{ "cells": [ { "attachments": {}, "cell_type": "markdown", "id": "5572546c", "metadata": { "papermill": { "duration": 0.004628, "end_time": "2023-10-09T13:45:05.220521", "exception": false, "start_time": "2023-10-09T13:45:05.215893", "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": "ae5764a7", "metadata": { "papermill": { "duration": 0.00219, "end_time": "2023-10-09T13:45:05.226063", "exception": false, "start_time": "2023-10-09T13:45:05.223873", "status": "completed" }, "tags": [] }, "source": [ "# Basic Setup" ] }, { "cell_type": "code", "execution_count": 1, "id": "3f2f42af", "metadata": { "execution": { "iopub.execute_input": "2023-10-09T13:45:05.230412Z", "iopub.status.busy": "2023-10-09T13:45:05.230127Z", "iopub.status.idle": "2023-10-09T13:45:05.892640Z", "shell.execute_reply": "2023-10-09T13:45:05.891799Z" }, "papermill": { "duration": 0.66692, "end_time": "2023-10-09T13:45:05.894598", "exception": false, "start_time": "2023-10-09T13:45:05.227678", "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": "f9fe66e5", "metadata": { "execution": { "iopub.execute_input": "2023-10-09T13:45:05.902589Z", "iopub.status.busy": "2023-10-09T13:45:05.902333Z", "iopub.status.idle": "2023-10-09T13:45:05.910444Z", "shell.execute_reply": "2023-10-09T13:45:05.909815Z" }, "papermill": { "duration": 0.013691, "end_time": "2023-10-09T13:45:05.911875", "exception": false, "start_time": "2023-10-09T13:45:05.898184", "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": "42e201fa", "metadata": { "execution": { "iopub.execute_input": "2023-10-09T13:45:05.917899Z", "iopub.status.busy": "2023-10-09T13:45:05.917753Z", "iopub.status.idle": "2023-10-09T13:48:07.032157Z", "shell.execute_reply": "2023-10-09T13:48:07.031472Z" }, "papermill": { "duration": 181.119294, "end_time": "2023-10-09T13:48:07.033897", "exception": false, "start_time": "2023-10-09T13:45:05.914603", "status": "completed" }, "tags": [] }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "--2023-10-09 13:45:06-- https://huggingface.co/rwkv-x-dev/rwkv-x-playground/resolve/main/experiment/rwkv-x-exp/multi-size-train/v5-L6-D2048-E0_01-enwiki-4k-p1.pth\r\n", "Resolving huggingface.co (huggingface.co)... 13.33.33.110, 13.33.33.20, 13.33.33.55, ...\r\n", "Connecting to huggingface.co (huggingface.co)|13.33.33.110|:443... connected.\r\n", "HTTP request sent, awaiting response... " ] }, { "name": "stdout", "output_type": "stream", "text": [ "302 Found\r\n", "Location: https://cdn-lfs.huggingface.co/repos/2e/f7/2ef78555202aa92abdbdf476ce3d0fd5a8b15f7245edf0b80d4d30572355f30d/235d88b0aa939596392f2b5734a426940535816aa13106498974a809051a4c75?response-content-disposition=attachment%3B+filename*%3DUTF-8%27%27v5-L6-D2048-E0_01-enwiki-4k-p1.pth%3B+filename%3D%22v5-L6-D2048-E0_01-enwiki-4k-p1.pth%22%3B&Expires=1697118306&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTY5NzExODMwNn19LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy5odWdnaW5nZmFjZS5jby9yZXBvcy8yZS9mNy8yZWY3ODU1NTIwMmFhOTJhYmRiZGY0NzZjZTNkMGZkNWE4YjE1ZjcyNDVlZGYwYjgwZDRkMzA1NzIzNTVmMzBkLzIzNWQ4OGIwYWE5Mzk1OTYzOTJmMmI1NzM0YTQyNjk0MDUzNTgxNmFhMTMxMDY0OTg5NzRhODA5MDUxYTRjNzU%7EcmVzcG9uc2UtY29udGVudC1kaXNwb3NpdGlvbj0qIn1dfQ__&Signature=mYDHt4qPU9P2R8jxStu6hpcsaYf2BJxybVQl7UxmG-XKJV07nwUZPobAk4lYRRGYfVYs0s7n%7EXzZAHQfpJLBnI38caOMBFB-KgCvGG44D5HX%7ErJ-oct2gxYuMbdA7CvMpolTV%7EEmyePEpzCoxFN0FMjIgz3w2jwCdEZfD1UMKU-QRWfCFBxNX97rai95wuqXDM6oC1QB4Jbz4TST9Pmci86nDc515naQSlO9K2SqPkl-Wqr%7EEK37a1mT48eNPBQtJjKsHV7eBZYSK2z1YNy29Bev6TIsZ3LQ70X9osEAYNqF%7EYfiTCNEq-SEdNxQpSnT%7EbWHksvc-QEWJ7BpX8l85Q__&Key-Pair-Id=KVTP0A1DKRTAX [following]\r\n", "--2023-10-09 13:45:06-- https://cdn-lfs.huggingface.co/repos/2e/f7/2ef78555202aa92abdbdf476ce3d0fd5a8b15f7245edf0b80d4d30572355f30d/235d88b0aa939596392f2b5734a426940535816aa13106498974a809051a4c75?response-content-disposition=attachment%3B+filename*%3DUTF-8%27%27v5-L6-D2048-E0_01-enwiki-4k-p1.pth%3B+filename%3D%22v5-L6-D2048-E0_01-enwiki-4k-p1.pth%22%3B&Expires=1697118306&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTY5NzExODMwNn19LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy5odWdnaW5nZmFjZS5jby9yZXBvcy8yZS9mNy8yZWY3ODU1NTIwMmFhOTJhYmRiZGY0NzZjZTNkMGZkNWE4YjE1ZjcyNDVlZGYwYjgwZDRkMzA1NzIzNTVmMzBkLzIzNWQ4OGIwYWE5Mzk1OTYzOTJmMmI1NzM0YTQyNjk0MDUzNTgxNmFhMTMxMDY0OTg5NzRhODA5MDUxYTRjNzU%7EcmVzcG9uc2UtY29udGVudC1kaXNwb3NpdGlvbj0qIn1dfQ__&Signature=mYDHt4qPU9P2R8jxStu6hpcsaYf2BJxybVQl7UxmG-XKJV07nwUZPobAk4lYRRGYfVYs0s7n%7EXzZAHQfpJLBnI38caOMBFB-KgCvGG44D5HX%7ErJ-oct2gxYuMbdA7CvMpolTV%7EEmyePEpzCoxFN0FMjIgz3w2jwCdEZfD1UMKU-QRWfCFBxNX97rai95wuqXDM6oC1QB4Jbz4TST9Pmci86nDc515naQSlO9K2SqPkl-Wqr%7EEK37a1mT48eNPBQtJjKsHV7eBZYSK2z1YNy29Bev6TIsZ3LQ70X9osEAYNqF%7EYfiTCNEq-SEdNxQpSnT%7EbWHksvc-QEWJ7BpX8l85Q__&Key-Pair-Id=KVTP0A1DKRTAX\r\n", "Resolving cdn-lfs.huggingface.co (cdn-lfs.huggingface.co)... " ] }, { "name": "stdout", "output_type": "stream", "text": [ "18.155.68.94, 18.155.68.73, 18.155.68.128, ...\r\n", "Connecting to cdn-lfs.huggingface.co (cdn-lfs.huggingface.co)|18.155.68.94|:443... connected.\r\n", "HTTP request sent, awaiting response... " ] }, { "name": "stdout", "output_type": "stream", "text": [ "200 OK\r\n", "Length: 1066537217 (1017M) [binary/octet-stream]\r\n", "Saving to: ‘v5-L6-D2048-E0_01-enwiki-4k-p1.pth’\r\n", "\r\n", "\r", " v5-L6-D20 0%[ ] 0 --.-KB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D204 0%[ ] 26.25K 116KB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048 0%[ ] 58.25K 128KB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048- 0%[ ] 147.30K 217KB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048-E 0%[ ] 314.87K 347KB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048-E0 0%[ ] 648.86K 572KB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048-E0_ 0%[ ] 1.28M 961KB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048-E0_0 0%[ ] 2.59M 1.63MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048-E0_01 0%[ ] 4.64M 2.55MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048-E0_01- 0%[ ] 6.78M 3.31MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "v5-L6-D2048-E0_01-e 0%[ ] 9.04M 3.98MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "5-L6-D2048-E0_01-en 1%[ ] 11.40M 4.56MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-L6-D2048-E0_01-enw 1%[ ] 13.89M 5.09MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "L6-D2048-E0_01-enwi 1%[ ] 16.48M 5.58MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "6-D2048-E0_01-enwik 1%[ ] 19.21M 6.04MB/s eta 2m 45s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-D2048-E0_01-enwiki 2%[ ] 22.09M 6.48MB/s eta 2m 45s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "D2048-E0_01-enwiki- 2%[ ] 25.11M 6.91MB/s eta 2m 45s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "2048-E0_01-enwiki-4 2%[ ] 28.28M 7.32MB/s eta 2m 45s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "048-E0_01-enwiki-4k 3%[ ] 31.59M 7.73MB/s eta 2m 45s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "48-E0_01-enwiki-4k- 3%[ ] 34.98M 8.10MB/s eta 2m 1s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "8-E0_01-enwiki-4k-p 3%[ ] 38.39M 8.42MB/s eta 2m 1s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-E0_01-enwiki-4k-p1 4%[ ] 42.00M 9.22MB/s eta 2m 1s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "E0_01-enwiki-4k-p1. 4%[ ] 45.67M 10.0MB/s eta 2m 1s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "0_01-enwiki-4k-p1.p 4%[ ] 49.39M 10.8MB/s eta 2m 1s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "_01-enwiki-4k-p1.pt 5%[> ] 53.11M 11.6MB/s eta 99s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "01-enwiki-4k-p1.pth 5%[> ] 56.86M 12.3MB/s eta 99s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "1-enwiki-4k-p1.pth 5%[> ] 60.57M 13.0MB/s eta 99s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-enwiki-4k-p1.pth 6%[> ] 64.29M 13.5MB/s eta 99s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "enwiki-4k-p1.pth 6%[> ] 67.73M 13.1MB/s eta 93s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "nwiki-4k-p1.pth 7%[> ] 71.81M 13.5MB/s eta 93s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "wiki-4k-p1.pth 7%[> ] 74.59M 13.6MB/s eta 93s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "iki-4k-p1.pth 7%[> ] 77.50M 13.8MB/s eta 93s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "ki-4k-p1.pth 7%[> ] 80.46M 13.9MB/s eta 93s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "i-4k-p1.pth 8%[> ] 83.51M 14.0MB/s eta 87s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-4k-p1.pth 8%[> ] 86.59M 14.0MB/s eta 87s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "4k-p1.pth 8%[> ] 89.75M 14.1MB/s eta 87s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "k-p1.pth 9%[> ] 92.95M 14.1MB/s eta 87s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-p1.pth 9%[> ] 96.20M 14.1MB/s eta 87s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "p1.pth 9%[> ] 99.50M 14.1MB/s eta 82s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "1.pth 10%[=> ] 102.82M 14.1MB/s eta 82s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", ".pth 10%[=> ] 106.20M 14.2MB/s eta 82s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "pth 10%[=> ] 109.64M 14.1MB/s eta 82s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "th 11%[=> ] 113.11M 14.1MB/s eta 82s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "h 11%[=> ] 116.61M 14.1MB/s eta 77s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 11%[=> ] 120.04M 14.0MB/s eta 77s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v 12%[=> ] 123.64M 14.0MB/s eta 77s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5 12%[=> ] 126.54M 13.2MB/s eta 77s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5- 12%[=> ] 130.29M 13.1MB/s eta 76s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L 13%[=> ] 132.87M 13.6MB/s eta 76s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6 13%[=> ] 135.48M 13.3MB/s eta 76s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6- 13%[=> ] 138.12M 13.2MB/s eta 76s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D 13%[=> ] 140.82M 13.2MB/s eta 76s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2 14%[=> ] 143.53M 13.1MB/s eta 75s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D20 14%[=> ] 146.29M 13.1MB/s eta 75s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D204 14%[=> ] 149.07M 13.0MB/s eta 75s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048 14%[=> ] 151.89M 12.9MB/s eta 75s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048- 15%[==> ] 154.71M 12.9MB/s eta 75s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048-E 15%[==> ] 157.14M 12.7MB/s eta 74s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048-E0 15%[==> ] 160.00M 12.6MB/s eta 74s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048-E0_ 16%[==> ] 162.89M 12.5MB/s eta 74s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048-E0_0 16%[==> ] 165.81M 12.4MB/s eta 74s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048-E0_01 16%[==> ] 168.73M 12.3MB/s eta 74s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048-E0_01- 16%[==> ] 171.68M 12.2MB/s eta 72s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "v5-L6-D2048-E0_01-e 17%[==> ] 174.64M 12.1MB/s eta 72s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "5-L6-D2048-E0_01-en 17%[==> ] 177.61M 12.0MB/s eta 72s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-L6-D2048-E0_01-enw 17%[==> ] 180.59M 11.9MB/s eta 72s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "L6-D2048-E0_01-enwi 18%[==> ] 183.61M 12.5MB/s eta 72s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "6-D2048-E0_01-enwik 18%[==> ] 186.62M 12.4MB/s eta 70s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-D2048-E0_01-enwiki 18%[==> ] 189.64M 12.5MB/s eta 70s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "D2048-E0_01-enwiki- 18%[==> ] 192.65M 12.6MB/s eta 70s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "2048-E0_01-enwiki-4 19%[==> ] 195.71M 12.7MB/s eta 70s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "048-E0_01-enwiki-4k 19%[==> ] 198.76M 12.8MB/s eta 70s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "48-E0_01-enwiki-4k- 19%[==> ] 201.82M 12.8MB/s eta 68s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "8-E0_01-enwiki-4k-p 20%[===> ] 204.87M 12.9MB/s eta 68s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-E0_01-enwiki-4k-p1 20%[===> ] 207.95M 13.0MB/s eta 68s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "E0_01-enwiki-4k-p1. 