[WIP] [GHA] experiment/rwkv-x-exp/v5-r3-memory/L12-D2048-E1e-1-ctx4k/part2.ipynb result model (multi-commit 77d8f6e110298a43a64351da3b8f52fc7a8b971c2d391337a6ca419cc5b11782)

.gitattributes

@@ -86,22 +86,3 @@ experiment/memory-bench/logs/v5-L6-D1024-E0_1-4k.csv filter=lfs diff=lfs merge=l
 experiment/memory-bench/logs/v5-L6-D1024-E0_1-16k.csv filter=lfs diff=lfs merge=lfs -text
 experiment/rwkv-x-exp/v5-r3-memory/L12-D2048-E1e-1-ctx4k/part1.ipynb filter=lfs diff=lfs merge=lfs -text
 experiment/rwkv-x-exp/v5-r3-memory/L6-D2048-E1e-1-ctx4k/part1.ipynb filter=lfs diff=lfs merge=lfs -text
-experiment/rwkv-x-exp/v5-r3-memory/L6-D2048-E1e-1-ctx4k/part2.ipynb filter=lfs diff=lfs merge=lfs -text
-experiment/rwkv-x-exp/v5-r3-memory/L12-D2048-E1e-1-ctx4k/part2.ipynb filter=lfs diff=lfs merge=lfs -text
-experiment/rwkv-x-exp/v5-r3-memory/L6-D2560-E1e-1-ctx4k/part1.ipynb filter=lfs diff=lfs merge=lfs -text
-experiment/rwkv-x-exp/v5-r3-memory/L6-D2560-E1e-1-ctx4k/stage2.ipynb filter=lfs diff=lfs merge=lfs -text
-experiment/rwkv-x-exp/v5-r3-memory/L6-D2048-E1e-1-ctx4k/stage2.ipynb filter=lfs diff=lfs merge=lfs -text
-experiment/rwkv-x-exp/v5-r3-memory/L6-D2560-E1e-1-ctx4k/stage3.ipynb filter=lfs diff=lfs merge=lfs -text
-experiment/rwkv-x-exp/v5-r3-memory/L6-D2048-E1e-1-ctx4k/stage3.ipynb filter=lfs diff=lfs merge=lfs -text
-experiment/rwkv-x-exp/v5-r3-memory/L6-D2560-E1e-1-ctx4k/stage4.ipynb filter=lfs diff=lfs merge=lfs -text
-experiment/rwkv-x-exp/v5-r3-memory/L6-D2048-E1e-1-ctx4k/stage4.ipynb filter=lfs diff=lfs merge=lfs -text
-experiment/rwkv-x-exp/v5-r3-memory/L6-D2560-E1e-1-ctx4k/stage5.ipynb filter=lfs diff=lfs merge=lfs -text
-experiment/rwkv-x-exp/v5-r3-memory/L6-D2048-E1e-1-ctx4k/stage5.ipynb filter=lfs diff=lfs merge=lfs -text
-experiment/rwkv-x-exp/multi-size-train/v5-L6-D2048-part1.ipynb filter=lfs diff=lfs merge=lfs -text
-experiment/rwkv-x-exp/multi-size-train/v5-L6-D2048-baseline.ipynb filter=lfs diff=lfs merge=lfs -text
-experiment/rwkv-x-exp/multi-size-train/v5-L12-D2048-part1.ipynb filter=lfs diff=lfs merge=lfs -text
-experiment/rwkv-x-exp/multi-size-train/v5-L12-D2048-baseline.ipynb filter=lfs diff=lfs merge=lfs -text
-experiment/rwkv-x-exp/multi-size-train/v5-L6+6-D2048-overwrite-naive.ipynb filter=lfs diff=lfs merge=lfs -text
-experiment/rwkv-x-exp/multi-size-train/v5-L6-D2048-split-train.ipynb filter=lfs diff=lfs merge=lfs -text
-experiment/rwkv-x-exp/multi-size-train/v5-L6+6-D2048-layer-expansion.ipynb filter=lfs diff=lfs merge=lfs -text
-experiment/rwkv-x-exp/multi-size-train/v5-L6-D2048-split-baseline.ipynb filter=lfs diff=lfs merge=lfs -text

experiment/rwkv-x-exp/multi-size-train/v5-L12-D2048-E0_01-baseline-p2.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c447bfd1844d0c3e536fb8824d029fd8b0e334e1368f807a4e85cd7099005130
-size 1721187285

experiment/rwkv-x-exp/multi-size-train/v5-L12-D2048-E0_01-baseline-p3.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:70b243f59685c4df841f16343bc7ff6947a3125cec5dabf9035b28b65c04da0e
-size 1721187285

experiment/rwkv-x-exp/multi-size-train/v5-L12-D2048-E0_01-enwiki-4k-p1.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a57c278ed7e7e2f9d7f0436540674bfa5178adcd04c3154f5d92992e0602c55b
-size 1721187621

experiment/rwkv-x-exp/multi-size-train/v5-L12-D2048-E0_01-neox-v5base-init.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:06105d96413046fce0ec189b9c4685a813cfa7147300851c5d2afc7b5adbcb38
-size 1721189797

experiment/rwkv-x-exp/multi-size-train/v5-L12-D2048-baseline.ipynb

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:31f61ce42e82d9a475446458ed015a190f16dd9b2b17bd67f4feedd9f72750ad
-size 16577145

experiment/rwkv-x-exp/multi-size-train/v5-L12-D2048-part1.ipynb

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b53c27ed2c20b9f1f690647a83c0fbe2ce09594518b9ec557f515a4f8b548f2b
-size 15941299

experiment/rwkv-x-exp/multi-size-train/v5-L6+6-D2048-E0_01-baseline-p3.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c380bcd4b861a8af263fd56dc6e183b9e06ba0bc8f9895c4dcd8a678b58296e8
-size 1721187621

experiment/rwkv-x-exp/multi-size-train/v5-L6+6-D2048-E0_01-layer-expansion-p1.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:89f8caf661887bdba1897a10009f033331c552bfb763112e6da1b850d8ec3ff7
-size 1721189525

experiment/rwkv-x-exp/multi-size-train/v5-L6+6-D2048-E0_01-layer-expansion-p2.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2680e091197e798686c97bdd2af0f6827f2b29c648cc1ae03f67d6f094859618
-size 1721189525

experiment/rwkv-x-exp/multi-size-train/v5-L6+6-D2048-E0_01-overwrite-naive-p1.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:35a5d7571d90160edc20ce95abfdbcb6109ad47eccdefe8051bd8f15d12bf326
-size 1721189525

experiment/rwkv-x-exp/multi-size-train/v5-L6+6-D2048-E0_01-overwrite-naive-p2.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f6b50bf05f191da87a6a17072d485d4059a4ded1335605e6b7bb8e9f2648d966
-size 1721189525

