{ "cells": [ { "cell_type": "markdown", "id": "541b2d35", "metadata": { "papermill": { "duration": 0.00391, "end_time": "2023-08-26T13:27:22.704411", "exception": false, "start_time": "2023-08-26T13:27:22.700501", "status": "completed" }, "tags": [] }, "source": [ "## Custom Experimental Memory benchmarking\n", "\n", "The following is meant to observe the memory performance in a more verbose CSV logging mode, for the baseline raven models" ] }, { "cell_type": "code", "execution_count": 1, "id": "13ce0b66", "metadata": { "execution": { "iopub.execute_input": "2023-08-26T13:27:22.713673Z", "iopub.status.busy": "2023-08-26T13:27:22.712927Z", "iopub.status.idle": "2023-08-26T13:30:39.555655Z", "shell.execute_reply": "2023-08-26T13:30:39.554517Z" }, "papermill": { "duration": 196.850037, "end_time": "2023-08-26T13:30:39.558120", "exception": false, "start_time": "2023-08-26T13:27:22.708083", "status": "completed" }, "tags": [] }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "--2023-08-26 13:27:23-- https://huggingface.co./picocreator/memory-size-experiment-for-rwkv/resolve/main/RWKV-v5-baseline/BaseV5-C-Tune5.pth\r\n", "Resolving huggingface.co (huggingface.co)... 18.154.227.7, 18.154.227.69, 18.154.227.87, ...\r\n", "Connecting to huggingface.co (huggingface.co)|18.154.227.7|:443... connected.\r\n", "HTTP request sent, awaiting response... 302 Found\r\n", "Location: https://cdn-lfs.huggingface.co/repos/cb/ef/cbef09abb2634a3375b28868bffa285226dfeabedec89b28c2fb302221164d66/c1f89b4d653a240f6f165d25988b51f6db36bf8a2388707e3e3242af751575eb?response-content-disposition=attachment%3B+filename*%3DUTF-8%27%27BaseV5-C-Tune5.pth%3B+filename%3D%22BaseV5-C-Tune5.pth%22%3B&Expires=1693315643&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTY5MzMxNTY0M319LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy5odWdnaW5nZmFjZS5jby9yZXBvcy9jYi9lZi9jYmVmMDlhYmIyNjM0YTMzNzViMjg4NjhiZmZhMjg1MjI2ZGZlYWJlZGVjODliMjhjMmZiMzAyMjIxMTY0ZDY2L2MxZjg5YjRkNjUzYTI0MGY2ZjE2NWQyNTk4OGI1MWY2ZGIzNmJmOGEyMzg4NzA3ZTNlMzI0MmFmNzUxNTc1ZWI%7EcmVzcG9uc2UtY29udGVudC1kaXNwb3NpdGlvbj0qIn1dfQ__&Signature=ziMFzO433qYsnTGI0xEqJgoCCxYDBIDL6BiUB8nY%7EUwhf8whZoVy%7E6kXBMldTd5DrWF1FBW-m%7EZ30YvJkMpWb282unhX6%7EInXiMnuT8KzIY8RmId7ttH21PN4yhomq6PQH5iM8hZq4rzmapJEyeRmDyBMJuHcDbXjYa%7EZonvxseG5TJACA3CIe8775U1sGNl2K8awoALSDKvpUJVIq86twhIdH38kCdQUrfRB52a6sX-xLHsGYpHUelYXtE9YcfajwTeg358Ds-ut4XP-we7vBLIusdR02y0MjvvyuWOIMLTI%7Ewq3OVRkY92Ks7HG7sk52iHWhH0x%7E12mvhQqM0Vzw__&Key-Pair-Id=KVTP0A1DKRTAX [following]\r\n", "--2023-08-26 13:27:23-- https://cdn-lfs.huggingface.co/repos/cb/ef/cbef09abb2634a3375b28868bffa285226dfeabedec89b28c2fb302221164d66/c1f89b4d653a240f6f165d25988b51f6db36bf8a2388707e3e3242af751575eb?response-content-disposition=attachment%3B+filename*%3DUTF-8%27%27BaseV5-C-Tune5.pth%3B+filename%3D%22BaseV5-C-Tune5.pth%22%3B&Expires=1693315643&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTY5MzMxNTY0M319LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy5odWdnaW5nZmFjZS5jby9yZXBvcy9jYi9lZi9jYmVmMDlhYmIyNjM0YTMzNzViMjg4NjhiZmZhMjg1MjI2ZGZlYWJlZGVjODliMjhjMmZiMzAyMjIxMTY0ZDY2L2MxZjg5YjRkNjUzYTI0MGY2ZjE2NWQyNTk4OGI1MWY2ZGIzNmJmOGEyMzg4NzA3ZTNlMzI0MmFmNzUxNTc1ZWI%7EcmVzcG9uc2UtY29udGVudC1kaXNwb3NpdGlvbj0qIn1dfQ__&Signature=ziMFzO433qYsnTGI0xEqJgoCCxYDBIDL6BiUB8nY%7EUwhf8whZoVy%7E6kXBMldTd5DrWF1FBW-m%7EZ30YvJkMpWb282unhX6%7EInXiMnuT8KzIY8RmId7ttH21PN4yhomq6PQH5iM8hZq4rzmapJEyeRmDyBMJuHcDbXjYa%7EZonvxseG5TJACA3CIe8775U1sGNl2K8awoALSDKvpUJVIq86twhIdH38kCdQUrfRB52a6sX-xLHsGYpHUelYXtE9YcfajwTeg358Ds-ut4XP-we7vBLIusdR02y0MjvvyuWOIMLTI%7Ewq3OVRkY92Ks7HG7sk52iHWhH0x%7E12mvhQqM0Vzw__&Key-Pair-Id=KVTP0A1DKRTAX\r\n", "Resolving cdn-lfs.huggingface.co (cdn-lfs.huggingface.co)... " ] }, { "name": "stdout", "output_type": "stream", "text": [ "108.138.64.121, 108.138.64.111, 108.138.64.36, ...