataset/gen-word-730-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8836/12318 [15:17:45<6:01:39, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8836/12318 [15:17:45<6:01:39, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 930 max words, 50 samples - at ../dataset/gen-word-930-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8837/12318 [15:17:50<6:01:33, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 20 samples (20 token repeat) - 4600 max words - at ../dataset/shuffle-word-4600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8837/12318 [15:17:50<6:01:33, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 590 max words, 50 samples - at ../dataset/gen-word-590-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8838/12318 [15:17:56<6:01:26, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8838/12318 [15:17:56<6:01:26, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 595 max words, 50 samples - at ../dataset/gen-word-595-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8839/12318 [15:18:05<6:01:21, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8839/12318 [15:18:05<6:01:21, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 20 samples (20 token repeat) - 3300 max words - at ../dataset/shuffle-word-3300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8840/12318 [15:18:11<6:01:15, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8840/12318 [15:18:11<6:01:15, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 820 max words, 50 samples - at ../dataset/gen-word-820-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8841/12318 [15:18:18<6:01:09, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8841/12318 [15:18:18<6:01:09, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 320 max words, 50 samples - at ../dataset/gen-word-320-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8842/12318 [15:18:24<6:01:02, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8842/12318 [15:18:24<6:01:02, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 20 samples (20 token repeat) - 5600 max words - at ../dataset/shuffle-word-5600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8843/12318 [15:18:33<6:00:57, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8843/12318 [15:18:33<6:00:57, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 4 samples (1 token repeat) - 750 max words - at ../dataset/shuffle-word-750-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8844/12318 [15:18:40<6:00:51, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8844/12318 [15:18:40<6:00:51, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 20 samples (20 token repeat) - 5300 max words - at ../dataset/shuffle-word-5300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8845/12318 [15:18:43<6:00:44, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8845/12318 [15:18:43<6:00:44, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 9 samples (1 token repeat) - 300 max words - at ../dataset/shuffle-word-300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8846/12318 [15:18:51<6:00:38, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8846/12318 [15:18:51<6:00:38, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 7 samples (1 token repeat) - 325 max words - at ../dataset/shuffle-word-325-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8847/12318 [15:18:56<6:00:32, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 670 max words, 50 samples - at ../dataset/gen-word-670-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8847/12318 [15:18:56<6:00:32, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 4 samples (1 token repeat) - 730 max words - at ../dataset/shuffle-word-730-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8848/12318 [15:19:02<6:00:25, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8848/12318 [15:19:02<6:00:25, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 20 samples (20 token repeat) - 4100 max words - at ../dataset/shuffle-word-4100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8849/12318 [15:19:08<6:00:19, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8849/12318 [15:19:08<6:00:19, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 11 samples (1 token repeat) - 205 max words - at ../dataset/shuffle-word-205-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8850/12318 [15:19:15<6:00:13, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8850/12318 [15:19:15<6:00:13, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 980 max words, 50 samples - at ../dataset/gen-word-980-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8851/12318 [15:19:18<6:00:06, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8851/12318 [15:19:18<6:00:06, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 935 max words, 50 samples - at ../dataset/gen-word-935-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8852/12318 [15:19:21<5:59:58, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8852/12318 [15:19:21<5:59:58, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 1000 max words, 50 samples - at ../dataset/gen-word-1000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8853/12318 [15:19:24<5:59:50, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8853/12318 [15:19:24<5:59:50, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 40 samples (20 token repeat) - 1900 max words - at ../dataset/shuffle-word-1900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8854/12318 [15:19:33<5:59:45, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8854/12318 [15:19:33<5:59:45, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 895 max words, 50 samples - at ../dataset/gen-word-895-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8855/12318 [15:19:38<5:59:38, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8855/12318 [15:19:38<5:59:38, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 3 samples (1 token repeat) - 870 max words - at ../dataset/shuffle-word-870-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8856/12318 [15:19:45<5:59:33, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8856/12318 [15:19:45<5:59:33, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 750 max words, 50 samples - at ../dataset/gen-word-750-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8857/12318 [15:19:48<5:59:25, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8857/12318 [15:19:48<5:59:25, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 9 samples (1 token repeat) - 245 max words - at ../dataset/shuffle-word-245-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8858/12318 [15:19:55<5:59:19, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8858/12318 [15:19:55<5:59:19, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 9 samples (1 token repeat) - 270 max words - at ../dataset/shuffle-word-270-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8859/12318 [15:20:03<5:59:14, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8859/12318 [15:20:03<5:59:14, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 7 samples (1 token repeat) - 380 max words - at ../dataset/shuffle-word-380-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8860/12318 [15:20:12<5:59:09, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8860/12318 [15:20:12<5:59:09, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 6 samples (1 token repeat) - 405 max words - at ../dataset/shuffle-word-405-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8861/12318 [15:20:17<5:59:02, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8861/12318 [15:20:17<5:59:02, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 6 samples (1 token repeat) - 420 max words - at ../dataset/shuffle-word-420-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8862/12318 [15:20:22<5:58:55, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8862/12318 [15:20:22<5:58:55, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 300 max words, 50 samples - at ../dataset/gen-word-300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8863/12318 [15:20:25<5:58:48, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 910 max words, 50 samples - at ../dataset/gen-word-910-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8863/12318 [15:20:25<5:58:48, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 735 max words, 50 samples - at ../dataset/gen-word-735-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8864/12318 [15:20:47<5:58:48, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8864/12318 [15:20:47<5:58:48, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 40 samples (20 token repeat) - 2000 max words - at ../dataset/shuffle-word-2000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8865/12318 [15:20:51<5:58:41, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8865/12318 [15:20:51<5:58:41, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 39 samples (20 token repeat) - 2400 max words - at ../dataset/shuffle-word-2400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8866/12318 [15:20:54<5:58:33, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8866/12318 [15:20:54<5:58:33, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 20 samples (20 token repeat) - 8000 max words - at ../dataset/shuffle-word-8000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8867/12318 [15:21:03<5:58:28, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8867/12318 [15:21:03<5:58:28, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 4 samples (1 token repeat) - 645 max words - at ../dataset/shuffle-word-645-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8868/12318 [15:21:09<5:58:22, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8868/12318 [15:21:09<5:58:22, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 630 max words, 50 samples - at ../dataset/gen-word-630-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8869/12318 [15:21:13<5:58:14, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8869/12318 [15:21:13<5:58:14, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 20 samples (20 token repeat) - 7400 max words - at ../dataset/shuffle-word-7400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8870/12318 [15:21:20<5:58:09, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8870/12318 [15:21:20<5:58:09, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 305 max words, 50 samples - at ../dataset/gen-word-305-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8871/12318 [15:21:25<5:58:02, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8871/12318 [15:21:25<5:58:02, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 6 samples (1 token repeat) - 455 max words - at ../dataset/shuffle-word-455-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8872/12318 [15:21:32<5:57:56, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8872/12318 [15:21:32<5:57:56, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 860 max words, 50 samples - at ../dataset/gen-word-860-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8873/12318 [15:21:37<5:57:49, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8873/12318 [15:21:37<5:57:49, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 20 samples (20 token repeat) - 7700 max words - at ../dataset/shuffle-word-7700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8874/12318 [15:21:42<5:57:42, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8874/12318 [15:21:42<5:57:42, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 185 max words, 50 samples - at ../dataset/gen-word-185-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8875/12318 [15:21:45<5:57:35, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8875/12318 [15:21:45<5:57:35, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 260 max words, 50 samples - at ../dataset/gen-word-260-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8876/12318 [15:21:53<5:57:29, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8876/12318 [15:21:53<5:57:29, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 920 max words, 50 samples - at ../dataset/gen-word-920-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8877/12318 [15:21:59<5:57:23, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8877/12318 [15:21:59<5:57:23, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 665 max words, 50 samples - at ../dataset/gen-word-665-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8878/12318 [15:22:01<5:57:15, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8878/12318 [15:22:01<5:57:15, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 565 max words, 50 samples - at ../dataset/gen-word-565-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8879/12318 [15:22:07<5:57:09, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8879/12318 [15:22:07<5:57:09, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 215 max words, 50 samples - at ../dataset/gen-word-215-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8880/12318 [15:22:16<5:57:04, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8880/12318 [15:22:16<5:57:04, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 5 samples (1 token repeat) - 540 max words - at ../dataset/shuffle-word-540-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8881/12318 [15:22:19<5:56:56, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8881/12318 [15:22:19<5:56:56, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 800 max words, 50 samples - at ../dataset/gen-word-800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8882/12318 [15:22:27<5:56:51, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 190 max words, 50 samples - at ../dataset/gen-word-190-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8882/12318 [15:22:27<5:56:51, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 5 samples (1 token repeat) - 560 max words - at ../dataset/shuffle-word-560-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8883/12318 [15:22:35<5:56:45, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8883/12318 [15:22:35<5:56:45, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 20 samples (20 token repeat) - 4700 max words - at ../dataset/shuffle-word-4700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8884/12318 [15:22:40<5:56:39, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8884/12318 [15:22:41<5:56:39, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 495 max words, 50 samples - at ../dataset/gen-word-495-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8885/12318 [15:22:46<5:56:32, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8885/12318 [15:22:46<5:56:32, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 360 max words, 50 samples - at ../dataset/gen-word-360-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8886/12318 [15:22:55<5:56:27, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8886/12318 [15:22:55<5:56:27, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 950 max words, 50 samples - at ../dataset/gen-word-950-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8887/12318 [15:23:02<5:56:21, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8887/12318 [15:23:02<5:56:21, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 4 samples (1 token repeat) - 615 max words - at ../dataset/shuffle-word-615-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8888/12318 [15:23:04<5:56:13, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8888/12318 [15:23:04<5:56:13, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 20 samples (20 token repeat) - 6300 max words - at ../dataset/shuffle-word-6300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8889/12318 [15:23:10<5:56:07, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8889/12318 [15:23:10<5:56:07, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 3 samples (1 token repeat) - 845 max words - at ../dataset/shuffle-word-845-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8890/12318 [15:23:19<5:56:02, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8890/12318 [15:23:19<5:56:02, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 505 max words, 50 samples - at ../dataset/gen-word-505-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8891/12318 [15:23:21<5:55:54, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8891/12318 [15:23:21<5:55:54, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 20 samples (20 token repeat) - 3900 max words - at ../dataset/shuffle-word-3900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8892/12318 [15:23:25<5:55:47, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8892/12318 [15:23:25<5:55:47, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 4 samples (1 token repeat) - 670 max words - at ../dataset/shuffle-word-670-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8893/12318 [15:23:27<5:55:39, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8893/12318 [15:23:27<5:55:39, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 20 samples (20 token repeat) - 6400 max words - at ../dataset/shuffle-word-6400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8894/12318 [15:23:35<5:55:33, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8894/12318 [15:23:35<5:55:33, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 815 max words, 50 samples - at ../dataset/gen-word-815-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8895/12318 [15:23:37<5:55:26, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8895/12318 [15:23:37<5:55:26, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 6 samples (1 token repeat) - 440 max words - at ../dataset/shuffle-word-440-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8896/12318 [15:24:07<5:55:28, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 40 samples (20 token repeat) - 1500 max words - at ../dataset/shuffle-word-1500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8896/12318 [15:24:07<5:55:28, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 3 samples (1 token repeat) - 925 max words - at ../dataset/shuffle-word-925-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8897/12318 [15:24:15<5:55:23, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8897/12318 [15:24:15<5:55:23, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 6 samples (1 token repeat) - 465 max words - at ../dataset/shuffle-word-465-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8898/12318 [15:24:17<5:55:15, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8898/12318 [15:24:17<5:55:15, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 690 max words, 50 samples - at ../dataset/gen-word-690-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8899/12318 [15:24:21<5:55:08, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8899/12318 [15:24:21<5:55:08, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 395 max words, 50 samples - at ../dataset/gen-word-395-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8900/12318 [15:24:29<5:55:02, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8900/12318 [15:24:29<5:55:02, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 265 max words, 50 samples - at ../dataset/gen-word-265-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8901/12318 [15:24:33<5:54:55, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8901/12318 [15:24:33<5:54:55, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 955 max words, 50 samples - at ../dataset/gen-word-955-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8902/12318 [15:24:38<5:54:48, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8902/12318 [15:24:38<5:54:48, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 885 max words, 50 samples - at ../dataset/gen-word-885-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8903/12318 [15:24:42<5:54:41, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8903/12318 [15:24:42<5:54:41, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 14 samples (1 token repeat) - 185 max words - at ../dataset/shuffle-word-185-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8904/12318 [15:24:45<5:54:34, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8904/12318 [15:24:45<5:54:34, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 240 max words, 50 samples - at ../dataset/gen-word-240-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8905/12318 [15:24:49<5:54:27, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8905/12318 [15:24:49<5:54:27, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 20 samples (20 token repeat) - 6600 max words - at ../dataset/shuffle-word-6600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8906/12318 [15:24:53<5:54:20, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8906/12318 [15:24:53<5:54:20, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 440 max words, 50 samples - at ../dataset/gen-word-440-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8907/12318 [15:25:01<5:54:14, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8907/12318 [15:25:01<5:54:14, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 135 max words, 50 samples - at ../dataset/gen-word-135-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8908/12318 [15:25:05<5:54:07, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8908/12318 [15:25:05<5:54:07, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 555 max words, 50 samples - at ../dataset/gen-word-555-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8909/12318 [15:25:12<5:54:01, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8909/12318 [15:25:12<5:54:01, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 605 max words, 50 samples - at ../dataset/gen-word-605-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8910/12318 [15:25:17<5:53:55, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8910/12318 [15:25:17<5:53:55, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 465 max words, 50 samples - at ../dataset/gen-word-465-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8911/12318 [15:25:26<5:53:49, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8911/12318 [15:25:26<5:53:49, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 295 max words, 50 samples - at ../dataset/gen-word-295-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8912/12318 [15:25:35<5:53:44, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8912/12318 [15:25:35<5:53:44, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 7 samples (1 token repeat) - 390 max words - at ../dataset/shuffle-word-390-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8913/12318 [15:25:38<5:53:37, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8913/12318 [15:25:38<5:53:37, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 900 max words, 50 samples - at ../dataset/gen-word-900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8914/12318 [15:25:43<5:53:30, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8914/12318 [15:25:43<5:53:30, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 975 max words, 50 samples - at ../dataset/gen-word-975-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8915/12318 [15:25:46<5:53:22, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8915/12318 [15:25:46<5:53:22, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 945 max words, 50 samples - at ../dataset/gen-word-945-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8916/12318 [15:25:51<5:53:16, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8916/12318 [15:25:51<5:53:16, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 6 samples (1 token repeat) - 480 max words - at ../dataset/shuffle-word-480-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8917/12318 [15:26:00<5:53:10, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8917/12318 [15:26:00<5:53:10, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 20 samples (20 token repeat) - 4900 max words - at ../dataset/shuffle-word-4900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8918/12318 [15:26:02<5:53:03, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8918/12318 [15:26:02<5:53:03, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 20 samples (20 token repeat) - 5800 max words - at ../dataset/shuffle-word-5800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8919/12318 [15:26:07<5:52:56, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8919/12318 [15:26:07<5:52:56, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 970 max words, 50 samples - at ../dataset/gen-word-970-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8920/12318 [15:26:14<5:52:50, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8920/12318 [15:26:14<5:52:50, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 4 samples (1 token repeat) - 605 max words - at ../dataset/shuffle-word-605-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8921/12318 [15:26:17<5:52:43, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8921/12318 [15:26:17<5:52:43, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 650 max words, 50 samples - at ../dataset/gen-word-650-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8922/12318 [15:26:21<5:52:35, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8922/12318 [15:26:21<5:52:35, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 3 samples (1 token repeat) - 985 max words - at ../dataset/shuffle-word-985-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8923/12318 [15:26:26<5:52:29, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8923/12318 [15:26:26<5:52:29, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 20 samples (20 token repeat) - 3800 max words - at ../dataset/shuffle-word-3800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8924/12318 [15:26:30<5:52:22, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8924/12318 [15:26:30<5:52:22, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 9 samples (1 token repeat) - 235 max words - at ../dataset/shuffle-word-235-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8925/12318 [15:26:39<5:52:17, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8925/12318 [15:26:39<5:52:17, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 20 samples (20 token repeat) - 7000 max words - at ../dataset/shuffle-word-7000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8926/12318 [15:26:43<5:52:09, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8926/12318 [15:26:43<5:52:09, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 5 samples (1 token repeat) - 570 max words - at ../dataset/shuffle-word-570-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8927/12318 [15:26:48<5:52:03, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8927/12318 [15:26:48<5:52:03, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 9 samples (1 token repeat) - 260 max words - at ../dataset/shuffle-word-260-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8928/12318 [15:27:16<5:52:05, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8928/12318 [15:27:16<5:52:05, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 280 max words, 50 samples - at ../dataset/gen-word-280-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8929/12318 [15:27:18<5:51:57, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8929/12318 [15:27:18<5:51:57, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 530 max words, 50 samples - at ../dataset/gen-word-530-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 72%|▋| 8930/12318 [15:27:22<5:51:50, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 72%|▋| 8930/12318 [15:27:22<5:51:50, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 20 samples (20 token repeat) - 2900 max words - at ../dataset/shuffle-word-2900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8931/12318 [15:27:29<5:51:44, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8931/12318 [15:27:29<5:51:44, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 4 samples (1 token repeat) - 775 max words - at ../dataset/shuffle-word-775-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8932/12318 [15:27:36<5:51:38, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8932/12318 [15:27:36<5:51:38, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 610 max words, 50 samples - at ../dataset/gen-word-610-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8933/12318 [15:27:45<5:51:33, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8933/12318 [15:27:45<5:51:33, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 675 max words, 50 samples - at ../dataset/gen-word-675-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8934/12318 [15:27:53<5:51:27, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8934/12318 [15:27:53<5:51:27, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 350 max words, 50 samples - at ../dataset/gen-word-350-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8935/12318 [15:27:54<5:51:19, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8935/12318 [15:27:54<5:51:19, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 710 max words, 50 samples - at ../dataset/gen-word-710-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8936/12318 [15:28:03<5:51:14, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8936/12318 [15:28:03<5:51:14, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 15 samples (1 token repeat) - 150 max words - at ../dataset/shuffle-word-150-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8937/12318 [15:28:08<5:51:07, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8937/12318 [15:28:08<5:51:07, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 475 max words, 50 samples - at ../dataset/gen-word-475-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8938/12318 [15:28:11<5:51:00, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8938/12318 [15:28:11<5:51:00, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 575 max words, 50 samples - at ../dataset/gen-word-575-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8939/12318 [15:28:19<5:50:54, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8939/12318 [15:28:19<5:50:54, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 30 samples (1 token repeat) - 90 max words - at ../dataset/shuffle-word-90-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8940/12318 [15:28:23<5:50:47, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8940/12318 [15:28:23<5:50:47, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 5 samples (1 token repeat) - 575 max words - at ../dataset/shuffle-word-575-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8941/12318 [15:28:28<5:50:40, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8941/12318 [15:28:28<5:50:40, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 3 samples (1 token repeat) - 805 max words - at ../dataset/shuffle-word-805-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8942/12318 [15:28:31<5:50:33, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8942/12318 [15:28:31<5:50:33, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 7 samples (1 token repeat) - 320 max words - at ../dataset/shuffle-word-320-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8943/12318 [15:28:37<5:50:27, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8943/12318 [15:28:37<5:50:27, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 5 samples (1 token repeat) - 665 max words - at ../dataset/shuffle-word-665-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8944/12318 [15:28:45<5:50:21, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8944/12318 [15:28:45<5:50:21, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 960 max words, 50 samples - at ../dataset/gen-word-960-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8945/12318 [15:28:48<5:50:14, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8945/12318 [15:28:48<5:50:14, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 490 max words, 50 samples - at ../dataset/gen-word-490-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8946/12318 [15:28:52<5:50:07, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8946/12318 [15:28:52<5:50:07, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 810 max words, 50 samples - at ../dataset/gen-word-810-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8947/12318 [15:28:56<5:49:59, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8947/12318 [15:28:56<5:49:59, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 4 samples (1 token repeat) - 695 max words - at ../dataset/shuffle-word-695-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8948/12318 [15:29:03<5:49:54, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8948/12318 [15:29:03<5:49:54, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 3 samples (1 token repeat) - 995 max words - at ../dataset/shuffle-word-995-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8949/12318 [15:29:11<5:49:48, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8949/12318 [15:29:11<5:49:48, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 770 max words, 50 samples - at ../dataset/gen-word-770-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8950/12318 [15:29:18<5:49:42, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8950/12318 [15:29:18<5:49:42, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 3 samples (1 token repeat) - 875 max words - at ../dataset/shuffle-word-875-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8951/12318 [15:29:22<5:49:35, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8951/12318 [15:29:22<5:49:35, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 7 samples (1 token repeat) - 395 max words - at ../dataset/shuffle-word-395-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8952/12318 [15:29:31<5:49:30, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8952/12318 [15:29:31<5:49:30, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 41 samples (20 token repeat) - 1400 max words - at ../dataset/shuffle-word-1400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8953/12318 [15:29:39<5:49:24, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8953/12318 [15:29:39<5:49:24, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 460 max words, 50 samples - at ../dataset/gen-word-460-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8954/12318 [15:29:48<5:49:19, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8954/12318 [15:29:48<5:49:19, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 20 samples (20 token repeat) - 7600 max words - at ../dataset/shuffle-word-7600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8955/12318 [15:29:56<5:49:13, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8955/12318 [15:29:56<5:49:13, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 20 samples (20 token repeat) - 7200 max words - at ../dataset/shuffle-word-7200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8956/12318 [15:30:01<5:49:07, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8956/12318 [15:30:01<5:49:07, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 20 samples (20 token repeat) - 4800 max words - at ../dataset/shuffle-word-4800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8957/12318 [15:30:02<5:48:59, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8957/12318 [15:30:02<5:48:59, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 20 samples (20 token repeat) - 3600 max words - at ../dataset/shuffle-word-3600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8958/12318 [15:30:10<5:48:53, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8958/12318 [15:30:10<5:48:53, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 535 max words, 50 samples - at ../dataset/gen-word-535-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8959/12318 [15:30:13<5:48:46, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8959/12318 [15:30:13<5:48:46, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 570 max words, 50 samples - at ../dataset/gen-word-570-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8960/12318 [15:30:35<5:48:45, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8960/12318 [15:30:35<5:48:45, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 4 samples (1 token repeat) - 700 max words - at ../dataset/shuffle-word-700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8961/12318 [15:30:41<5:48:39, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8961/12318 [15:30:41<5:48:39, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 985 max words, 50 samples - at ../dataset/gen-word-985-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8962/12318 [15:30:50<5:48:34, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8962/12318 [15:30:50<5:48:34, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 510 max words, 50 samples - at ../dataset/gen-word-510-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8963/12318 [15:30:55<5:48:27, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8963/12318 [15:30:55<5:48:27, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 16 samples (1 token repeat) - 145 max words - at ../dataset/shuffle-word-145-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8964/12318 [15:30:57<5:48:19, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8964/12318 [15:30:57<5:48:19, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 7 samples (1 token repeat) - 340 max words - at ../dataset/shuffle-word-340-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8965/12318 [15:31:01<5:48:12, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8965/12318 [15:31:01<5:48:12, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 5 samples (1 token repeat) - 515 max words - at ../dataset/shuffle-word-515-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8966/12318 [15:31:04<5:48:05, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8966/12318 [15:31:04<5:48:05, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 6 samples (1 token repeat) - 435 max words - at ../dataset/shuffle-word-435-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8967/12318 [15:31:12<5:47:59, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8967/12318 [15:31:12<5:47:59, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 4 samples (1 token repeat) - 640 max words - at ../dataset/shuffle-word-640-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8968/12318 [15:31:18<5:47:53, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8968/12318 [15:31:18<5:47:53, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 775 max words, 50 samples - at ../dataset/gen-word-775-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8969/12318 [15:31:22<5:47:46, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8969/12318 [15:31:22<5:47:46, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 5 samples (1 token repeat) - 565 max words - at ../dataset/shuffle-word-565-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8970/12318 [15:31:30<5:47:40, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8970/12318 [15:31:30<5:47:40, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 6 samples (1 token repeat) - 415 max words - at ../dataset/shuffle-word-415-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8971/12318 [15:31:37<5:47:34, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8971/12318 [15:31:37<5:47:34, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 835 max words, 50 samples - at ../dataset/gen-word-835-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8972/12318 [15:31:39<5:47:27, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8972/12318 [15:31:39<5:47:27, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 20 samples (20 token repeat) - 6700 max words - at ../dataset/shuffle-word-6700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8973/12318 [15:31:47<5:47:21, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8973/12318 [15:31:47<5:47:21, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 335 max words, 50 samples - at ../dataset/gen-word-335-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8974/12318 [15:31:52<5:47:14, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8974/12318 [15:31:52<5:47:14, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 620 max words, 50 samples - at ../dataset/gen-word-620-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8975/12318 [15:31:55<5:47:07, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8975/12318 [15:31:55<5:47:07, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 870 max words, 50 samples - at ../dataset/gen-word-870-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8976/12318 [15:32:01<5:47:01, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8976/12318 [15:32:01<5:47:01, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 3 samples (1 token repeat) - 890 max words - at ../dataset/shuffle-word-890-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8977/12318 [15:32:09<5:46:55, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8977/12318 [15:32:09<5:46:55, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 5 samples (1 token repeat) - 460 max words - at ../dataset/shuffle-word-460-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8978/12318 [15:32:14<5:46:48, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8978/12318 [15:32:14<5:46:48, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 4 samples (1 token repeat) - 765 max words - at ../dataset/shuffle-word-765-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8979/12318 [15:32:16<5:46:41, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8979/12318 [15:32:16<5:46:41, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 4 samples (1 token repeat) - 635 max words - at ../dataset/shuffle-word-635-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8980/12318 [15:32:22<5:46:34, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8980/12318 [15:32:22<5:46:34, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 500 max words, 50 samples - at ../dataset/gen-word-500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8981/12318 [15:32:27<5:46:28, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8981/12318 [15:32:27<5:46:28, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 9 samples (1 token repeat) - 290 max words - at ../dataset/shuffle-word-290-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8982/12318 [15:32:32<5:46:21, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8982/12318 [15:32:32<5:46:21, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 720 max words, 50 samples - at ../dataset/gen-word-720-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8983/12318 [15:32:37<5:46:14, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8983/12318 [15:32:37<5:46:14, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 4 samples (1 token repeat) - 850 max words - at ../dataset/shuffle-word-850-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8984/12318 [15:32:44<5:46:08, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8984/12318 [15:32:44<5:46:08, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 3 samples (1 token repeat) - 1000 max words - at ../dataset/shuffle-word-1000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8985/12318 [15:32:53<5:46:03, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8985/12318 [15:32:53<5:46:03, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 20 samples (20 token repeat) - 3700 max words - at ../dataset/shuffle-word-3700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8986/12318 [15:33:00<5:45:57, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8986/12318 [15:33:00<5:45:57, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 160 max words, 50 samples - at ../dataset/gen-word-160-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8987/12318 [15:33:04<5:45:50, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8987/12318 [15:33:04<5:45:50, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 5 samples (1 token repeat) - 505 max words - at ../dataset/shuffle-word-505-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8988/12318 [15:33:05<5:45:42, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8988/12318 [15:33:05<5:45:42, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 30 samples (20 token repeat) - 2600 max words - at ../dataset/shuffle-word-2600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8989/12318 [15:33:10<5:45:35, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8989/12318 [15:33:10<5:45:35, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 3 samples (1 token repeat) - 910 max words - at ../dataset/shuffle-word-910-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8990/12318 [15:33:15<5:45:28, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8990/12318 [15:33:15<5:45:28, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 22 samples (20 token repeat) - 2700 max words - at ../dataset/shuffle-word-2700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8991/12318 [15:33:23<5:45:23, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8991/12318 [15:33:23<5:45:23, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 700 max words, 50 samples - at ../dataset/gen-word-700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8992/12318 [15:34:01<5:45:28, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8992/12318 [15:34:01<5:45:28, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 20 samples (20 token repeat) - 5200 max words - at ../dataset/shuffle-word-5200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8993/12318 [15:34:02<5:45:20, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8993/12318 [15:34:02<5:45:20, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 4 samples (1 token repeat) - 710 max words - at ../dataset/shuffle-word-710-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8994/12318 [15:34:08<5:45:14, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8994/12318 [15:34:08<5:45:14, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 3 samples (1 token repeat) - 935 max words - at ../dataset/shuffle-word-935-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8995/12318 [15:34:14<5:45:08, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8995/12318 [15:34:14<5:45:08, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 3 samples (1 token repeat) - 885 max words - at ../dataset/shuffle-word-885-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8996/12318 [15:34:16<5:45:00, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8996/12318 [15:34:16<5:45:00, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 20 samples (20 token repeat) - 3200 max words - at ../dataset/shuffle-word-3200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8997/12318 [15:34:25<5:44:54, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8997/12318 [15:34:25<5:44:54, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 40 samples (20 token repeat) - 1800 max words - at ../dataset/shuffle-word-1800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8998/12318 [15:34:30<5:44:48, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8998/12318 [15:34:30<5:44:48, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 785 max words, 50 samples - at ../dataset/gen-word-785-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 8999/12318 [15:34:39<5:44:43, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 8999/12318 [15:34:39<5:44:43, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 6 samples (1 token repeat) - 475 max words - at ../dataset/shuffle-word-475-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 9000/12318 [15:34:46<5:44:37, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 9000/12318 [15:34:46<5:44:37, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 40 samples (20 token repeat) - 2200 max words - at ../dataset/shuffle-word-2200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 9001/12318 [15:34:51<5:44:30, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 9001/12318 [15:34:51<5:44:30, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 20 samples (20 token repeat) - 6000 max words - at ../dataset/shuffle-word-6000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 9002/12318 [15:34:56<5:44:23, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 9002/12318 [15:34:56<5:44:23, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 645 max words, 50 samples - at ../dataset/gen-word-645-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 9003/12318 [15:35:00<5:44:16, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 9003/12318 [15:35:00<5:44:16, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 205 max words, 50 samples - at ../dataset/gen-word-205-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 9004/12318 [15:35:05<5:44:10, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 9004/12318 [15:35:05<5:44:10, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 4 samples (1 token repeat) - 650 max words - at ../dataset/shuffle-word-650-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 9005/12318 [15:35:09<5:44:03, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 9005/12318 [15:35:09<5:44:03, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 5 samples (1 token repeat) - 555 max words - at ../dataset/shuffle-word-555-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 9006/12318 [15:35:14<5:43:56, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 875 max words, 50 samples - at ../dataset/gen-word-875-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 9006/12318 [15:35:14<5:43:56, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 3 samples (1 token repeat) - 900 max words - at ../dataset/shuffle-word-900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 9007/12318 [15:35:18<5:43:49, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 9007/12318 [15:35:18<5:43:49, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 20 samples (20 token repeat) - 4400 max words - at ../dataset/shuffle-word-4400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 9008/12318 [15:35:24<5:43:43, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 9008/12318 [15:35:24<5:43:43, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 3 samples (1 token repeat) - 965 max words - at ../dataset/shuffle-word-965-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 9009/12318 [15:35:29<5:43:36, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 9009/12318 [15:35:29<5:43:36, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 3 samples (1 token repeat) - 950 max words - at ../dataset/shuffle-word-950-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 9010/12318 [15:35:33<5:43:29, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 9010/12318 [15:35:33<5:43:29, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 20 samples (20 token repeat) - 3500 max words - at ../dataset/shuffle-word-3500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 9011/12318 [15:35:41<5:43:23, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 9011/12318 [15:35:41<5:43:23, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 615 max words, 50 samples - at ../dataset/gen-word-615-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 9012/12318 [15:35:49<5:43:17, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 9012/12318 [15:35:49<5:43:17, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 20 samples (20 token repeat) - 5500 max words - at ../dataset/shuffle-word-5500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 9013/12318 [15:35:51<5:43:10, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 9013/12318 [15:35:51<5:43:10, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 4 samples (1 token repeat) - 675 max words - at ../dataset/shuffle-word-675-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 9014/12318 [15:35:52<5:43:02, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 9014/12318 [15:35:52<5:43:02, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 6 samples (1 token repeat) - 410 max words - at ../dataset/shuffle-word-410-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 9015/12318 [15:35:54<5:42:54, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 9015/12318 [15:35:54<5:42:54, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 7 samples (1 token repeat) - 370 max words - at ../dataset/shuffle-word-370-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 9016/12318 [15:35:57<5:42:47, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 9016/12318 [15:35:57<5:42:47, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 7 samples (1 token repeat) - 385 max words - at ../dataset/shuffle-word-385-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 9017/12318 [15:36:03<5:42:40, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 9017/12318 [15:36:03<5:42:40, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 855 max words, 50 samples - at ../dataset/gen-word-855-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 9018/12318 [15:36:06<5:42:33, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 9018/12318 [15:36:06<5:42:33, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 20 samples (20 token repeat) - 7500 max words - at ../dataset/shuffle-word-7500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 9019/12318 [15:36:11<5:42:26, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 9019/12318 [15:36:11<5:42:26, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 20 samples (20 token repeat) - 3400 max words - at ../dataset/shuffle-word-3400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 9020/12318 [15:36:14<5:42:19, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 9020/12318 [15:36:14<5:42:19, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 40 samples (20 token repeat) - 1600 max words - at ../dataset/shuffle-word-1600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 9021/12318 [15:36:16<5:42:11, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 9021/12318 [15:36:16<5:42:11, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 3 samples (1 token repeat) - 880 max words - at ../dataset/shuffle-word-880-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 9022/12318 [15:36:20<5:42:04, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 9022/12318 [15:36:20<5:42:04, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 20 samples (20 token repeat) - 6800 max words - at ../dataset/shuffle-word-6800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 9023/12318 [15:36:24<5:41:57, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 9023/12318 [15:36:24<5:41:57, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 3 samples (1 token repeat) - 930 max words - at ../dataset/shuffle-word-930-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 9024/12318 [15:37:23<5:42:10, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 9024/12318 [15:37:23<5:42:10, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 20 samples (20 token repeat) - 6200 max words - at ../dataset/shuffle-word-6200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 9025/12318 [15:37:31<5:42:04, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 9025/12318 [15:37:31<5:42:04, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 20 samples (20 token repeat) - 3100 max words - at ../dataset/shuffle-word-3100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 9026/12318 [15:37:35<5:41:57, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 9026/12318 [15:37:35<5:41:57, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 780 max words, 50 samples - at ../dataset/gen-word-780-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 9027/12318 [15:37:36<5:41:49, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 9027/12318 [15:37:36<5:41:49, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 20 samples (20 token repeat) - 5000 max words - at ../dataset/shuffle-word-5000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 9028/12318 [15:37:43<5:41:43, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 9028/12318 [15:37:43<5:41:43, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 21 samples (20 token repeat) - 2800 max words - at ../dataset/shuffle-word-2800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 9029/12318 [15:37:48<5:41:37, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 9029/12318 [15:37:48<5:41:37, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 20 samples (20 token repeat) - 6500 max words - at ../dataset/shuffle-word-6500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 9030/12318 [15:37:56<5:41:31, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 9030/12318 [15:37:56<5:41:31, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 20 samples (20 token repeat) - 6900 max words - at ../dataset/shuffle-word-6900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 