experiment/rwkv-x-exp/multi-size-train/v5-L6+6-D2048-layer-baseline.ipynb

@@ -1,2461 +0,0 @@
-{
- "cells": [
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "id": "d3126ef2",
-   "metadata": {
-    "papermill": {
-     "duration": 0.004879,
-     "end_time": "2023-10-11T08:02:23.608034",
-     "exception": false,
-     "start_time": "2023-10-11T08:02:23.603155",
-     "status": "completed"
-    },
-    "tags": []
-   },
-   "source": [
-    "# RWKV v5 multi-size training experiment\n",
-    "\n",
-    "**Note:** This project assumes you have the rwkv-infctx conda env setup"
-   ]
-  },
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "id": "986070aa",
-   "metadata": {
-    "papermill": {
-     "duration": 0.002523,
-     "end_time": "2023-10-11T08:02:23.613605",
-     "exception": false,
-     "start_time": "2023-10-11T08:02:23.611082",
-     "status": "completed"
-    },
-    "tags": []
-   },
-   "source": [
-    "# Basic Setup"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "dc924c7f",
-   "metadata": {
-    "execution": {
-     "iopub.execute_input": "2023-10-11T08:02:23.620990Z",
-     "iopub.status.busy": "2023-10-11T08:02:23.620432Z",
-     "iopub.status.idle": "2023-10-11T08:02:24.379549Z",
-     "shell.execute_reply": "2023-10-11T08:02:24.378580Z"
-    },
-    "papermill": {
-     "duration": 0.765369,
-     "end_time": "2023-10-11T08:02:24.381741",
-     "exception": false,
-     "start_time": "2023-10-11T08:02:23.616372",
-     "status": "completed"
-    },
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "# First lets setup the various directories, and init the model\n",
-    "!mkdir -p ../../../../model/\n",
-    "!mkdir -p ../../../../datapath/\n",
-    "!mkdir -p ../../../../checkpoint/"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "2bbc32ac",
-   "metadata": {
-    "execution": {
-     "iopub.execute_input": "2023-10-11T08:02:24.389788Z",
-     "iopub.status.busy": "2023-10-11T08:02:24.389227Z",
-     "iopub.status.idle": "2023-10-11T08:02:24.398441Z",
-     "shell.execute_reply": "2023-10-11T08:02:24.397578Z"
-    },
-    "papermill": {
-     "duration": 0.015548,
-     "end_time": "2023-10-11T08:02:24.400362",
-     "exception": false,
-     "start_time": "2023-10-11T08:02:24.384814",
-     "status": "completed"
-    },
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "DEEPSPEED_STRAT: deepspeed_stage_2_offload\n",
-      "ENABLE_WANDB: True\n",
-      "GPU_DEVICES: auto\n",
-      "NOTEBOOK_DIR: /actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/notebook/experiment/rwkv-x-exp/multi-size-train\n",
-      "INFERENCE_DIR: /actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/RWKV-v5\n",
-      "TRAINER_DIR: /actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/RWKV-v5\n",
-      "PROJECT_DIR: /actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer\n"
-     ]
-    }
-   ],
-   "source": [
-    "DEEPSPEED_STRAT=\"deepspeed_stage_2_offload\"\n",
-    "GPU_DEVICES=\"auto\"\n",
-    "ENABLE_WANDB=True\n",
-    "\n",
-    "EMBED_SCALE=0.01\n",
-    "EMBED_SCALE_LABEL=str(EMBED_SCALE).replace(\".\", \"_\")\n",
-    "\n",
-    "EMBED_SIZE=2048\n",
-    "\n",
-    "WANDB_PREFIX=f\"[Multi-size] v5-L6+6-D{EMBED_SIZE}-E{EMBED_SCALE}\"\n",
-    "FILENAME_PREFIX=f\"v5-L6+6-D{EMBED_SIZE}-E{EMBED_SCALE_LABEL}\"\n",
-    "\n",
-    "print(\"DEEPSPEED_STRAT:\", DEEPSPEED_STRAT)\n",
-    "print(\"ENABLE_WANDB:\", ENABLE_WANDB)\n",
-    "print(\"GPU_DEVICES:\", GPU_DEVICES)\n",
-    "\n",
-    "if ENABLE_WANDB:\n",
-    "    WANDB_MODE=\"online\"\n",
-    "else:\n",
-    "    WANDB_MODE=\"disabled\"\n",
-    "\n",
-    "# Computing the notebook, and various paths\n",
-    "import os\n",
-    "NOTEBOOK_DIR=os.path.dirname(os.path.abspath(\"__file__\"))\n",
-    "PROJECT_DIR=os.path.abspath(os.path.join(NOTEBOOK_DIR, \"../../../../\"))\n",
-    "TRAINER_DIR=os.path.abspath(os.path.join(PROJECT_DIR, \"./RWKV-v5/\"))\n",
-    "INFERENCE_DIR=os.path.abspath(os.path.join(PROJECT_DIR, \"./RWKV-v5/\"))\n",
-    "\n",
-    "print(\"NOTEBOOK_DIR:\", NOTEBOOK_DIR)\n",
-    "print(\"INFERENCE_DIR:\", INFERENCE_DIR)\n",
-    "print(\"TRAINER_DIR:\", TRAINER_DIR)\n",
-    "print(\"PROJECT_DIR:\", PROJECT_DIR)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "ffa69634",
-   "metadata": {
-    "execution": {
-     "iopub.execute_input": "2023-10-11T08:02:24.408311Z",
-     "iopub.status.busy": "2023-10-11T08:02:24.407798Z",
-     "iopub.status.idle": "2023-10-11T08:03:19.634663Z",
-     "shell.execute_reply": "2023-10-11T08:03:19.633765Z"
-    },
-    "papermill": {
-     "duration": 55.233419,
-     "end_time": "2023-10-11T08:03:19.636895",
-     "exception": false,
-     "start_time": "2023-10-11T08:02:24.403476",
-     "status": "completed"
-    },
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "--2023-10-11 08:02:24--  https://huggingface.co/rwkv-x-dev/rwkv-x-playground/resolve/0600b94a58219f658326b4792ef5cd020e9d1a43/experiment/rwkv-x-exp/multi-size-train/v5-L6-D2048-E0_01-split-2a.pth\r\n",
-      "Resolving huggingface.co (huggingface.co)... 18.154.227.87, 18.154.227.7, 18.154.227.69, ...\r\n",
-      "Connecting to huggingface.co (huggingface.co)|18.154.227.87|:443... connected.\r\n",
-      "HTTP request sent, awaiting response... 302 Found\r\n",
-      "Location: https://cdn-lfs.huggingface.co/repos/2e/f7/2ef78555202aa92abdbdf476ce3d0fd5a8b15f7245edf0b80d4d30572355f30d/2f52085cee9c3db4bb079dc44edf50b0a19c170bd92128e918e6203efef83cea?response-content-disposition=attachment%3B+filename*%3DUTF-8%27%27v5-L6-D2048-E0_01-split-2a.pth%3B+filename%3D%22v5-L6-D2048-E0_01-split-2a.pth%22%3B&Expires=1697270544&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTY5NzI3MDU0NH19LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy5odWdnaW5nZmFjZS5jby9yZXBvcy8yZS9mNy8yZWY3ODU1NTIwMmFhOTJhYmRiZGY0NzZjZTNkMGZkNWE4YjE1ZjcyNDVlZGYwYjgwZDRkMzA1NzIzNTVmMzBkLzJmNTIwODVjZWU5YzNkYjRiYjA3OWRjNDRlZGY1MGIwYTE5YzE3MGJkOTIxMjhlOTE4ZTYyMDNlZmVmODNjZWE%7EcmVzcG9uc2UtY29udGVudC1kaXNwb3NpdGlvbj0qIn1dfQ__&Signature=AW451jyDioqxesXvDVp%7EgfYV3uhgFTDwTn3SlZa-gk-yCDb7c-QR44rTm9sWCGSJjaa%7EvJvj9zLGUK7fvbr%7E%7EGQJgL2L%7Es9vkVPg8qs1k%7EtCh-MX%7E45bxo4CapTIo8fx4xLJ738Tks8uzpx3Sy9hWbfuGQFCUwBHzJXG5uGNRzPv87Zdfy4gIIAt0NytaC3bFmKZl4DbXLF4%7EtVWXED7H3NAlBvGETdhjzK5Qr0FLZB2vqC1LQpPTexdTH-ETkPEIQpXRBV-JctzaKBfI1Da-tGpt4JdPlhyPIu1kaNtX13yTibuBrT-mDOy6OVJZ9Zsj%7EHdVUtDrdp-I01dhylHpQ__&Key-Pair-Id=KVTP0A1DKRTAX [following]\r\n",
-      "--2023-10-11 08:02:24--  https://cdn-lfs.huggingface.co/repos/2e/f7/2ef78555202aa92abdbdf476ce3d0fd5a8b15f7245edf0b80d4d30572355f30d/2f52085cee9c3db4bb079dc44edf50b0a19c170bd92128e918e6203efef83cea?response-content-disposition=attachment%3B+filename*%3DUTF-8%27%27v5-L6-D2048-E0_01-split-2a.pth%3B+filename%3D%22v5-L6-D2048-E0_01-split-2a.pth%22%3B&Expires=1697270544&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTY5NzI3MDU0NH19LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy5odWdnaW5nZmFjZS5jby9yZXBvcy8yZS9mNy8yZWY3ODU1NTIwMmFhOTJhYmRiZGY0NzZjZTNkMGZkNWE4YjE1ZjcyNDVlZGYwYjgwZDRkMzA1NzIzNTVmMzBkLzJmNTIwODVjZWU5YzNkYjRiYjA3OWRjNDRlZGY1MGIwYTE5YzE3MGJkOTIxMjhlOTE4ZTYyMDNlZmVmODNjZWE%7EcmVzcG9uc2UtY29udGVudC1kaXNwb3NpdGlvbj0qIn1dfQ__&Signature=AW451jyDioqxesXvDVp%7EgfYV3uhgFTDwTn3SlZa-gk-yCDb7c-QR44rTm9sWCGSJjaa%7EvJvj9zLGUK7fvbr%7E%7EGQJgL2L%7Es9vkVPg8qs1k%7EtCh-MX%7E45bxo4CapTIo8fx4xLJ738Tks8uzpx3Sy9hWbfuGQFCUwBHzJXG5uGNRzPv87Zdfy4gIIAt0NytaC3bFmKZl4DbXLF4%7EtVWXED7H3NAlBvGETdhjzK5Qr0FLZB2vqC1LQpPTexdTH-ETkPEIQpXRBV-JctzaKBfI1Da-tGpt4JdPlhyPIu1kaNtX13yTibuBrT-mDOy6OVJZ9Zsj%7EHdVUtDrdp-I01dhylHpQ__&Key-Pair-Id=KVTP0A1DKRTAX\r\n",
-      "Resolving cdn-lfs.huggingface.co (cdn-lfs.huggingface.co)... 3.162.112.69, 3.162.112.2, 3.162.112.100, ...\r\n",
-      "Connecting to cdn-lfs.huggingface.co (cdn-lfs.huggingface.co)|3.162.112.69|:443... connected.\r\n",
-      "HTTP request sent, awaiting response... "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "200 OK\r\n",
-      "Length: 1066536657 (1017M) [binary/octet-stream]\r\n",
-      "Saving to: ‘v5-L6-D2048-E0_01-split-2a.pth’\r\n",
-      "\r\n",
-      "\r",
-      "          v5-L6-D20   0%[                    ]       0  --.-KB/s               "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "         v5-L6-D204   1%[                    ]  15.26M  42.9MB/s               "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "        v5-L6-D2048   3%[                    ]  30.52M  47.7MB/s               "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "       v5-L6-D2048-   4%[                    ]  45.26M  51.5MB/s               "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "      v5-L6-D2048-E   5%[>                   ]  59.20M  52.1MB/s               "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "     v5-L6-D2048-E0   6%[>                   ]  65.20M  48.8MB/s               "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "    v5-L6-D2048-E0_   7%[>                   ]  76.29M  44.4MB/s               "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "   v5-L6-D2048-E0_0   8%[>                   ]  91.03M  47.2MB/s               "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "  v5-L6-D2048-E0_01   9%[>                   ]  91.55M  43.0MB/s               "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      " v5-L6-D2048-E0_01-  10%[=>                  ] 106.81M  43.2MB/s               "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "v5-L6-D2048-E0_01-s  11%[=>                  ] 120.25M  43.9MB/s               "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "5-L6-D2048-E0_01-sp  12%[=>                  ] 122.07M  41.4MB/s               "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "-L6-D2048-E0_01-spl  13%[=>                  ] 136.81M  42.5MB/s    eta 21s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "L6-D2048-E0_01-spli  14%[=>                  ] 152.07M  42.8MB/s    eta 21s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "6-D2048-E0_01-split  15%[==>                 ] 152.72M  40.5MB/s    eta 21s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "-D2048-E0_01-split-  16%[==>                 ] 167.85M  41.5MB/s    eta 21s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "D2048-E0_01-split-2  18%[==>                 ] 183.10M  43.0MB/s    eta 19s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "2048-E0_01-split-2a  19%[==>                 ] 198.36M  43.4MB/s    eta 19s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "048-E0_01-split-2a.  20%[===>                ] 213.11M  