\r\n", "Connecting to cdn-lfs.huggingface.co (cdn-lfs.huggingface.co)|108.138.64.121|:443... connected.\r\n", "HTTP request sent, awaiting response... 200 OK\r\n", "Length: 6060483063 (5.6G) [binary/octet-stream]\r\n", "Saving to: ‘BaseV5-C-Tune5.pth’\r\n", "\r\n", "\r", "BaseV5-C-Tune5.pth 0%[ ] 0 --.-KB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 1%[ ] 73.21M 366MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 2%[ ] 146.94M 367MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 3%[ ] 220.93M 368MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 5%[> ] 295.39M 369MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 6%[> ] 369.07M 369MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 7%[> ] 442.84M 369MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 8%[> ] 515.57M 368MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 10%[=> ] 589.96M 369MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 11%[=> ] 665.46M 370MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 12%[=> ] 741.08M 371MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 14%[=> ] 816.99M 371MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 15%[==> ] 892.84M 372MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 16%[==> ] 969.40M 373MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 18%[==> ] 1.02G 373MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 19%[==> ] 1.09G 374MB/s eta 12s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 20%[===> ] 1.17G 375MB/s eta 12s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 22%[===> ] 1.24G 375MB/s eta 12s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 23%[===> ] 1.32G 376MB/s eta 12s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 24%[===> ] 1.39G 378MB/s eta 12s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 26%[====> ] 1.47G 379MB/s eta 11s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 27%[====> ] 1.55G 380MB/s eta 11s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 28%[====> ] 1.63G 383MB/s eta 11s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 30%[=====> ] 1.70G 384MB/s eta 11s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 31%[=====> ] 1.78G 385MB/s eta 11s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 32%[=====> ] 1.86G 386MB/s eta 10s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 34%[=====> ] 1.93G 387MB/s eta 10s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 35%[======> ] 2.01G 388MB/s eta 10s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 36%[======> ] 2.07G 382MB/s eta 10s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 37%[======> ] 2.14G 381MB/s eta 10s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 39%[======> ] 2.21G 381MB/s eta 9s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 40%[=======> ] 2.29G 381MB/s eta 9s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 41%[=======> ] 2.36G 382MB/s eta 9s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 43%[=======> ] 2.44G 383MB/s eta 9s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 44%[=======> ] 2.51G 382MB/s eta 9s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 45%[========> ] 2.59G 382MB/s eta 8s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 47%[========> ] 2.67G 382MB/s eta 8s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 48%[========> ] 2.74G 381MB/s eta 8s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 49%[========> ] 2.82G 381MB/s eta 8s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 51%[=========> ] 2.89G 381MB/s eta 8s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 52%[=========> ] 2.97G 380MB/s eta 7s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 53%[=========> ] 3.04G 380MB/s eta 7s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 55%[==========> ] 3.12G 380MB/s eta 7s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 56%[==========> ] 3.20G 385MB/s