9031/12318 [15:37:58<5:41:23, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 9031/12318 [15:37:58<5:41:23, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 925 max words, 50 samples - at ../dataset/gen-word-925-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 9032/12318 [15:38:03<5:41:16, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 9032/12318 [15:38:03<5:41:16, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 940 max words, 50 samples - at ../dataset/gen-word-940-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 9033/12318 [15:38:05<5:41:09, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 9033/12318 [15:38:05<5:41:09, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 680 max words, 50 samples - at ../dataset/gen-word-680-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 9034/12318 [15:38:09<5:41:02, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 9034/12318 [15:38:09<5:41:02, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 20 samples (20 token repeat) - 6100 max words - at ../dataset/shuffle-word-6100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 9035/12318 [15:38:17<5:40:56, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 9035/12318 [15:38:17<5:40:56, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 485 max words, 50 samples - at ../dataset/gen-word-485-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 9036/12318 [15:38:24<5:40:50, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 3 samples (1 token repeat) - 840 max words - at ../dataset/shuffle-word-840-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 9036/12318 [15:38:24<5:40:50, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 850 max words, 50 samples - at ../dataset/gen-word-850-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 9037/12318 [15:38:27<5:40:43, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 9037/12318 [15:38:28<5:40:43, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 20 samples (20 token repeat) - 4300 max words - at ../dataset/shuffle-word-4300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 9038/12318 [15:38:36<5:40:38, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 20 samples (20 token repeat) - 7800 max words - at ../dataset/shuffle-word-7800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 9038/12318 [15:38:36<5:40:38, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 865 max words, 50 samples - at ../dataset/gen-word-865-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 9039/12318 [15:38:40<5:40:30, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 9039/12318 [15:38:40<5:40:30, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 3 samples (1 token repeat) - 915 max words - at ../dataset/shuffle-word-915-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 9040/12318 [15:38:49<5:40:25, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 9040/12318 [15:38:49<5:40:25, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 20 samples (20 token repeat) - 5700 max words - at ../dataset/shuffle-word-5700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 9041/12318 [15:38:53<5:40:18, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 9041/12318 [15:38:53<5:40:18, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 20 samples (20 token repeat) - 5100 max words - at ../dataset/shuffle-word-5100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 9042/12318 [15:39:00<5:40:12, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 9042/12318 [15:39:00<5:40:12, 6.23s/it, v_num=e4xv, train/loss" + "Generated a single JSONL file with 20 samples (20 token repeat) - 4500 max words - at ../dataset/shuffle-word-4500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 9043/12318 [15:39:03<5:40:05, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 9043/12318 [15:39:03<5:40:05, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 1100 max words, 2000 samples - at ../dataset/gen-word-1100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 9044/12318 [15:39:12<5:40:00, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 9044/12318 [15:39:12<5:40:00, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 1400 max words, 2000 samples - at ../dataset/gen-word-1400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 9045/12318 [15:39:20<5:39:54, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 9045/12318 [15:39:20<5:39:54, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 1300 max words, 2000 samples - at ../dataset/gen-word-1300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 9046/12318 [15:39:26<5:39:48, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 9046/12318 [15:39:26<5:39:48, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 1200 max words, 2000 samples - at ../dataset/gen-word-1200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 9047/12318 [15:39:32<5:39:41, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 9047/12318 [15:39:32<5:39:41, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 1500 max words, 2000 samples - at ../dataset/gen-word-1500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 9048/12318 [15:39:39<5:39:36, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 9048/12318 [15:39:39<5:39:36, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 1700 max words, 2000 samples - at ../dataset/gen-word-1700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 9049/12318 [15:39:46<5:39:29, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 9049/12318 [15:39:46<5:39:29, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 1800 max words, 2000 samples - at ../dataset/gen-word-1800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 9050/12318 [15:39:51<5:39:23, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 9050/12318 [15:39:51<5:39:23, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 1600 max words, 2000 samples - at ../dataset/gen-word-1600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 9051/12318 [15:39:56<5:39:16, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 9051/12318 [15:39:56<5:39:16, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 1900 max words, 2000 samples - at ../dataset/gen-word-1900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 9052/12318 [15:40:02<5:39:10, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 9052/12318 [15:40:02<5:39:10, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 2100 max words, 2000 samples - at ../dataset/gen-word-2100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 73%|▋| 9053/12318 [15:40:08<5:39:03, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 73%|▋| 9053/12318 [15:40:08<5:39:03, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 2000 max words, 2000 samples - at ../dataset/gen-word-2000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9054/12318 [15:40:13<5:38:57, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9054/12318 [15:40:13<5:38:57, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 2200 max words, 2000 samples - at ../dataset/gen-word-2200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9055/12318 [15:40:15<5:38:49, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9055/12318 [15:40:15<5:38:49, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 2300 max words, 2000 samples - at ../dataset/gen-word-2300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9056/12318 [15:40:37<5:38:49, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9056/12318 [15:40:37<5:38:49, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 2500 max words, 2000 samples - at ../dataset/gen-word-2500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|���| 9057/12318 [15:40:39<5:38:41, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9057/12318 [15:40:39<5:38:41, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 2400 max words, 2000 samples - at ../dataset/gen-word-2400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9058/12318 [15:40:44<5:38:34, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9058/12318 [15:40:44<5:38:34, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 2600 max words, 2000 samples - at ../dataset/gen-word-2600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9059/12318 [15:40:49<5:38:27, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9059/12318 [15:40:49<5:38:27, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 2800 max words, 2000 samples - at ../dataset/gen-word-2800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9060/12318 [15:40:50<5:38:19, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9060/12318 [15:40:50<5:38:19, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 2700 max words, 2000 samples - at ../dataset/gen-word-2700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9061/12318 [15:40:54<5:38:12, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9061/12318 [15:40:54<5:38:12, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 3300 max words, 2000 samples - at ../dataset/gen-word-3300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9062/12318 [15:40:57<5:38:05, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9062/12318 [15:40:57<5:38:05, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 3000 max words, 2000 samples - at ../dataset/gen-word-3000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9063/12318 [15:40:59<5:37:57, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9063/12318 [15:40:59<5:37:57, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 3100 max words, 2000 samples - at ../dataset/gen-word-3100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9064/12318 [15:41:05<5:37:51, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9064/12318 [15:41:05<5:37:51, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 2900 max words, 2000 samples - at ../dataset/gen-word-2900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9065/12318 [15:41:10<5:37:44, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9065/12318 [15:41:10<5:37:44, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 3400 max words, 2000 samples - at ../dataset/gen-word-3400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9066/12318 [15:41:14<5:37:37, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9066/12318 [15:41:14<5:37:37, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 4100 max words, 2000 samples - at ../dataset/gen-word-4100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9067/12318 [15:41:21<5:37:31, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9067/12318 [15:41:21<5:37:31, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 3200 max words, 2000 samples - at ../dataset/gen-word-3200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9068/12318 [15:41:25<5:37:24, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9068/12318 [15:41:25<5:37:24, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 3600 max words, 2000 samples - at ../dataset/gen-word-3600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9069/12318 [15:41:33<5:37:18, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9069/12318 [15:41:33<5:37:18, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 3500 max words, 2000 samples - at ../dataset/gen-word-3500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9070/12318 [15:41:39<5:37:12, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9070/12318 [15:41:39<5:37:12, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 3800 max words, 2000 samples - at ../dataset/gen-word-3800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9071/12318 [15:41:44<5:37:05, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9071/12318 [15:41:44<5:37:05, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 4000 max words, 2000 samples - at ../dataset/gen-word-4000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9072/12318 [15:41:46<5:36:58, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9072/12318 [15:41:46<5:36:58, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 3700 max words, 2000 samples - at ../dataset/gen-word-3700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9073/12318 [15:41:50<5:36:51, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 3900 max words, 2000 samples - at ../dataset/gen-word-3900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9073/12318 [15:41:50<5:36:51, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 4500 max words, 2000 samples - at ../dataset/gen-word-4500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9074/12318 [15:41:55<5:36:44, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9074/12318 [15:41:55<5:36:44, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 4300 max words, 2000 samples - at ../dataset/gen-word-4300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9075/12318 [15:42:03<5:36:38, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9075/12318 [15:42:03<5:36:38, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 4400 max words, 2000 samples - at ../dataset/gen-word-4400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9076/12318 [15:42:10<5:36:33, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9076/12318 [15:42:10<5:36:33, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 5300 max words, 2000 samples - at ../dataset/gen-word-5300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9077/12318 [15:42:18<5:36:27, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9077/12318 [15:42:18<5:36:27, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 4600 max words, 2000 samples - at ../dataset/gen-word-4600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9078/12318 [15:42:21<5:36:20, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9078/12318 [15:42:21<5:36:20, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 4800 max words, 2000 samples - at ../dataset/gen-word-4800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9079/12318 [15:42:24<5:36:12, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9079/12318 [15:42:24<5:36:12, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 4200 max words, 2000 samples - at ../dataset/gen-word-4200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9080/12318 [15:42:26<5:36:04, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9080/12318 [15:42:26<5:36:04, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 5000 max words, 2000 samples - at ../dataset/gen-word-5000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9081/12318 [15:42:35<5:35:59, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9081/12318 [15:42:35<5:35:59, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 4700 max words, 2000 samples - at ../dataset/gen-word-4700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9082/12318 [15:42:39<5:35:52, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9082/12318 [15:42:39<5:35:52, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 5200 max words, 2000 samples - at ../dataset/gen-word-5200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9083/12318 [15:42:45<5:35:46, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9083/12318 [15:42:45<5:35:46, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 5700 max words, 2000 samples - at ../dataset/gen-word-5700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9084/12318 [15:42:49<5:35:39, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9084/12318 [15:42:49<5:35:39, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 5600 max words, 2000 samples - at ../dataset/gen-word-5600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9085/12318 [15:42:57<5:35:33, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9085/12318 [15:42:57<5:35:33, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 5100 max words, 2000 samples - at ../dataset/gen-word-5100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9086/12318 [15:43:01<5:35:26, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9086/12318 [15:43:01<5:35:26, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 6800 max words, 2000 samples - at ../dataset/gen-word-6800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9087/12318 [15:43:08<5:35:20, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9087/12318 [15:43:08<5:35:20, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 4900 max words, 2000 samples - at ../dataset/gen-word-4900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9088/12318 [15:43:58<5:35:30, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9088/12318 [15:43:58<5:35:30, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 5400 max words, 2000 samples - at ../dataset/gen-word-5400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9089/12318 [15:44:03<5:35:23, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9089/12318 [15:44:03<5:35:23, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 5800 max words, 2000 samples - at ../dataset/gen-word-5800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9090/12318 [15:44:09<5:35:17, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9090/12318 [15:44:09<5:35:17, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 6900 max words, 2000 samples - at ../dataset/gen-word-6900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9091/12318 [15:44:13<5:35:10, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9091/12318 [15:44:13<5:35:10, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 6300 max words, 2000 samples - at ../dataset/gen-word-6300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9092/12318 [15:44:22<5:35:04, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9092/12318 [15:44:22<5:35:04, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 6400 max words, 2000 samples - at ../dataset/gen-word-6400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9093/12318 [15:44:28<5:34:58, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9093/12318 [15:44:28<5:34:58, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 5900 max words, 2000 samples - at ../dataset/gen-word-5900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9094/12318 [15:44:35<5:34:52, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9094/12318 [15:44:35<5:34:52, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 6200 max words, 2000 samples - at ../dataset/gen-word-6200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9095/12318 [15:44:38<5:34:45, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9095/12318 [15:44:38<5:34:45, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 5500 max words, 2000 samples - at ../dataset/gen-word-5500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9096/12318 [15:44:41<5:34:37, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9096/12318 [15:44:41<5:34:37, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 7800 max words, 2000 samples - at ../dataset/gen-word-7800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9097/12318 [15:44:50<5:34:32, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9097/12318 [15:44:50<5:34:32, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 6500 max words, 2000 samples - at ../dataset/gen-word-6500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9098/12318 [15:44:56<5:34:26, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9098/12318 [15:44:56<5:34:26, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 6700 max words, 2000 samples - at ../dataset/gen-word-6700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9099/12318 [15:45:05<5:34:21, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9099/12318 [15:45:05<5:34:21, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 6100 max words, 2000 samples - at ../dataset/gen-word-6100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9100/12318 [15:45:13<5:34:15, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9100/12318 [15:45:13<5:34:15, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 7000 max words, 2000 samples - at ../dataset/gen-word-7000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9101/12318 [15:45:16<5:34:08, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9101/12318 [15:45:16<5:34:08, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 7200 max words, 2000 samples - at ../dataset/gen-word-7200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9102/12318 [15:45:18<5:34:00, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9102/12318 [15:45:18<5:34:00, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 6000 max words, 2000 samples - at ../dataset/gen-word-6000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9103/12318 [15:45:26<5:33:54, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9103/12318 [15:45:26<5:33:54, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 6600 max words, 2000 samples - at ../dataset/gen-word-6600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9104/12318 [15:45:31<5:33:48, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9104/12318 [15:45:31<5:33:48, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 7100 max words, 2000 samples - at ../dataset/gen-word-7100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9105/12318 [15:45:34<5:33:40, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9105/12318 [15:45:34<5:33:40, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 7400 max words, 2000 samples - at ../dataset/gen-word-7400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9106/12318 [15:45:39<5:33:34, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9106/12318 [15:45:39<5:33:34, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 7300 max words, 2000 samples - at ../dataset/gen-word-7300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9107/12318 [15:45:46<5:33:28, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9107/12318 [15:45:46<5:33:28, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 7500 max words, 2000 samples - at ../dataset/gen-word-7500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9108/12318 [15:45:47<5:33:20, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9108/12318 [15:45:47<5:33:20, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 7900 max words, 2000 samples - at ../dataset/gen-word-7900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9109/12318 [15:45:53<5:33:13, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9109/12318 [15:45:53<5:33:13, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 8000 max words, 2000 samples - at ../dataset/gen-word-8000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9110/12318 [15:45:54<5:33:05, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9110/12318 [15:45:54<5:33:05, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 7700 max words, 2000 samples - at ../dataset/gen-word-7700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9111/12318 [15:46:01<5:32:59, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9111/12318 [15:46:01<5:32:59, 6.23s/it, v_num=e4xv, train/loss" + "Generated JSONL file with - 7600 max words, 2000 samples - at ../dataset/gen-word-7600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9112/12318 [15:46:07<5:32:53, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9112/12318 [15:46:07<5:32:53, 6.23s/it, v_num=e4xv, train/loss" + "## Done ##\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9113/12318 [15:46:11<5:32:46, 6.23s/it, v_num=e4xv, train/loss" + "total 6.1G\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9113/12318 [15:46:11<5:32:46, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 11K Sep 2 06:17 gen-word-10-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9114/12318 [15:46:16<5:32:39, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9114/12318 [15:46:16<5:32:39, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 56K Sep 2 06:17 gen-word-100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9115/12318 [15:46:18<5:32:31, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9115/12318 [15:46:18<5:32:31, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 487K Sep 2 06:17 gen-word-1000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9116/12318 [15:46:26<5:32:26, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9116/12318 [15:46:26<5:32:26, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 58K Sep 2 06:17 gen-word-105-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9117/12318 [15:46:33<5:32:20, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9117/12318 [15:46:33<5:32:20, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 58K Sep 2 06:17 gen-word-110-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9118/12318 [15:46:38<5:32:13, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9118/12318 [15:46:38<5:32:13, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 22M Sep 2 06:17 gen-word-1100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9119/12318 [15:46:44<5:32:07, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9119/12318 [15:46:44<5:32:07, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 62K Sep 2 06:17 gen-word-115-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9120/12318 [15:47:23<5:32:12, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 63K Sep 2 06:17 gen-word-120-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9120/12318 [15:47:23<5:32:12, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 23M Sep 2 06:17 gen-word-1200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9121/12318 [15:47:26<5:32:05, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9121/12318 [15:47:26<5:32:05, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 65K Sep 2 06:17 gen-word-125-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9122/12318 [15:47:34<5:31:59, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9122/12318 [15:47:34<5:31:59, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 68K Sep 2 06:17 gen-word-130-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9123/12318 [15:47:37<5:31:52, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9123/12318 [15:47:37<5:31:52, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 25M Sep 2 06:17 gen-word-1300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9124/12318 [15:47:42<5:31:45, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9124/12318 [15:47:42<5:31:45, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 72K Sep 2 06:17 gen-word-135-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9125/12318 [15:47:44<5:31:37, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 73K Sep 2 06:17 gen-word-140-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9125/12318 [15:47:44<5:31:37, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27M Sep 2 06:17 gen-word-1400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9126/12318 [15:47:50<5:31:31, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9126/12318 [15:47:50<5:31:31, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 76K Sep 2 06:17 gen-word-145-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9127/12318 [15:47:55<5:31:24, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9127/12318 [15:47:55<5:31:24, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 13K Sep 2 06:17 gen-word-15-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9128/12318 [15:48:04<5:31:19, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9128/12318 [15:48:04<5:31:19, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 81K Sep 2 06:17 gen-word-150-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9129/12318 [15:48:09<5:31:13, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9129/12318 [15:48:09<5:31:13, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 29M Sep 2 06:17 gen-word-1500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9130/12318 [15:48:17<5:31:07, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9130/12318 [15:48:17<5:31:07, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 82K Sep 2 06:17 gen-word-155-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9131/12318 [15:48:26<5:31:01, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9131/12318 [15:48:26<5:31:01, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 83K Sep 2 06:17 gen-word-160-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9132/12318 [15:48:32<5:30:55, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9132/12318 [15:48:32<5:30:55, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 31M Sep 2 06:17 gen-word-1600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9133/12318 [15:48:38<5:30:49, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9133/12318 [15:48:38<5:30:49, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 87K Sep 2 06:17 gen-word-165-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9134/12318 [15:48:46<5:30:43, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9134/12318 [15:48:46<5:30:43, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 86K Sep 2 06:17 gen-word-170-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9135/12318 [15:48:52<5:30:37, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9135/12318 [15:48:52<5:30:37, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 33M Sep 2 06:17 gen-word-1700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9136/12318 [15:48:58<5:30:31, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 88K Sep 2 06:17 gen-word-175-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9136/12318 [15:48:58<5:30:31, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 93K Sep 2 06:17 gen-word-180-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9137/12318 [15:49:06<5:30:25, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9137/12318 [15:49:06<5:30:25, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 35M Sep 2 06:17 gen-word-1800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9138/12318 [15:49:15<5:30:20, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9138/12318 [15:49:15<5:30:20, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 92K Sep 2 06:17 gen-word-185-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9139/12318 [15:49:23<5:30:14, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9139/12318 [15:49:23<5:30:14, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 99K Sep 2 06:17 gen-word-190-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9140/12318 [15:49:27<5:30:07, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9140/12318 [15:49:27<5:30:07, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 37M Sep 2 06:17 gen-word-1900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9141/12318 [15:49:35<5:30:02, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9141/12318 [15:49:35<5:30:02, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 102K Sep 2 06:17 gen-word-195-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9142/12318 [15:49:40<5:29:55, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9142/12318 [15:49:40<5:29:55, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 15K Sep 2 06:17 gen-word-20-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9143/12318 [15:49:45<5:29:48, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9143/12318 [15:49:45<5:29:48, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 103K Sep 2 06:17 gen-word-200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9144/12318 [15:49:52<5:29:42, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9144/12318 [15:49:52<5:29:42, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 39M Sep 2 06:17 gen-word-2000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9145/12318 [15:49:57<5:29:36, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9145/12318 [15:49:57<5:29:36, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 103K Sep 2 06:17 gen-word-205-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9146/12318 [15:50:02<5:29:29, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9146/12318 [15:50:02<5:29:29, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 108K Sep 2 06:17 gen-word-210-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9147/12318 [15:50:06<5:29:22, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9147/12318 [15:50:06<5:29:22, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 41M Sep 2 06:17 gen-word-2100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9148/12318 [15:50:15<5:29:17, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9148/12318 [15:50:15<5:29:17, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 113K Sep 2 06:17 gen-word-215-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9149/12318 [15:50:17<5:29:09, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9149/12318 [15:50:17<5:29:09, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 114K Sep 2 06:17 gen-word-220-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9150/12318 [15:50:24<5:29:03, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9150/12318 [15:50:24<5:29:03, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 42M Sep 2 06:17 gen-word-2200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9151/12318 [15:50:28<5:28:56, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9151/12318 [15:50:28<5:28:56, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 116K Sep 2 06:17 gen-word-225-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9152/12318 [15:50:46<5:28:54, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9152/12318 [15:50:46<5:28:54, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 114K Sep 2 06:17 gen-word-230-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9153/12318 [15:50:51<5:28:47, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9153/12318 [15:50:51<5:28:47, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 44M Sep 2 06:17 gen-word-2300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9154/12318 [15:50:56<5:28:41, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9154/12318 [15:50:56<5:28:41, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 117K Sep 2 06:17 gen-word-235-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9155/12318 [15:51:05<5:28:35, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9155/12318 [15:51:05<5:28:35, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 124K Sep 2 06:17 gen-word-240-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9156/12318 [15:51:13<5:28:30, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9156/12318 [15:51:13<5:28:30, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 46M Sep 2 06:17 gen-word-2400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9157/12318 [15:51:16<5:28:22, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9157/12318 [15:51:16<5:28:22, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 122K Sep 2 06:17 gen-word-245-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9158/12318 [15:51:22<5:28:16, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9158/12318 [15:51:22<5:28:16, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 17K Sep 2 06:17 gen-word-25-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9159/12318 [15:51:26<5:28:09, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9159/12318 [15:51:26<5:28:09, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 125K Sep 2 06:17 gen-word-250-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9160/12318 [15:51:30<5:28:02, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9160/12318 [15:51:30<5:28:02, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 48M Sep 2 06:17 gen-word-2500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9161/12318 [15:51:38<5:27:56, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9161/12318 [15:51:38<5:27:56, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 128K Sep 2 06:17 gen-word-255-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9162/12318 [15:51:42<5:27:49, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9162/12318 [15:51:42<5:27:49, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 134K Sep 2 06:17 gen-word-260-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9163/12318 [15:51:47<5:27:43, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9163/12318 [15:51:47<5:27:43, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 50M Sep 2 06:17 gen-word-2600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9164/12318 [15:51:50<5:27:36, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9164/12318 [15:51:50<5:27:36, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 135K Sep 2 06:17 gen-word-265-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9165/12318 [15:51:57<5:27:29, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9165/12318 [15:51:57<5:27:29, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 134K Sep 2 06:17 gen-word-270-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9166/12318 [15:52:01<5:27:22, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9166/12318 [15:52:01<5:27:22, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 52M Sep 2 06:17 gen-word-2700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9167/12318 [15:52:06<5:27:16, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9167/12318 [15:52:06<5:27:16, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 140K Sep 2 06:17 gen-word-275-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9168/12318 [15:52:14<5:27:10, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9168/12318 [15:52:14<5:27:10, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 143K Sep 2 06:17 gen-word-280-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9169/12318 [15:52:19<5:27:04, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9169/12318 [15:52:19<5:27:04, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 54M Sep 2 06:17 gen-word-2800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9170/12318 [15:52:27<5:26:58, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9170/12318 [15:52:27<5:26:58, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 141K Sep 2 06:17 gen-word-285-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9171/12318 [15:52:29<5:26:50, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9171/12318 [15:52:29<5:26:50, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 144K Sep 2 06:17 gen-word-290-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9172/12318 [15:52:33<5:26:43, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9172/12318 [15:52:33<5:26:43, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 56M Sep 2 06:17 gen-word-2900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9173/12318 [15:52:42<5:26:38, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9173/12318 [15:52:42<5:26:38, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 150K Sep 2 06:17 gen-word-295-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9174/12318 [15:52:43<5:26:30, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9174/12318 [15:52:43<5:26:30, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 20K Sep 2 06:17 gen-word-30-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9175/12318 [15:52:49<5:26:24, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9175/12318 [15:52:49<5:26:24, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 155K Sep 2 06:17 gen-word-300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 74%|▋| 9176/12318 [15:52:53<5:26:17, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 74%|▋| 9176/12318 [15:52:53<5:26:17, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 58M Sep 2 06:17 gen-word-3000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9177/12318 [15:53:00<5:26:11, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▋| 9177/12318 [15:53:00<5:26:11, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 155K Sep 2 06:17 gen-word-305-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9178/12318 [15:53:03<5:26:03, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▋| 9178/12318 [15:53:03<5:26:03, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 156K Sep 2 06:17 gen-word-310-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9179/12318 [15:53:12<5:25:58, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▋| 9179/12318 [15:53:12<5:25:58, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 60M Sep 2 06:17 gen-word-3100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9180/12318 [15:53:18<5:25:52, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▋| 9180/12318 [15:53:18<5:25:52, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 157K Sep 2 06:17 gen-word-315-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9181/12318 [15:53:26<5:25:46, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▋| 9181/12318 [15:53:26<5:25:46, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 159K Sep 2 06:17 gen-word-320-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9182/12318 [15:53:33<5:25:40, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▋| 9182/12318 [15:53:33<5:25:40, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 61M Sep 2 06:17 gen-word-3200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9183/12318 [15:53:41<5:25:35, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▋| 9183/12318 [15:53:41<5:25:35, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 166K Sep 2 06:17 gen-word-325-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9184/12318 [15:54:05<5:25:34, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▋| 9184/12318 [15:54:05<5:25:34, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 166K Sep 2 06:17 gen-word-330-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9185/12318 [15:54:09<5:25:27, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▋| 9185/12318 [15:54:09<5:25:27, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 63M Sep 2 06:17 gen-word-3300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9186/12318 [15:54:16<5:25:21, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▋| 9186/12318 [15:54:16<5:25:21, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 165K Sep 2 06:17 gen-word-335-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9187/12318 [15:54:18<5:25:13, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▋| 9187/12318 [15:54:18<5:25:13, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 171K Sep 2 06:17 gen-word-340-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9188/12318 [15:54:24<5:25:07, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▋| 9188/12318 [15:54:24<5:25:07, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 65M Sep 2 06:17 gen-word-3400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9189/12318 [15:54:31<5:25:01, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▋| 9189/12318 [15:54:31<5:25:01, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 171K Sep 2 06:17 gen-word-345-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9190/12318 [15:54:38<5:24:55, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▋| 9190/12318 [15:54:38<5:24:55, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 21K Sep 2 06:17 gen-word-35-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9191/12318 [15:54:47<5:24:50, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▋| 9191/12318 [15:54:47<5:24:50, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 175K Sep 2 06:17 gen-word-350-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9192/12318 [15:54:50<5:24:43, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▋| 9192/12318 [15:54:50<5:24:43, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 67M Sep 2 06:17 gen-word-3500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9193/12318 [15:54:57<5:24:37, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▋| 9193/12318 [15:54:57<5:24:37, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 175K Sep 2 06:17 gen-word-355-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9194/12318 [15:55:01<5:24:30, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▋| 9194/12318 [15:55:01<5:24:30, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 180K Sep 2 06:17 gen-word-360-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9195/12318 [15:55:08<5:24:24, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▋| 9195/12318 [15:55:08<5:24:24, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 69M Sep 2 06:17 gen-word-3600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9196/12318 [15:55:12<5:24:17, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▋| 9196/12318 [15:55:12<5:24:17, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 181K Sep 2 06:17 gen-word-365-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9197/12318 [15:55:17<5:24:10, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▋| 9197/12318 [15:55:17<5:24:10, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 185K Sep 2 06:17 gen-word-370-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9198/12318 [15:55:26<5:24:05, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▋| 9198/12318 [15:55:26<5:24:05, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 71M Sep 2 06:17 gen-word-3700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9199/12318 [15:55:30<5:23:58, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▋| 9199/12318 [15:55:30<5:23:58, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 190K Sep 2 06:17 gen-word-375-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9200/12318 [15:55:39<5:23:53, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▋| 9200/12318 [15:55:39<5:23:53, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 189K Sep 2 06:17 gen-word-380-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9201/12318 [15:55:40<5:23:45, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▋| 9201/12318 [15:55:40<5:23:45, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 73M Sep 2 06:17 gen-word-3800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9202/12318 [15:55:42<5:23:37, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▋| 9202/12318 [15:55:42<5:23:37, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 190K Sep 2 06:17 gen-word-385-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9203/12318 [15:55:48<5:23:31, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▋| 9203/12318 [15:55:48<5:23:31, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 195K Sep 2 06:17 gen-word-390-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9204/12318 [15:55:55<5:23:25, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▋| 9204/12318 [15:55:55<5:23:25, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 75M Sep 2 06:17 gen-word-3900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9205/12318 [15:55:56<5:23:17, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▋| 9205/12318 [15:55:56<5:23:17, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 199K Sep 2 06:17 gen-word-395-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9206/12318 [15:56:02<5:23:10, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▋| 9206/12318 [15:56:02<5:23:10, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 25K Sep 2 06:17 gen-word-40-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9207/12318 [15:56:10<5:23:05, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▋| 9207/12318 [15:56:10<5:23:05, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 200K Sep 2 06:17 gen-word-400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9208/12318 [15:56:15<5:22:58, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▋| 9208/12318 [15:56:15<5:22:58, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 77M Sep 2 06:17 gen-word-4000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9209/12318 [15:56:24<5:22:53, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▋| 9209/12318 [15:56:24<5:22:53, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 205K Sep 2 06:17 gen-word-405-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9210/12318 [15:56:25<5:22:45, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▋| 9210/12318 [15:56:25<5:22:45, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 208K Sep 2 06:17 gen-word-410-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9211/12318 [15:56:34<5:22:39, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▋| 9211/12318 [15:56:34<5:22:39, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 79M Sep 2 06:17 gen-word-4100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9212/12318 [15:56:38<5:22:32, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▋| 9212/12318 [15:56:38<5:22:32, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 206K Sep 2 06:17 gen-word-415-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9213/12318 [15:56:39<5:22:24, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▋| 9213/12318 [15:56:39<5:22:24, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 212K Sep 2 06:17 gen-word-420-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9214/12318 [15:56:48<5:22:19, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▋| 9214/12318 [15:56:48<5:22:19, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 80M Sep 2 06:17 gen-word-4200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9215/12318 [15:56:51<5:22:12, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▋| 9215/12318 [15:56:51<5:22:12, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 214K Sep 2 06:17 gen-word-425-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9216/12318 [15:57:14<5:22:11, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▋| 9216/12318 [15:57:14<5:22:11, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 214K Sep 2 06:17 gen-word-430-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9217/12318 [15:57:20<5:22:05, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▋| 9217/12318 [15:57:20<5:22:05, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 82M Sep 2 06:17 gen-word-4300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9218/12318 [15:57:23<5:21:58, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▋| 9218/12318 [15:57:23<5:21:58, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 214K Sep 2 06:17 gen-word-435-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9219/12318 [15:57:31<5:21:52, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▋| 9219/12318 [15:57:31<5:21:52, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 219K Sep 2 06:17 gen-word-440-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9220/12318 [15:57:32<5:21:44, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▋| 9220/12318 [15:57:32<5:21:44, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 84M Sep 2 06:17 gen-word-4400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9221/12318 [15:57:35<5:21:37, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▋| 9221/12318 [15:57:35<5:21:37, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 222K Sep 2 06:17 gen-word-445-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9222/12318 [15:57:39<5:21:30, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▋| 9222/12318 [15:57:39<5:21:30, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 28K Sep 2 06:17 gen-word-45-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9223/12318 [15:57:48<5:21:24, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▋| 9223/12318 [15:57:48<5:21:24, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 223K Sep 2 06:17 gen-word-450-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9224/12318 [15:57:51<5:21:17, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▋| 9224/12318 [15:57:51<5:21:17, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 86M Sep 2 06:17 gen-word-4500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9225/12318 [15:57:55<5:21:10, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▋| 9225/12318 [15:57:55<5:21:10, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 226K Sep 2 06:17 gen-word-455-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9226/12318 [15:57:57<5:21:02, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 231K Sep 2 06:17 gen-word-460-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9226/12318 [15:57:57<5:21:02, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 88M Sep 2 06:17 gen-word-4600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9227/12318 [15:58:05<5:20:57, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▋| 9227/12318 [15:58:05<5:20:57, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 233K Sep 2 06:17 gen-word-465-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9228/12318 [15:58:09<5:20:50, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▋| 9228/12318 [15:58:09<5:20:50, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 230K Sep 2 06:17 gen-word-470-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9229/12318 [15:58:12<5:20:43, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▋| 9229/12318 [15:58:12<5:20:43, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 90M Sep 2 06:17 gen-word-4700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9230/12318 [15:58:15<5:20:35, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▋| 9230/12318 [15:58:15<5:20:35, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 238K Sep 2 06:17 gen-word-475-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9231/12318 [15:58:22<5:20:29, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▋| 9231/12318 [15:58:22<5:20:29, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 236K Sep 2 06:17 gen-word-480-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9232/12318 [15:58:30<5:20:24, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▋| 9232/12318 [15:58:30<5:20:24, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 92M Sep 2 06:17 gen-word-4800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9233/12318 [15:58:36<5:20:17, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▋| 9233/12318 [15:58:36<5:20:17, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 241K Sep 2 06:17 gen-word-485-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9234/12318 [15:58:38<5:20:10, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▋| 9234/12318 [15:58:38<5:20:10, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 239K Sep 2 06:17 gen-word-490-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9235/12318 [15:58:39<5:20:02, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▋| 9235/12318 [15:58:39<5:20:02, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 94M Sep 2 06:17 gen-word-4900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9236/12318 [15:58:47<5:19:56, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 245K Sep 2 06:17 gen-word-495-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9236/12318 [15:58:47<5:19:56, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 7.3K Sep 2 06:17 gen-word-5-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9237/12318 [15:58:48<5:19:48, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▋| 9237/12318 [15:58:48<5:19:48, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 31K Sep 2 06:17 gen-word-50-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▋| 9238/12318 [15:58:55<5:19:42, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▋| 9238/12318 [15:58:55<5:19:42, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 248K Sep 2 06:17 gen-word-500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9239/12318 [15:58:57<5:19:35, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9239/12318 [15:58:57<5:19:35, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 96M Sep 2 06:17 gen-word-5000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9240/12318 [15:59:05<5:19:29, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9240/12318 [15:59:05<5:19:29, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 252K Sep 2 06:17 gen-word-505-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9241/12318 [15:59:10<5:19:22, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9241/12318 [15:59:10<5:19:22, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 256K Sep 2 06:17 gen-word-510-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9242/12318 [15:59:17<5:19:16, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9242/12318 [15:59:17<5:19:16, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 98M Sep 2 06:17 gen-word-5100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9243/12318 [15:59:23<5:19:10, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9243/12318 [15:59:23<5:19:10, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 261K Sep 2 06:17 gen-word-515-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9244/12318 [15:59:27<5:19:03, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9244/12318 [15:59:27<5:19:03, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 262K Sep 2 06:17 gen-word-520-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9245/12318 [15:59:30<5:18:56, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9245/12318 [15:59:30<5:18:56, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 99M Sep 2 06:17 