44.1MB/s    eta 19s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "48-E0_01-split-2a.p  22%[===>                ] 228.36M  43.3MB/s    eta 19s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "8-E0_01-split-2a.pt  22%[===>                ] 228.87M  41.1MB/s    eta 18s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "-E0_01-split-2a.pth  24%[===>                ] 244.13M  41.0MB/s    eta 18s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "E0_01-split-2a.pth   25%[====>               ] 259.40M  42.4MB/s    eta 18s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "0_01-split-2a.pth    26%[====>               ] 272.83M  40.4MB/s    eta 18s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "_01-split-2a.pth     28%[====>               ] 289.40M  41.4MB/s    eta 18s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "01-split-2a.pth      28%[====>               ] 289.92M  37.9MB/s    eta 18s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "1-split-2a.pth       29%[====>               ] 304.66M  36.1MB/s    eta 19s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "-split-2a.pth        30%[=====>              ] 305.18M  33.4MB/s    eta 19s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "split-2a.pth         31%[=====>              ] 318.60M  33.2MB/s    eta 19s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "plit-2a.pth          31%[=====>              ] 320.29M  33.3MB/s    eta 19s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "lit-2a.pth           31%[=====>              ] 320.57M  30.7MB/s    eta 19s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "it-2a.pth            32%[=====>              ] 335.18M  30.1MB/s    eta 19s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "t-2a.pth             33%[=====>              ] 345.53M  31.2MB/s    eta 19s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "-2a.pth              34%[=====>              ] 350.82M  29.7MB/s    eta 19s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "2a.pth               35%[======>             ] 360.98M  31.3MB/s    eta 19s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "a.pth                36%[======>             ] 366.20M  29.6MB/s    eta 19s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      ".pth                 37%[======>             ] 380.96M  30.8MB/s    eta 17s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "pth                  38%[======>             ] 392.79M  32.0MB/s    eta 17s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "th                   39%[======>             ] 396.73M  29.1MB/s    eta 17s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "h                    40%[=======>            ] 411.99M  29.1MB/s    eta 17s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "                     41%[=======>            ] 426.73M  28.7MB/s    eta 16s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "                  v  42%[=======>            ] 427.25M  29.1MB/s    eta 16s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "                 v5  42%[=======>            ] 435.25M  27.9MB/s    eta 16s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "                v5-  43%[=======>            ] 438.04M  28.2MB/s    eta 16s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "               v5-L  43%[=======>            ] 442.05M  29.7MB/s    eta 16s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "              v5-L6  43%[=======>            ] 446.00M  31.1MB/s    eta 16s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "             v5-L6-  44%[=======>            ] 457.24M  33.9MB/s    eta 16s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "            v5-L6-D  45%[========>           ] 457.89M  31.6MB/s    eta 16s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "           v5-L6-D2  46%[========>           ] 473.02M  34.8MB/s    eta 16s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "          v5-L6-D20  48%[========>           ] 488.28M  34.1MB/s    eta 15s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "         v5-L6-D204  49%[========>           ] 503.03M  34.6MB/s    eta 15s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "        v5-L6-D2048  50%[=========>          ] 518.29M  37.3MB/s    eta 15s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "       v5-L6-D2048-  51%[=========>          ] 525.10M  35.8MB/s    eta 15s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "      v5-L6-D2048-E  52%[=========>          ] 534.05M  34.4MB/s    eta 13s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "     v5-L6-D2048-E0  53%[=========>          ] 548.80M  34.4MB/s    eta 13s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "    v5-L6-D2048-E0_  55%[==========>         ] 562.75M  33.8MB/s    eta 13s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "   v5-L6-D2048-E0_0  56%[==========>         ] 579.31M  36.0MB/s    eta 13s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "  v5-L6-D2048-E0_01  57%[==========>         ] 581.49M  36.7MB/s    eta 12s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      " v5-L6-D2048-E0_01-  58%[==========>         ] 592.93M  37.4MB/s    eta 12s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "v5-L6-D2048-E0_01-s  58%[==========>         ] 595.09M  37.1MB/s    eta 12s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "5-L6-D2048-E0_01-sp  60%[===========>        ] 610.35M  38.5MB/s    eta 12s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "-L6-D2048-E0_01-spl  61%[===========>        ] 625.61M  38.7MB/s    eta 11s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "L6-D2048-E0_01-spli  62%[===========>        ] 640.36M  39.9MB/s    eta 11s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "6-D2048-E0_01-split  64%[===========>        ] 653.30M  39.5MB/s    eta 11s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "-D2048-E0_01-split-  64%[===========>        ] 656.13M  38.5MB/s    eta 11s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "D2048-E0_01-split-2  66%[============>       ] 671.38M  38.9MB/s    eta 9s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "2048-E0_01-split-2a  67%[============>       ] 685.57M  39.7MB/s    eta 9s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "048-E0_01-split-2a.  67%[============>       ] 686.64M  37.5MB/s    eta 9s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "48-E0_01-split-2a.p  68%[============>       ] 701.39M  37.9MB/s    eta 9s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "8-E0_01-split-2a.pt  69%[============>       ] 708.59M  38.8MB/s    eta 8s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "-E0_01-split-2a.pth  70%[=============>      ] 715.34M  38.2MB/s    eta 8s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "E0_01-split-2a.pth   71%[=============>      ] 731.91M  40.7MB/s    eta 8s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "0_01-split-2a.pth    73%[=============>      ] 747.17M  38.0MB/s    eta 8s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "_01-split-2a.pth     73%[=============>      ] 747.75M  38.0MB/s    eta 7s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "01-split-2a.pth      74%[=============>      ] 762.42M  40.2MB/s    eta 7s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "1-split-2a.pth       75%[==============>     ] 762.94M  37.2MB/s    eta 7s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "-split-2a.pth        76%[==============>     ] 776.37M  36.7MB/s    eta 7s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "split-2a.pth         76%[==============>     ] 778.20M  34.9MB/s    eta 7s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "plit-2a.pth          77%[==============>     ] 791.63M  38.1MB/s    eta 7s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "lit-2a.pth           78%[==============>     ] 793.46M  36.0MB/s    eta 7s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "it-2a.pth            79%[==============>     ] 808.20M  38.6MB/s    eta 7s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "t-2a.pth             80%[===============>    ] 816.07M  36.7MB/s    eta 7s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "-2a.pth              81%[===============>    ] 823.97M  34.7MB/s    eta 5s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "2a.pth               82%[===============>    ] 837.41M  36.4MB/s    eta 5s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "a.pth                83%[===============>    ] 853.98M  38.3MB/s    eta 5s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      ".pth                 85%[================>   ] 867.67M  38.4MB/s    eta 5s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "pth                  85%[================>   ] 873.17M  39.1MB/s    eta 5s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "th                   87%[================>   ] 885.01M  36.1MB/s    eta 4s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "h                    88%[================>   ] 899.75M  37.6MB/s    eta 4s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "                     88%[================>   ] 900.40M  34.6MB/s    eta 4s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "                  v  90%[=================>  ] 915.53M  35.4MB/s    eta 4s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "                 v5  91%[=================>  ] 930.78M  37.6MB/s    eta 2s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "                v5-  92%[=================>  ] 945.53M  40.9MB/s    eta 2s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "               v5-L  93%[=================>  ] 946.04M  37.6MB/s    eta 2s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "              v5-L6  94%[=================>  ] 959.48M  38.0MB/s    eta 2s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "             v5-L6-  94%[=================>  ] 961.30M  33.1MB/s    eta 2s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "            v5-L6-D  95%[==================> ] 976.05M  34.9MB/s    eta 2s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "           v5-L6-D2  97%[==================> ] 991.31M  34.8MB/s    eta 2s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "          v5-L6-D20  97%[==================> ] 992.94M  35.0MB/s    eta 2s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "         v5-L6-D204  98%[==================> ]   1005M  34.7MB/s    eta 0s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "        v5-L6-D2048  99%[==================> ]   1016M  33.7MB/s    eta 0s     \r",