20%[===> ] 211.03M 13.0MB/s eta 68s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "0_01-enwiki-4k-p1.p 21%[===> ] 214.12M 13.1MB/s eta 68s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "_01-enwiki-4k-p1.pt 21%[===> ] 217.18M 13.2MB/s eta 66s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "01-enwiki-4k-p1.pth 21%[===> ] 220.28M 13.3MB/s eta 66s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "1-enwiki-4k-p1.pth 21%[===> ] 223.37M 13.3MB/s eta 66s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-enwiki-4k-p1.pth 22%[===> ] 226.48M 13.4MB/s eta 66s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "enwiki-4k-p1.pth 22%[===> ] 229.57M 13.4MB/s eta 66s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "nwiki-4k-p1.pth 22%[===> ] 232.65M 13.4MB/s eta 65s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "wiki-4k-p1.pth 23%[===> ] 235.75M 13.5MB/s eta 65s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "iki-4k-p1.pth 23%[===> ] 238.84M 13.5MB/s eta 65s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "ki-4k-p1.pth 23%[===> ] 241.95M 13.5MB/s eta 65s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "i-4k-p1.pth 24%[===> ] 245.04M 13.6MB/s eta 65s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-4k-p1.pth 24%[===> ] 248.15M 13.6MB/s eta 63s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "4k-p1.pth 24%[===> ] 251.26M 13.6MB/s eta 63s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "k-p1.pth 25%[====> ] 254.36M 13.6MB/s eta 63s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-p1.pth 25%[====> ] 257.45M 13.6MB/s eta 63s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "p1.pth 25%[====> ] 260.56M 13.6MB/s eta 63s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "1.pth 25%[====> ] 263.65M 13.6MB/s eta 61s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", ".pth 26%[====> ] 266.76M 13.6MB/s eta 61s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "pth 26%[====> ] 269.86M 13.6MB/s eta 61s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "th 26%[====> ] 272.96M 13.7MB/s eta 61s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "h 27%[====> ] 276.07M 13.6MB/s eta 61s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 27%[====> ] 279.18M 13.7MB/s eta 60s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v 27%[====> ] 282.31M 13.6MB/s eta 60s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5 28%[====> ] 285.42M 13.7MB/s eta 60s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5- 28%[====> ] 288.54M 13.7MB/s eta 60s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L 28%[====> ] 291.65M 13.5MB/s eta 60s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6 28%[====> ] 294.78M 13.3MB/s eta 58s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6- 29%[====> ] 297.90M 13.8MB/s eta 58s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D 29%[====> ] 301.03M 13.7MB/s eta 58s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2 29%[====> ] 304.17M 13.7MB/s eta 58s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D20 30%[=====> ] 307.28M 13.7MB/s eta 58s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D204 30%[=====> ] 310.40M 13.7MB/s eta 57s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048 30%[=====> ] 313.53M 13.7MB/s eta 57s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048- 31%[=====> ] 316.67M 13.7MB/s eta 57s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048-E 31%[=====> ] 319.82M 13.7MB/s eta 57s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048-E0 31%[=====> ] 322.98M 13.7MB/s eta 57s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048-E0_ 32%[=====> ] 326.07M 13.8MB/s eta 55s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048-E0_0 32%[=====> ] 329.18M 13.5MB/s eta 55s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048-E0_01 32%[=====> ] 332.28M 13.5MB/s eta 55s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048-E0_01- 32%[=====> ] 335.34M 13.5MB/s eta 55s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "v5-L6-D2048-E0_01-e 33%[=====> ] 338.54M 13.5MB/s eta 54s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "5-L6-D2048-E0_01-en 33%[=====> ] 341.71M 13.5MB/s eta 54s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-L6-D2048-E0_01-enw 33%[=====> ] 344.93M 13.5MB/s eta 54s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "L6-D2048-E0_01-enwi 34%[=====> ] 348.18M 13.5MB/s eta 54s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "6-D2048-E0_01-enwik 34%[=====> ] 351.45M 13.6MB/s eta 54s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-D2048-E0_01-enwiki 34%[=====> ] 354.68M 13.6MB/s eta 52s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "D2048-E0_01-enwiki- 35%[======> ] 357.89M 13.6MB/s eta 52s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "2048-E0_01-enwiki-4 35%[======> ] 361.12M 13.6MB/s eta 52s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "048-E0_01-enwiki-4k 35%[======> ] 364.36M 13.6MB/s eta 52s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "48-E0_01-enwiki-4k- 36%[======> ] 367.68M 13.7MB/s eta 52s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "8-E0_01-enwiki-4k-p 36%[======> ] 371.07M 13.7MB/s eta 51s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-E0_01-enwiki-4k-p1 36%[======> ] 374.43M 13.8MB/s eta 51s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "E0_01-enwiki-4k-p1. 37%[======> ] 377.78M 13.9MB/s eta 51s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "0_01-enwiki-4k-p1.p 37%[======> ] 381.23M 13.9MB/s eta 51s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "_01-enwiki-4k-p1.pt 37%[======> ] 384.14M 13.8MB/s eta 51s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "01-enwiki-4k-p1.pth 38%[======> ] 387.65M 13.9MB/s eta 49s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "1-enwiki-4k-p1.pth 38%[======> ] 391.20M 14.0MB/s eta 49s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-enwiki-4k-p1.pth 38%[======> ] 394.79M 14.4MB/s eta 49s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "enwiki-4k-p1.pth 39%[======> ] 398.20M 14.4MB/s eta 49s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "nwiki-4k-p1.pth 39%[======> ] 401.82M 14.5MB/s eta 49s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "wiki-4k-p1.pth 39%[======> ] 405.51M 14.6MB/s eta 48s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "iki-4k-p1.pth 40%[=======> ] 409.25M 14.8MB/s eta 48s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "ki-4k-p1.pth 40%[=======> ] 413.03M 14.9MB/s eta 48s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "i-4k-p1.pth 40%[=======> ] 416.84M 15.0MB/s eta 48s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-4k-p1.pth 41%[=======> ] 420.68M 15.1MB/s eta 48s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "4k-p1.pth 41%[=======> ] 424.43M 15.2MB/s eta 46s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "k-p1.pth 42%[=======> ] 428.31M 15.4MB/s eta 46s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-p1.pth 42%[=======> ] 430.81M 15.2MB/s eta 46s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "p1.pth 42%[=======> ] 434.56M 15.3MB/s eta 46s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "1.pth 43%[=======> ] 437.71M 15.3MB/s eta 46s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", ".pth 43%[=======> ] 441.43M 15.3MB/s eta 44s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "pth 43%[=======> ] 445.15M 15.3MB/s eta 44s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "th 44%[=======> ] 449.07M 15.5MB/s eta 44s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "h 44%[=======> ] 452.84M 15.6MB/s eta 44s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 44%[=======> ] 456.57M 15.8MB/s eta 44s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v 45%[========> ] 460.32M 15.8MB/s eta 42s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5 45%[========> ] 464.25M 15.9MB/s eta 42s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5- 46%[========> ] 468.06M 16.0MB/s eta 42s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L 46%[========> ] 471.79M 16.0MB/s eta 42s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6 46%[========> ] 475.67M 16.1MB/s eta 42s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6- 47%[========> ] 479.40M 16.1MB/s eta 41s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D 47%[========> ] 483.12M 16.1MB/s eta 41s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2 47%[========> ] 486.84M 16.1MB/s eta 41s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D20 48%[========> ] 490.81M 16.1MB/s eta 41s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D204 48%[========> ] 494.53M 16.1MB/s eta 41s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048 48%[========> ] 498.31M 16.1MB/s eta 39s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048- 49%[========> ] 502.36M 15.4MB/s eta 39s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048-E 49%[========> ] 506.37M 15.7MB/s eta 39s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048-E0 50%[=========> ] 509.48M 15.6MB/s eta 39s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048-E0_ 50%[=========> ] 512.36M 15.5MB/s eta 38s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048-E0_0 50%[=========> ] 515.75M 15.4MB/s eta 38s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048-E0_01 51%[=========> ] 519.18M 15.4MB/s eta 38s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048-E0_01- 51%[=========> ] 522.68M 15.3MB/s eta 38s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "v5-L6-D2048-E0_01-e 51%[=========> ] 526.23M 15.3MB/s eta 38s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "5-L6-D2048-E0_01-en 51%[=========> ] 528.79M 15.0MB/s eta 37s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-L6-D2048-E0_01-enw 52%[=========> ] 532.37M 15.0MB/s eta 37s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "L6-D2048-E0_01-enwi 52%[=========> ] 536.09M 14.9MB/s eta 37s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "6-D2048-E0_01-enwik 53%[=========> ] 539.86M 15.0MB/s eta 37s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-D2048-E0_01-enwiki 53%[=========> ] 543.56M 15.0MB/s eta 37s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "D2048-E0_01-enwiki- 53%[=========> ] 547.28M 14.9MB/s eta 35s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "2048-E0_01-enwiki-4 54%[=========> ] 551.03M 14.9MB/s eta 35s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "048-E0_01-enwiki-4k 54%[=========> ] 554.95M 15.0MB/s eta 35s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "48-E0_01-enwiki-4k- 54%[=========> ] 558.81M 15.0MB/s eta 35s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "8-E0_01-enwiki-4k-p 55%[==========> ] 562.56M 14.9MB/s eta 35s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-E0_01-enwiki-4k-p1 55%[==========> ] 566.28M 14.9MB/s eta 33s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "E0_01-enwiki-4k-p1. 