eta 7s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 57%[==========> ] 3.27G 385MB/s eta 7s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 59%[==========> ] 3.35G 388MB/s eta 6s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 60%[===========> ] 3.42G 388MB/s eta 6s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 61%[===========> ] 3.50G 387MB/s eta 6s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 63%[===========> ] 3.57G 387MB/s eta 6s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 64%[===========> ] 3.65G 387MB/s eta 6s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 65%[============> ] 3.72G 387MB/s eta 5s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 67%[============> ] 3.80G 387MB/s eta 5s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 68%[============> ] 3.88G 387MB/s eta 5s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 70%[=============> ] 3.95G 387MB/s eta 5s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 71%[=============> ] 4.03G 387MB/s eta 5s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 72%[=============> ] 4.08G 379MB/s eta 4s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 72%[=============> ] 4.10G 362MB/s eta 4s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 74%[=============> ] 4.18G 362MB/s eta 4s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 75%[==============> ] 4.25G 362MB/s eta 4s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 76%[==============> ] 4.33G 362MB/s eta 4s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 78%[==============> ] 4.41G 363MB/s eta 3s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 79%[==============> ] 4.48G 363MB/s eta 3s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 80%[===============> ] 4.55G 361MB/s eta 3s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 81%[===============> ] 4.60G 352MB/s eta 3s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 82%[===============> ] 4.67G 351MB/s eta 3s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 84%[===============> ] 4.75G 351MB/s eta 2s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 85%[================> ] 4.83G 352MB/s eta 2s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 86%[================> ] 4.90G 351MB/s eta 2s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 88%[================> ] 4.98G 352MB/s eta 2s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 89%[================> ] 5.05G 352MB/s eta 2s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 90%[=================> ] 5.13G 353MB/s eta 1s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 92%[=================> ] 5.21G 372MB/s eta 1s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 93%[=================> ] 5.28G 377MB/s eta 1s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 94%[=================> ] 5.36G 377MB/s eta 1s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 96%[==================> ] 5.44G 378MB/s eta 1s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 97%[==================> ] 5.51G 378MB/s eta 0s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 99%[==================> ] 5.59G 377MB/s eta 0s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "BaseV5-C-Tune5.pth 100%[===================>] 5.64G 377MB/s in 15s \r\n", "\r\n", "2023-08-26 13:27:38 (377 MB/s) - ‘BaseV5-C-Tune5.pth’ saved [6060483063/6060483063]\r\n", "\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "--2023-08-26 13:27:38-- https://huggingface.co./picocreator/RWKV-x-playground/resolve/main/V5-16k/EWR-1B5-E0_1-mem-ctx-8k.pth\r\n", "Resolving huggingface.co (huggingface.co)... 18.154.227.7, 18.154.227.87, 18.154.227.69, ...\r\n", "Connecting to huggingface.co (huggingface.co)|18.154.227.7|:443... connected.\r\n", "HTTP request sent, awaiting response... 