-      "v5-L6-D2048-E0_01-s 100%[===================>]   1017M  33.9MB/s    in 28s     \r\n",
-      "\r\n",
-      "2023-10-11 08:02:52 (36.4 MB/s) - ‘v5-L6-D2048-E0_01-split-2a.pth’ saved [1066536657/1066536657]\r\n",
-      "\r\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "--2023-10-11 08:02:53--  https://huggingface.co/rwkv-x-dev/rwkv-x-playground/resolve/0600b94a58219f658326b4792ef5cd020e9d1a43/experiment/rwkv-x-exp/multi-size-train/v5-L6-D2048-E0_01-split-2b.pth\r\n",
-      "Resolving huggingface.co (huggingface.co)... 18.154.227.67, 18.154.227.69, 18.154.227.7, ...\r\n",
-      "Connecting to huggingface.co (huggingface.co)|18.154.227.67|:443... connected.\r\n",
-      "HTTP request sent, awaiting response... 302 Found\r\n",
-      "Location: https://cdn-lfs.huggingface.co/repos/2e/f7/2ef78555202aa92abdbdf476ce3d0fd5a8b15f7245edf0b80d4d30572355f30d/6b64a1018631b9ddd15a746002bab3eafe956dced78a91af7abcdadaae4a7b25?response-content-disposition=attachment%3B+filename*%3DUTF-8%27%27v5-L6-D2048-E0_01-split-2b.pth%3B+filename%3D%22v5-L6-D2048-E0_01-split-2b.pth%22%3B&Expires=1697270573&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTY5NzI3MDU3M319LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy5odWdnaW5nZmFjZS5jby9yZXBvcy8yZS9mNy8yZWY3ODU1NTIwMmFhOTJhYmRiZGY0NzZjZTNkMGZkNWE4YjE1ZjcyNDVlZGYwYjgwZDRkMzA1NzIzNTVmMzBkLzZiNjRhMTAxODYzMWI5ZGRkMTVhNzQ2MDAyYmFiM2VhZmU5NTZkY2VkNzhhOTFhZjdhYmNkYWRhYWU0YTdiMjU%7EcmVzcG9uc2UtY29udGVudC1kaXNwb3NpdGlvbj0qIn1dfQ__&Signature=WkKE1KjbKeVQp4dWdBuAAbOfx2JJs%7EDJaKbx8gRQSGABLfGDhkq2L8Q9KZ1fg1v%7E74c0Mkrbvop33pAwQDh782jzEiogbDb8HXSO7AtIYQqvI6K-fmb%7EpxQPFrmypJwWhQj9ePRZX2KSL6LcqN1X0GAheI-PQENpVH3svxhhib2-fYDmuvnpGX7pc6n36GES6lvwOuCQOxfIhlFnIiuNEU00NaBdDiaXb-uteXhSkKO-1EFCM0fBtwT5hVkdHZQG2m6iMcI2KaN0AHV%7EvF838f4DM%7ERbjVkRgwphRaYZxmJxUKZxGTV7rRJjIQA%7EOlnPllE1dSdwJ7y0ULOIKQHYUQ__&Key-Pair-Id=KVTP0A1DKRTAX [following]\r\n",
-      "--2023-10-11 08:02:53--  https://cdn-lfs.huggingface.co/repos/2e/f7/2ef78555202aa92abdbdf476ce3d0fd5a8b15f7245edf0b80d4d30572355f30d/6b64a1018631b9ddd15a746002bab3eafe956dced78a91af7abcdadaae4a7b25?response-content-disposition=attachment%3B+filename*%3DUTF-8%27%27v5-L6-D2048-E0_01-split-2b.pth%3B+filename%3D%22v5-L6-D2048-E0_01-split-2b.pth%22%3B&Expires=1697270573&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTY5NzI3MDU3M319LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy5odWdnaW5nZmFjZS5jby9yZXBvcy8yZS9mNy8yZWY3ODU1NTIwMmFhOTJhYmRiZGY0NzZjZTNkMGZkNWE4YjE1ZjcyNDVlZGYwYjgwZDRkMzA1NzIzNTVmMzBkLzZiNjRhMTAxODYzMWI5ZGRkMTVhNzQ2MDAyYmFiM2VhZmU5NTZkY2VkNzhhOTFhZjdhYmNkYWRhYWU0YTdiMjU%7EcmVzcG9uc2UtY29udGVudC1kaXNwb3NpdGlvbj0qIn1dfQ__&Signature=WkKE1KjbKeVQp4dWdBuAAbOfx2JJs%7EDJaKbx8gRQSGABLfGDhkq2L8Q9KZ1fg1v%7E74c0Mkrbvop33pAwQDh782jzEiogbDb8HXSO7AtIYQqvI6K-fmb%7EpxQPFrmypJwWhQj9ePRZX2KSL6LcqN1X0GAheI-PQENpVH3svxhhib2-fYDmuvnpGX7pc6n36GES6lvwOuCQOxfIhlFnIiuNEU00NaBdDiaXb-uteXhSkKO-1EFCM0fBtwT5hVkdHZQG2m6iMcI2KaN0AHV%7EvF838f4DM%7ERbjVkRgwphRaYZxmJxUKZxGTV7rRJjIQA%7EOlnPllE1dSdwJ7y0ULOIKQHYUQ__&Key-Pair-Id=KVTP0A1DKRTAX\r\n",
-      "Resolving cdn-lfs.huggingface.co (cdn-lfs.huggingface.co)... 3.162.112.95, 3.162.112.100, 3.162.112.2, ...\r\n",
-      "Connecting to cdn-lfs.huggingface.co (cdn-lfs.huggingface.co)|3.162.112.95|:443... connected.\r\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "HTTP request sent, awaiting response... "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "200 OK\r\n",
-      "Length: 1066536657 (1017M) [binary/octet-stream]\r\n",
-      "Saving to: ‘v5-L6-D2048-E0_01-split-2b.pth’\r\n",
-      "\r\n",
-      "\r",
-      "          v5-L6-D20   0%[                    ]       0  --.-KB/s               "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "         v5-L6-D204   1%[                    ]  14.74M  67.8MB/s               "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "        v5-L6-D2048   2%[                    ]  28.69M  63.1MB/s               "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "       v5-L6-D2048-   3%[                    ]  30.52M  42.3MB/s               "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "      v5-L6-D2048-E   4%[                    ]  45.26M  45.2MB/s               "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "     v5-L6-D2048-E0   4%[                    ]  45.78M  37.9MB/s               "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "    v5-L6-D2048-E0_   6%[>                   ]  61.03M  41.2MB/s               "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "   v5-L6-D2048-E0_0   7%[>                   ]  75.78M  45.0MB/s               "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "  v5-L6-D2048-E0_01   8%[>                   ]  85.94M  45.6MB/s               "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      " v5-L6-D2048-E0_01-   9%[>                   ]  91.55M  40.8MB/s               "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "v5-L6-D2048-E0_01-s  10%[=>                  ] 106.81M  40.5MB/s               "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "5-L6-D2048-E0_01-sp  12%[=>                  ] 122.07M  40.2MB/s    eta 22s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "-L6-D2048-E0_01-spl  13%[=>                  ] 137.33M  41.7MB/s    eta 22s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "L6-D2048-E0_01-spli  14%[=>                  ] 152.07M  42.9MB/s    eta 22s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "6-D2048-E0_01-split  16%[==>                 ] 167.33M  43.6MB/s    eta 22s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "-D2048-E0_01-split-  17%[==>                 ] 181.32M  44.9MB/s    eta 19s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "D2048-E0_01-split-2  18%[==>                 ] 183.10M  41.7MB/s    eta 19s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "2048-E0_01-split-2b  19%[==>                 ] 196.53M  41.8MB/s    eta 19s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "048-E0_01-split-2b.  19%[==>                 ] 198.36M  39.0MB/s    eta 19s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "48-E0_01-split-2b.p  20%[===>                ] 213.11M  39.0MB/s    eta 20s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "8-E0_01-split-2b.pt  21%[===>                ] 220.29M  40.8MB/s    eta 20s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "-E0_01-split-2b.pth  22%[===>                ] 228.36M  39.9MB/s    eta 20s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "E0_01-split-2b.pth   24%[===>                ] 244.13M  40.3MB/s    eta 20s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "0_01-split-2b.pth    25%[====>               ] 259.40M  40.4MB/s    eta 18s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "_01-split-2b.pth     26%[====>               ] 274.14M  42.1MB/s    eta 18s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "01-split-2b.pth      27%[====>               ] 274.66M  38.5MB/s    eta 18s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "1-split-2b.pth       28%[====>               ] 289.92M  41.6MB/s    eta 18s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "-split-2b.pth        30%[=====>              ] 305.18M  41.6MB/s    eta 17s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "split-2b.pth         31%[=====>              ] 320.43M  40.9MB/s    eta 17s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "plit-2b.pth          32%[=====>              ] 335.18M  41.2MB/s    eta 17s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "lit-2b.pth           33%[=====>              ] 335.69M  38.5MB/s    eta 17s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "it-2b.pth            34%[=====>              ] 350.95M  38.6MB/s    eta 16s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "t-2b.pth             35%[======>             ] 365.70M  40.9MB/s    eta 16s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "-2b.pth              36%[======>             ] 366.20M  38.0MB/s    eta 16s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "2b.pth               37%[======>             ] 381.47M  38.8MB/s    eta 16s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "b.pth                37%[======>             ] 385.65M  39.1MB/s    eta 16s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      ".pth                 39%[======>             ] 396.73M  36.3MB/s    eta 16s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "pth                  39%[======>             ] 406.75M  37.5MB/s    eta 16s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "th                   40%[=======>            ] 411.99M  33.0MB/s    eta 16s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "h                    42%[=======>            ] 427.25M  33.6MB/s    eta 15s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "                     43%[=======>            ] 441.98M  32.7MB/s    eta 15s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "                  v  43%[=======>            ] 442.51M  32.5MB/s    eta 15s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "                 v5  44%[=======>            ] 457.25M  32.2MB/s    eta 15s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "                v5-  45%[========>           ] 457.76M  32.2MB/s    eta 15s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "               v5-L  46%[========>           ] 472.50M  31.5MB/s    eta 14s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "              v5-L6  46%[========>           ] 473.02M  31.5MB/s    eta 14s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "             v5-L6-  48%[========>           ] 488.28M  30.9MB/s    eta 14s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "            v5-L6-D  49%[========>           ] 503.54M  33.6MB/s    eta 14s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "           v5-L6-D2  50%[=========>          ] 518.29M  34.2MB/s    eta 14s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "          v5-L6-D20  51%[=========>          ] 518.80M  34.8MB/s    eta 13s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "         v5-L6-D204  52%[=========>          ] 534.05M  34.2MB/s    eta 13s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "        v5-L6-D2048  54%[=========>          ] 549.31M  37.5MB/s    eta 13s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "       v5-L6-D2048-  55%[==========>         ] 564.06M  37.7MB/s    eta 13s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "      v5-L6-D2048-E  55%[==========>         ] 