56%[==========> ] 570.00M 14.9MB/s eta 33s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "0_01-enwiki-4k-p1.p 56%[==========> ] 573.81M 15.6MB/s eta 33s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "_01-enwiki-4k-p1.pt 56%[==========> ] 577.53M 15.5MB/s eta 33s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "01-enwiki-4k-p1.pth 57%[==========> ] 581.31M 15.7MB/s eta 33s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "1-enwiki-4k-p1.pth 57%[==========> ] 585.31M 15.9MB/s eta 32s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-enwiki-4k-p1.pth 57%[==========> ] 587.75M 14.9MB/s eta 32s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "enwiki-4k-p1.pth 58%[==========> ] 591.68M 15.1MB/s eta 32s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "nwiki-4k-p1.pth 58%[==========> ] 594.63M 14.9MB/s eta 32s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "wiki-4k-p1.pth 58%[==========> ] 597.62M 14.8MB/s eta 31s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "iki-4k-p1.pth 59%[==========> ] 600.68M 14.9MB/s eta 31s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "ki-4k-p1.pth 59%[==========> ] 603.65M 14.8MB/s eta 31s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "i-4k-p1.pth 59%[==========> ] 606.79M 14.7MB/s eta 31s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-4k-p1.pth 59%[==========> ] 609.53M 14.5MB/s eta 31s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "4k-p1.pth 60%[===========> ] 612.65M 14.3MB/s eta 30s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "k-p1.pth 60%[===========> ] 615.17M 14.1MB/s eta 30s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-p1.pth 60%[===========> ] 618.32M 14.0MB/s eta 30s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "p1.pth 61%[===========> ] 621.53M 13.9MB/s eta 30s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "1.pth 61%[===========> ] 624.79M 13.8MB/s eta 30s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", ".pth 61%[===========> ] 627.56M 13.6MB/s eta 29s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "pth 62%[===========> ] 630.89M 13.5MB/s eta 29s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "th 62%[===========> ] 633.40M 13.2MB/s eta 29s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "h 62%[===========> ] 636.68M 13.1MB/s eta 29s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 62%[===========> ] 639.39M 12.9MB/s eta 29s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v 63%[===========> ] 642.81M 12.9MB/s eta 28s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5 63%[===========> ] 646.25M 12.7MB/s eta 28s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5- 63%[===========> ] 649.65M 13.6MB/s eta 28s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L 64%[===========> ] 652.26M 13.3MB/s eta 28s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6 64%[===========> ] 655.62M 13.4MB/s eta 28s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6- 64%[===========> ] 659.11M 13.5MB/s eta 26s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D 65%[============> ] 661.76M 13.4MB/s eta 26s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2 65%[============> ] 665.25M 13.5MB/s eta 26s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D20 65%[============> ] 668.78M 13.6MB/s eta 26s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D204 66%[============> ] 672.26M 13.8MB/s eta 26s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048 66%[============> ] 675.79M 13.8MB/s eta 25s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048- 66%[============> ] 679.31M 14.0MB/s eta 25s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048-E 67%[============> ] 682.84M 14.1MB/s eta 25s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048-E0 67%[============> ] 686.39M 14.2MB/s eta 25s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048-E0_ 67%[============> ] 689.92M 14.2MB/s eta 25s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048-E0_0 68%[============> ] 693.46M 14.4MB/s eta 24s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048-E0_01 68%[============> ] 697.03M 14.5MB/s eta 24s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048-E0_01- 68%[============> ] 700.59M 14.7MB/s eta 24s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "v5-L6-D2048-E0_01-e 69%[============> ] 704.17M 14.7MB/s eta 24s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "5-L6-D2048-E0_01-en 69%[============> ] 707.70M 14.9MB/s eta 24s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-L6-D2048-E0_01-enw 69%[============> ] 711.28M 14.9MB/s eta 22s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "L6-D2048-E0_01-enwi 70%[=============> ] 713.36M 14.4MB/s eta 22s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "6-D2048-E0_01-enwik 70%[=============> ] 717.18M 14.4MB/s eta 22s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-D2048-E0_01-enwiki 70%[=============> ] 719.67M 14.4MB/s eta 22s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "D2048-E0_01-enwiki- 71%[=============> ] 722.21M 13.9MB/s eta 22s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "2048-E0_01-enwiki-4 71%[=============> ] 727.48M 14.0MB/s eta 22s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "048-E0_01-enwiki-4k 71%[=============> ] 730.17M 13.8MB/s eta 22s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "48-E0_01-enwiki-4k- 72%[=============> ] 732.87M 13.6MB/s eta 22s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "8-E0_01-enwiki-4k-p 72%[=============> ] 735.59M 13.4MB/s eta 21s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-E0_01-enwiki-4k-p1 72%[=============> ] 738.36M 13.3MB/s eta 21s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "E0_01-enwiki-4k-p1. 72%[=============> ] 741.14M 13.2MB/s eta 21s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "0_01-enwiki-4k-p1.p 73%[=============> ] 743.93M 13.0MB/s eta 21s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "_01-enwiki-4k-p1.pt 73%[=============> ] 746.75M 12.8MB/s eta 21s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "01-enwiki-4k-p1.pth 73%[=============> ] 749.59M 12.7MB/s eta 20s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "1-enwiki-4k-p1.pth 73%[=============> ] 752.45M 12.6MB/s eta 20s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-enwiki-4k-p1.pth 74%[=============> ] 755.32M 12.4MB/s eta 20s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "enwiki-4k-p1.pth 74%[=============> ] 758.14M 12.3MB/s eta 20s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "nwiki-4k-p1.pth 74%[=============> ] 761.04M 12.2MB/s eta 20s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "wiki-4k-p1.pth 75%[==============> ] 763.96M 12.0MB/s eta 19s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "iki-4k-p1.pth 75%[==============> ] 766.90M 11.9MB/s eta 19s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "ki-4k-p1.pth 75%[==============> ] 769.86M 12.3MB/s eta 19s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "i-4k-p1.pth 75%[==============> ] 772.81M 12.1MB/s eta 19s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-4k-p1.pth 76%[==============> ] 775.78M 12.2MB/s eta 19s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "4k-p1.pth 76%[==============> ] 778.73M 12.6MB/s eta 18s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "k-p1.pth 76%[==============> ] 781.71M 12.5MB/s eta 18s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-p1.pth 77%[==============> ] 784.70M 12.6MB/s eta 18s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "p1.pth 77%[==============> ] 787.70M 12.5MB/s eta 18s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "1.pth 77%[==============> ] 790.71M 12.6MB/s eta 18s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", ".pth 78%[==============> ] 793.71M 12.8MB/s eta 17s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "pth 78%[==============> ] 796.73M 12.8MB/s eta 17s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "th 78%[==============> ] 799.75M 12.9MB/s eta 17s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "h 78%[==============> ] 802.78M 12.9MB/s eta 17s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 79%[==============> ] 805.79M 13.0MB/s eta 17s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v 79%[==============> ] 808.82M 13.0MB/s eta 15s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5 79%[==============> ] 811.87M 13.1MB/s eta 15s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5- 80%[===============> ] 814.92M 13.1MB/s eta 15s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L 80%[===============> ] 817.95M 13.2MB/s eta 15s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6 80%[===============> ] 820.45M 13.1MB/s eta 15s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6- 80%[===============> ] 823.50M 13.1MB/s eta 14s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D 81%[===============> ] 826.54M 13.1MB/s eta 14s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2 81%[===============> ] 829.59M 13.2MB/s eta 14s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D20 81%[===============> ] 832.64M 13.2MB/s eta 14s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D204 82%[===============> ] 835.62M 13.2MB/s eta 14s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048 82%[===============> ] 838.67M 13.2MB/s eta 13s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048- 82%[===============> ] 841.71M 13.2MB/s eta 13s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048-E 82%[===============> ] 844.18M 13.1MB/s eta 13s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048-E0 83%[===============> ] 847.23M 13.1MB/s eta 13s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048-E0_ 83%[===============> ] 850.28M 13.1MB/s eta 13s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048-E0_0 83%[===============> ] 852.89M 13.0MB/s eta 12s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048-E0_01 84%[===============> ] 855.93M 13.0MB/s eta 12s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048-E0_01- 84%[===============> ] 858.98M 13.0MB/s eta 12s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "v5-L6-D2048-E0_01-e 84%[===============> ] 862.03M 13.0MB/s eta 12s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "5-L6-D2048-E0_01-en 85%[================> ] 865.07M 13.0MB/s eta 12s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-L6-D2048-E0_01-enw 85%[================> ] 868.12M 13.0MB/s eta 11s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "L6-D2048-E0_01-enwi 85%[================> ] 871.17M 13.0MB/s eta 11s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "6-D2048-E0_01-enwik 85%[================> ] 874.21M 13.0MB/s eta 11s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-D2048-E0_01-enwiki 86%[================> ] 877.26M 13.0MB/s eta 11s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "D2048-E0_01-enwiki- 86%[================> ] 880.32M 13.2MB/s eta 11s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "2048-E0_01-enwiki-4 86%[================> ] 883.37M 13.2MB/s eta 10s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "048-E0_01-enwiki-4k 87%[================> ] 886.43M 13.2MB/s eta 10s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "48-E0_01-enwiki-4k- 87%[================> ] 889.50M 13.2MB/s eta 10s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "8-E0_01-enwiki-4k-p 87%[================> ] 892.57M 13.2MB/s eta 10s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-E0_01-enwiki-4k-p1 88%[================> ] 895.65M 13.2MB/s eta 10s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "E0_01-enwiki-4k-p1. 88%[================> ] 898.75M 13.2MB/s eta 9s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "0_01-enwiki-4k-p1.p 88%[================> ] 901.84M 13.2MB/s eta 9s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "_01-enwiki-4k-p1.pt 88%[================> ] 904.95M 13.4MB/s eta 9s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "01-enwiki-4k-p1.pth 89%[================> ] 908.06M 13.4MB/s eta 9s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "1-enwiki-4k-p1.pth 89%[================> ] 911.17M 13.4MB/s eta 9s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-enwiki-4k-p1.pth 89%[================> ] 914.29M 13.5MB/s eta 8s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "enwiki-4k-p1.pth 90%[=================> ] 917.43M 13.5MB/s eta 8s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "nwiki-4k-p1.pth 90%[=================> ] 920.59M 13.6MB/s eta 8s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "wiki-4k-p1.pth 90%[=================> ] 923.75M 13.6MB/s eta 8s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "iki-4k-p1.pth 91%[=================> ] 926.93M 13.6MB/s eta 8s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "ki-4k-p1.pth 91%[=================> ] 930.11M 13.6MB/s eta 6s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "i-4k-p1.pth 91%[=================> ] 933.21M 13.7MB/s eta 6s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-4k-p1.pth 92%[=================> ] 936.34M 13.7MB/s eta 6s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "4k-p1.pth 92%[=================> ] 939.48M 13.7MB/s eta 6s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "k-p1.pth 92%[=================> ] 942.75M 13.7MB/s eta 6s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-p1.pth 93%[=================> ] 946.03M 13.8MB/s eta 5s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "p1.pth 93%[=================> ] 949.34M 13.9MB/s eta 5s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "1.pth 93%[=================> ] 952.65M 13.9MB/s eta 5s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", ".pth 93%[=================> ] 956.01M 14.0MB/s eta 5s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "pth 94%[=================> ] 959.39M 14.0MB/s eta 5s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "th 94%[=================> ] 962.78M 14.1MB/s eta 4s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "h 94%[=================> ] 966.20M 14.2MB/s