gen-word-5200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9246/12318 [15:59:36<5:18:49, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9246/12318 [15:59:36<5:18:49, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 261K Sep 2 06:17 gen-word-525-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9247/12318 [15:59:41<5:18:43, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9247/12318 [15:59:41<5:18:43, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 262K Sep 2 06:17 gen-word-530-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9248/12318 [16:00:34<5:18:52, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9248/12318 [16:00:34<5:18:52, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 101M Sep 2 06:17 gen-word-5300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9249/12318 [16:00:42<5:18:47, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9249/12318 [16:00:42<5:18:47, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 266K Sep 2 06:17 gen-word-535-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9250/12318 [16:00:46<5:18:40, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9250/12318 [16:00:46<5:18:40, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 264K Sep 2 06:17 gen-word-540-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9251/12318 [16:00:52<5:18:33, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9251/12318 [16:00:52<5:18:33, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 103M Sep 2 06:17 gen-word-5400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9252/12318 [16:01:01<5:18:28, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9252/12318 [16:01:01<5:18:28, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 273K Sep 2 06:17 gen-word-545-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9253/12318 [16:01:06<5:18:21, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9253/12318 [16:01:06<5:18:21, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 31K Sep 2 06:17 gen-word-55-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9254/12318 [16:01:10<5:18:14, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9254/12318 [16:01:10<5:18:14, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 277K Sep 2 06:17 gen-word-550-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9255/12318 [16:01:17<5:18:08, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9255/12318 [16:01:17<5:18:08, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 105M Sep 2 06:17 gen-word-5500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9256/12318 [16:01:24<5:18:02, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9256/12318 [16:01:24<5:18:02, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 278K Sep 2 06:17 gen-word-555-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9257/12318 [16:01:29<5:17:56, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9257/12318 [16:01:29<5:17:56, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 272K Sep 2 06:17 gen-word-560-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9258/12318 [16:01:36<5:17:50, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9258/12318 [16:01:36<5:17:50, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 107M Sep 2 06:17 gen-word-5600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9259/12318 [16:01:41<5:17:43, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9259/12318 [16:01:41<5:17:43, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 282K Sep 2 06:17 gen-word-565-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9260/12318 [16:01:46<5:17:36, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9260/12318 [16:01:46<5:17:36, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 283K Sep 2 06:17 gen-word-570-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9261/12318 [16:01:48<5:17:29, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9261/12318 [16:01:48<5:17:29, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 109M Sep 2 06:17 gen-word-5700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9262/12318 [16:01:50<5:17:21, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9262/12318 [16:01:50<5:17:21, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 285K Sep 2 06:17 gen-word-575-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9263/12318 [16:01:57<5:17:15, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9263/12318 [16:01:57<5:17:15, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 290K Sep 2 06:17 gen-word-580-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9264/12318 [16:02:03<5:17:09, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9264/12318 [16:02:03<5:17:09, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 111M Sep 2 06:17 gen-word-5800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9265/12318 [16:02:08<5:17:02, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9265/12318 [16:02:08<5:17:02, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 286K Sep 2 06:17 gen-word-585-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9266/12318 [16:02:12<5:16:55, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9266/12318 [16:02:12<5:16:55, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 290K Sep 2 06:17 gen-word-590-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9267/12318 [16:02:19<5:16:49, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9267/12318 [16:02:19<5:16:49, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 113M Sep 2 06:17 gen-word-5900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9268/12318 [16:02:26<5:16:43, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9268/12318 [16:02:26<5:16:43, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 291K Sep 2 06:17 gen-word-595-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9269/12318 [16:02:29<5:16:36, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9269/12318 [16:02:29<5:16:36, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 35K Sep 2 06:17 gen-word-60-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9270/12318 [16:02:30<5:16:28, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9270/12318 [16:02:30<5:16:28, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 302K Sep 2 06:17 gen-word-600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9271/12318 [16:02:39<5:16:23, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9271/12318 [16:02:39<5:16:23, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 115M Sep 2 06:17 gen-word-6000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9272/12318 [16:02:43<5:16:16, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9272/12318 [16:02:43<5:16:16, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 298K Sep 2 06:17 gen-word-605-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9273/12318 [16:02:46<5:16:08, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9273/12318 [16:02:46<5:16:08, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 304K Sep 2 06:17 gen-word-610-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9274/12318 [16:02:51<5:16:02, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9274/12318 [16:02:51<5:16:02, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 117M Sep 2 06:17 gen-word-6100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9275/12318 [16:02:55<5:15:55, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9275/12318 [16:02:55<5:15:55, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 306K Sep 2 06:17 gen-word-615-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9276/12318 [16:03:02<5:15:49, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9276/12318 [16:03:02<5:15:49, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 304K Sep 2 06:17 gen-word-620-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9277/12318 [16:03:08<5:15:43, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9277/12318 [16:03:08<5:15:43, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 118M Sep 2 06:17 gen-word-6200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9278/12318 [16:03:15<5:15:37, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9278/12318 [16:03:15<5:15:37, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 306K Sep 2 06:17 gen-word-625-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9279/12318 [16:03:23<5:15:31, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9279/12318 [16:03:23<5:15:31, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 310K Sep 2 06:17 gen-word-630-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9280/12318 [16:04:01<5:15:35, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9280/12318 [16:04:01<5:15:35, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 120M Sep 2 06:17 gen-word-6300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9281/12318 [16:04:07<5:15:29, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9281/12318 [16:04:07<5:15:29, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 312K Sep 2 06:17 gen-word-635-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9282/12318 [16:04:11<5:15:22, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9282/12318 [16:04:11<5:15:22, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 317K Sep 2 06:17 gen-word-640-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9283/12318 [16:04:14<5:15:15, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9283/12318 [16:04:14<5:15:15, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 122M Sep 2 06:17 gen-word-6400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9284/12318 [16:04:17<5:15:07, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9284/12318 [16:04:17<5:15:07, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 322K Sep 2 06:17 gen-word-645-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9285/12318 [16:04:26<5:15:02, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9285/12318 [16:04:26<5:15:02, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 36K Sep 2 06:17 gen-word-65-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9286/12318 [16:04:32<5:14:56, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9286/12318 [16:04:32<5:14:56, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 322K Sep 2 06:17 gen-word-650-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9287/12318 [16:04:36<5:14:49, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9287/12318 [16:04:36<5:14:49, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 124M Sep 2 06:17 gen-word-6500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9288/12318 [16:04:38<5:14:41, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9288/12318 [16:04:38<5:14:41, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 328K Sep 2 06:17 gen-word-655-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9289/12318 [16:04:41<5:14:34, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9289/12318 [16:04:41<5:14:34, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 325K Sep 2 06:17 gen-word-660-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9290/12318 [16:04:47<5:14:27, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9290/12318 [16:04:47<5:14:27, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 126M Sep 2 06:17 gen-word-6600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9291/12318 [16:04:53<5:14:21, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9291/12318 [16:04:53<5:14:21, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 329K Sep 2 06:17 gen-word-665-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9292/12318 [16:04:55<5:14:13, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9292/12318 [16:04:55<5:14:13, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 334K Sep 2 06:17 gen-word-670-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9293/12318 [16:05:01<5:14:07, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9293/12318 [16:05:01<5:14:07, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 128M Sep 2 06:17 gen-word-6700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9294/12318 [16:05:08<5:14:01, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9294/12318 [16:05:08<5:14:01, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 332K Sep 2 06:17 gen-word-675-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9295/12318 [16:05:09<5:13:53, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9295/12318 [16:05:09<5:13:53, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 333K Sep 2 06:17 gen-word-680-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9296/12318 [16:05:17<5:13:48, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9296/12318 [16:05:17<5:13:48, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 130M Sep 2 06:17 gen-word-6800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9297/12318 [16:05:21<5:13:41, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9297/12318 [16:05:21<5:13:41, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 341K Sep 2 06:17 gen-word-685-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9298/12318 [16:05:22<5:13:33, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9298/12318 [16:05:22<5:13:33, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 338K Sep 2 06:17 gen-word-690-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9299/12318 [16:05:26<5:13:26, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9299/12318 [16:05:26<5:13:26, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 132M Sep 2 06:17 gen-word-6900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 75%|▊| 9300/12318 [16:05:34<5:13:20, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 75%|▊| 9300/12318 [16:05:34<5:13:20, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 340K Sep 2 06:17 gen-word-695-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9301/12318 [16:05:43<5:13:15, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9301/12318 [16:05:43<5:13:15, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 39K Sep 2 06:17 gen-word-70-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9302/12318 [16:05:48<5:13:08, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9302/12318 [16:05:48<5:13:08, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 342K Sep 2 06:17 gen-word-700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9303/12318 [16:05:50<5:13:01, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9303/12318 [16:05:50<5:13:01, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 134M Sep 2 06:17 gen-word-7000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9304/12318 [16:05:59<5:12:55, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9304/12318 [16:05:59<5:12:55, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 351K Sep 2 06:17 gen-word-705-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9305/12318 [16:06:03<5:12:48, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9305/12318 [16:06:03<5:12:48, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 347K Sep 2 06:17 gen-word-710-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9306/12318 [16:06:06<5:12:41, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9306/12318 [16:06:06<5:12:41, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 136M Sep 2 06:17 gen-word-7100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9307/12318 [16:06:15<5:12:36, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9307/12318 [16:06:15<5:12:36, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 352K Sep 2 06:17 gen-word-715-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9308/12318 [16:06:17<5:12:28, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9308/12318 [16:06:17<5:12:28, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 355K Sep 2 06:17 gen-word-720-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9309/12318 [16:06:24<5:12:22, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9309/12318 [16:06:24<5:12:22, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 137M Sep 2 06:17 gen-word-7200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9310/12318 [16:06:30<5:12:16, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9310/12318 [16:06:30<5:12:16, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 354K Sep 2 06:17 gen-word-725-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9311/12318 [16:06:36<5:12:09, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9311/12318 [16:06:36<5:12:09, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 358K Sep 2 06:17 gen-word-730-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9312/12318 [16:07:10<5:12:12, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9312/12318 [16:07:10<5:12:12, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 139M Sep 2 06:17 gen-word-7300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9313/12318 [16:07:13<5:12:05, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9313/12318 [16:07:13<5:12:05, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 372K Sep 2 06:17 gen-word-735-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9314/12318 [16:07:19<5:11:59, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9314/12318 [16:07:19<5:11:59, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 363K Sep 2 06:17 gen-word-740-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9315/12318 [16:07:25<5:11:52, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9315/12318 [16:07:25<5:11:52, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 141M Sep 2 06:17 gen-word-7400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9316/12318 [16:07:30<5:11:46, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9316/12318 [16:07:30<5:11:46, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 364K Sep 2 06:17 gen-word-745-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9317/12318 [16:07:39<5:11:40, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9317/12318 [16:07:39<5:11:40, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 42K Sep 2 06:17 gen-word-75-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9318/12318 [16:07:43<5:11:33, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9318/12318 [16:07:43<5:11:33, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 372K Sep 2 06:17 gen-word-750-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9319/12318 [16:07:48<5:11:27, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9319/12318 [16:07:48<5:11:27, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 143M Sep 2 06:17 gen-word-7500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9320/12318 [16:07:53<5:11:20, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9320/12318 [16:07:53<5:11:20, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 366K Sep 2 06:17 gen-word-755-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9321/12318 [16:07:57<5:11:13, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9321/12318 [16:07:57<5:11:13, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 376K Sep 2 06:17 gen-word-760-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9322/12318 [16:08:06<5:11:08, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9322/12318 [16:08:06<5:11:08, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 145M Sep 2 06:17 gen-word-7600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9323/12318 [16:08:11<5:11:01, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9323/12318 [16:08:11<5:11:01, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 372K Sep 2 06:17 gen-word-765-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9324/12318 [16:08:17<5:10:55, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9324/12318 [16:08:17<5:10:55, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 381K Sep 2 06:17 gen-word-770-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9325/12318 [16:08:18<5:10:47, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9325/12318 [16:08:18<5:10:47, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 147M Sep 2 06:17 gen-word-7700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9326/12318 [16:08:20<5:10:40, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9326/12318 [16:08:20<5:10:40, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 387K Sep 2 06:17 gen-word-775-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9327/12318 [16:08:21<5:10:32, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9327/12318 [16:08:21<5:10:32, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 381K Sep 2 06:17 gen-word-780-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9328/12318 [16:08:23<5:10:24, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9328/12318 [16:08:23<5:10:24, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 149M Sep 2 06:17 gen-word-7800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9329/12318 [16:08:31<5:10:18, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9329/12318 [16:08:31<5:10:18, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 381K Sep 2 06:17 gen-word-785-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9330/12318 [16:08:40<5:10:13, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9330/12318 [16:08:40<5:10:13, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 390K Sep 2 06:17 gen-word-790-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9331/12318 [16:08:45<5:10:07, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 151M Sep 2 06:17 gen-word-7900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9331/12318 [16:08:46<5:10:07, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 391K Sep 2 06:17 gen-word-795-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9332/12318 [16:08:48<5:09:59, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9332/12318 [16:08:48<5:09:59, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 44K Sep 2 06:17 gen-word-80-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9333/12318 [16:08:54<5:09:53, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9333/12318 [16:08:54<5:09:53, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 391K Sep 2 06:17 gen-word-800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9334/12318 [16:09:01<5:09:47, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9334/12318 [16:09:01<5:09:47, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 153M Sep 2 06:17 gen-word-8000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9335/12318 [16:09:04<5:09:40, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9335/12318 [16:09:04<5:09:40, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 396K Sep 2 06:17 gen-word-805-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9336/12318 [16:09:09<5:09:33, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9336/12318 [16:09:09<5:09:33, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 400K Sep 2 06:17 gen-word-810-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9337/12318 [16:09:13<5:09:26, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9337/12318 [16:09:13<5:09:26, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 398K Sep 2 06:17 gen-word-815-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9338/12318 [16:09:20<5:09:20, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9338/12318 [16:09:20<5:09:20, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 409K Sep 2 06:17 gen-word-820-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9339/12318 [16:09:25<5:09:13, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9339/12318 [16:09:25<5:09:13, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 403K Sep 2 06:17 gen-word-825-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9340/12318 [16:09:32<5:09:07, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9340/12318 [16:09:32<5:09:07, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 409K Sep 2 06:17 gen-word-830-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9341/12318 [16:09:40<5:09:02, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 411K Sep 2 06:17 gen-word-835-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9341/12318 [16:09:40<5:09:02, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 414K Sep 2 06:17 gen-word-840-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9342/12318 [16:09:42<5:08:54, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9342/12318 [16:09:42<5:08:54, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 413K Sep 2 06:17 gen-word-845-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9343/12318 [16:09:44<5:08:47, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9343/12318 [16:09:44<5:08:47, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 46K Sep 2 06:17 gen-word-85-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9344/12318 [16:10:29<5:08:53, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9344/12318 [16:10:29<5:08:53, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 412K Sep 2 06:17 gen-word-850-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9345/12318 [16:10:35<5:08:46, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9345/12318 [16:10:35<5:08:46, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 418K Sep 2 06:17 gen-word-855-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9346/12318 [16:10:36<5:08:39, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9346/12318 [16:10:36<5:08:39, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 417K Sep 2 06:17 gen-word-860-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9347/12318 [16:10:45<5:08:33, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9347/12318 [16:10:45<5:08:33, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 432K Sep 2 06:17 gen-word-865-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9348/12318 [16:10:49<5:08:26, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9348/12318 [16:10:49<5:08:26, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 429K Sep 2 06:17 gen-word-870-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9349/12318 [16:10:51<5:08:19, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9349/12318 [16:10:51<5:08:19, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 429K Sep 2 06:17 gen-word-875-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9350/12318 [16:10:54<5:08:11, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9350/12318 [16:10:54<5:08:11, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 432K Sep 2 06:17 gen-word-880-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9351/12318 [16:11:01<5:08:05, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9351/12318 [16:11:01<5:08:05, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 437K Sep 2 06:17 gen-word-885-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9352/12318 [16:11:06<5:07:59, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9352/12318 [16:11:06<5:07:59, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 432K Sep 2 06:17 gen-word-890-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9353/12318 [16:11:08<5:07:51, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9353/12318 [16:11:08<5:07:51, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 446K Sep 2 06:17 gen-word-895-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9354/12318 [16:11:10<5:07:44, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9354/12318 [16:11:10<5:07:44, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 49K Sep 2 06:17 gen-word-90-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9355/12318 [16:11:17<5:07:38, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9355/12318 [16:11:17<5:07:38, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 448K Sep 2 06:17 gen-word-900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9356/12318 [16:11:24<5:07:32, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9356/12318 [16:11:24<5:07:32, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 448K Sep 2 06:17 gen-word-905-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9357/12318 [16:11:26<5:07:24, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9357/12318 [16:11:26<5:07:24, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 441K Sep 2 06:17 gen-word-910-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9358/12318 [16:11:32<5:07:18, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9358/12318 [16:11:32<5:07:18, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 449K Sep 2 06:17 gen-word-915-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9359/12318 [16:11:35<5:07:11, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9359/12318 [16:11:35<5:07:11, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 