565.78M  37.7MB/s    eta 12s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "     v5-L6-D2048-E0  57%[==========>         ] 579.83M  37.8MB/s    eta 12s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "    v5-L6-D2048-E0_  58%[==========>         ] 595.09M  39.7MB/s    eta 12s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "   v5-L6-D2048-E0_0  60%[===========>        ] 610.35M  40.9MB/s    eta 12s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "  v5-L6-D2048-E0_01  61%[===========>        ] 625.47M  44.1MB/s    eta 10s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      " v5-L6-D2048-E0_01-  61%[===========>        ] 629.82M  42.6MB/s    eta 10s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "v5-L6-D2048-E0_01-s  63%[===========>        ] 640.87M  42.6MB/s    eta 10s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "5-L6-D2048-E0_01-sp  64%[===========>        ] 656.13M  45.6MB/s    eta 10s    "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "-L6-D2048-E0_01-spl  66%[============>       ] 671.38M  45.8MB/s    eta 9s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "L6-D2048-E0_01-spli  67%[============>       ] 686.64M  47.1MB/s    eta 9s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "6-D2048-E0_01-split  69%[============>       ] 701.90M  47.0MB/s    eta 9s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "-D2048-E0_01-split-  70%[=============>      ] 717.16M  46.9MB/s    eta 9s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "D2048-E0_01-split-2  71%[=============>      ] 730.60M  47.8MB/s    eta 7s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "2048-E0_01-split-2b  73%[=============>      ] 747.17M  45.9MB/s    eta 7s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "048-E0_01-split-2b.  74%[=============>      ] 755.98M  45.7MB/s    eta 7s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "48-E0_01-split-2b.p  75%[==============>     ] 762.94M  43.2MB/s    eta 6s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "8-E0_01-split-2b.pt  76%[==============>     ] 777.68M  45.4MB/s    eta 6s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "-E0_01-split-2b.pth  76%[==============>     ] 778.32M  42.7MB/s    eta 6s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "E0_01-split-2b.pth   78%[==============>     ] 793.46M  42.0MB/s    eta 6s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "0_01-split-2b.pth    79%[==============>     ] 808.20M  41.7MB/s    eta 5s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "_01-split-2b.pth     80%[===============>    ] 814.09M  42.3MB/s    eta 5s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "01-split-2b.pth      80%[===============>    ] 823.46M  41.0MB/s    eta 5s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "1-split-2b.pth       81%[===============>    ] 823.97M  40.5MB/s    eta 5s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "-split-2b.pth        82%[===============>    ] 838.71M  38.6MB/s    eta 4s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "split-2b.pth         83%[===============>    ] 853.98M  41.4MB/s    eta 4s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "plit-2b.pth          84%[===============>    ] 854.61M  38.0MB/s    eta 4s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "lit-2b.pth           85%[================>   ] 869.24M  35.7MB/s    eta 4s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "it-2b.pth            85%[================>   ] 869.75M  35.3MB/s    eta 4s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "t-2b.pth             86%[================>   ] 875.74M  34.3MB/s    eta 4s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "-2b.pth              87%[================>   ] 885.01M  32.5MB/s    eta 4s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "2b.pth               88%[================>   ] 900.27M  33.8MB/s    eta 4s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "b.pth                89%[================>   ] 913.70M  34.5MB/s    eta 3s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      ".pth                 90%[=================>  ] 924.21M  34.8MB/s    eta 3s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "pth                  91%[=================>  ] 930.27M  35.3MB/s    eta 3s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "th                   93%[=================>  ] 946.04M  34.9MB/s    eta 3s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "h                    94%[=================>  ] 961.30M  37.2MB/s    eta 1s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "                     95%[==================> ] 970.14M  35.7MB/s    eta 1s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "                  v  96%[==================> ] 976.55M  34.9MB/s    eta 1s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "                 v5  97%[==================> ] 991.82M  37.0MB/s    eta 1s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "                v5-  98%[==================> ] 998.13M  35.6MB/s    eta 1s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "               v5-L  98%[==================> ]   1007M  37.2MB/s    eta 0s     "
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "              v5-L6  99%[==================> ]   1016M  34.9MB/s    eta 0s     \r",
-      "v5-L6-D2048-E0_01-s 100%[===================>]   1017M  35.1MB/s    in 26s     \r\n",
-      "\r\n",
-      "2023-10-11 08:03:19 (38.9 MB/s) - ‘v5-L6-D2048-E0_01-split-2b.pth’ saved [1066536657/1066536657]\r\n",
-      "\r\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Get the init split model, and finetune from there\n",
-    "!cd \"{PROJECT_DIR}/model/\" && wget -nc \"https://huggingface.co/rwkv-x-dev/rwkv-x-playground/resolve/0600b94a58219f658326b4792ef5cd020e9d1a43/experiment/rwkv-x-exp/multi-size-train/v5-L6-D2048-E0_01-split-2a.pth\"\n",
-    "!cd \"{PROJECT_DIR}/model/\" && wget -nc \"https://huggingface.co/rwkv-x-dev/rwkv-x-playground/resolve/0600b94a58219f658326b4792ef5cd020e9d1a43/experiment/rwkv-x-exp/multi-size-train/v5-L6-D2048-E0_01-split-2b.pth\""
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "2a3cd2d1",
-   "metadata": {
-    "execution": {
-     "iopub.execute_input": "2023-10-11T08:03:19.666619Z",
-     "iopub.status.busy": "2023-10-11T08:03:19.665958Z",
-     "iopub.status.idle": "2023-10-11T08:03:29.305787Z",
-     "shell.execute_reply": "2023-10-11T08:03:29.304873Z"
-    },
-    "papermill": {
-     "duration": 9.658186,
-     "end_time": "2023-10-11T08:03:29.308744",
-     "exception": false,
-     "start_time": "2023-10-11T08:03:19.650558",
-     "status": "completed"
-    },
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "Saving the dataset (0/2 shards):   0%|         | 0/27200 [00:00<?, ? examples/s]"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "Saving the dataset (0/2 shards):   7%| | 2000/27200 [00:00<00:01, 16356.85 examp"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "Saving the dataset (0/2 shards):  15%|▏| 4000/27200 [00:00<00:01, 17283.77 examp"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "Saving the dataset (0/2 shards):  22%|▏| 6000/27200 [00:00<00:01, 17873.97 examp"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "Saving the dataset (0/2 shards):  29%|▎| 8000/27200 [00:00<00:01, 18442.59 examp"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "Saving the dataset (0/2 shards):  40%|▍| 11000/27200 [00:00<00:00, 19135.78 exam"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "Saving the dataset (0/2 shards):  50%|▌| 13600/27200 [00:00<00:00, 19543.92 exam\r",
-      "Saving the dataset (1/2 shards):  50%|▌| 13600/27200 [00:00<00:00, 19543.92 exam"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "Saving the dataset (1/2 shards):  65%|▋| 17600/27200 [00:00<00:00, 20515.42 exam"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "Saving the dataset (1/2 shards):  79%|▊| 21600/27200 [00:01<00:00, 21426.57 exam"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "Saving the dataset (1/2 shards):  94%|▉| 25600/27200 [00:01<00:00, 22078.81 exam"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\r",
-      "Saving the dataset (2/2 shards): 100%|█| 27200/27200 [00:01<00:00, 22078.81 exam\r",
-      "Saving the dataset (2/2 shards): 100%|█| 27200/27200 [00:01<00:00, 20603.99 exam\r\n",
-      "\r",
-      "Saving the dataset (0/1 shards):   0%|           | 0/109 [00:00<?, ? examples/s]\r",
-      "Saving the dataset (1/1 shards): 100%|█| 109/109 [00:00<00:00, 8117.24 examples/\r",
-      "Saving the dataset (1/1 shards): 100%|█| 109/109 [00:00<00:00, 7809.82 examples/\r\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Lets preload the requried datasets\n",
-    "!cd \"{TRAINER_DIR}\" && \\\n",
-    "    python3 preload_datapath.py \"{NOTEBOOK_DIR}/enwiki-4k-part3.yaml\""
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "77d1d3e8",
-   "metadata": {
-    "papermill": {
-     "duration": 0.016656,
-     "end_time": "2023-10-11T08:03:29.342825",
-     "exception": false,
-     "start_time": "2023-10-11T08:03:29.326169",
-     "status": "completed"
-    },
-    "tags": []
-   },
-   "source": [
-    "## Enwiki Stage 3 : Split-Baseline-A training"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "42cb403e",
-   "metadata": {
-    "execution": {
-     "iopub.execute_input": "2023-10-11T08:03:29.379159Z",
-     "iopub.status.busy": "2023-10-11T08:03:29.378428Z",
-     "iopub.status.idle": "2023-10-11T08:03:46.935627Z",
-     "shell.execute_reply": "2023-10-11T08:03:46.934802Z"
-    },
-    "papermill": {
-     "duration": 17.577903,
-     "end_time": "2023-10-11T08:03:46.937715",
-     "exception": false,
-     "start_time": "2023-10-11T08:03:29.359812",
-     "status": "completed"
-    },
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "[2023-10-11 08:03:33,838] [INFO] [real_accelerator.py:133:get_accelerator] 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/python3.10/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/multi-size-train/enwiki-4k-part3.yaml', '--trainer.logger.init_args.name=[Multi-size] v5-L6+6-D2048-E0.01 - layer-expansion A3 (train-ctx=4k, deepspeed_stage_2_offload)', '--trainer.strategy=deepspeed_stage_2_offload', '--trainer.devices=auto', '--trainer.callbacks.init_args.dirpath=../checkpoint/v5-L6+6-D2048-E0_01-layer-expansion-a3/', '--model.load_model=../model/v5-L6+6-D2048-E0_01-split-2a.pth', '--model.ctx_len=4096', '--model.bptt_learning_range=1'], args=['fit', '-c', '/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/notebook/experiment/rwkv-x-exp/multi-size-train/enwiki-4k-part3.yaml', '--trainer.logger.init_args.name=[Multi-size] v5-L6+6-D2048-E0.01 - layer-expansion A3 (train-ctx=4k, deepspeed_stage_2_offload)', '--trainer.strategy=deepspeed_stage_2_offload', '--trainer.devices=auto', '--trainer.callbacks.init_args.dirpath=../checkpoint/v5-L6+6-D2048-E0_01-layer-expansion-a3/', '--model.load_model=../model/v5-L6+6-D2048-E0_01-split-2a.pth', '--model.ctx_len=4096', '--model.bptt_learning_range=1'].\r\n",