eta 4s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 95%[==================> ] 969.67M 14.3MB/s eta 4s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v 95%[==================> ] 973.17M 14.3MB/s eta 4s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5 96%[==================> ] 976.57M 14.4MB/s eta 4s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5- 96%[==================> ] 980.14M 14.5MB/s eta 3s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L 96%[==================> ] 983.73M 14.6MB/s eta 3s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6 97%[==================> ] 987.32M 14.7MB/s eta 3s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6- 97%[==================> ] 991.01M 14.9MB/s eta 3s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D 97%[==================> ] 994.73M 15.0MB/s eta 3s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2 98%[==================> ] 998.51M 14.8MB/s eta 1s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D20 98%[==================> ] 1002M 15.0MB/s eta 1s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D204 98%[==================> ] 1006M 15.1MB/s eta 1s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048 99%[==================> ] 1010M 15.2MB/s eta 1s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048- 99%[==================> ] 1012M 14.1MB/s eta 0s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048-E 99%[==================> ] 1015M 14.2MB/s eta 0s \r", "v5-L6-D2048-E0_01-e 100%[===================>] 1017M 14.5MB/s in 75s \r\n", "\r\n", "2023-10-09 13:46:22 (13.5 MB/s) - ‘v5-L6-D2048-E0_01-enwiki-4k-p1.pth’ saved [1066537217/1066537217]\r\n", "\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "--2023-10-09 13:46:23-- https://huggingface.co/rwkv-x-dev/rwkv-x-playground/resolve/main/experiment/rwkv-x-exp/multi-size-train/v5-L12-D2048-E0_01-neox-v5base-init.pth\r\n", "Resolving huggingface.co (huggingface.co)... 13.33.33.55, 13.33.33.110, 13.33.33.102, ...\r\n", "Connecting to huggingface.co (huggingface.co)|13.33.33.55|:443... connected.\r\n", "HTTP request sent, awaiting response... " ] }, { "name": "stdout", "output_type": "stream", "text": [ "302 Found\r\n", "Location: https://cdn-lfs.huggingface.co/repos/2e/f7/2ef78555202aa92abdbdf476ce3d0fd5a8b15f7245edf0b80d4d30572355f30d/06105d96413046fce0ec189b9c4685a813cfa7147300851c5d2afc7b5adbcb38?response-content-disposition=attachment%3B+filename*%3DUTF-8%27%27v5-L12-D2048-E0_01-neox-v5base-init.pth%3B+filename%3D%22v5-L12-D2048-E0_01-neox-v5base-init.pth%22%3B&Expires=1697118383&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTY5NzExODM4M319LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy5odWdnaW5nZmFjZS5jby9yZXBvcy8yZS9mNy8yZWY3ODU1NTIwMmFhOTJhYmRiZGY0NzZjZTNkMGZkNWE4YjE1ZjcyNDVlZGYwYjgwZDRkMzA1NzIzNTVmMzBkLzA2MTA1ZDk2NDEzMDQ2ZmNlMGVjMTg5YjljNDY4NWE4MTNjZmE3MTQ3MzAwODUxYzVkMmFmYzdiNWFkYmNiMzg%7EcmVzcG9uc2UtY29udGVudC1kaXNwb3NpdGlvbj0qIn1dfQ__&Signature=kzZilHhZvddaNFoit6Wo-sHUcFMwnJ-lyCrMqv8rODaw3nx1-atQMmw2NJlKDSPTrDtq-nsdN%7EXRDadCZxNdfOnVh41qrAbj4Rb9lqg7CPls1GRWS6j2tw4ZMZ151dO1DsdimId0RZllQb1bW4cyoR7KyoqejnW8lflzejQQfDsdNwBo8Xq2sL%7ENJDHP0TD9VsH3MA7tQrugSqmBuqH2tjelnYFMW4LwwYAxDIMS2MJLbr%7ENsjHATHzFb3lSLCNDrKJ5wp2U5yCbKgfJv3RlxCN2cH3K3Fl4jFsxlyDNzxOd9XNpBfAJpUIoES8nTUeZrs6DUkYY17RmEFQohbP5vA__&Key-Pair-Id=KVTP0A1DKRTAX [following]\r\n", "--2023-10-09 13:46:23-- https://cdn-lfs.huggingface.co/repos/2e/f7/2ef78555202aa92abdbdf476ce3d0fd5a8b15f7245edf0b80d4d30572355f30d/06105d96413046fce0ec189b9c4685a813cfa7147300851c5d2afc7b5adbcb38?response-content-disposition=attachment%3B+filename*%3DUTF-8%27%27v5-L12-D2048-E0_01-neox-v5base-init.pth%3B+filename%3D%22v5-L12-D2048-E0_01-neox-v5base-init.pth%22%3B&Expires=1697118383&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTY5NzExODM4M319LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy5odWdnaW5nZmFjZS5jby9yZXBvcy8yZS9mNy8yZWY3ODU1NTIwMmFhOTJhYmRiZGY0NzZjZTNkMGZkNWE4YjE1ZjcyNDVlZGYwYjgwZDRkMzA1NzIzNTVmMzBkLzA2MTA1ZDk2NDEzMDQ2ZmNlMGVjMTg5YjljNDY4NWE4MTNjZmE3MTQ3MzAwODUxYzVkMmFmYzdiNWFkYmNiMzg%7EcmVzcG9uc2UtY29udGVudC1kaXNwb3NpdGlvbj0qIn1dfQ__&Signature=kzZilHhZvddaNFoit6Wo-sHUcFMwnJ-lyCrMqv8rODaw3nx1-atQMmw2NJlKDSPTrDtq-nsdN%7EXRDadCZxNdfOnVh41qrAbj4Rb9lqg7CPls1GRWS6j2tw4ZMZ151dO1DsdimId0RZllQb1bW4cyoR7KyoqejnW8lflzejQQfDsdNwBo8Xq2sL%7ENJDHP0TD9VsH3MA7tQrugSqmBuqH2tjelnYFMW4LwwYAxDIMS2MJLbr%7ENsjHATHzFb3lSLCNDrKJ5wp2U5yCbKgfJv3RlxCN2cH3K3Fl4jFsxlyDNzxOd9XNpBfAJpUIoES8nTUeZrs6DUkYY17RmEFQohbP5vA__&Key-Pair-Id=KVTP0A1DKRTAX\r\n", "Resolving cdn-lfs.huggingface.co (cdn-lfs.huggingface.co)... " ] }, { "name": "stdout", "output_type": "stream", "text": [ "18.155.68.73, 18.155.68.128, 18.155.68.94, ...\r\n", "Connecting to cdn-lfs.huggingface.co (cdn-lfs.huggingface.co)|18.155.68.73|: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: 1721189797 (1.6G) [binary/octet-stream]\r\n", "Saving to: ‘v5-L12-D2048-E0_01-neox-v5base-init.pth’\r\n", "\r\n", "\r", " v5-L12-D2 0%[ ] 0 --.-KB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D20 0%[ ] 9.26K 40.6KB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D204 0%[ ] 41.26K 90.7KB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2048 0%[ ] 109.26K 160KB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2048- 0%[ ] 211.26K 232KB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2048-E 0%[ ] 449.26K 394KB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2048-E0 0%[ ] 925.26K 676KB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2048-E0_ 0%[ ] 1.82M 1.14MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2048-E0_0 0%[ ] 3.65M 2.00MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2048-E0_01 0%[ ] 7.26M 3.53MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "v5-L12-D2048-E0_01- 0%[ ] 10.79M 4.73MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "5-L12-D2048-E0_01-n 0%[ ] 14.65M 5.83MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-L12-D2048-E0_01-ne 1%[ ] 18.58M 6.77MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "L12-D2048-E0_01-neo 1%[ ] 22.33M 7.50MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "12-D2048-E0_01-neox 1%[ ] 26.14M 8.15MB/s eta 3m 18s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "2-D2048-E0_01-neox- 1%[ ] 29.93M 8.71MB/s eta 3m 18s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-D2048-E0_01-neox-v 2%[ ] 33.83M 9.22MB/s eta 3m 18s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "D2048-E0_01-neox-v5 2%[ ] 37.64M 9.65MB/s eta 3m 18s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "2048-E0_01-neox-v5b 2%[ ] 41.36M 10.0MB/s eta 3m 18s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "048-E0_01-neox-v5ba 2%[ ] 45.08M 10.3MB/s eta 2m 34s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "48-E0_01-neox-v5bas 2%[ ] 48.83M 10.6MB/s eta 2m 34s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "8-E0_01-neox-v5base 3%[ ] 52.09M 11.3MB/s eta 2m 34s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-E0_01-neox-v5base- 3%[ ] 55.98M 12.2MB/s eta 2m 34s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "E0_01-neox-v5base-i 3%[ ] 59.86M 13.0MB/s eta 2m 34s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "0_01-neox-v5base-in 3%[ ] 63.59M 13.8MB/s eta 2m 17s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "_01-neox-v5base-ini 4%[ ] 67.34M 14.5MB/s eta 2m 17s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "01-neox-v5base-init 4%[ ] 71.14M 15.2MB/s eta 2m 17s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "1-neox-v5base-init. 4%[ ] 75.03M 15.9MB/s eta 2m 17s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-neox-v5base-init.p 4%[ ] 78.84M 16.3MB/s eta 2m 17s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "neox-v5base-init.pt 5%[> ] 82.73M 16.3MB/s eta 2m 6s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "eox-v5base-init.pth 5%[> ] 86.64M 16.4MB/s eta 2m 6s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "ox-v5base-init.pth 5%[> ] 90.37M 16.4MB/s eta 2m 6s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "x-v5base-init.pth 5%[> ] 94.28M 16.4MB/s eta 2m 6s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-v5base-init.pth 5%[> ] 98.20M 16.4MB/s eta 2m 6s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "v5base-init.pth 6%[> ] 102.11M 16.5MB/s eta 1m 58s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "5base-init.pth 6%[> ] 105.84M 16.4MB/s eta 1m 58s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "base-init.pth 6%[> ] 109.56M 16.4MB/s eta 1m 58s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "ase-init.pth 6%[> ] 113.39M 16.4MB/s eta 1m 58s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "se-init.pth 7%[> ] 117.14M 16.4MB/s eta 1m 58s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "e-init.pth 7%[> ] 120.83M 16.4MB/s eta 1m 53s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-init.pth 7%[> ] 124.67M 16.4MB/s eta 1m 53s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "init.pth 7%[> ] 128.54M 16.6MB/s eta 1m 53s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "nit.pth 8%[> ] 132.43M 16.6MB/s eta 1m 53s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "it.pth 8%[> ] 136.18M 16.5MB/s eta 1m 53s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "t.pth 8%[> ] 139.95M 16.5MB/s eta 1m 49s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", ".pth 8%[> ] 143.79M 16.6MB/s eta 1m 49s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "pth 8%[> ] 147.70M 16.6MB/s eta 1m 49s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "th 9%[> ] 151.56M 16.6MB/s eta 1m 49s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "h 9%[> ] 155.33M 16.6MB/s eta 1m 49s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 9%[> ] 159.15M 16.6MB/s eta 1m 45s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v 9%[> ] 163.01M 16.5MB/s eta 1m 45s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5 10%[=> ] 166.86M 16.6MB/s eta 1m 45s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5- 10%[=> ] 170.62M 16.5MB/s eta 1m 45s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L 10%[=> ] 174.36M 16.5MB/s eta 1m 45s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L1 10%[=> ] 178.23M 16.5MB/s eta 1m 42s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12 11%[=> ] 182.08M 16.5MB/s eta 1m 42s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12- 11%[=> ] 185.81M 16.5MB/s eta 1m 42s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D 11%[=> ] 189.61M 16.5MB/s eta 1m 42s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2 11%[=> ] 193.42M 16.5MB/s eta 1m 42s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D20 12%[=> ] 197.18M 16.5MB/s eta 1m 40s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D204 12%[=> ] 201.04M 16.5MB/s eta 1m 40s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2048 12%[=> ] 203.64M 16.3MB/s eta 1m 40s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2048- 12%[=> ] 207.51M 16.3MB/s eta 1m 40s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2048-E 12%[=> ] 211.31M 16.3MB/s eta 1m 40s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2048-E0 13%[=> ] 215.08M 16.3MB/s eta 98s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2048-E0_ 13%[=> ] 218.98M 16.3MB/s eta 98s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2048-E0_0 13%[=> ] 222.92M 16.3MB/s eta 98s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2048-E0_01 13%[=> ] 226.67M 16.3MB/s eta 98s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "v5-L12-D2048-E0_01- 14%[=> ] 230.58M 16.3MB/s eta 98s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "5-L12-D2048-E0_01-n 14%[=> ] 234.40M 16.3MB/s eta 95s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-L12-D2048-E0_01-ne 14%[=> ] 238.25M 16.3MB/s eta 95s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "L12-D2048-E0_01-neo 14%[=> ] 242.03M 16.3MB/s eta 95s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "12-D2048-E0_01-neox 14%[=> ] 245.90M 16.3MB/s eta 95s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "2-D2048-E0_01-neox- 15%[==> ] 249.78M 16.3MB/s eta 95s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-D2048-E0_01-neox-v 15%[==> ] 253.64M 16.3MB/s eta 93s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "D2048-E0_01-neox-v5 15%[==> ] 257.47M 16.3MB/s eta 93s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "2048-E0_01-neox-v5b 15%[==> ] 261.33M 16.4MB/s eta 93s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "048-E0_01-neox-v5ba 16%[==> ] 265.09M 16.3MB/s eta 