302 Found\r\n", "Location: https://cdn-lfs.huggingface.co/repos/69/e5/69e55a6299441d3070ee1690632f8d12440ea004de9c6a51b873ccd49ea78ea0/e886ffafd5148b502a00b1c10c847ca918cec61c4c956956a2fe9811c210029b?response-content-disposition=attachment%3B+filename*%3DUTF-8%27%27EWR-1B5-E0_1-mem-ctx-8k.pth%3B+filename%3D%22EWR-1B5-E0_1-mem-ctx-8k.pth%22%3B&Expires=1693315658&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTY5MzMxNTY1OH19LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy5odWdnaW5nZmFjZS5jby9yZXBvcy82OS9lNS82OWU1NWE2Mjk5NDQxZDMwNzBlZTE2OTA2MzJmOGQxMjQ0MGVhMDA0ZGU5YzZhNTFiODczY2NkNDllYTc4ZWEwL2U4ODZmZmFmZDUxNDhiNTAyYTAwYjFjMTBjODQ3Y2E5MThjZWM2MWM0Yzk1Njk1NmEyZmU5ODExYzIxMDAyOWI%7EcmVzcG9uc2UtY29udGVudC1kaXNwb3NpdGlvbj0qIn1dfQ__&Signature=uku0uUHXaL19jduBgCuGdQVstpytTc2QSL0CxF3ZbE%7E3KoqpZgFWx1DJLuTk7pRnrXBNW-0cOp2MV-WONmJU7VmZvSwnbX6o3FCRpQ6xTneRWKmWXa1%7E73xUgwvg7tzs32tkYbOPkHjJXsHTZD1Pbceks1qp-brKKR58sOX%7EaB2aUPZwBgM15qjmy5fgPzyK8UgDTQ27%7EJAXtzIP8tS73n0hIaaePD1aItyVcNGs2nu4Cq6fEIfGJgvcitTm9rsLy8kUO6J6JwHrWon3PR-H5yIol5F2rVjtbmv-V9lJHq-5i1a2f%7E4AV3GlSzQ2TlOqPpExnfoeteDBPlFtzNj5%7EA__&Key-Pair-Id=KVTP0A1DKRTAX [following]\r\n", "--2023-08-26 13:27:38-- https://cdn-lfs.huggingface.co/repos/69/e5/69e55a6299441d3070ee1690632f8d12440ea004de9c6a51b873ccd49ea78ea0/e886ffafd5148b502a00b1c10c847ca918cec61c4c956956a2fe9811c210029b?response-content-disposition=attachment%3B+filename*%3DUTF-8%27%27EWR-1B5-E0_1-mem-ctx-8k.pth%3B+filename%3D%22EWR-1B5-E0_1-mem-ctx-8k.pth%22%3B&Expires=1693315658&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTY5MzMxNTY1OH19LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy5odWdnaW5nZmFjZS5jby9yZXBvcy82OS9lNS82OWU1NWE2Mjk5NDQxZDMwNzBlZTE2OTA2MzJmOGQxMjQ0MGVhMDA0ZGU5YzZhNTFiODczY2NkNDllYTc4ZWEwL2U4ODZmZmFmZDUxNDhiNTAyYTAwYjFjMTBjODQ3Y2E5MThjZWM2MWM0Yzk1Njk1NmEyZmU5ODExYzIxMDAyOWI%7EcmVzcG9uc2UtY29udGVudC1kaXNwb3NpdGlvbj0qIn1dfQ__&Signature=uku0uUHXaL19jduBgCuGdQVstpytTc2QSL0CxF3ZbE%7E3KoqpZgFWx1DJLuTk7pRnrXBNW-0cOp2MV-WONmJU7VmZvSwnbX6o3FCRpQ6xTneRWKmWXa1%7E73xUgwvg7tzs32tkYbOPkHjJXsHTZD1Pbceks1qp-brKKR58sOX%7EaB2aUPZwBgM15qjmy5fgPzyK8UgDTQ27%7EJAXtzIP8tS73n0hIaaePD1aItyVcNGs2nu4Cq6fEIfGJgvcitTm9rsLy8kUO6J6JwHrWon3PR-H5yIol5F2rVjtbmv-V9lJHq-5i1a2f%7E4AV3GlSzQ2TlOqPpExnfoeteDBPlFtzNj5%7EA__&Key-Pair-Id=KVTP0A1DKRTAX\r\n", "Resolving cdn-lfs.huggingface.co (cdn-lfs.huggingface.co)... 108.138.64.49, 108.138.64.36, 108.138.64.111, ...\r\n", "Connecting to cdn-lfs.huggingface.co (cdn-lfs.huggingface.co)|108.138.64.49|: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: 6060483163 (5.6G) [binary/octet-stream]\r\n", "Saving to: ‘EWR-1B5-E0_1-mem-ctx-8k.pth’\r\n", "\r\n", "\r", " EWR-1B5-E 0%[ ] 0 --.-KB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0 0%[ ] 15.26M 48.0MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_ 0%[ ] 30.52M 47.4MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1 0%[ ] 45.78M 52.5MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1- 1%[ ] 61.03M 53.0MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1-m 1%[ ] 76.29M 54.5MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1-me 1%[ ] 91.55M 54.1MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1-mem 1%[ ] 106.29M 55.8MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1-mem- 2%[ ] 119.78M 56.9MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1-mem-c 2%[ ] 136.81M 58.2MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "EWR-1B5-E0_1-mem-ct 2%[ ] 152.59M 58.4MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "WR-1B5-E0_1-mem-ctx 2%[ ] 167.85M 58.2MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "R-1B5-E0_1-mem-ctx- 3%[ ] 188.29M 61.0MB/s eta 92s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-1B5-E0_1-mem-ctx-8 3%[ ] 197.85M 59.8MB/s eta 92s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "1B5-E0_1-mem-ctx-8k 3%[ ] 198.49M 55.4MB/s eta 