-      "  rank_zero_warn(\r\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "/usr/local/lib/python3.10/dist-packages/lightning/fabric/utilities/seed.py:39: UserWarning: No seed found, seed set to 1933922385\r\n",
-      "  rank_zero_warn(f\"No seed found, seed set to {seed}\")\r\n",
-      "Global seed set to 1933922385\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 0.15.12\r\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: Run data is saved locally in \u001b[35m\u001b[1m./wandb/run-20231011_080337-5696uouo\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[33m[Multi-size] v5-L6+6-D2048-E0.01 - layer-expansion A3 (train-ctx=4k, deepspeed_stage_2_offload)\u001b[0m\r\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: ⭐️ View project at \u001b[34m\u001b[4mhttps://wandb.ai/rwkv-x-dev/RWKV-5X-Experiments\u001b[0m\r\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: 🚀 View run at \u001b[34m\u001b[4mhttps://wandb.ai/rwkv-x-dev/RWKV-5X-Experiments/runs/5696uouo\u001b[0m\r\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Traceback (most recent call last):\r\n",
-      "  File \"/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/RWKV-v5/lightning_trainer.py\", line 278, in <module>\r\n",
-      "    cli_main()\r\n",
-      "  File \"/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/RWKV-v5/lightning_trainer.py\", line 253, in cli_main\r\n",
-      "    LightningCLI(\r\n",
-      "  File \"/usr/local/lib/python3.10/dist-packages/lightning/pytorch/cli.py\", line 350, in __init__\r\n",
-      "    self.instantiate_classes()\r\n",
-      "  File \"/usr/local/lib/python3.10/dist-packages/lightning/pytorch/cli.py\", line 499, in instantiate_classes\r\n",
-      "    self.config_init = self.parser.instantiate_classes(self.config)\r\n",
-      "  File \"/usr/local/lib/python3.10/dist-packages/jsonargparse/_deprecated.py\", line 139, in patched_instantiate_classes\r\n",
-      "    cfg = self._unpatched_instantiate_classes(cfg, **kwargs)\r\n",
-      "  File \"/usr/local/lib/python3.10/dist-packages/jsonargparse/_core.py\", line 1130, in instantiate_classes\r\n",
-      "    cfg[subcommand] = subparser.instantiate_classes(cfg[subcommand], instantiate_groups=instantiate_groups)\r\n",
-      "  File \"/usr/local/lib/python3.10/dist-packages/jsonargparse/_deprecated.py\", line 139, in patched_instantiate_classes\r\n",
-      "    cfg = self._unpatched_instantiate_classes(cfg, **kwargs)\r\n",
-      "  File \"/usr/local/lib/python3.10/dist-packages/jsonargparse/_core.py\", line 1124, in instantiate_classes\r\n",
-      "    component.instantiate_class(component, cfg)\r\n",
-      "  File \"/usr/local/lib/python3.10/dist-packages/jsonargparse/_signatures.py\", line 561, in group_instantiate_class\r\n",
-      "    parent[key] = group.group_class(**value)\r\n",
-      "  File \"/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/RWKV-v5/src/model.py\", line 566, in __init__\r\n",
-      "    raise ValueError(f\"load_model file '{load_model}' does not exist\")\r\n",
-      "ValueError: load_model file '../model/v5-L6+6-D2048-E0_01-split-2a.pth' does not exist\r\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\u001b[34m\u001b[1mwandb\u001b[0m: Waiting for W&B process to finish... \u001b[31m(failed 1).\u001b[0m Press Control-C to abort syncing.\r\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\u001b[34m\u001b[1mwandb\u001b[0m: 🚀 View run \u001b[33m[Multi-size] v5-L6+6-D2048-E0.01 - layer-expansion A3 (train-ctx=4k, deepspeed_stage_2_offload)\u001b[0m at: \u001b[34m\u001b[4mhttps://wandb.ai/rwkv-x-dev/RWKV-5X-Experiments/runs/5696uouo\u001b[0m\r\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: ️⚡ View job at \u001b[34m\u001b[4mhttps://wandb.ai/rwkv-x-dev/RWKV-5X-Experiments/jobs/QXJ0aWZhY3RDb2xsZWN0aW9uOjk0OTk4MDcy/version_details/v16\u001b[0m\r\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: Synced 5 W&B file(s), 0 media file(s), 2 artifact file(s) and 0 other file(s)\r\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: Find logs at: \u001b[35m\u001b[1m./wandb/run-20231011_080337-5696uouo/logs\u001b[0m\r\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Start the foundation model training\n",
-    "!cd \"{TRAINER_DIR}\" && \\\n",
-    "    export WANDB_MODE=\"{WANDB_MODE}\" && \\\n",
-    "    python3 lightning_trainer.py fit \\\n",
-    "        -c \"{NOTEBOOK_DIR}/enwiki-4k-part3.yaml\" \\\n",
-    "        --trainer.logger.init_args.name=\"{WANDB_PREFIX} - layer-expansion A3 (train-ctx=4k, {DEEPSPEED_STRAT})\" \\\n",
-    "        --trainer.strategy=\"{DEEPSPEED_STRAT}\" \\\n",
-    "        --trainer.devices=\"{GPU_DEVICES}\" \\\n",
-    "        --trainer.callbacks.init_args.dirpath=\"../checkpoint/{FILENAME_PREFIX}-layer-expansion-a3/\" \\\n",
-    "        --model.load_model=\"../model/{FILENAME_PREFIX}-split-2a.pth\" \\\n",
-    "        --model.ctx_len=4096 \\\n",
-    "        --model.bptt_learning_range=1"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "53867c42",
-   "metadata": {
-    "execution": {
-     "iopub.execute_input": "2023-10-11T08:03:46.969471Z",
-     "iopub.status.busy": "2023-10-11T08:03:46.969019Z",
-     "iopub.status.idle": "2023-10-11T08:03:50.682437Z",
-     "shell.execute_reply": "2023-10-11T08:03:50.680986Z"
-    },
-    "papermill": {
-     "duration": 3.732808,
-     "end_time": "2023-10-11T08:03:50.685581",
-     "exception": false,
-     "start_time": "2023-10-11T08:03:46.952773",
-     "status": "completed"
-    },
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "[2023-10-11 08:03:49,278] [INFO] [real_accelerator.py:133:get_accelerator] Setting ds_accelerator to cuda (auto detect)\r\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Traceback (most recent call last):\r\n",
-      "  File \"/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/RWKV-v5/export_checkpoint.py\", line 651, in <module>\r\n",
-      "    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir, output_file, save_dtype=args.dtype)\r\n",
-      "  File \"/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/RWKV-v5/export_checkpoint.py\", line 542, in convert_zero_checkpoint_to_fp32_state_dict\r\n",
-      "    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)\r\n",
-      "  File \"/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/RWKV-v5/export_checkpoint.py\", line 516, in get_fp32_state_dict_from_zero_checkpoint\r\n",
-      "    raise ValueError(f\"Unable to find 'latest' file at {latest_path}\")\r\n",
-      "ValueError: Unable to find 'latest' file at ../checkpoint/v5-L6+6-D2048-E0_01-layer-expansion-a3/last.ckpt/latest\r\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "ls: cannot access '../model/v5-L6+6-D2048-E0_01-layer-expansion-a3.pth': No such file or directory\r\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Lets export the model from the checkpoint\n",
-    "!cd \"{TRAINER_DIR}\" && \\\n",
-    "    python3 export_checkpoint.py \"../checkpoint/{FILENAME_PREFIX}-layer-expansion-a3/last.ckpt\" \"../model/{FILENAME_PREFIX}-layer-expansion-a3.pth\" \"bf16\"\n",
-    "!cd \"{TRAINER_DIR}\" && ls -alh \"../model/{FILENAME_PREFIX}-layer-expansion-a3.pth\""
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "5688e577",
-   "metadata": {
-    "execution": {
-     "iopub.execute_input": "2023-10-11T08:03:50.806267Z",
-     "iopub.status.busy": "2023-10-11T08:03:50.804997Z",
-     "iopub.status.idle": "2023-10-11T08:03:56.788036Z",
-     "shell.execute_reply": "2023-10-11T08:03:56.786568Z"
-    },
-    "papermill": {
-     "duration": 6.08675,
-     "end_time": "2023-10-11T08:03:56.790510",
-     "exception": false,
-     "start_time": "2023-10-11T08:03:50.703760",
-     "status": "completed"
-    },
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "[2023-10-11 08:03:54,934] [INFO] [real_accelerator.py:133:get_accelerator] 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": [
-      "Traceback (most recent call last):\r\n",
-      "  File \"/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/RWKV-v5/dragon_test.py\", line 52, in <module>\r\n",
-      "    model = SimpleRWKV(MODEL_PATH, device=DEVICE)\r\n",
-      "  File \"/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/RWKV-v5/src/model.py\", line 1420, in __init__\r\n",
-      "    self.model = RWKV(**model_config)\r\n",
-      "  File \"/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/RWKV-v5/src/model.py\", line 566, in __init__\r\n",
-      "    raise ValueError(f\"load_model file '{load_model}' does not exist\")\r\n",
-      "ValueError: load_model file '../model/v5-L6+6-D2048-E0_01-layer-expansion-a3.pth' does not exist\r\n"
-     ]
-    }
-   ],
-   "source": [
-    "# # Lets do a quick dragon prompt validation\n",
-    "!cd \"{INFERENCE_DIR}\" && \\\n",
-    "    python3 dragon_test.py \"../model/{FILENAME_PREFIX}-layer-expansion-a3.pth\" \"cuda fp32\""
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "b4927e87",
-   "metadata": {
-    "papermill": {
-     "duration": 0.015295,
-     "end_time": "2023-10-11T08:03:56.820640",
-     "exception": false,
-     "start_time": "2023-10-11T08:03:56.805345",
-     "status": "completed"
-    },
-    "tags": []
-   },
-   "source": [
-    "## Enwiki Stage 3 : Split-Baseline-B training"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "6bdd285a",
-   "metadata": {
-    "execution": {
-     "iopub.execute_input": "2023-10-11T08:03:56.853495Z",
-     "iopub.status.busy": "2023-10-11T08:03:56.852946Z",
-     "iopub.status.idle": "2023-10-11T08:04:11.500794Z",
-     "shell.execute_reply": "2023-10-11T08:04:11.499336Z"
-    },
-    "papermill": {
-     "duration": 14.668001,
-     "end_time": "2023-10-11T08:04:11.503644",
-     "exception": false,
-     "start_time": "2023-10-11T08:03:56.835643",
-     "status": "completed"
-    },