93s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "48-E0_01-neox-v5bas 16%[==> ] 268.98M 16.4MB/s eta 93s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "8-E0_01-neox-v5base 16%[==> ] 272.84M 16.4MB/s eta 91s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-E0_01-neox-v5base- 16%[==> ] 276.65M 16.4MB/s eta 91s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "E0_01-neox-v5base-i 17%[==> ] 280.51M 16.6MB/s eta 91s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "0_01-neox-v5base-in 17%[==> ] 284.26M 16.6MB/s eta 91s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "_01-neox-v5base-ini 17%[==> ] 288.12M 16.6MB/s eta 91s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "01-neox-v5base-init 17%[==> ] 291.93M 16.6MB/s eta 90s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "1-neox-v5base-init. 18%[==> ] 295.78M 16.6MB/s eta 90s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-neox-v5base-init.p 18%[==> ] 299.54M 16.6MB/s eta 90s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "neox-v5base-init.pt 18%[==> ] 303.33M 16.6MB/s eta 90s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "eox-v5base-init.pth 18%[==> ] 307.12M 16.6MB/s eta 90s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "ox-v5base-init.pth 18%[==> ] 310.92M 16.5MB/s eta 88s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "x-v5base-init.pth 19%[==> ] 313.47M 16.3MB/s eta 88s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-v5base-init.pth 19%[==> ] 317.25M 16.3MB/s eta 88s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "v5base-init.pth 19%[==> ] 319.84M 16.0MB/s eta 88s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "5base-init.pth 19%[==> ] 323.73M 16.0MB/s eta 88s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "base-init.pth 19%[==> ] 327.47M 16.0MB/s eta 87s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "ase-init.pth 20%[===> ] 331.25M 16.0MB/s eta 87s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "se-init.pth 20%[===> ] 335.01M 16.0MB/s eta 87s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "e-init.pth 20%[===> ] 338.84M 16.0MB/s eta 87s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-init.pth 20%[===> ] 342.62M 16.0MB/s eta 87s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "init.pth 21%[===> ] 346.36M 15.9MB/s eta 85s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "nit.pth 21%[===> ] 350.23M 15.9MB/s eta 85s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "it.pth 21%[===> ] 354.03M 15.9MB/s eta 85s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "t.pth 21%[===> ] 357.90M 16.0MB/s eta 85s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", ".pth 22%[===> ] 361.73M 16.0MB/s eta 85s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "pth 22%[===> ] 365.59M 16.0MB/s eta 84s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "th 22%[===> ] 369.33M 15.9MB/s eta 84s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "h 22%[===> ] 373.08M 15.9MB/s eta 84s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 22%[===> ] 376.92M 16.0MB/s eta 84s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v 23%[===> ] 380.76M 16.0MB/s eta 84s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5 23%[===> ] 384.56M 16.0MB/s eta 82s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5- 23%[===> ] 388.29M 16.2MB/s eta 82s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L 23%[===> ] 392.11M 16.2MB/s eta 82s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L1 24%[===> ] 395.89M 16.5MB/s eta 82s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12 24%[===> ] 399.76M 16.5MB/s eta 82s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12- 24%[===> ] 403.62M 16.4MB/s eta 81s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D 24%[===> ] 407.48M 16.5MB/s eta 81s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2 25%[====> ] 411.36M 16.5MB/s eta 81s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D20 25%[====> ] 415.09M 16.5MB/s eta 81s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D204 25%[====> ] 418.97M 16.5MB/s eta 81s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2048 25%[====> ] 422.73M 16.5MB/s eta 79s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2048- 25%[====> ] 426.48M 16.5MB/s eta 79s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2048-E 26%[====> ] 430.20M 16.5MB/s eta 79s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2048-E0 26%[====> ] 434.01M 16.5MB/s eta 79s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2048-E0_ 26%[====> ] 437.90M 16.5MB/s eta 79s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2048-E0_0 26%[====> ] 441.73M 16.5MB/s eta 78s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2048-E0_01 27%[====> ] 445.64M 16.5MB/s eta 78s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "v5-L12-D2048-E0_01- 27%[====> ] 449.48M 16.5MB/s eta 78s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "5-L12-D2048-E0_01-n 27%[====> ] 453.33M 16.6MB/s eta 78s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-L12-D2048-E0_01-ne 27%[====> ] 457.20M 16.6MB/s eta 78s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "L12-D2048-E0_01-neo 28%[====> ] 461.09M 16.6MB/s eta 76s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "12-D2048-E0_01-neox 28%[====> ] 464.89M 16.6MB/s eta 76s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "2-D2048-E0_01-neox- 28%[====> ] 468.67M 16.6MB/s eta 76s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-D2048-E0_01-neox-v 28%[====> ] 472.47M 16.6MB/s eta 76s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "D2048-E0_01-neox-v5 29%[====> ] 476.37M 16.6MB/s eta 76s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "2048-E0_01-neox-v5b 29%[====> ] 480.20M 16.6MB/s eta 75s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "048-E0_01-neox-v5ba 29%[====> ] 484.06M 16.6MB/s eta 75s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "48-E0_01-neox-v5bas 29%[====> ] 487.95M 16.6MB/s eta 75s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "8-E0_01-neox-v5base 29%[====> ] 491.75M 16.6MB/s eta 75s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-E0_01-neox-v5base- 30%[=====> ] 495.61M 16.6MB/s eta 75s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "E0_01-neox-v5base-i 30%[=====> ] 499.36M 16.6MB/s eta 73s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "0_01-neox-v5base-in 30%[=====> ] 503.23M 16.6MB/s eta 73s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "_01-neox-v5base-ini 30%[=====> ] 507.04M 16.6MB/s eta 73s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "01-neox-v5base-init 31%[=====> ] 510.78M 16.6MB/s eta 73s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "1-neox-v5base-init. 31%[=====> ] 514.51M 16.5MB/s eta 73s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-neox-v5base-init.p 31%[=====> ] 518.26M 16.5MB/s eta 72s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "neox-v5base-init.pt 31%[=====> ] 522.08M 16.5MB/s eta 72s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "eox-v5base-init.pth 32%[=====> ] 525.81M 16.5MB/s eta 72s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "ox-v5base-init.pth 32%[=====> ] 529.58M 16.5MB/s eta 72s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "x-v5base-init.pth 32%[=====> ] 533.40M 16.5MB/s eta 72s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-v5base-init.pth 32%[=====> ] 537.23M 16.4MB/s eta 71s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "v5base-init.pth 32%[=====> ] 540.59M 16.4MB/s eta 71s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "5base-init.pth 33%[=====> ] 544.48M 16.4MB/s eta 71s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "base-init.pth 33%[=====> ] 548.28M 16.4MB/s eta 71s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "ase-init.pth 33%[=====> ] 552.15M 16.4MB/s eta 71s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "se-init.pth 33%[=====> ] 555.98M 16.4MB/s eta 69s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "e-init.pth 34%[=====> ] 559.87M 16.4MB/s eta 69s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-init.pth 34%[=====> ] 563.75M 16.4MB/s eta 69s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "init.pth 34%[=====> ] 567.64M 16.4MB/s eta 69s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "nit.pth 34%[=====> ] 571.48M 16.4MB/s eta 69s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "it.pth 35%[======> ] 575.31M 16.4MB/s eta 68s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "t.pth 35%[======> ] 579.23M 16.4MB/s eta 68s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", ".pth 35%[======> ] 583.00M 16.4MB/s eta 68s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "pth 35%[======> ] 586.73M 16.4MB/s eta 68s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "th 35%[======> ] 590.50M 16.4MB/s eta 68s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "h 36%[======> ] 593.50M 16.3MB/s eta 67s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 36%[======> ] 597.25M 16.3MB/s eta 67s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v 36%[======> ] 601.20M 16.3MB/s eta 67s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5 36%[======> ] 605.00M 16.3MB/s eta 67s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5- 37%[======> ] 608.84M 16.3MB/s eta 67s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L 37%[======> ] 612.59M 16.3MB/s eta 66s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L1 37%[======> ] 616.33M 16.3MB/s eta 66s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12 37%[======> ] 618.95M 16.1MB/s eta 66s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12- 37%[======> ] 622.68M 16.1MB/s eta 66s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D 38%[======> ] 626.40M 16.1MB/s eta 66s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2 38%[======> ] 630.28M 16.1MB/s eta 64s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D20 38%[======> ] 634.01M 16.0MB/s eta 64s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D204 38%[======> ] 637.87M 16.0MB/s eta 64s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2048 39%[======> ] 641.64M 16.0MB/s eta 64s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2048- 39%[======> ] 645.51M 16.0MB/s eta 64s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2048-E 39%[======> ] 649.36M 16.0MB/s eta 63s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2048-E0 39%[======> ] 653.20M 16.0MB/s eta 63s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2048-E0_ 40%[=======> ] 657.01M 16.0MB/s eta 63s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2048-E0_0 40%[=======> ] 660.78M 16.0MB/s eta 63s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2048-E0_01 40%[=======> ] 664.53M 16.0MB/s eta 63s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "v5-L12-D2048-E0_01- 40%[=======> ] 668.34M 16.2MB/s eta 62s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "5-L12-D2048-E0_01-n 40%[=======> ] 672.08M 16.2MB/s eta 62s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-L12-D2048-E0_01-ne 41%[=======> ] 675.97M 16.2MB/s eta 62s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "L12-D2048-E0_01-neo 41%[=======> ] 679.79M 16.2MB/s eta 62s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "12-D2048-E0_01-neox 41%[=======> ] 683.59M 16.2MB/s eta 62s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "2-D2048-E0_01-neox- 41%[=======> ] 687.45M 16.2MB/s eta 61s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-D2048-E0_01-neox-v 42%[=======> ] 691.25M 16.2MB/s eta 61s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "D2048-E0_01-neox-v5 42%[=======> ] 695.04M 16.5MB/s eta 61s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "2048-E0_01-neox-v5b 42%[=======> ] 698.93M 16.5MB/s eta 61s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "048-E0_01-neox-v5ba 42%[=======> ] 702.75M 16.5MB/s eta 61s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "48-E0_01-neox-v5bas 43%[=======> ] 706.48M 16.5MB/s eta 59s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "8-E0_01-neox-v5base 43%[=======> ] 710.29M 16.5MB/s eta 59s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-E0_01-neox-v5base- 43%[=======> ] 713.42M 16.4MB/s eta 59s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "E0_01-neox-v5base-i 43%[=======> ] 717.29M 16.4MB/s eta 59s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "0_01-neox-v5base-in 43%[=======> ] 721.04M 16.4MB/s eta 59s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "_01-neox-v5base-ini 44%[=======> ] 