92s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "B5-E0_1-mem-ctx-8k. 3%[ ] 213.62M 55.5MB/s eta 92s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "5-E0_1-mem-ctx-8k.p 4%[ ] 243.63M 59.3MB/s eta 93s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-E0_1-mem-ctx-8k.pt 4%[ ] 256.89M 58.3MB/s eta 93s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "E0_1-mem-ctx-8k.pth 4%[ ] 259.40M 56.3MB/s eta 93s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "0_1-mem-ctx-8k.pth 4%[ ] 274.52M 58.9MB/s eta 93s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "_1-mem-ctx-8k.pth 5%[> ] 289.40M 58.6MB/s eta 93s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "1-mem-ctx-8k.pth 5%[> ] 304.66M 59.7MB/s eta 94s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-mem-ctx-8k.pth 5%[> ] 320.43M 59.6MB/s eta 94s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "mem-ctx-8k.pth 5%[> ] 328.90M 58.2MB/s eta 94s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "em-ctx-8k.pth 6%[> ] 350.44M 62.2MB/s eta 94s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "m-ctx-8k.pth 6%[> ] 365.70M 60.4MB/s eta 92s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-ctx-8k.pth 6%[> ] 378.57M 59.1MB/s eta 92s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "ctx-8k.pth 6%[> ] 381.47M 56.2MB/s eta 92s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "tx-8k.pth 6%[> ] 396.73M 54.2MB/s eta 92s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "x-8k.pth 7%[> ] 412.11M 57.5MB/s eta 92s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-8k.pth 7%[> ] 429.56M 60.0MB/s eta 92s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "8k.pth 7%[> ] 442.51M 60.2MB/s eta 92s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "k.pth 7%[> ] 455.93M 58.7MB/s eta 92s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", ".pth 7%[> ] 459.83M 55.8MB/s eta 92s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "pth 8%[> ] 473.02M 53.8MB/s eta 92s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "th 8%[> ] 488.28M 56.0MB/s eta 94s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "h 8%[> ] 503.54M 55.2MB/s eta 94s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 9%[> ] 524.76M 56.2MB/s eta 94s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " E 9%[> ] 548.80M 61.4MB/s eta 94s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EW 9%[> ] 557.00M 58.1MB/s eta 94s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR 9%[> ] 564.84M 58.3MB/s eta 90s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR- 10%[=> ] 580.87M 58.5MB/s eta 90s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1 10%[=> ] 595.69M 57.2MB/s eta 90s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B 10%[=> ] 608.90M 59.8MB/s eta 90s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5 10%[=> ] 621.86M 58.7MB/s eta 90s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5- 11%[=> ] 640.87M 62.3MB/s eta 87s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E 11%[=> ] 656.13M 61.3MB/s eta 87s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0 11%[=> ] 671.38M 61.1MB/s eta 87s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_ 11%[=> ] 686.13M 61.7MB/s eta 87s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1 12%[=> ] 700.08M 62.2MB/s eta 87s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1- 12%[=> ] 716.64M 61.7MB/s eta 87s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1-m 12%[=> ] 732.42M 63.1MB/s eta 87s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1-me 12%[=> ] 748.05M 62.9MB/s eta 87s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1-mem 13%[=> ] 762.94M 62.3MB/s eta 87s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1-mem- 13%[=> ] 778.20M 61.8MB/s eta 85s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1-mem-c 13%[=> ] 805.10M 65.5MB/s eta 85s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "EWR-1B5-E0_1-mem-ct 