450K Sep 2 06:17 gen-word-920-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9360/12318 [16:11:39<5:07:04, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9360/12318 [16:11:39<5:07:04, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 460K Sep 2 06:17 gen-word-925-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9361/12318 [16:11:48<5:06:58, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9361/12318 [16:11:48<5:06:58, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 464K Sep 2 06:17 gen-word-930-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9362/12318 [16:11:50<5:06:51, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9362/12318 [16:11:50<5:06:51, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 458K Sep 2 06:17 gen-word-935-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9363/12318 [16:11:55<5:06:44, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9363/12318 [16:11:55<5:06:44, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 465K Sep 2 06:17 gen-word-940-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9364/12318 [16:11:57<5:06:37, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9364/12318 [16:11:57<5:06:37, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 467K Sep 2 06:17 gen-word-945-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9365/12318 [16:12:01<5:06:30, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9365/12318 [16:12:01<5:06:30, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 53K Sep 2 06:17 gen-word-95-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9366/12318 [16:12:10<5:06:24, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9366/12318 [16:12:10<5:06:24, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 466K Sep 2 06:17 gen-word-950-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9367/12318 [16:12:15<5:06:18, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9367/12318 [16:12:15<5:06:18, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 464K Sep 2 06:17 gen-word-955-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9368/12318 [16:12:22<5:06:12, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9368/12318 [16:12:22<5:06:12, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 473K Sep 2 06:17 gen-word-960-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9369/12318 [16:12:26<5:06:05, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9369/12318 [16:12:26<5:06:05, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 474K Sep 2 06:17 gen-word-965-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9370/12318 [16:12:29<5:05:57, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9370/12318 [16:12:29<5:05:57, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 475K Sep 2 06:17 gen-word-970-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9371/12318 [16:12:38<5:05:52, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9371/12318 [16:12:38<5:05:52, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 477K Sep 2 06:17 gen-word-975-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9372/12318 [16:12:41<5:05:45, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9372/12318 [16:12:41<5:05:45, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 483K Sep 2 06:17 gen-word-980-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9373/12318 [16:12:43<5:05:37, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9373/12318 [16:12:43<5:05:37, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 485K Sep 2 06:17 gen-word-985-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9374/12318 [16:12:48<5:05:31, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9374/12318 [16:12:48<5:05:31, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 486K Sep 2 06:17 gen-word-990-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9375/12318 [16:12:53<5:05:24, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9375/12318 [16:12:53<5:05:24, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 486K Sep 2 06:17 gen-word-995-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9376/12318 [16:13:51<5:05:34, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9376/12318 [16:13:51<5:05:34, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 52K Sep 2 06:17 shuffle-word-10-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9377/12318 [16:13:56<5:05:27, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9377/12318 [16:13:56<5:05:27, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 28K Sep 2 06:17 shuffle-word-100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9378/12318 [16:13:59<5:05:20, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9378/12318 [16:13:59<5:05:20, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 26K Sep 2 06:17 shuffle-word-1000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9379/12318 [16:14:08<5:05:15, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9379/12318 [16:14:08<5:05:15, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 28K Sep 2 06:17 shuffle-word-105-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9380/12318 [16:14:17<5:05:09, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9380/12318 [16:14:17<5:05:09, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 28K Sep 2 06:17 shuffle-word-110-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9381/12318 [16:14:19<5:05:02, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9381/12318 [16:14:19<5:05:02, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 523K Sep 2 06:17 shuffle-word-1100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9382/12318 [16:14:22<5:04:55, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9382/12318 [16:14:22<5:04:55, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 28K Sep 2 06:17 shuffle-word-115-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9383/12318 [16:14:28<5:04:48, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9383/12318 [16:14:28<5:04:48, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 28K Sep 2 06:17 shuffle-word-120-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9384/12318 [16:14:32<5:04:42, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9384/12318 [16:14:32<5:04:42, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 523K Sep 2 06:17 shuffle-word-1200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9385/12318 [16:14:36<5:04:35, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9385/12318 [16:14:36<5:04:35, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-125-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9386/12318 [16:14:44<5:04:29, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9386/12318 [16:14:44<5:04:29, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 29K Sep 2 06:17 shuffle-word-130-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9387/12318 [16:14:52<5:04:23, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9387/12318 [16:14:52<5:04:23, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 519K Sep 2 06:17 shuffle-word-1300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9388/12318 [16:14:56<5:04:16, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9388/12318 [16:14:56<5:04:16, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 28K Sep 2 06:17 shuffle-word-135-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9389/12318 [16:15:03<5:04:10, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9389/12318 [16:15:03<5:04:10, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 28K Sep 2 06:17 shuffle-word-140-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9390/12318 [16:15:11<5:04:05, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9390/12318 [16:15:11<5:04:05, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 518K Sep 2 06:17 shuffle-word-1400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9391/12318 [16:15:19<5:03:59, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9391/12318 [16:15:19<5:03:59, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-145-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9392/12318 [16:15:26<5:03:53, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9392/12318 [16:15:26<5:03:53, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 45K Sep 2 06:17 shuffle-word-15-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9393/12318 [16:15:28<5:03:45, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9393/12318 [16:15:28<5:03:45, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 29K Sep 2 06:17 shuffle-word-150-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9394/12318 [16:15:36<5:03:40, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9394/12318 [16:15:36<5:03:40, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 520K Sep 2 06:17 shuffle-word-1500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9395/12318 [16:15:42<5:03:33, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9395/12318 [16:15:42<5:03:33, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-155-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9396/12318 [16:15:44<5:03:26, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9396/12318 [16:15:44<5:03:26, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 29K Sep 2 06:17 shuffle-word-160-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9397/12318 [16:15:50<5:03:20, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9397/12318 [16:15:50<5:03:20, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 520K Sep 2 06:17 shuffle-word-1600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9398/12318 [16:15:59<5:03:14, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9398/12318 [16:15:59<5:03:14, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 28K Sep 2 06:17 shuffle-word-165-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9399/12318 [16:16:02<5:03:07, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9399/12318 [16:16:02<5:03:07, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 28K Sep 2 06:17 shuffle-word-170-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9400/12318 [16:16:10<5:03:01, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9400/12318 [16:16:10<5:03:01, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 522K Sep 2 06:17 shuffle-word-1700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9401/12318 [16:16:12<5:02:54, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9401/12318 [16:16:12<5:02:54, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-175-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9402/12318 [16:16:16<5:02:47, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9402/12318 [16:16:16<5:02:47, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-180-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9403/12318 [16:16:19<5:02:40, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9403/12318 [16:16:19<5:02:40, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 522K Sep 2 06:17 shuffle-word-1800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9404/12318 [16:16:23<5:02:33, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9404/12318 [16:16:23<5:02:33, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 29K Sep 2 06:17 shuffle-word-185-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9405/12318 [16:16:26<5:02:25, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9405/12318 [16:16:26<5:02:25, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-190-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9406/12318 [16:16:34<5:02:20, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|��| 9406/12318 [16:16:34<5:02:20, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 520K Sep 2 06:17 shuffle-word-1900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9407/12318 [16:16:43<5:02:14, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9407/12318 [16:16:43<5:02:14, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 28K Sep 2 06:17 shuffle-word-195-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9408/12318 [16:17:14<5:02:16, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9408/12318 [16:17:14<5:02:16, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 40K Sep 2 06:17 shuffle-word-20-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9409/12318 [16:17:20<5:02:09, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9409/12318 [16:17:20<5:02:09, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9410/12318 [16:17:25<5:02:03, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9410/12318 [16:17:25<5:02:03, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 521K Sep 2 06:17 shuffle-word-2000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9411/12318 [16:17:29<5:01:56, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9411/12318 [16:17:29<5:01:56, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-205-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9412/12318 [16:17:34<5:01:49, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9412/12318 [16:17:34<5:01:49, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 28K Sep 2 06:17 shuffle-word-210-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9413/12318 [16:17:42<5:01:44, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9413/12318 [16:17:42<5:01:44, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 522K Sep 2 06:17 shuffle-word-2100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9414/12318 [16:17:48<5:01:37, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9414/12318 [16:17:48<5:01:37, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 28K Sep 2 06:17 shuffle-word-215-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9415/12318 [16:17:54<5:01:31, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9415/12318 [16:17:54<5:01:31, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-220-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9416/12318 [16:18:01<5:01:25, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9416/12318 [16:18:01<5:01:25, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 520K Sep 2 06:17 shuffle-word-2200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9417/12318 [16:18:06<5:01:19, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9417/12318 [16:18:06<5:01:19, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 26K Sep 2 06:17 shuffle-word-225-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9418/12318 [16:18:09<5:01:11, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9418/12318 [16:18:09<5:01:11, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 28K Sep 2 06:17 shuffle-word-230-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9419/12318 [16:18:13<5:01:04, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9419/12318 [16:18:13<5:01:04, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 520K Sep 2 06:17 shuffle-word-2300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9420/12318 [16:18:17<5:00:57, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9420/12318 [16:18:17<5:00:57, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-235-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9421/12318 [16:18:25<5:00:52, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9421/12318 [16:18:25<5:00:52, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-240-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9422/12318 [16:18:31<5:00:45, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9422/12318 [16:18:31<5:00:45, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 522K Sep 2 06:17 shuffle-word-2400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 76%|▊| 9423/12318 [16:18:34<5:00:38, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 76%|▊| 9423/12318 [16:18:34<5:00:38, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 28K Sep 2 06:17 shuffle-word-245-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9424/12318 [16:18:39<5:00:32, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9424/12318 [16:18:39<5:00:32, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 35K Sep 2 06:17 shuffle-word-25-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9425/12318 [16:18:48<5:00:26, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9425/12318 [16:18:48<5:00:26, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 26K Sep 2 06:17 shuffle-word-250-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9426/12318 [16:18:54<5:00:20, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9426/12318 [16:18:54<5:00:20, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 518K Sep 2 06:17 shuffle-word-2500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9427/12318 [16:18:59<5:00:13, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9427/12318 [16:18:59<5:00:13, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-255-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9428/12318 [16:19:07<5:00:08, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9428/12318 [16:19:07<5:00:08, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 28K Sep 2 06:17 shuffle-word-260-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9429/12318 [16:19:13<5:00:01, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9429/12318 [16:19:13<5:00:01, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 516K Sep 2 06:17 shuffle-word-2600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9430/12318 [16:19:21<4:59:56, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9430/12318 [16:19:21<4:59:56, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-265-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9431/12318 [16:19:29<4:59:50, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9431/12318 [16:19:29<4:59:50, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-270-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9432/12318 [16:19:34<4:59:43, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9432/12318 [16:19:34<4:59:43, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 510K Sep 2 06:17 shuffle-word-2700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9433/12318 [16:19:37<4:59:36, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9433/12318 [16:19:37<4:59:36, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-275-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9434/12318 [16:19:46<4:59:31, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9434/12318 [16:19:46<4:59:31, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-280-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9435/12318 [16:19:51<4:59:24, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9435/12318 [16:19:51<4:59:24, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 509K Sep 2 06:17 shuffle-word-2800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9436/12318 [16:19:56<4:59:17, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9436/12318 [16:19:56<4:59:17, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-285-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9437/12318 [16:20:00<4:59:11, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9437/12318 [16:20:00<4:59:11, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 26K Sep 2 06:17 shuffle-word-290-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9438/12318 [16:20:09<4:59:05, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9438/12318 [16:20:09<4:59:05, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 509K Sep 2 06:17 shuffle-word-2900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9439/12318 [16:20:16<4:58:59, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9439/12318 [16:20:16<4:58:59, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-295-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9440/12318 [16:20:33<4:58:56, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9440/12318 [16:20:33<4:58:56, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 34K Sep 2 06:17 shuffle-word-30-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9441/12318 [16:20:42<4:58:51, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9441/12318 [16:20:42<4:58:51, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 28K Sep 2 06:17 shuffle-word-300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9442/12318 [16:20:50<4:58:45, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9442/12318 [16:20:50<4:58:45, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 509K Sep 2 06:17 shuffle-word-3000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9443/12318 [16:20:56<4:58:39, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9443/12318 [16:20:56<4:58:39, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 28K Sep 2 06:17 shuffle-word-305-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9444/12318 [16:20:59<4:58:32, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9444/12318 [16:20:59<4:58:32, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-310-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9445/12318 [16:21:05<4:58:25, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9445/12318 [16:21:05<4:58:25, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 509K Sep 2 06:17 shuffle-word-3100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9446/12318 [16:21:12<4:58:19, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9446/12318 [16:21:12<4:58:19, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-315-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9447/12318 [16:21:18<4:58:13, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9447/12318 [16:21:18<4:58:13, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-320-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9448/12318 [16:21:24<4:58:07, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9448/12318 [16:21:24<4:58:07, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 509K Sep 2 06:17 shuffle-word-3200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9449/12318 [16:21:31<4:58:01, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9449/12318 [16:21:31<4:58:01, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 26K Sep 2 06:17 shuffle-word-325-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9450/12318 [16:21:38<4:57:55, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9450/12318 [16:21:38<4:57:55, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-330-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9451/12318 [16:21:47<4:57:49, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9451/12318 [16:21:47<4:57:49, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 508K Sep 2 06:17 shuffle-word-3300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9452/12318 [16:21:56<4:57:44, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9452/12318 [16:21:56<4:57:44, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 28K Sep 2 06:17 shuffle-word-335-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9453/12318 [16:22:02<4:57:38, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9453/12318 [16:22:02<4:57:38, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-340-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9454/12318 [16:22:07<4:57:31, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9454/12318 [16:22:07<4:57:31, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 509K Sep 2 06:17 shuffle-word-3400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9455/12318 [16:22:15<4:57:25, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9455/12318 [16:22:15<4:57:25, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-345-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9456/12318 [16:22:22<4:57:19, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9456/12318 [16:22:22<4:57:19, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 33K Sep 2 06:17 shuffle-word-35-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9457/12318 [16:22:29<4:57:13, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9457/12318 [16:22:29<4:57:13, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-350-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9458/12318 [16:22:34<4:57:07, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9458/12318 [16:22:34<4:57:07, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 509K Sep 2 06:17 shuffle-word-3500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9459/12318 [16:22:38<4:57:00, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9459/12318 [16:22:38<4:57:00, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-355-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9460/12318 [16:22:45<4:56:54, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9460/12318 [16:22:45<4:56:54, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-360-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9461/12318 [16:22:48<4:56:47, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9461/12318 [16:22:48<4:56:47, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 509K Sep 2 06:17 shuffle-word-3600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9462/12318 [16:22:52<4:56:40, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9462/12318 [16:22:52<4:56:40, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-365-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9463/12318 [16:22:55<4:56:32, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9463/12318 [16:22:55<4:56:32, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 26K Sep 2 06:17 shuffle-word-370-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9464/12318 [16:22:59<4:56:26, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9464/12318 [16:22:59<4:56:26, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 509K Sep 2 06:17 shuffle-word-3700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9465/12318 [16:23:01<4:56:18, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9465/12318 [16:23:01<4:56:18, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-375-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9466/12318 [16:23:10<4:56:13, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9466/12318 [16:23:10<4:56:13, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-380-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9467/12318 [16:23:19<4:56:07, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9467/12318 [16:23:19<4:56:07, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 509K Sep 2 06:17 shuffle-word-3800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9468/12318 [16:23:25<4:56:01, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9468/12318 [16:23:25<4:56:01, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-385-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9469/12318 [16:23:26<4:55:53, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9469/12318 [16:23:26<4:55:53, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-390-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9470/12318 [16:23:29<4:55:46, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9470/12318 [16:23:29<4:55:46, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 509K Sep 2 06:17 shuffle-word-3900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9471/12318 [16:23:31<4:55:38, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9471/12318 [16:23:31<4:55:38, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-395-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9472/12318 [16:23:56<4:55:38, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9472/12318 [16:23:56<4:55:38, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 32K Sep 2 06:17 shuffle-word-40-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9473/12318 [16:24:00<4:55:31, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9473/12318 [16:24:00<4:55:31, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 26K Sep 2 06:17 shuffle-word-400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9474/12318 [16:24:01<4:55:23, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9474/12318 [16:24:01<4:55:23, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 509K Sep 2 06:17 shuffle-word-4000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9475/12318 [16:24:02<4:55:15, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9475/12318 [16:24:02<4:55:15, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-405-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9476/12318 [16:24:10<4:55:10, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-410-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9476/12318 [16:24:10<4:55:10, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 509K Sep 2 06:17 shuffle-word-4100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9477/12318 [16:24:12<4:55:02, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9477/12318 [16:24:12<4:55:02, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 26K Sep 2 06:17 shuffle-word-415-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9478/12318 [16:24:15<4:54:55, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 26K Sep 2 06:17 shuffle-word-420-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9478/12318 [16:24:15<4:54:55, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 509K Sep 2 06:17 shuffle-word-4200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9479/12318 [16:24:19<4:54:48, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9479/12318 [16:24:19<4:54:48, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-425-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9480/12318 [16:24:27<4:54:43, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9480/12318 [16:24:27<4:54:43, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-430-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9481/12318 [16:24:33<4:54:36, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9481/12318 [16:24:33<4:54:36, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 509K Sep 2 06:17 shuffle-word-4300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9482/12318 [16:24:36<4:54:29, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9482/12318 [16:24:36<4:54:29, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 26K Sep 2 06:17 shuffle-word-435-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9483/12318 [16:24:44<4:54:23, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9483/12318 [16:24:44<4:54:23, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-440-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9484/12318 [16:24:53<4:54:18, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9484/12318 [16:24:53<4:54:18, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 509K Sep 2 06:17 shuffle-word-4400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9485/12318 [16:24:56<4:54:11, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9485/12318 [16:24:56<4:54:11, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 26K Sep 2 06:17 shuffle-word-445-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9486/12318 [16:24:57<4:54:03, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9486/12318 [16:24:57<4:54:03, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 33K Sep 2 06:17 shuffle-word-45-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9487/12318 [16:25:06<4:53:57, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9487/12318 [16:25:06<4:53:57, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-450-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9488/12318 [16:25:15<4:53:52, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9488/12318 [16:25:15<4:53:52, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 509K Sep 2 06:17 shuffle-word-4500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9489/12318 [16:25:23<4:53:46, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9489/12318 [16:25:23<4:53:46, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 28K Sep 2 06:17 shuffle-word-455-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9490/12318 [16:25:32<4:53:41, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9490/12318 [16:25:32<4:53:41, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-460-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9491/12318 [16:25:36<4:53:34, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9491/12318 [16:25:36<4:53:34, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 508K Sep 2 06:17 shuffle-word-4600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9492/12318 [16:25:43<4:53:28, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9492/12318 [16:25:43<4:53:28, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-465-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9493/12318 [16:25:46<4:53:21, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9493/12318 [16:25:46<4:53:21, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 28K Sep 2 06:17 shuffle-word-470-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9494/12318 [16:25:49<4:53:14, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9494/12318 [16:25:49<4:53:14, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 509K Sep 2 06:17 shuffle-word-4700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9495/12318 [16:25:52<4:53:07, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9495/12318 [16:25:52<4:53:07, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-475-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9496/12318 [16:25:57<4:53:00, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9496/12318 [16:25:57<4:53:00, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-480-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9497/12318 [16:26:06<4:52:54, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 509K Sep 2 06:17 shuffle-word-4800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9497/12318 [16:26:06<4:52:54, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 28K Sep 2 06:17 shuffle-word-485-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9498/12318 [16:26:13<4:52:48, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9498/12318 [16:26:13<4:52:48, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-490-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9499/12318 [16:26:22<4:52:43, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9499/12318 [16:26:22<4:52:43, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 509K Sep 2 06:17 shuffle-word-4900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9500/12318 [16:26:31<4:52:37, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9500/12318 [16:26:31<4:52:37, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-495-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9501/12318 [16:26:35<4:52:31, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9501/12318 [16:26:35<4:52:31, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 85K Sep 2 06:17 shuffle-word-5-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9502/12318 [16:26:39<4:52:24, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9502/12318 [16:26:39<4:52:24, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 32K Sep 2 06:17 shuffle-word-50-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9503/12318 [16:26:46<4:52:18, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9503/12318 [16:26:46<4:52:18, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9504/12318 [16:27:09<4:52:17, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9504/12318 [16:27:09<4:52:17, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 508K Sep 2 06:17 shuffle-word-5000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9505/12318 [16:27:15<4:52:10, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9505/12318 [16:27:15<4:52:10, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-505-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9506/12318 [16:27:20<4:52:04, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9506/12318 [16:27:20<4:52:04, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-510-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9507/12318 [16:27:27<4:51:58, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9507/12318 [16:27:27<4:51:58, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 509K Sep 2 06:17 shuffle-word-5100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9508/12318 [16:27:33<4:51:51, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9508/12318 [16:27:33<4:51:51, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-515-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9509/12318 [16:27:34<4:51:43, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9509/12318 [16:27:34<4:51:43, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 26K Sep 2 06:17 shuffle-word-520-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9510/12318 [16:27:41<4:51:37, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9510/12318 [16:27:41<4:51:37, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 509K Sep 2 06:17 shuffle-word-5200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9511/12318 [16:27:47<4:51:31, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9511/12318 [16:27:47<4:51:31, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 26K Sep 2 06:17 shuffle-word-525-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9512/12318 [16:27:51<4:51:24, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9512/12318 [16:27:51<4:51:24, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-530-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9513/12318 [16:27:55<4:51:18, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9513/12318 [16:27:55<4:51:18, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 509K Sep 2 06:17 shuffle-word-5300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9514/12318 [16:28:00<4:51:11, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9514/12318 [16:28:00<4:51:11, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-535-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9515/12318 [16:28:05<4:51:04, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9515/12318 [16:28:05<4:51:04, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-540-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9516/12318 [16:28:13<4:50:59, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9516/12318 [16:28:13<4:50:59, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 508K Sep 2 06:17 shuffle-word-5400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9517/12318 [16:28:21<4:50:53, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9517/12318 [16:28:21<4:50:53, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-545-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9518/12318 [16:28:22<4:50:45, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9518/12318 [16:28:22<4:50:45, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 31K Sep 2 06:17 shuffle-word-55-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9519/12318 [16:28:27<4:50:38, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9519/12318 [16:28:27<4:50:38, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-550-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9520/12318 [16:28:32<4:50:32, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9520/12318 [16:28:32<4:50:32, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 508K Sep 2 06:17 shuffle-word-5500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9521/12318 [16:28:39<4:50:26, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9521/12318 [16:28:39<4:50:26, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 28K Sep 2 06:17 shuffle-word-555-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9522/12318 [16:28:44<4:50:19, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9522/12318 [16:28:44<4:50:19, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 26K Sep 2 06:17 shuffle-word-560-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9523/12318 [16:28:48<4:50:12, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9523/12318 [16:28:48<4:50:12, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 509K Sep 2 06:17 shuffle-word-5600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9524/12318 [16:28:57<4:50:07, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9524/12318 [16:28:57<4:50:07, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-565-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9525/12318 [16:29:04<4:50:01, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9525/12318 [16:29:04<4:50:01, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-570-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9526/12318 [16:29:11<4:49:55, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9526/12318 [16:29:11<4:49:55, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 509K Sep 2 06:17 shuffle-word-5700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9527/12318 [16:29:12<4:49:47, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9527/12318 [16:29:12<4:49:47, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-575-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9528/12318 [16:29:16<4:49:40, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9528/12318 [16:29:16<4:49:40, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-580-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9529/12318 [16:29:25<4:49:35, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9529/12318 [16:29:25<4:49:35, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 509K Sep 2 06:17 shuffle-word-5800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9530/12318 [16:29:29<4:49:28, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9530/12318 [16:29:29<4:49:28, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 26K Sep 2 06:17 shuffle-word-585-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9531/12318 [16:29:33<4:49:21, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9531/12318 [16:29:33<4:49:21, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-590-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9532/12318 [16:29:34<4:49:14, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9532/12318 [16:29:34<4:49:14, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 509K Sep 2 06:17 shuffle-word-5900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9533/12318 [16:29:43<4:49:08, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9533/12318 [16:29:43<4:49:08, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 26K Sep 2 06:17 shuffle-word-595-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9534/12318 [16:29:48<4:49:01, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9534/12318 [16:29:48<4:49:01, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 30K Sep 2 06:17 shuffle-word-60-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9535/12318 [16:29:57<4:48:56, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9535/12318 [16:29:57<4:48:56, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9536/12318 [16:30:32<4:48:58, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9536/12318 [16:30:32<4:48:58, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 509K Sep 2 06:17 shuffle-word-6000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9537/12318 [16:30:40<4:48:52, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9537/12318 [16:30:40<4:48:52, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-605-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9538/12318 [16:30:43<4:48:45, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9538/12318 [16:30:43<4:48:45, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-610-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9539/12318 [16:30:48<4:48:39, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9539/12318 [16:30:48<4:48:39, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 509K Sep 2 06:17 shuffle-word-6100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9540/12318 [16:30:52<4:48:32, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9540/12318 [16:30:52<4:48:32, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-615-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9541/12318 [16:31:01<4:48:26, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9541/12318 [16:31:01<4:48:26, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-620-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9542/12318 [16:31:06<4:48:20, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9542/12318 [16:31:06<4:48:20, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 509K Sep 2 06:17 shuffle-word-6200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9543/12318 [16:31:11<4:48:13, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9543/12318 [16:31:11<4:48:13, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 26K Sep 2 06:17 shuffle-word-625-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9544/12318 [16:31:16<4:48:07, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9544/12318 [16:31:16<4:48:07, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-630-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9545/12318 [16:31:23<4:48:00, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9545/12318 [16:31:23<4:48:00, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 509K Sep 2 06:17 shuffle-word-6300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 77%|▊| 9546/12318 [16:31:25<4:47:53, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 77%|▊| 9546/12318 [16:31:25<4:47:53, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-635-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9547/12318 [16:31:32<4:47:47, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9547/12318 [16:31:32<4:47:47, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 26K Sep 2 06:17 shuffle-word-640-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9548/12318 [16:31:39<4:47:41, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9548/12318 [16:31:39<4:47:41, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 509K Sep 2 06:17 shuffle-word-6400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9549/12318 [16:31:44<4:47:35, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-645-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9549/12318 [16:31:44<4:47:35, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 31K Sep 2 06:17 shuffle-word-65-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9550/12318 [16:31:53<4:47:29, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9550/12318 [16:31:53<4:47:29, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-650-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9551/12318 [16:31:55<4:47:22, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9551/12318 [16:31:55<4:47:22, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 509K Sep 2 06:17 shuffle-word-6500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9552/12318 [16:32:03<4:47:16, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9552/12318 [16:32:03<4:47:16, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 26K Sep 2 06:17 shuffle-word-655-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9553/12318 [16:32:10<4:47:10, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9553/12318 [16:32:10<4:47:10, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 26K Sep 2 06:17 shuffle-word-660-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9554/12318 [16:32:15<4:47:03, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9554/12318 [16:32:15<4:47:03, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 508K Sep 2 06:17 shuffle-word-6600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9555/12318 [16:32:24<4:46:58, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9555/12318 [16:32:24<4:46:58, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-665-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9556/12318 [16:32:29<4:46:51, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9556/12318 [16:32:29<4:46:51, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-670-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9557/12318 [16:32:33<4:46:44, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9557/12318 [16:32:33<4:46:44, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 508K Sep 2 06:17 shuffle-word-6700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9558/12318 [16:32:42<4:46:39, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9558/12318 [16:32:42<4:46:39, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-675-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9559/12318 [16:32:49<4:46:33, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9559/12318 [16:32:49<4:46:33, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 26K Sep 2 06:17 shuffle-word-680-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9560/12318 [16:32:51<4:46:26, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9560/12318 [16:32:51<4:46:26, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 509K Sep 2 06:17 shuffle-word-6800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9561/12318 [16:32:56<4:46:19, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9561/12318 [16:32:56<4:46:19, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-685-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9562/12318 [16:33:02<4:46:13, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9562/12318 [16:33:02<4:46:13, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-690-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9563/12318 [16:33:10<4:46:07, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 509K Sep 2 06:17 shuffle-word-6900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9563/12318 [16:33:10<4:46:07, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-695-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9564/12318 [16:33:18<4:46:01, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9564/12318 [16:33:18<4:46:01, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 30K Sep 2 06:17 shuffle-word-70-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9565/12318 [16:33:19<4:45:53, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9565/12318 [16:33:19<4:45:53, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9566/12318 [16:33:28<4:45:48, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 508K Sep 2 06:17 shuffle-word-7000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9566/12318 [16:33:28<4:45:48, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-705-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9567/12318 [16:33:31<4:45:41, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9567/12318 [16:33:31<4:45:41, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 26K Sep 2 06:17 shuffle-word-710-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9568/12318 [16:34:03<4:45:42, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9568/12318 [16:34:03<4:45:42, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 509K Sep 2 06:17 shuffle-word-7100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9569/12318 [16:34:08<4:45:36, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9569/12318 [16:34:08<4:45:36, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 26K Sep 2 06:17 shuffle-word-715-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9570/12318 [16:34:10<4:45:28, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9570/12318 [16:34:10<4:45:28, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-720-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9571/12318 [16:34:18<4:45:22, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9571/12318 [16:34:18<4:45:22, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 509K Sep 2 06:17 shuffle-word-7200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9572/12318 [16:34:25<4:45:16, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9572/12318 [16:34:25<4:45:16, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 26K Sep 2 06:17 shuffle-word-725-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9573/12318 [16:34:27<4:45:09, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9573/12318 [16:34:27<4:45:09, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-730-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9574/12318 [16:34:29<4:45:01, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9574/12318 [16:34:29<4:45:01, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 509K Sep 2 06:17 shuffle-word-7300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9575/12318 [16:34:31<4:44:54, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9575/12318 [16:34:31<4:44:54, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 26K Sep 2 06:17 shuffle-word-735-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9576/12318 [16:34:34<4:44:47, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9576/12318 [16:34:34<4:44:47, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-740-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9577/12318 [16:34:41<4:44:41, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9577/12318 [16:34:41<4:44:41, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 508K Sep 2 06:17 shuffle-word-7400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9578/12318 [16:34:45<4:44:34, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9578/12318 [16:34:45<4:44:34, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 26K Sep 2 06:17 shuffle-word-745-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9579/12318 [16:34:51<4:44:28, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9579/12318 [16:34:51<4:44:28, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 29K Sep 2 06:17 shuffle-word-75-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9580/12318 [16:35:00<4:44:22, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9580/12318 [16:35:00<4:44:22, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 26K Sep 2 06:17 shuffle-word-750-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9581/12318 [16:35:07<4:44:16, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9581/12318 [16:35:07<4:44:16, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 509K Sep 2 06:17 shuffle-word-7500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9582/12318 [16:35:13<4:44:10, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9582/12318 [16:35:13<4:44:10, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-755-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9583/12318 [16:35:20<4:44:04, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9583/12318 [16:35:20<4:44:04, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 26K Sep 2 06:17 shuffle-word-760-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9584/12318 [16:35:27<4:43:58, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9584/12318 [16:35:27<4:43:58, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 509K Sep 2 06:17 shuffle-word-7600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9585/12318 [16:35:32<4:43:51, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 26K Sep 2 06:17 shuffle-word-765-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9585/12318 [16:35:32<4:43:51, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-770-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9586/12318 [16:35:40<4:43:45, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9586/12318 [16:35:40<4:43:45, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 509K Sep 2 06:17 shuffle-word-7700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9587/12318 [16:35:44<4:43:39, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9587/12318 [16:35:44<4:43:39, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 26K Sep 2 06:17 shuffle-word-775-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9588/12318 [16:35:51<4:43:33, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9588/12318 [16:35:51<4:43:33, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 26K Sep 2 06:17 shuffle-word-780-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9589/12318 [16:35:55<4:43:26, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9589/12318 [16:35:55<4:43:26, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 509K Sep 2 06:17 shuffle-word-7800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9590/12318 [16:35:59<4:43:19, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9590/12318 [16:35:59<4:43:19, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-785-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9591/12318 [16:36:06<4:43:13, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9591/12318 [16:36:06<4:43:13, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-790-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9592/12318 [16:36:13<4:43:07, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9592/12318 [16:36:13<4:43:07, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 509K Sep 2 06:17 shuffle-word-7900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9593/12318 [16:36:15<4:42:59, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9593/12318 [16:36:15<4:42:59, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-795-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9594/12318 [16:36:17<4:42:52, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9594/12318 [16:36:17<4:42:52, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 29K Sep 2 06:17 shuffle-word-80-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9595/12318 [16:36:22<4:42:46, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9595/12318 [16:36:22<4:42:46, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9596/12318 [16:36:26<4:42:39, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9596/12318 [16:36:26<4:42:39, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 509K Sep 2 06:17 shuffle-word-8000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9597/12318 [16:36:29<4:42:31, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9597/12318 [16:36:29<4:42:31, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 26K Sep 2 06:17 shuffle-word-805-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9598/12318 [16:36:35<4:42:25, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9598/12318 [16:36:35<4:42:25, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-810-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9599/12318 [16:36:41<4:42:19, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9599/12318 [16:36:41<4:42:19, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 26K Sep 2 06:17 shuffle-word-815-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9600/12318 [16:37:16<4:42:21, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9600/12318 [16:37:16<4:42:21, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-820-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9601/12318 [16:37:43<4:42:20, 6.24s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9601/12318 [16:37:43<4:42:20, 6.24s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-825-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9602/12318 [16:37:48<4:42:14, 6.24s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9602/12318 [16:37:48<4:42:14, 6.24s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-830-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9603/12318 [16:37:53<4:42:07, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9603/12318 [16:37:53<4:42:07, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-835-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9604/12318 [16:37:56<4:42:00, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9604/12318 [16:37:56<4:42:00, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 26K Sep 2 06:17 shuffle-word-840-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9605/12318 [16:38:00<4:41:53, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9605/12318 [16:38:00<4:41:53, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-845-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9606/12318 [16:38:05<4:41:47, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9606/12318 [16:38:05<4:41:47, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 29K Sep 2 06:17 shuffle-word-85-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9607/12318 [16:38:11<4:41:40, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9607/12318 [16:38:11<4:41:40, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 28K Sep 2 06:17 shuffle-word-850-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9608/12318 [16:38:19<4:41:34, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9608/12318 [16:38:19<4:41:34, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-855-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9609/12318 [16:38:27<4:41:29, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9609/12318 [16:38:27<4:41:29, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 26K Sep 2 06:17 shuffle-word-860-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9610/12318 [16:38:31<4:41:22, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9610/12318 [16:38:31<4:41:22, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 26K Sep 2 06:17 shuffle-word-865-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9611/12318 [16:38:37<4:41:16, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9611/12318 [16:38:37<4:41:16, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 26K Sep 2 06:17 shuffle-word-870-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9612/12318 [16:38:42<4:41:09, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9612/12318 [16:38:42<4:41:09, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-875-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9613/12318 [16:38:48<4:41:03, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9613/12318 [16:38:48<4:41:03, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 26K Sep 2 06:17 shuffle-word-880-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9614/12318 [16:38:54<4:40:56, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9614/12318 [16:38:54<4:40:56, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-885-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9615/12318 [16:38:59<4:40:50, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9615/12318 [16:38:59<4:40:50, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-890-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9616/12318 [16:39:08<4:40:44, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9616/12318 [16:39:08<4:40:44, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-895-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9617/12318 [16:39:11<4:40:37, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9617/12318 [16:39:11<4:40:37, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 29K Sep 2 06:17 shuffle-word-90-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9618/12318 [16:39:16<4:40:31, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9618/12318 [16:39:16<4:40:31, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9619/12318 [16:39:20<4:40:24, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9619/12318 [16:39:20<4:40:24, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-905-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9620/12318 [16:39:27<4:40:18, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9620/12318 [16:39:27<4:40:18, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-910-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9621/12318 [16:39:35<4:40:12, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9621/12318 [16:39:35<4:40:12, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-915-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9622/12318 [16:39:40<4:40:06, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9622/12318 [16:39:40<4:40:06, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 26K Sep 2 06:17 shuffle-word-920-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9623/12318 [16:39:45<4:39:59, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9623/12318 [16:39:45<4:39:59, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-925-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9624/12318 [16:39:47<4:39:51, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-930-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9624/12318 [16:39:47<4:39:51, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 26K Sep 2 06:17 shuffle-word-935-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9625/12318 [16:39:52<4:39:45, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9625/12318 [16:39:52<4:39:45, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 26K Sep 2 06:17 shuffle-word-940-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9626/12318 [16:39:56<4:39:38, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9626/12318 [16:39:56<4:39:38, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 26K Sep 2 06:17 shuffle-word-945-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9627/12318 [16:40:05<4:39:33, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9627/12318 [16:40:05<4:39:33, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-95-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9628/12318 [16:40:13<4:39:27, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9628/12318 [16:40:13<4:39:27, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 26K Sep 2 06:17 shuffle-word-950-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9629/12318 [16:40:14<4:39:19, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9629/12318 [16:40:14<4:39:19, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-955-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9630/12318 [16:40:22<4:39:13, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9630/12318 [16:40:22<4:39:13, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-960-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9631/12318 [16:40:28<4:39:07, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9631/12318 [16:40:28<4:39:07, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-965-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9632/12318 [16:40:55<4:39:07, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9632/12318 [16:40:55<4:39:07, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 26K Sep 2 06:17 shuffle-word-970-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9633/12318 [16:40:58<4:39:00, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9633/12318 [16:40:58<4:39:00, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-975-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9634/12318 [16:41:02<4:38:53, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-980-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9634/12318 [16:41:02<4:38:53, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 26K Sep 2 06:17 shuffle-word-985-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9635/12318 [16:41:06<4:38:46, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9635/12318 [16:41:06<4:38:46, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 26K Sep 2 06:17 shuffle-word-990-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9636/12318 [16:41:07<4:38:38, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9636/12318 [16:41:07<4:38:38, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 27K Sep 2 06:17 shuffle-word-995-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9637/12318 [16:41:12<4:38:31, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9637/12318 [16:41:12<4:38:31, 6.23s/it, v_num=e4xv, train/loss" + "-rw-r--r-- 1 root root 6.0K Sep 2 06:17 word-2-count.jsonl\n" ] + } + ], + "source": [ + "%%script bash\n", + "\n", + "########################################\n", + "# Generate the required jsonl dataset\n", + "########################################\n", + "\n", + "# Reset the dataset dir\n", + "mkdir -p ../dataset\n", + "rm -rf ../dataset/*.jsonl\n", + "\n", + "# Generate the various datasets\n", + "echo \"## Generating word reptition dataset ##\"\n", + "\n", + "#\n", + "# We reduce the training set for < 50 words - and shift the focus upwards\n", + "# (aka 50-100 token * 2 : ~100 - 250 token ctx len)\n", + "#\n", + "python ../memory_script/gen_limited_prompt_completion_jsonl.py ../dataset/word-2-count.jsonl 2 50 &\n", + "for i in {5..1000..5} \n", + "do\n", + " python ../memory_script/gen_limited_prompt_completion_jsonl.py ../dataset/gen-word-$i-count.jsonl $i 50 & \n", + " python ../memory_script/shuffle_limited_prompt_completion_jsonl.py ../dataset/shuffle-word-$i-count.jsonl $i 1 & \n", + "done\n", + "\n", + "#\n", + "# Ramping up the 50+ - 4200 words dataset\n", + "# \n", + "for i in {1100..8000..100} \n", + "do\n", + " python ../memory_script/gen_limited_prompt_completion_jsonl.py ../dataset/gen-word-$i-count.jsonl $i 2000 & \n", + " python ../memory_script/shuffle_limited_prompt_completion_jsonl.py ../dataset/shuffle-word-$i-count.jsonl $i 20 & \n", + "done\n", + "\n", + "wait\n", + "echo \"## Done ##\"\n", + "\n", + "ls -lh ../dataset/" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "id": "2eb840b5", + "metadata": { + "execution": { + "iopub.execute_input": "2023-09-02T06:17:49.255288Z", + "iopub.status.busy": "2023-09-02T06:17:49.254615Z" + }, + "papermill": { + "duration": null, + "end_time": null, + "exception": false, + "start_time": "2023-09-02T06:17:49.184772", + "status": "running" }, + "tags": [] + }, + "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9638/12318 [16:41:19<4:38:26, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9638/12318 [16:41:19<4:38:26, 6.23s/it, v_num=e4xv, train/loss" + "Setting ds_accelerator to cuda (auto detect)\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9639/12318 [16:41:26<4:38:19, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9639/12318 [16:41:26<4:38:19, 6.23s/it, v_num=e4xv, train/loss" + "[RWKV.model] Running RWKV model using 'torch-jit' with torch '2.0.1+cu118'\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9640/12318 [16:41:33<4:38:14, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9640/12318 [16:41:33<4:38:14, 6.23s/it, v_num=e4xv, train/loss" + "/usr/local/lib/python3.11/dist-packages/lightning/pytorch/cli.py:484: UserWarning: LightningCLI's args parameter is intended to run from within Python like if it were from the command line. To prevent mistakes it is not recommended to provide both args and command line arguments, got: sys.argv[1:]=['fit', '-c', '/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/notebook/experiment/rwkv-x-exp/v5-memory/config-mem-template.yaml', '--trainer.logger.init_args.name=v5-L96-D1024-E0.1 - Mem-Tune ctx-8k (train-ctx=4k, deepspeed_stage_1)', '--trainer.strategy=deepspeed_stage_1', '--trainer.devices=auto', '--trainer.callbacks.init_args.dirpath=../checkpoint/v5-L96-D1024-E0_1-mem-ctx-8k/', '--model.lr_init=3e-4', '--model.lr_final=1e-4', '--data.max_token_size=8192', '--model.ctx_len=4096', '--model.bptt_learning_range=2', '--model.load_model=../model/v5-L96-D1024-E0_1-mem-ctx-4k.pth'], args=['fit', '-c', '/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/notebook/experiment/rwkv-x-exp/v5-memory/config-mem-template.yaml', '--trainer.logger.init_args.name=v5-L96-D1024-E0.1 - Mem-Tune ctx-8k (train-ctx=4k, deepspeed_stage_1)', '--trainer.strategy=deepspeed_stage_1', '--trainer.devices=auto', '--trainer.callbacks.init_args.dirpath=../checkpoint/v5-L96-D1024-E0_1-mem-ctx-8k/', '--model.lr_init=3e-4', '--model.lr_final=1e-4', '--data.max_token_size=8192', '--model.ctx_len=4096', '--model.bptt_learning_range=2', '--model.load_model=../model/v5-L96-D1024-E0_1-mem-ctx-4k.pth'].\r\n", + " rank_zero_warn(\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9641/12318 [16:41:40<4:38:07, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9641/12318 [16:41:40<4:38:07, 6.23s/it, v_num=e4xv, train/loss" + "/usr/local/lib/python3.11/dist-packages/lightning/fabric/utilities/seed.py:39: UserWarning: No seed found, seed set to 4016710040\r\n", + " rank_zero_warn(f\"No seed found, seed set to {seed}\")\r\n", + "Global seed set to 4016710040\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9642/12318 [16:41:45<4:38:01, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9642/12318 [16:41:45<4:38:01, 6.23s/it, v_num=e4xv, train/loss" + "\u001b[34m\u001b[1mwandb\u001b[0m: Currently logged in as: \u001b[33mpicocreator\u001b[0m (\u001b[33mrwkv-x-dev\u001b[0m). Use \u001b[1m`wandb login --relogin`\u001b[0m to force relogin\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9643/12318 [16:41:47<4:37:54, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9643/12318 [16:41:47<4:37:54, 6.23s/it, v_num=e4xv, train/loss" + "\u001b[34m\u001b[1mwandb\u001b[0m: Tracking run with wandb version 0.15.9\r\n", + "\u001b[34m\u001b[1mwandb\u001b[0m: Run data is saved locally in \u001b[35m\u001b[1m./wandb/run-20230902_061755-f2kzi2o7\u001b[0m\r\n", + "\u001b[34m\u001b[1mwandb\u001b[0m: Run \u001b[1m`wandb offline`\u001b[0m to turn off syncing.\r\n", + "\u001b[34m\u001b[1mwandb\u001b[0m: Syncing run \u001b[33mv5-L96-D1024-E0.1 - Mem-Tune ctx-8k (train-ctx=4k, deepspeed_stage_1)\u001b[0m\r\n", + "\u001b[34m\u001b[1mwandb\u001b[0m: ⭐️ View project at \u001b[34m\u001b[4mhttps://wandb.ai/rwkv-x-dev/RWKV-X-Experiments\u001b[0m\r\n", + "\u001b[34m\u001b[1mwandb\u001b[0m: 🚀 View run at \u001b[34m\u001b[4mhttps://wandb.ai/rwkv-x-dev/RWKV-X-Experiments/runs/f2kzi2o7\u001b[0m\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 78%|▊| 9644/12318 [16:41:55<4:37:48, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9644/12318 [16:41:55<4:37:48, 6.23s/it, v_num=e4xv, train/loss" + "/usr/local/lib/python3.11/dist-packages/lightning/fabric/connector.py:562: UserWarning: bf16 is supported for historical reasons but its usage is discouraged. Please set your precision to bf16-mixed instead!\r\n", + " rank_zero_warn(\r\n", + "GPU available: True (cuda), used: True\r\n", + "TPU available: False, using: 0 TPU cores\r\n", + "IPU available: False, using: 0 IPUs\r\n", + "HPU available: False, using: 0 HPUs\r\n", + "\r\n", + "\r\n", + "[RWKV.Trainer] Applying 'target_batch_size' with the following:\r\n", + " - target_batch_size: 256\r\n", + " - num_nodes: 1\r\n", + " - num_devices: 8\r\n", + " - accumulate_grad_batches: 32\r\n", + " - effective_batch_size: 256\r\n", + "\r\n" ] }, { @@ -112807,17 +10645,20 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 78%|▊| 9645/12318 [16:41:59<4:37:41, 6.23s/it, v_num=e4xv, train/loss\r", - "Epoch 0: 78%|▊| 9645/12318 [16:41:59<4:37:41, 6.23s/it, v_num=e4xv, train/loss" + "Resolving data files: 0%| | 0/541 [00:00=12.1), as this is known to have freeze issues\r\n", + "# - The terms used in wandb / the progress bar can be confusing, see the github README.md for beter clarifications\r\n", + "# - When resuming from checkpoint, the estimated time is inaccurate\r\n", + "#\r\n", + "\r\n", + "[RWKV.model] Configuring optimizer with\r\n", + " - lr_init: 3.000e-04 (0.0003)\r\n", + " - lr_final: 1.000e-04 (0.0001)\r\n", + "\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 93%|▉| 11453/12318 [19:50:12<1:29:53, 6.24s/it, v_num=e4xv, train/los\r", - "Epoch 0: 93%|▉| 11453/12318 [19:50:12<1:29:53, 6.24s/it, v_num=e4xv, train/los" + "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", + "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", + "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", + "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", + "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", + "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", + "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", + "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", + "Detected CUDA files, patching ldflags\r\n", + "Emitting ninja build file /root/.cache/torch_extensions/py311_cu118/fused_adam/build.ninja...\r\n", + "Building extension module fused_adam...\r\n", + "Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 93%|▉| 11454/12318 [19:50:15<1:29:47, 6.24s/it, v_num=e4xv, train/los\r", - "Epoch 0: 93%|▉| 11454/12318 [19:50:15<1:29:47, 6.24s/it, v_num=e4xv, train/los" + "ninja: no work to do.\r\n", + "Loading extension module fused_adam...\r\n", + "Time to load fused_adam op: 0.06581354141235352 seconds\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 93%|▉| 11455/12318 [19:50:21<1:29:40, 6.23s/it, v_num=e4xv, train/los\r", - "Epoch 0: 93%|▉| 11455/12318 [19:50:21<1:29:40, 6.23s/it, v_num=e4xv, train/los" + "Loading extension module fused_adam...\r\n", + "Time to load fused_adam op: 0.10160326957702637 seconds\r\n", + "Loading extension module fused_adam...\r\n", + "Loading extension module fused_adam...\r\n", + "Loading extension module fused_adam...\r\n", + "Loading extension module fused_adam...\r\n", + "Time to load fused_adam op: 0.10122323036193848 seconds\r\n", + "Time to load fused_adam op: 0.10131621360778809 seconds\r\n", + "Time to load fused_adam op: 0.10161590576171875 seconds\r\n", + "Time to load fused_adam op: 0.10172796249389648 seconds\r\n", + "Loading extension module fused_adam...\r\n", + "Time to load fused_adam op: 0.10164880752563477 seconds\r\n", + "Loading `train_dataloader` to estimate number of stepping batches.\r\n", + "Loading extension module fused_adam...\r\n", + "Time to load fused_adam op: 0.10137581825256348 seconds\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 93%|▉| 11456/12318 [19:51:00<1:29:36, 6.24s/it, v_num=e4xv, train/los\r", - "Epoch 0: 93%|▉| 11456/12318 [19:51:00<1:29:36, 6.24s/it, v_num=e4xv, train/los" + "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", + "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 93%|▉| 11457/12318 [19:51:05<1:29:30, 6.24s/it, v_num=e4xv, train/los\r", - "Epoch 0: 93%|▉| 11457/12318 [19:51:05<1:29:30, 6.24s/it, v_num=e4xv, train/los" + "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", + "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", + "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", + "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", + "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", + "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", + "Emitting ninja build file /root/.cache/torch_extensions/py311_cu118/utils/build.ninja...\r\n", + "Building extension module utils...\r\n", + "Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 93%|▉| 11458/12318 [19:51:07<1:29:24, 6.24s/it, v_num=e4xv, train/los\r", - "Epoch 0: 93%|▉| 11458/12318 [19:51:07<1:29:24, 6.24s/it, v_num=e4xv, train/los" + "ninja: no work to do.\r\n", + "Loading extension module utils...\r\n", + "Time to load utils op: 0.0746297836303711 seconds\r\n", + "Loading extension module utils...\r\n", + "Time to load utils op: 0.10225343704223633 seconds\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 93%|▉| 11459/12318 [19:51:09<1:29:17, 6.24s/it, v_num=e4xv, train/los" + "Loading extension module utils...\r\n", + "Loading extension module utils...\r\n", + "Time to load utils op: 0.1022336483001709 seconds\r\n", + "Time to load utils op: 0.10247349739074707 seconds\r\n", + "Loading extension module utils...\r\n", + "Loading extension module utils...\r\n", + "Time to load utils op: 0.1032721996307373 seconds\r\n", + "Time to load utils op: 0.10237407684326172 seconds\r\n", + "Loading extension module utils...\r\n", + "Time to load utils op: 0.10254526138305664 seconds\r\n", + "Loading extension module utils...\r\n", + "Time to load utils op: 0.10282373428344727 seconds\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 93%|▉| 11459/12318 [19:51:09<1:29:17, 6.24s/it, v_num=e4xv, train/los" + "Rank: 5 partition count [8, 8] and sizes[(176584448, False), (384, False)] \r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 93%|▉| 11460/12318 [19:51:10<1:29:10, 6.24s/it, v_num=e4xv, train/los\r", - "Epoch 0: 93%|▉| 11460/12318 [19:51:10<1:29:10, 6.24s/it, v_num=e4xv, train/los" + "Rank: 1 partition count [8, 8] and sizes[(176584448, False), (384, False)] " ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 93%|▉| 11461/12318 [19:51:14<1:29:04, 6.24s/it, v_num=e4xv, train/los\r", - "Epoch 0: 93%|▉| 11461/12318 [19:51:14<1:29:04, 6.24s/it, v_num=e4xv, train/los" + "\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 93%|▉| 11462/12318 [19:51:20<1:28:58, 6.24s/it, v_num=e4xv, train/los" + "Rank: 2 partition count [8, 8] and sizes[(176584448, False), (384, False)] \r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 93%|▉| 11462/12318 [19:51:20<1:28:58, 6.24s/it, v_num=e4xv, train/los" + "Rank: 4 partition count [8, 8] and sizes[(176584448, False), (384, False)] \r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 93%|▉| 11463/12318 [19:51:29<1:28:52, 6.24s/it, v_num=e4xv, train/los\r", - "Epoch 0: 93%|▉| 11463/12318 [19:51:29<1:28:52, 6.24s/it, v_num=e4xv, train/los" + "Rank: 7 partition count [8, 8] and sizes[(176584448, False), (384, False)] \r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 93%|▉| 11464/12318 [19:51:37<1:28:46, 6.24s/it, v_num=e4xv, train/los\r", - "Epoch 0: 93%|▉| 11464/12318 [19:51:37<1:28:46, 6.24s/it, v_num=e4xv, train/los" + "Rank: 0 partition count [8, 8] and sizes[(176584448, False), (384, False)] \r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 93%|▉| 11465/12318 [19:51:43<1:28:39, 6.24s/it, v_num=e4xv, train/los\r", - "Epoch 0: 93%|▉| 11465/12318 [19:51:43<1:28:39, 6.24s/it, v_num=e4xv, train/los" + "Rank: 3 partition count [8, 8] and sizes[(176584448, False), (384, False)] \r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 93%|▉| 11466/12318 [19:51:51<1:28:33, 6.24s/it, v_num=e4xv, train/los\r", - "Epoch 0: 93%|▉| 11466/12318 [19:51:51<1:28:33, 6.24s/it, v_num=e4xv, train/los" + "Rank: 6 partition count [8, 8] and sizes[(176584448, False), (384, False)] \r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 93%|▉| 11467/12318 [19:51:59<1:28:27, 6.24s/it, v_num=e4xv, train/los\r", - "Epoch 0: 93%|▉| 11467/12318 [19:51:59<1:28:27, 6.24s/it, v_num=e4xv, train/los" + "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", + "No modifications detected for re-loaded extension module utils, skipping build step...\r\n", + "Loading extension module utils...\r\n", + "Time to load utils op: 0.0006437301635742188 seconds\r\n", + "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", + "No modifications detected for re-loaded extension module utils, skipping build step...\r\n", + "Loading extension module utils...\r\n", + "Time to load utils op: 0.0009703636169433594 seconds\r\n", + "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", + "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", + "No modifications detected for re-loaded extension module utils, skipping build step...\r\n", + "Loading extension module utils...\r\n", + "Time to load utils op: 0.0006546974182128906 seconds\r\n", + "No modifications detected for re-loaded extension module utils, skipping build step...\r\n", + "Loading extension module utils...\r\n", + "Time to load utils op: 0.0006368160247802734 seconds\r\n", + "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", + "No modifications detected for re-loaded extension module utils, skipping build step...\r\n", + "Loading extension module utils...\r\n", + "Time to load utils op: 0.0006356239318847656 seconds\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 93%|▉| 11468/12318 [19:52:00<1:28:21, 6.24s/it, v_num=e4xv, train/los\r", - "Epoch 0: 93%|▉| 11468/12318 [19:52:00<1:28:21, 6.24s/it, v_num=e4xv, train/los" + "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", + "No modifications detected for re-loaded extension module utils, skipping build step...\r\n", + "Loading extension module utils...\r\n", + "Time to load utils op: 0.0006177425384521484 seconds\r\n", + "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", + "No modifications detected for re-loaded extension module utils, skipping build step...\r\n", + "Loading extension module utils...\r\n", + "Time to load utils op: 0.0008919239044189453 seconds\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 93%|▉| 11469/12318 [19:52:06<1:28:14, 6.24s/it, v_num=e4xv, train/los\r", - "Epoch 0: 93%|▉| 11469/12318 [19:52:06<1:28:14, 6.24s/it, v_num=e4xv, train/los" + "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", + "No modifications detected for re-loaded extension module utils, skipping build step...\r\n", + "Loading extension module utils...\r\n", + "Time to load utils op: 0.0009381771087646484 seconds\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\r", - "Epoch 0: 93%|▉| 11470/12318 [19:52:09<1:28:08, 6.24s/it, v_num=e4xv, train/los\r", - "Epoch 0: 93%|▉| 11470/12318 [19:52:09<1:28:08, 6.24s/it, v_num=e4xv, train/los" + "\r\n", + " | Name | Type | Params\r\n", + "--------------------------------------\r\n", + "0 | emb | Embedding | 51.5 M\r\n", + "1 | blocks | ModuleList | 1.3 B \r\n", + "2 | ln_out | LayerNorm | 2.0 K \r\n", + "3 | head | Linear | 51.5 M\r\n", + "--------------------------------------\r\n", + "1.4 B Trainable params\r\n", + "0 Non-trainable params\r\n", + "1.4 B Total params\r\n", + "5,650.715 Total estimated model params size (MB)\r\n" ] }, { @@ -129703,8 +25780,9 @@ "output_type": "stream", "text": [ "\r", - "Epoch 0: 93%|▉| 11471/12318 [19:52:16<1:28:02, 6.24s/it, v_num=e4xv, train/los\r", - "Epoch 0: 93%|▉| 11471/12318 [19:52:16<1:28:02, 6.24s/it, v_num=e4xv, train/los" + "Training: 0it [00:00, ?it/s]\r", + "Training: 0%| | 0/12323 [00:00