724.87M 16.3MB/s eta 58s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "01-neox-v5base-init 44%[=======> ] 728.73M 16.3MB/s eta 58s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "1-neox-v5base-init. 44%[=======> ] 732.53M 16.3MB/s eta 58s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-neox-v5base-init.p 44%[=======> ] 736.26M 16.3MB/s eta 58s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "neox-v5base-init.pt 45%[========> ] 740.12M 16.3MB/s eta 58s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "eox-v5base-init.pth 45%[========> ] 743.90M 16.3MB/s eta 57s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "ox-v5base-init.pth 45%[========> ] 747.73M 16.3MB/s eta 57s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "x-v5base-init.pth 45%[========> ] 751.58M 16.4MB/s eta 57s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-v5base-init.pth 46%[========> ] 755.40M 16.3MB/s eta 57s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "v5base-init.pth 46%[========> ] 759.28M 16.4MB/s eta 57s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "5base-init.pth 46%[========> ] 763.08M 16.4MB/s eta 56s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "base-init.pth 46%[========> ] 766.90M 16.4MB/s eta 56s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "ase-init.pth 46%[========> ] 770.68M 16.4MB/s eta 56s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "se-init.pth 47%[========> ] 774.43M 16.3MB/s eta 56s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "e-init.pth 47%[========> ] 778.31M 16.3MB/s eta 56s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-init.pth 47%[========> ] 782.14M 16.4MB/s eta 54s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "init.pth 47%[========> ] 785.90M 16.4MB/s eta 54s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "nit.pth 48%[========> ] 788.81M 16.3MB/s eta 54s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "it.pth 48%[========> ] 791.98M 16.2MB/s eta 54s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "t.pth 48%[========> ] 795.78M 16.2MB/s eta 54s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", ".pth 48%[========> ] 799.54M 16.2MB/s eta 53s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "pth 48%[========> ] 803.40M 16.2MB/s eta 53s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "th 49%[========> ] 807.14M 16.2MB/s eta 53s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "h 49%[========> ] 810.95M 16.2MB/s eta 53s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 49%[========> ] 814.73M 16.2MB/s eta 53s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v 49%[========> ] 818.50M 16.2MB/s eta 52s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5 50%[=========> ] 822.31M 16.2MB/s eta 52s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5- 50%[=========> ] 826.06M 16.1MB/s eta 52s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L 50%[=========> ] 829.89M 16.1MB/s eta 52s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L1 50%[=========> ] 833.72M 16.1MB/s eta 52s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12 51%[=========> ] 837.51M 16.1MB/s eta 51s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12- 51%[=========> ] 841.48M 16.1MB/s eta 51s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D 51%[=========> ] 845.23M 16.1MB/s eta 51s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2 51%[=========> ] 848.98M 16.1MB/s eta 51s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D20 51%[=========> ] 852.75M 16.1MB/s eta 51s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D204 52%[=========> ] 856.50M 16.1MB/s eta 50s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2048 52%[=========> ] 860.36M 16.1MB/s eta 50s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2048- 52%[=========> ] 864.23M 16.3MB/s eta 50s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2048-E 52%[=========> ] 868.08M 16.5MB/s eta 50s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2048-E0 53%[=========> ] 871.81M 16.5MB/s eta 50s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2048-E0_ 53%[=========> ] 875.61M 16.5MB/s eta 48s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2048-E0_0 53%[=========> ] 879.45M 16.5MB/s eta 48s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2048-E0_01 53%[=========> ] 883.68M 16.6MB/s eta 48s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "v5-L12-D2048-E0_01- 54%[=========> ] 887.53M 16.6MB/s eta 48s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "5-L12-D2048-E0_01-n 54%[=========> ] 891.48M 16.6MB/s eta 48s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-L12-D2048-E0_01-ne 54%[=========> ] 895.25M 16.6MB/s eta 47s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "L12-D2048-E0_01-neo 54%[=========> ] 899.06M 16.6MB/s eta 47s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "12-D2048-E0_01-neox 55%[==========> ] 902.84M 16.6MB/s eta 47s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "2-D2048-E0_01-neox- 55%[==========> ] 906.70M 16.6MB/s eta 47s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-D2048-E0_01-neox-v 55%[==========> ] 910.48M 16.6MB/s eta 47s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "D2048-E0_01-neox-v5 55%[==========> ] 914.26M 16.6MB/s eta 46s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "2048-E0_01-neox-v5b 55%[==========> ] 918.11M 16.6MB/s eta 46s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "048-E0_01-neox-v5ba 56%[==========> ] 921.98M 16.6MB/s eta 46s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "48-E0_01-neox-v5bas 56%[==========> ] 925.76M 16.6MB/s eta 46s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "8-E0_01-neox-v5base 56%[==========> ] 929.58M 16.6MB/s eta 46s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-E0_01-neox-v5base- 56%[==========> ] 933.36M 16.6MB/s eta 44s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "E0_01-neox-v5base-i 57%[==========> ] 937.22M 16.6MB/s eta 44s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "0_01-neox-v5base-in 57%[==========> ] 940.98M 16.6MB/s eta 44s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "_01-neox-v5base-ini 57%[==========> ] 945.00M 16.6MB/s eta 44s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "01-neox-v5base-init 57%[==========> ] 948.86M 16.6MB/s eta 44s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "1-neox-v5base-init. 58%[==========> ] 952.67M 16.6MB/s eta 43s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-neox-v5base-init.p 58%[==========> ] 956.40M 16.6MB/s eta 43s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "neox-v5base-init.pt 58%[==========> ] 960.17M 16.5MB/s eta 43s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "eox-v5base-init.pth 58%[==========> ] 964.00M 16.5MB/s eta 43s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "ox-v5base-init.pth 58%[==========> ] 967.76M 16.5MB/s eta 43s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "x-v5base-init.pth 59%[==========> ] 971.59M 16.5MB/s eta 42s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-v5base-init.pth 59%[==========> ] 975.39M 16.5MB/s eta 42s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "v5base-init.pth 59%[==========> ] 979.23M 16.5MB/s eta 42s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "5base-init.pth 59%[==========> ] 983.08M 16.5MB/s eta 42s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "base-init.pth 60%[===========> ] 986.81M 16.5MB/s eta 42s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "ase-init.pth 60%[===========> ] 990.62M 16.5MB/s eta 41s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "se-init.pth 60%[===========> ] 994.34M 16.5MB/s eta 41s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "e-init.pth 60%[===========> ] 998.06M 16.5MB/s eta 41s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-init.pth 61%[===========> ] 1002M 16.5MB/s eta 41s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "init.pth 61%[===========> ] 1005M 16.2MB/s eta 41s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "nit.pth 61%[===========> ] 1008M 16.2MB/s eta 40s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "it.pth 61%[===========> ] 1011M 16.0MB/s eta 40s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "t.pth 61%[===========> ] 1015M 16.0MB/s eta 40s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", ".pth 62%[===========> ] 1018M 15.9MB/s eta 40s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "pth 62%[===========> ] 1022M 15.9MB/s eta 40s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "th 62%[===========> ] 1.00G 15.9MB/s eta 39s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "h 62%[===========> ] 1.00G 15.9MB/s eta 39s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 62%[===========> ] 1.01G 15.9MB/s eta 39s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v 63%[===========> ] 1.01G 15.9MB/s eta 39s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5 63%[===========> ] 1.02G 15.9MB/s eta 39s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5- 63%[===========> ] 1.02G 15.9MB/s eta 37s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L 63%[===========> ] 1.02G 15.9MB/s eta 37s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L1 64%[===========> ] 1.03G 15.9MB/s eta 37s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12 64%[===========> ] 1.03G 15.9MB/s eta 37s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12- 64%[===========> ] 1.04G 15.9MB/s eta 37s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D 64%[===========> ] 1.04G 15.9MB/s eta 36s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2 65%[============> ] 1.04G 15.9MB/s eta 36s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D20 65%[============> ] 1.05G 15.9MB/s eta 36s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D204 65%[============> ] 1.05G 15.9MB/s eta 36s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2048 65%[============> ] 1.05G 16.1MB/s eta 36s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2048- 65%[============> ] 1.06G 15.9MB/s eta 35s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2048-E 66%[============> ] 1.06G 16.1MB/s eta 35s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2048-E0 66%[============> ] 1.06G 16.1MB/s eta 35s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2048-E0_ 66%[============> ] 1.07G 16.1MB/s eta 35s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2048-E0_0 66%[============> ] 1.07G 16.2MB/s eta 35s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2048-E0_01 67%[============> ] 1.07G 16.2MB/s eta 34s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "v5-L12-D2048-E0_01- 67%[============> ] 1.08G 16.2MB/s eta 34s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "5-L12-D2048-E0_01-n 67%[============> ] 1.08G 16.2MB/s eta 34s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-L12-D2048-E0_01-ne 67%[============> ] 1.09G 16.2MB/s eta 34s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "L12-D2048-E0_01-neo 67%[============> ] 1.09G 16.2MB/s eta 34s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "12-D2048-E0_01-neox 68%[============> ] 1.09G 16.2MB/s eta 33s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "2-D2048-E0_01-neox- 68%[============> ] 1.10G 16.2MB/s eta 33s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-D2048-E0_01-neox-v 68%[============> ] 1.10G 16.2MB/s eta 33s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "D2048-E0_01-neox-v5 68%[============> ] 1.10G 16.2MB/s eta 33s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "2048-E0_01-neox-v5b 69%[============> ] 1.11G 16.2MB/s eta 33s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "048-E0_01-neox-v5ba 69%[============> ] 1.11G 16.2MB/s eta 31s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "48-E0_01-neox-v5bas 69%[============> ] 1.11G 16.1MB/s eta 31s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "8-E0_01-neox-v5base 69%[============> ] 1.12G 16.1MB/s eta 31s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-E0_01-neox-v5base- 70%[=============> ] 1.12G 16.1MB/s eta 31s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "E0_01-neox-v5base-i 70%[=============> ] 1.12G 15.9MB/s eta 31s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "0_01-neox-v5base-in 70%[=============> ] 1.13G 16.2MB/s eta 30s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "_01-neox-v5base-ini 70%[=============> ] 1.13G 16.2MB/s eta 30s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "01-neox-v5base-init 