13%[=> ] 808.71M 63.9MB/s eta 85s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "WR-1B5-E0_1-mem-ctx 14%[=> ] 823.46M 63.6MB/s eta 85s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "R-1B5-E0_1-mem-ctx- 14%[=> ] 838.71M 62.6MB/s eta 85s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-1B5-E0_1-mem-ctx-8 14%[=> ] 854.49M 63.7MB/s eta 83s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "1B5-E0_1-mem-ctx-8k 14%[=> ] 863.43M 58.8MB/s eta 83s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "B5-E0_1-mem-ctx-8k. 15%[==> ] 869.75M 59.2MB/s eta 83s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "5-E0_1-mem-ctx-8k.p 15%[==> ] 895.53M 61.7MB/s eta 83s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-E0_1-mem-ctx-8k.pt 15%[==> ] 912.72M 63.1MB/s eta 83s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "E0_1-mem-ctx-8k.pth 16%[==> ] 930.27M 64.0MB/s eta 80s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "0_1-mem-ctx-8k.pth 16%[==> ] 946.04M 65.8MB/s eta 80s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "_1-mem-ctx-8k.pth 16%[==> ] 976.55M 70.6MB/s eta 80s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "1-mem-ctx-8k.pth 17%[==> ] 991.82M 70.7MB/s eta 80s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-mem-ctx-8k.pth 17%[==> ] 1007M 69.5MB/s eta 78s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "mem-ctx-8k.pth 17%[==> ] 1013M 67.1MB/s eta 78s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "em-ctx-8k.pth 17%[==> ] 1022M 65.3MB/s eta 78s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "m-ctx-8k.pth 18%[==> ] 1.02G 67.6MB/s eta 78s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-ctx-8k.pth 18%[==> ] 1.03G 62.7MB/s eta 78s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "ctx-8k.pth 18%[==> ] 1.05G 64.9MB/s eta 77s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "tx-8k.pth 18%[==> ] 1.06G 66.9MB/s eta 77s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "x-8k.pth 18%[==> ] 1.07G 67.2MB/s eta 77s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-8k.pth 19%[==> ] 1.08G 63.0MB/s eta 77s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "8k.pth 19%[==> ] 1.09G 64.2MB/s eta 77s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "k.pth 19%[==> ] 1.10G 63.7MB/s eta 77s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", ".pth 19%[==> ] 1.12G 62.6MB/s eta 77s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "pth 20%[===> ] 1.13G 61.6MB/s eta 77s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "th 20%[===> ] 1.15G 61.3MB/s eta 77s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "h 20%[===> ] 1.16G 60.6MB/s eta 77s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 20%[===> ] 1.18G 58.5MB/s eta 76s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " E 21%[===> ] 1.19G 58.3MB/s eta 76s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EW 21%[===> ] 1.21G 59.0MB/s eta 76s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR 21%[===> ] 1.22G 58.0MB/s eta 76s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR- 22%[===> ] 1.25G 62.4MB/s eta 76s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1 22%[===> ] 1.25G 61.8MB/s eta 74s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B 22%[===> ] 1.27G 59.8MB/s eta 74s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5 22%[===> ] 1.27G 57.5MB/s eta 74s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5- 22%[===> ] 1.28G 58.3MB/s eta 74s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E 22%[===> ] 1.30G 58.0MB/s eta 74s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0 23%[===> ] 1.31G 57.3MB/s eta 74s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_ 23%[===> ] 1.32G 57.0MB/s eta 74s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1 23%[===> ] 1.33G 56.8MB/s eta 74s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1- 