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "[2023-10-11 08:04:01,096] [INFO] [real_accelerator.py:133:get_accelerator] 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/python3.10/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/multi-size-train/enwiki-4k-part3.yaml', '--trainer.logger.init_args.name=[Multi-size] v5-L6+6-D2048-E0.01 - layer-expansion B3 (train-ctx=4k, deepspeed_stage_2_offload)', '--trainer.strategy=deepspeed_stage_2_offload', '--trainer.devices=auto', '--trainer.callbacks.init_args.dirpath=../checkpoint/v5-L6+6-D2048-E0_01-layer-expansion-b3/', '--model.load_model=../model/v5-L6+6-D2048-E0_01-split-2b.pth', '--model.ctx_len=4096', '--model.bptt_learning_range=1'], args=['fit', '-c', '/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/notebook/experiment/rwkv-x-exp/multi-size-train/enwiki-4k-part3.yaml', '--trainer.logger.init_args.name=[Multi-size] v5-L6+6-D2048-E0.01 - layer-expansion B3 (train-ctx=4k, deepspeed_stage_2_offload)', '--trainer.strategy=deepspeed_stage_2_offload', '--trainer.devices=auto', '--trainer.callbacks.init_args.dirpath=../checkpoint/v5-L6+6-D2048-E0_01-layer-expansion-b3/', '--model.load_model=../model/v5-L6+6-D2048-E0_01-split-2b.pth', '--model.ctx_len=4096', '--model.bptt_learning_range=1'].\r\n",
-      "  rank_zero_warn(\r\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "/usr/local/lib/python3.10/dist-packages/lightning/fabric/utilities/seed.py:39: UserWarning: No seed found, seed set to 1732922148\r\n",
-      "  rank_zero_warn(f\"No seed found, seed set to {seed}\")\r\n",
-      "Global seed set to 1732922148\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 0.15.12\r\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: Run data is saved locally in \u001b[35m\u001b[1m./wandb/run-20231011_080403-88lcuk7j\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[33m[Multi-size] v5-L6+6-D2048-E0.01 - layer-expansion B3 (train-ctx=4k, deepspeed_stage_2_offload)\u001b[0m\r\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: ⭐️ View project at \u001b[34m\u001b[4mhttps://wandb.ai/rwkv-x-dev/RWKV-5X-Experiments\u001b[0m\r\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: 🚀 View run at \u001b[34m\u001b[4mhttps://wandb.ai/rwkv-x-dev/RWKV-5X-Experiments/runs/88lcuk7j\u001b[0m\r\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Traceback (most recent call last):\r\n",
-      "  File \"/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/RWKV-v5/lightning_trainer.py\", line 278, in <module>\r\n",
-      "    cli_main()\r\n",
-      "  File \"/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/RWKV-v5/lightning_trainer.py\", line 253, in cli_main\r\n",
-      "    LightningCLI(\r\n",
-      "  File \"/usr/local/lib/python3.10/dist-packages/lightning/pytorch/cli.py\", line 350, in __init__\r\n",
-      "    self.instantiate_classes()\r\n",
-      "  File \"/usr/local/lib/python3.10/dist-packages/lightning/pytorch/cli.py\", line 499, in instantiate_classes\r\n",
-      "    self.config_init = self.parser.instantiate_classes(self.config)\r\n",
-      "  File \"/usr/local/lib/python3.10/dist-packages/jsonargparse/_deprecated.py\", line 139, in patched_instantiate_classes\r\n",
-      "    cfg = self._unpatched_instantiate_classes(cfg, **kwargs)\r\n",
-      "  File \"/usr/local/lib/python3.10/dist-packages/jsonargparse/_core.py\", line 1130, in instantiate_classes\r\n",
-      "    cfg[subcommand] = subparser.instantiate_classes(cfg[subcommand], instantiate_groups=instantiate_groups)\r\n",
-      "  File \"/usr/local/lib/python3.10/dist-packages/jsonargparse/_deprecated.py\", line 139, in patched_instantiate_classes\r\n",
-      "    cfg = self._unpatched_instantiate_classes(cfg, **kwargs)\r\n",
-      "  File \"/usr/local/lib/python3.10/dist-packages/jsonargparse/_core.py\", line 1124, in instantiate_classes\r\n",
-      "    component.instantiate_class(component, cfg)\r\n",
-      "  File \"/usr/local/lib/python3.10/dist-packages/jsonargparse/_signatures.py\", line 561, in group_instantiate_class\r\n",
-      "    parent[key] = group.group_class(**value)\r\n",
-      "  File \"/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/RWKV-v5/src/model.py\", line 566, in __init__\r\n",
-      "    raise ValueError(f\"load_model file '{load_model}' does not exist\")\r\n",
-      "ValueError: load_model file '../model/v5-L6+6-D2048-E0_01-split-2b.pth' does not exist\r\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\u001b[34m\u001b[1mwandb\u001b[0m: Waiting for W&B process to finish... \u001b[31m(failed 1).\u001b[0m Press Control-C to abort syncing.\r\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\u001b[34m\u001b[1mwandb\u001b[0m: 🚀 View run \u001b[33m[Multi-size] v5-L6+6-D2048-E0.01 - layer-expansion B3 (train-ctx=4k, deepspeed_stage_2_offload)\u001b[0m at: \u001b[34m\u001b[4mhttps://wandb.ai/rwkv-x-dev/RWKV-5X-Experiments/runs/88lcuk7j\u001b[0m\r\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: ️⚡ View job at \u001b[34m\u001b[4mhttps://wandb.ai/rwkv-x-dev/RWKV-5X-Experiments/jobs/QXJ0aWZhY3RDb2xsZWN0aW9uOjk0OTk4MDcy/version_details/v16\u001b[0m\r\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)\r\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: Find logs at: \u001b[35m\u001b[1m./wandb/run-20231011_080403-88lcuk7j/logs\u001b[0m\r\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Start the foundation model training\n",
-    "!cd \"{TRAINER_DIR}\" && \\\n",
-    "    export WANDB_MODE=\"{WANDB_MODE}\" && \\\n",
-    "    python3 lightning_trainer.py fit \\\n",
-    "        -c \"{NOTEBOOK_DIR}/enwiki-4k-part3.yaml\" \\\n",
-    "        --trainer.logger.init_args.name=\"{WANDB_PREFIX} - layer-expansion B3 (train-ctx=4k, {DEEPSPEED_STRAT})\" \\\n",
-    "        --trainer.strategy=\"{DEEPSPEED_STRAT}\" \\\n",
-    "        --trainer.devices=\"{GPU_DEVICES}\" \\\n",
-    "        --trainer.callbacks.init_args.dirpath=\"../checkpoint/{FILENAME_PREFIX}-layer-expansion-b3/\" \\\n",
-    "        --model.load_model=\"../model/{FILENAME_PREFIX}-split-2b.pth\" \\\n",
-    "        --model.ctx_len=4096 \\\n",
-    "        --model.bptt_learning_range=1"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "ae4623a1",
-   "metadata": {
-    "execution": {
-     "iopub.execute_input": "2023-10-11T08:04:11.546046Z",
-     "iopub.status.busy": "2023-10-11T08:04:11.544870Z",
-     "iopub.status.idle": "2023-10-11T08:04:15.274349Z",
-     "shell.execute_reply": "2023-10-11T08:04:15.272957Z"
-    },
-    "papermill": {
-     "duration": 3.754115,
-     "end_time": "2023-10-11T08:04:15.277163",
-     "exception": false,
-     "start_time": "2023-10-11T08:04:11.523048",
-     "status": "completed"
-    },
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "[2023-10-11 08:04:13,869] [INFO] [real_accelerator.py:133:get_accelerator] Setting ds_accelerator to cuda (auto detect)\r\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Traceback (most recent call last):\r\n",
-      "  File \"/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/RWKV-v5/export_checkpoint.py\", line 651, in <module>\r\n",
-      "    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir, output_file, save_dtype=args.dtype)\r\n",
-      "  File \"/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/RWKV-v5/export_checkpoint.py\", line 542, in convert_zero_checkpoint_to_fp32_state_dict\r\n",
-      "    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)\r\n",
-      "  File \"/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/RWKV-v5/export_checkpoint.py\", line 516, in get_fp32_state_dict_from_zero_checkpoint\r\n",
-      "    raise ValueError(f\"Unable to find 'latest' file at {latest_path}\")\r\n",
-      "ValueError: Unable to find 'latest' file at ../checkpoint/v5-L6+6-D2048-E0_01-layer-expansion-b3/last.ckpt/latest\r\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "ls: cannot access '../model/v5-L6+6-D2048-E0_01-layer-expansion-b3.pth': No such file or directory\r\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Lets export the model from the checkpoint\n",
-    "!cd \"{TRAINER_DIR}\" && \\\n",
-    "    python3 export_checkpoint.py \"../checkpoint/{FILENAME_PREFIX}-layer-expansion-b3/last.ckpt\" \"../model/{FILENAME_PREFIX}-layer-expansion-b3.pth\" \"bf16\"\n",
-    "!cd \"{TRAINER_DIR}\" && ls -alh \"../model/{FILENAME_PREFIX}-layer-expansion-b3.pth\""
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "id": "8e1b1152",
-   "metadata": {
-    "execution": {
-     "iopub.execute_input": "2023-10-11T08:04:15.319747Z",
-     "iopub.status.busy": "2023-10-11T08:04:15.318636Z",
-     "iopub.status.idle": "2023-10-11T08:04:21.268526Z",
-     "shell.execute_reply": "2023-10-11T08:04:21.267073Z"
-    },
-    "papermill": {
-     "duration": 5.974644,
-     "end_time": "2023-10-11T08:04:21.271495",
-     "exception": false,
-     "start_time": "2023-10-11T08:04:15.296851",
-     "status": "completed"
-    },
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "[2023-10-11 08:04:19,430] [INFO] [real_accelerator.py:133:get_accelerator] 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",
-      "Traceback (most recent call last):\r\n",
-      "  File \"/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/RWKV-v5/dragon_test.py\", line 52, in <module>\r\n",
-      "    model = SimpleRWKV(MODEL_PATH, device=DEVICE)\r\n",
-      "  File \"/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/RWKV-v5/src/model.py\", line 1420, in __init__\r\n",
-      "    self.model = RWKV(**model_config)\r\n",
-      "  File \"/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/RWKV-v5/src/model.py\", line 566, in __init__\r\n",
-      "    raise ValueError(f\"load_model file '{load_model}' does not exist\")\r\n",
-      "ValueError: load_model file '../model/v5-L6+6-D2048-E0_01-layer-expansion-b3.pth' does not exist\r\n"
-     ]
-    }
-   ],
-   "source": [
-    "# # Lets do a quick dragon prompt validation\n",
-    "!cd \"{INFERENCE_DIR}\" && \\\n",
-    "    python3 dragon_test.py \"../model/{FILENAME_PREFIX}-layer-expansion-b3.pth\" \"cuda fp32\""
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.10.12"
-  },
-  "papermill": {
-   "default_parameters": {},
-   "duration": 119.315066,
-   "end_time": "2023-10-11T08:04:21.714050",
-   "environment_variables": {},
-   "exception": null,
-   "input_path": "/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/notebook/experiment/rwkv-x-exp/multi-size-train/v5-L6+6-D2048-layer-baseline.ipynb",
-   "output_path": "/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/rwkv-x-exp/multi-size-train/v5-L6+6-D2048-layer-baseline.ipynb",
-   "parameters": {},
-   "start_time": "2023-10-11T08:02:22.398984",
-   "version": "2.4.0"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