70%[=============> ] 1.14G 16.2MB/s eta 30s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "1-neox-v5base-init. 71%[=============> ] 1.14G 16.2MB/s eta 30s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-neox-v5base-init.p 71%[=============> ] 1.14G 16.2MB/s eta 30s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "neox-v5base-init.pt 71%[=============> ] 1.15G 16.3MB/s eta 29s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "eox-v5base-init.pth 71%[=============> ] 1.15G 16.3MB/s eta 29s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "ox-v5base-init.pth 72%[=============> ] 1.16G 16.3MB/s eta 29s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "x-v5base-init.pth 72%[=============> ] 1.16G 16.3MB/s eta 29s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-v5base-init.pth 72%[=============> ] 1.16G 16.3MB/s eta 29s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "v5base-init.pth 72%[=============> ] 1.17G 16.3MB/s eta 28s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "5base-init.pth 73%[=============> ] 1.17G 16.3MB/s eta 28s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "base-init.pth 73%[=============> ] 1.17G 16.3MB/s eta 28s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "ase-init.pth 73%[=============> ] 1.18G 16.3MB/s eta 28s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "se-init.pth 73%[=============> ] 1.18G 16.3MB/s eta 28s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "e-init.pth 73%[=============> ] 1.19G 16.4MB/s eta 27s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-init.pth 74%[=============> ] 1.19G 16.5MB/s eta 27s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "init.pth 74%[=============> ] 1.19G 16.5MB/s eta 27s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "nit.pth 74%[=============> ] 1.20G 16.5MB/s eta 27s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "it.pth 74%[=============> ] 1.20G 16.7MB/s eta 27s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "t.pth 75%[==============> ] 1.20G 16.6MB/s eta 26s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", ".pth 75%[==============> ] 1.21G 16.6MB/s eta 26s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "pth 75%[==============> ] 1.21G 16.6MB/s eta 26s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "th 75%[==============> ] 1.21G 16.6MB/s eta 26s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "h 76%[==============> ] 1.22G 16.6MB/s eta 26s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 76%[==============> ] 1.22G 16.5MB/s eta 24s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v 76%[==============> ] 1.23G 16.5MB/s eta 24s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5 76%[==============> ] 1.23G 16.5MB/s eta 24s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5- 76%[==============> ] 1.23G 16.5MB/s eta 24s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L 77%[==============> ] 1.24G 16.5MB/s eta 24s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L1 77%[==============> ] 1.24G 16.5MB/s eta 23s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12 77%[==============> ] 1.25G 16.4MB/s eta 23s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12- 77%[==============> ] 1.25G 16.5MB/s eta 23s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D 78%[==============> ] 1.25G 16.5MB/s eta 23s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2 78%[==============> ] 1.26G 16.4MB/s eta 23s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D20 78%[==============> ] 1.26G 16.4MB/s eta 22s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D204 78%[==============> ] 1.26G 16.4MB/s eta 22s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2048 79%[==============> ] 1.27G 16.4MB/s eta 22s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2048- 79%[==============> ] 1.27G 16.4MB/s eta 22s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2048-E 79%[==============> ] 1.27G 16.4MB/s eta 22s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2048-E0 79%[==============> ] 1.28G 16.4MB/s eta 21s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2048-E0_ 80%[===============> ] 1.28G 16.4MB/s eta 21s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2048-E0_0 80%[===============> ] 1.29G 16.4MB/s eta 21s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2048-E0_01 80%[===============> ] 1.29G 16.4MB/s eta 21s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "v5-L12-D2048-E0_01- 80%[===============> ] 1.29G 16.4MB/s eta 21s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "5-L12-D2048-E0_01-n 80%[===============> ] 1.30G 16.5MB/s eta 20s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-L12-D2048-E0_01-ne 81%[===============> ] 1.30G 16.5MB/s eta 20s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "L12-D2048-E0_01-neo 81%[===============> ] 1.30G 16.5MB/s eta 20s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "12-D2048-E0_01-neox 81%[===============> ] 1.31G 16.5MB/s eta 20s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "2-D2048-E0_01-neox- 81%[===============> ] 1.31G 16.5MB/s eta 20s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-D2048-E0_01-neox-v 82%[===============> ] 1.32G 16.5MB/s eta 18s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "D2048-E0_01-neox-v5 82%[===============> ] 1.32G 16.5MB/s eta 18s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "2048-E0_01-neox-v5b 82%[===============> ] 1.32G 16.5MB/s eta 18s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "048-E0_01-neox-v5ba 82%[===============> ] 1.33G 16.5MB/s eta 18s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "48-E0_01-neox-v5bas 83%[===============> ] 1.33G 16.5MB/s eta 18s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "8-E0_01-neox-v5base 83%[===============> ] 1.33G 16.6MB/s eta 17s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-E0_01-neox-v5base- 83%[===============> ] 1.34G 16.6MB/s eta 17s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "E0_01-neox-v5base-i 83%[===============> ] 1.34G 16.6MB/s eta 17s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "0_01-neox-v5base-in 83%[===============> ] 1.35G 16.5MB/s eta 17s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "_01-neox-v5base-ini 84%[===============> ] 1.35G 16.6MB/s eta 17s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "01-neox-v5base-init 84%[===============> ] 1.35G 16.6MB/s eta 16s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "1-neox-v5base-init. 84%[===============> ] 1.36G 16.6MB/s eta 16s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-neox-v5base-init.p 84%[===============> ] 1.36G 16.6MB/s eta 16s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "neox-v5base-init.pt 85%[================> ] 1.36G 16.6MB/s eta 16s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "eox-v5base-init.pth 85%[================> ] 1.37G 16.6MB/s eta 16s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "ox-v5base-init.pth 85%[================> ] 1.37G 16.6MB/s eta 15s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "x-v5base-init.pth 85%[================> ] 1.38G 16.3MB/s eta 15s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-v5base-init.pth 86%[================> ] 1.38G 16.3MB/s eta 15s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "v5base-init.pth 86%[================> ] 1.38G 16.3MB/s eta 15s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "5base-init.pth 86%[================> ] 1.39G 16.4MB/s eta 15s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "base-init.pth 86%[================> ] 1.39G 16.4MB/s eta 14s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "ase-init.pth 86%[================> ] 1.39G 16.4MB/s eta 14s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "se-init.pth 87%[================> ] 1.40G 16.4MB/s eta 14s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "e-init.pth 87%[================> ] 1.40G 16.4MB/s eta 14s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-init.pth 87%[================> ] 1.41G 16.4MB/s eta 14s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "init.pth 87%[================> ] 1.41G 16.4MB/s eta 12s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "nit.pth 88%[================> ] 1.41G 16.4MB/s eta 12s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "it.pth 88%[================> ] 1.42G 16.4MB/s eta 12s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "t.pth 88%[================> ] 1.42G 16.4MB/s eta 12s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", ".pth 88%[================> ] 1.42G 16.2MB/s eta 12s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "pth 89%[================> ] 1.43G 16.2MB/s eta 11s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "th 89%[================> ] 1.43G 16.2MB/s eta 11s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "h 89%[================> ] 1.43G 16.2MB/s eta 11s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 89%[================> ] 1.44G 16.0MB/s eta 11s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v 89%[================> ] 1.44G 16.0MB/s eta 11s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5 90%[=================> ] 1.44G 16.0MB/s eta 10s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5- 90%[=================> ] 1.45G 16.2MB/s eta 10s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L 90%[=================> ] 1.45G 16.3MB/s eta 10s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L1 90%[=================> ] 1.46G 16.3MB/s eta 10s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12 91%[=================> ] 1.46G 16.2MB/s eta 10s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12- 91%[=================> ] 1.46G 16.2MB/s eta 9s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D 91%[=================> ] 1.47G 16.2MB/s eta 9s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2 91%[=================> ] 1.47G 16.1MB/s eta 9s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D20 91%[=================> ] 1.47G 15.3MB/s eta 9s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D204 91%[=================> ] 1.47G 15.3MB/s eta 9s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2048 92%[=================> ] 1.48G 15.2MB/s eta 8s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2048- 92%[=================> ] 1.48G 15.2MB/s eta 8s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2048-E 92%[=================> ] 1.48G 15.2MB/s eta 8s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2048-E0 92%[=================> ] 1.49G 15.1MB/s eta 8s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2048-E0_ 93%[=================> ] 1.49G 15.3MB/s eta 8s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2048-E0_0 93%[=================> ] 1.50G 15.3MB/s eta 7s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L12-D2048-E0_01 93%[=================> ] 1.50G 15.3MB/s eta 7s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "v5-L12-D2048-E0_01- 93%[=================> ] 1.50G 15.3MB/s eta 7s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "5-L12-D2048-E0_01-n 94%[=================> ] 1.51G 15.5MB/s eta 7s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-L12-D2048-E0_01-ne 94%[=================> ] 1.51G 15.5MB/s eta 7s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "L12-D2048-E0_01-neo 94%[=================> ] 1.51G 15.5MB/s eta 6s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "12-D2048-E0_01-neox 94%[=================> ] 1.52G 15.4MB/s eta 6s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "2-D2048-E0_01-neox- 94%[=================> ] 1.52G 15.4MB/s eta 6s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-D2048-E0_01-neox-v 95%[==================> ] 1.53G 15.4MB/s eta 6s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "D2048-E0_01-neox-v5 95%[==================> ] 1.53G 15.4MB/s eta 6s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "2048-E0_01-neox-v5b 95%[==================> ] 1.53G 15.4MB/s eta 4s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "048-E0_01-neox-v5ba 95%[==================> ] 1.54G 15.4MB/s eta 4s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "48-E0_01-neox-v5bas 96%[==================> ] 1.54G 15.5MB/s eta 4s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "8-E0_01-neox-v5base 96%[==================> ] 1.54G 16.0MB/s eta 4s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-E0_01-neox-v5base- 96%[==================> ] 1.55G 16.0MB/s eta 4s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "E0_01-neox-v5base-i 96%[==================> ] 1.55G 16.0MB/s eta 3s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "0_01-neox-v5base-in 96%[==================> ] 1.55G 16.0MB/s eta 3s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "_01-neox-v5base-ini 97%[==================> ] 1.56G 16.0MB/s eta 3s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "01-neox-v5base-init 97%[==================> ] 1.56G 16.0MB/s eta 3s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "1-neox-v5base-init. 97%[==================> ] 1.56G 16.0MB/s eta 3s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-neox-v5base-init.p 97%[==================> ] 1.57G 16.0MB/s eta 2s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "neox-v5base-init.pt 98%[==================> ] 1.57G 16.0MB/s eta 2s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "eox-v5base-init.pth 98%[==================> ] 1.58G 16.0MB/s eta 2s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "ox-v5base-init.pth 98%[==================> ] 1.58G 16.0MB/s eta 2s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "x-v5base-init.pth 98%[==================> ] 1.58G 16.0MB/s eta 2s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-v5base-init.pth 98%[==================> ] 1.59G 15.9MB/s eta 1s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "v5base-init.pth 99%[==================> ] 1.59G 16.0MB/s eta 1s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "5base-init.pth 99%[==================> ] 1.59G 16.1MB/s eta 1s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "base-init.pth 99%[==================> ] 1.60G 16.0MB/s eta 1s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "ase-init.pth 99%[==================> ] 1.60G 16.0MB/s eta 1s \r", "v5-L12-D2048-E0_01- 100%[===================>] 1.60G 16.3MB/s in 1m 42s \r\n", "\r\n", "2023-10-09 13:48:06 (16.0 MB/s) - ‘v5-L12-D2048-E0_01-neox-v5base-init.pth’ saved [1721189797/1721189797]\r\n", "\r\n" ] } ], "source": [ "# Get the init L12 model, and download the L6 model\n", "!cd \"{PROJECT_DIR}/model/\" && wget -nc \"https://huggingface.co/rwkv-x-dev/rwkv-x-playground/resolve/main/experiment/rwkv-x-exp/multi-size-train/v5-L6-D2048-E0_01-enwiki-4k-p1.pth\"\n", "!cd \"{PROJECT_DIR}/model/\" && wget -nc \"https://huggingface.co/rwkv-x-dev/rwkv-x-playground/resolve/main/experiment/rwkv-x-exp/multi-size-train/v5-L12-D2048-E0_01-neox-v5base-init.pth\"" ] }, { "cell_type": "code", "execution_count": 4, "id": "f0d2bb56", "metadata": { "execution": { "iopub.execute_input": "2023-10-09T13:48:07.098176Z", "iopub.status.busy": "2023-10-09T13:48:07.097929Z", "iopub.status.idle": "2023-10-09T13:48:09.573628Z", "shell.execute_reply": "2023-10-09T13:48:09.572808Z" }, "papermill": { "duration": 2.507798, "end_time": "2023-10-09T13:48:09.575915", "exception": false, "start_time": "2023-10-09T13:48:07.068117", "status": "completed" }, "tags": [] }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "---- Merging model ----\r\n", "Baseline model path: /actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/v5-L12-D2048-E0_01-neox-v5base-init.pth\r\n", "Source model path: /actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/v5-L6-D2048-E0_01-enwiki-4k-p1.pth\r\n", "Output model path: /actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/v5-L6+6-D2048-E0_01-layer-expansion-p1.pth\r\n", "Merge mode: layer_expansion\r\n", "---- ----- ----\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Merging blocks.0.att.gate.weight ...\r\n", "Traceback (most recent call last):\r\n", " File \"/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/RWKV-v5/model_merge.py\", line 143, in \r\n", " main()\r\n", " File \"/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/RWKV-v5/model_merge.py\", line 133, in main\r\n", " model_merge(\r\n", " File \"/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/RWKV-v5/model_merge.py\", line 102, in model_merge\r\n", " raise Exception(f\"Unknown merge mode: {merge_mode}\")\r\n", "Exception: Unknown merge mode: layer_expansion\r\n" ] } ], "source": [ "# Lets build the merged model\n", "!cd \"{TRAINER_DIR}\" && \\\n", " python3 model_merge.py \\\n", " --merge-mode=\"layer_expansion\" \\\n", " \"{PROJECT_DIR}/model/v5-L12-D2048-E0_01-neox-v5base-init.pth\" \\\n", " \"{PROJECT_DIR}/model/v5-L6-D2048-E0_01-enwiki-4k-p1.pth\" \\\n", " \"{PROJECT_DIR}/model/{FILENAME_PREFIX}-layer-expansion-p1.pth\"" ] }, { "cell_type": "code", "execution_count": 5, "id": "442ff792", "metadata": { "execution": { "iopub.execute_input": "2023-10-09T13:48:09.642247Z", "iopub.status.busy": "2023-10-09T13:48:09.641983Z", "iopub.status.idle": "2023-10-09T13:48:26.217655Z", "shell.execute_reply": "2023-10-09T13:48:26.216922Z" }, "papermill": { "duration": 16.607674, "end_time": "2023-10-09T13:48:26.219531", "exception": false, "start_time": "2023-10-09T13:48:09.611857", "status": "completed" }, "tags": [] }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\r", "Saving the dataset (0/2 shards): 0%| | 0/27202 [00:00\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-layer-expansion-p1.pth' does not exist\r\n", "\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 - Overwrite Merge Part 2 (train-ctx=4k, deepspeed_stage_2_offload)\u001b[0m at: \u001b[34m\u001b[4mhttps://wandb.ai/rwkv-x-dev/RWKV-5X-Experiments/runs/tl8hlm81\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/v12\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-20231009_134831-tl8hlm81/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-part2.yaml\" \\\n", " --trainer.logger.init_args.name=\"{WANDB_PREFIX} - Overwrite Merge Part 2 (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-p2/\" \\\n", " --model.load_model=\"../model/{FILENAME_PREFIX}-layer-expansion-p1.pth\" \\\n", " --model.ctx_len=4096 \\\n", " --model.bptt_learning_range=1" ] }, { "cell_type": "code", "execution_count": 7, "id": "1881f480", "metadata": { "execution": { "iopub.execute_input": "2023-10-09T13:48:44.732320Z", "iopub.status.busy": "2023-10-09T13:48:44.732037Z", "iopub.status.idle": "2023-10-09T13:48:47.165329Z", "shell.execute_reply": "2023-10-09T13:48:47.164581Z" }, "papermill": { "duration": 2.466466, "end_time": "2023-10-09T13:48:47.167249", "exception": false, "start_time": "2023-10-09T13:48:44.700783", "status": "completed" }, "tags": [] }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[2023-10-09 13:48:46,300] [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 \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-p2/last.ckpt/latest\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "ls: cannot access '../model/v5-L6+6-D2048-E0_01-layer-expansion-p2.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-p2/last.ckpt\" \"../model/{FILENAME_PREFIX}-layer-expansion-p2.pth\" \"bf16\"\n", "!cd \"{TRAINER_DIR}\" && ls -alh \"../model/{FILENAME_PREFIX}-layer-expansion-p2.pth\"" ] }, { "cell_type": "code", "execution_count": 8, "id": "6f61da9e", "metadata": { "execution": { "iopub.execute_input": "2023-10-09T13:48:47.234633Z", "iopub.status.busy": "2023-10-09T13:48:47.234376Z", "iopub.status.idle": "2023-10-09T13:48:50.881224Z", "shell.execute_reply": "2023-10-09T13:48:50.880426Z" }, "papermill": { "duration": 3.680171, "end_time": "2023-10-09T13:48:50.882989", "exception": false, "start_time": "2023-10-09T13:48:47.202818", "status": "completed" }, "tags": [] }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[2023-10-09 13:48:49,874] [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 \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-p2.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-p2.pth\" \"cuda fp32\"" ] }, { "cell_type": "markdown", "id": "9ce3bb19", "metadata": { "papermill": { "duration": 0.031127, "end_time": "2023-10-09T13:48:50.949593", "exception": false, "start_time": "2023-10-09T13:48:50.918466", "status": "completed" }, "tags": [] }, "source": [ "## Enwiki Stage 3 : Baseline training" ] }, { "cell_type": "code", "execution_count": 9, "id": "fedfb2cd", "metadata": { "execution": { "iopub.execute_input": "2023-10-09T13:48:51.013263Z", "iopub.status.busy": "2023-10-09T13:48:51.012897Z", "iopub.status.idle": "2023-10-09T13:49:05.228016Z", "shell.execute_reply": "2023-10-09T13:49:05.227238Z" }, "papermill": { "duration": 14.248955, "end_time": "2023-10-09T13:49:05.230066", "exception": false, "start_time": "2023-10-09T13:48:50.981111", "status": "completed" }, "tags": [] }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[2023-10-09 13:48:53,746] [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 - Overwrite Merge Part 3 (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-baseline-p3/', '--model.load_model=../model/v5-L6+6-D2048-E0_01-layer-expansion-p2.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 - Overwrite Merge Part 3 (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-baseline-p3/', '--model.load_model=../model/v5-L6+6-D2048-E0_01-layer-expansion-p2.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 4224737379\r\n", " rank_zero_warn(f\"No seed found, seed set to {seed}\")\r\n", "Global seed set to 4224737379\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-20231009_134856-e7u5abp0\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 - Overwrite Merge Part 3 (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/e7u5abp0\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 \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-layer-expansion-p2.pth' does not exist\r\n", "\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 - Overwrite Merge Part 3 (train-ctx=4k, deepspeed_stage_2_offload)\u001b[0m at: \u001b[34m\u001b[4mhttps://wandb.ai/rwkv-x-dev/RWKV-5X-Experiments/runs/e7u5abp0\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/v12\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-20231009_134856-e7u5abp0/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} - Overwrite Merge Part 3 (train-ctx=4k, {DEEPSPEED_STRAT})\" \\\n", " --trainer.strategy=\"{DEEPSPEED_STRAT}\" \\\n", " --trainer.devices=\"{GPU_DEVICES}\" \\\n", " --trainer.callbacks.init_args.dirpath=\"../checkpoint/{FILENAME_PREFIX}-baseline-p3/\" \\\n", " --model.load_model=\"../model/{FILENAME_PREFIX}-layer-expansion-p2.pth\" \\\n", " --model.ctx_len=4096 \\\n", " --model.bptt_learning_range=1" ] }, { "cell_type": "code", "execution_count": 10, "id": "949f3c5e", "metadata": { "execution": { "iopub.execute_input": "2023-10-09T13:49:05.299647Z", "iopub.status.busy": "2023-10-09T13:49:05.299382Z", "iopub.status.idle": "2023-10-09T13:49:07.735160Z", "shell.execute_reply": "2023-10-09T13:49:07.734306Z" }, "papermill": { "duration": 2.470473, "end_time": "2023-10-09T13:49:07.736956", "exception": false, "start_time": "2023-10-09T13:49:05.266483", "status": "completed" }, "tags": [] }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[2023-10-09 13:49:06,868] [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 \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-baseline-p3/last.ckpt/latest\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "ls: cannot access '../model/v5-L6+6-D2048-E0_01-layer-expansion-p3.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}-baseline-p3/last.ckpt\" \"../model/{FILENAME_PREFIX}-baseline-p3.pth\" \"bf16\"\n", "!cd \"{TRAINER_DIR}\" && ls -alh \"../model/{FILENAME_PREFIX}-layer-expansion-p3.pth\"" ] }, { "cell_type": "code", "execution_count": 11, "id": "c103f807", "metadata": { "execution": { "iopub.execute_input": "2023-10-09T13:49:07.805018Z", "iopub.status.busy": "2023-10-09T13:49:07.804739Z", "iopub.status.idle": "2023-10-09T13:49:11.452591Z", "shell.execute_reply": "2023-10-09T13:49:11.451770Z" }, "papermill": { "duration": 3.682354, "end_time": "2023-10-09T13:49:11.454743", "exception": false, "start_time": "2023-10-09T13:49:07.772389", "status": "completed" }, "tags": [] }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[2023-10-09 13:49:10,451] [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 \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-p3.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-p3.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": 247.305847, "end_time": "2023-10-09T13:49:11.610093", "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-expansion.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-expansion.ipynb", "parameters": {}, "start_time": "2023-10-09T13:45:04.304246", "version": "2.4.0" } }, "nbformat": 4, "nbformat_minor": 5 }