experiment/rwkv-x-exp/multi-size-train/v5-L6+6-D2048-layer-expansion.ipynb

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b0aa2c37ab25e53ed3e45a9e7b5b09d1ac2d2f627412df5c98cc1f113838d800
-size 15734950

experiment/rwkv-x-exp/multi-size-train/v5-L6+6-D2048-overwrite-naive.ipynb

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d643e2a64a0f7323eb7b14b90ce5a0e5457818349c75e666dbf52b7319f5de72
-size 15733849

experiment/rwkv-x-exp/multi-size-train/v5-L6-D2048-E0_01-baseline-p2.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:849b57b4d493d40313ef04b30ffc22ec6f5cb99e05225615ee0cb00acb78a95d
-size 1066537077

experiment/rwkv-x-exp/multi-size-train/v5-L6-D2048-E0_01-baseline-p3.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8413565273ef40f61db246dcbf793e045b39d1163e18885441be5a16d733f34c
-size 1066537077

experiment/rwkv-x-exp/multi-size-train/v5-L6-D2048-E0_01-enwiki-4k-p1.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:235d88b0aa939596392f2b5734a426940535816aa13106498974a809051a4c75
-size 1066537217

experiment/rwkv-x-exp/multi-size-train/v5-L6-D2048-E0_01-layer-expansion-a3.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1afd8d92632792f498805ac222d159524badf4ecbcaaae597060b6bb87a53110
-size 1066538057

experiment/rwkv-x-exp/multi-size-train/v5-L6-D2048-E0_01-layer-expansion-b3.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9e61d8f8901d1eb50759f0242e2886678ed24b9931295a270b14120ba74cb5c3
-size 1066538057

experiment/rwkv-x-exp/multi-size-train/v5-L6-D2048-E0_01-neox-v5base-init.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c2d60ede71bc384ee4eff0a591b3fa57dd670c27e5e8ce5eadf25a7f0d7e226d
-size 1066538337

experiment/rwkv-x-exp/multi-size-train/v5-L6-D2048-E0_01-split-2a.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2f52085cee9c3db4bb079dc44edf50b0a19c170bd92128e918e6203efef83cea
-size 1066536657

experiment/rwkv-x-exp/multi-size-train/v5-L6-D2048-E0_01-split-2b.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6b64a1018631b9ddd15a746002bab3eafe956dced78a91af7abcdadaae4a7b25
-size 1066536657

experiment/rwkv-x-exp/multi-size-train/v5-L6-D2048-E0_01-split-merge-2m.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f10f8f00c42b6408db81a3b26d53411c41edc7f23f5097ac095ad3096d6c5dc1
-size 1066537497

experiment/rwkv-x-exp/multi-size-train/v5-L6-D2048-E0_01-split-merge-p3.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6f07a8414cd0cd1c3df705dff8a0f2142231171ee52a94d12c55dfe7c888fef7
-size 1066537497

experiment/rwkv-x-exp/multi-size-train/v5-L6-D2048-baseline.ipynb

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0fccffc430231ad06fdb02a7e50ea57acfbeae3c42a97b018f62f937d30736e4
-size 16519239

experiment/rwkv-x-exp/multi-size-train/v5-L6-D2048-part1.ipynb

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7260b3fe80de461d6dc923b21af87361f71e26a4a7191d51dd9665403728ddfa
-size 15732960

experiment/rwkv-x-exp/multi-size-train/v5-L6-D2048-split-baseline.ipynb

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f95adf89d498a4dd58af22ba192b2fd4d08ceec250784c7e9f6f9b8de0fed2bc
-size 15855123

experiment/rwkv-x-exp/multi-size-train/v5-L6-D2048-split-train.ipynb

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c308e5ae9f8fde5fd24cafccf60917dca9c97fc2e0a5fbcfa01027d6d50e927d
-size 16623766

experiment/rwkv-x-exp/v5-r3-memory/L12-D2048-E1e-1-ctx4k/v5r3-L12-D2048-E0_1-enwiki-instruct.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf36cb2931ec033f98652643fa297578e6492fdde20223c63fc118f315ec34da
+oid sha256:85cc3102244062433a37b10b3abfd8c6f37f02e36ec7e723c88f89a70fa8076d
 size 1721188709

experiment/rwkv-x-exp/v5-r3-memory/L12-D2048-E1e-1-ctx4k/v5r3-L12-D2048-E0_1-mem-ctx-512.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:428165f24369bec63746c64c9da6816dc26c17c18a80be1fff372da78294329c
-size 1721187621

experiment/rwkv-x-exp/v5-r3-memory/L12-D2048-E1e-1-ctx4k/v5r3-L12-D2048-E0_1-mem-instruct.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:106e6576d2bbb4c31571bf79e574b3fb8233217a6e8a8739b4d8d75de77e73a1
-size 1721187893

experiment/rwkv-x-exp/v5-r3-memory/L6-D2048-E1e-1-ctx4k/part1.ipynb

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1ad9f654a7f6ed10dcf0b15fce28a0b191ce8f52bffde64090163e063ac19ab
-size 24177949
+oid sha256:562fdf69a4267c753b425812f407e66acd1a0e0bd0dc29eef451d5f9af9193d1
+size 24740731

experiment/rwkv-x-exp/v5-r3-memory/L6-D2048-E1e-1-ctx4k/stage2.ipynb

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:04b893c23868d4438d1733d8b85afe79f3065c7074b4f3d1ebc27a0b29b350a0
-size 52755279

experiment/rwkv-x-exp/v5-r3-memory/L6-D2048-E1e-1-ctx4k/stage3.ipynb

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0439ce7fb6866af36cb53bbddaf6a1ed49656c85a84d6a2aabd6754b30fa2109
-size 61159745

experiment/rwkv-x-exp/v5-r3-memory/L6-D2048-E1e-1-ctx4k/stage4.ipynb

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3855c5ed19072f2ecaec4294c3945a3290e692d15c0aa7351c7d4917404fbf65
-size 38208798

experiment/rwkv-x-exp/v5-r3-memory/L6-D2048-E1e-1-ctx4k/stage5.ipynb

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e318ecc4d20d89232f8a0677c54f8489d602cb3d66632cadb29c028c917eb00e
-size 30322339

experiment/rwkv-x-exp/v5-r3-memory/L6-D2048-E1e-1-ctx4k/v5r3-L6-D2048-E0_1-enwiki-4k.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a98bb4421b50083bfbb0e4233838456ff812373a85d2bf87d23cdb8aa6b8d702
+oid sha256:7eb7abfda2e4cfb2a961ba4d52564f9b330830ba1a836966556e28753468ea1e
 size 1066536937

experiment/rwkv-x-exp/v5-r3-memory/L6-D2048-E1e-1-ctx4k/v5r3-L6-D2048-E0_1-enwiki-instruct.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a83bdbbf6d686bfa77529fc9bbde3a91fc8d182e1dc33ce8d18f2a0abbe2576
+oid sha256:f3f8a205f62d0b8c773766d39ec62bfd98918e977beba55d333548ad1df81dfe
 size 1066537777

experiment/rwkv-x-exp/v5-r3-memory/L6-D2048-E1e-1-ctx4k/v5r3-L6-D2048-E0_1-mem-ctx-1k.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:cf3a15d56db013d138bed6780d58c4362ca96b3ef98fb98e2d1444f325c582b5
-size 1066537077

experiment/rwkv-x-exp/v5-r3-memory/L6-D2048-E1e-1-ctx4k/v5r3-L6-D2048-E0_1-mem-ctx-2k.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:76cc2d79013781f18c6507848a138150084d37c3aae0f20145e7e5854bcabb99
-size 1066537077

experiment/rwkv-x-exp/v5-r3-memory/L6-D2048-E1e-1-ctx4k/v5r3-L6-D2048-E0_1-mem-ctx-4k.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2f1b8811c3f2f8c12c564edb973392bb486c9d674152f3eb769ac206c20bcfc0
-size 1066537077

experiment/rwkv-x-exp/v5-r3-memory/L6-D2048-E1e-1-ctx4k/v5r3-L6-D2048-E0_1-mem-ctx-512.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:92bee66e66bfcba8c592c785b63cb88f4e4889d78d7cdc49c33bd53bf0e3c31f
-size 1066537217

experiment/rwkv-x-exp/v5-r3-memory/L6-D2048-E1e-1-ctx4k/v5r3-L6-D2048-E0_1-mem-ctx-8k.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:db7ab09a447f96d9fcdbee4761bd35f2c3bce9868d3136959ed601a8e478083c
-size 1066537077

experiment/rwkv-x-exp/v5-r3-memory/L6-D2048-E1e-1-ctx4k/v5r3-L6-D2048-E0_1-mem-instruct.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d9ec28149b79524846c14ec90b0a206a3529abb584575553320f2427be475225
-size 1066537357

experiment/rwkv-x-exp/v5-r3-memory/L6-D2048-E1e-1-ctx4k/v5r3-L6-D2048-E0_1-neox-init.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98ff68af85a7db87d6e8aeb68d8e36d403dc41e947e090dcbc8e13dbeeb50406
+oid sha256:ea0b14c5aafb10ad2506806e44a34c09ad518076fc485ab5dfec004219cf6db5
 size 1066537497

experiment/rwkv-x-exp/v5-r3-memory/L6-D2560-E1e-1-ctx4k/part1.ipynb

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b0977926c2d6b24d07dbdbaff2712954f647d5b697863bc918c4ffc0f431f572
-size 24384207

experiment/rwkv-x-exp/v5-r3-memory/L6-D2560-E1e-1-ctx4k/stage2.ipynb

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:97d1563b2840253fdb03cb024ff0447bb295fdc9a3c255c4c39bc01eb46720a0
-size 48457692