23%[===> ] 1.34G 55.8MB/s eta 74s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1-m 23%[===> ] 1.34G 55.4MB/s eta 74s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1-me 24%[===> ] 1.36G 56.5MB/s eta 74s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1-mem 24%[===> ] 1.37G 54.5MB/s eta 74s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1-mem- 24%[===> ] 1.39G 53.5MB/s eta 74s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1-mem-c 24%[===> ] 1.40G 52.8MB/s eta 74s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "EWR-1B5-E0_1-mem-ct 24%[===> ] 1.40G 49.1MB/s eta 74s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "WR-1B5-E0_1-mem-ctx 25%[====> ] 1.42G 49.6MB/s eta 74s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "R-1B5-E0_1-mem-ctx- 25%[====> ] 1.43G 50.7MB/s eta 74s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-1B5-E0_1-mem-ctx-8 25%[====> ] 1.45G 51.7MB/s eta 74s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "1B5-E0_1-mem-ctx-8k 25%[====> ] 1.47G 51.5MB/s eta 74s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "B5-E0_1-mem-ctx-8k. 26%[====> ] 1.47G 52.0MB/s eta 72s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "5-E0_1-mem-ctx-8k.p 26%[====> ] 1.49G 55.0MB/s eta 72s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-E0_1-mem-ctx-8k.pt 26%[====> ] 1.50G 53.3MB/s eta 72s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "E0_1-mem-ctx-8k.pth 26%[====> ] 1.51G 50.7MB/s eta 72s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "0_1-mem-ctx-8k.pth 27%[====> ] 1.53G 53.3MB/s eta 71s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "_1-mem-ctx-8k.pth 27%[====> ] 1.54G 53.8MB/s eta 71s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "1-mem-ctx-8k.pth 27%[====> ] 1.57G 56.2MB/s eta 71s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-mem-ctx-8k.pth 27%[====> ] 1.57G 56.5MB/s eta 71s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "mem-ctx-8k.pth 28%[====> ] 1.59G 56.8MB/s eta 71s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "em-ctx-8k.pth 28%[====> ] 1.60G 58.8MB/s eta 70s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "m-ctx-8k.pth 28%[====> ] 1.61G 55.0MB/s eta 70s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-ctx-8k.pth 28%[====> ] 1.62G 60.7MB/s eta 70s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "ctx-8k.pth 28%[====> ] 1.63G 58.7MB/s eta 70s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "tx-8k.pth 29%[====> ] 1.65G 59.2MB/s eta 70s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "x-8k.pth 29%[====> ] 1.67G 58.5MB/s eta 69s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-8k.pth 29%[====> ] 1.68G 56.9MB/s eta 69s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "8k.pth 30%[=====> ] 1.70G 59.8MB/s eta 69s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "k.pth 30%[=====> ] 1.71G 59.5MB/s eta 69s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", ".pth 30%[=====> ] 1.73G 62.8MB/s eta 69s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "pth 30%[=====> ] 1.75G 64.8MB/s eta 67s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "th 31%[=====> ] 1.76G 62.1MB/s eta 67s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "h 31%[=====> ] 1.77G 62.7MB/s eta 67s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 31%[=====> ] 1.79G 59.0MB/s eta 67s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " E 31%[=====> ] 1.79G 56.4MB/s eta 67s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EW 31%[=====> ] 1.80G 59.3MB/s eta 67s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR 32%[=====> ] 1.82G 59.8MB/s eta 67s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR- 32%[=====> ] 1.83G 61.9MB/s eta 67s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1 32%[=====> ] 1.85G 60.6MB/s eta 67s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B 33%[=====> ] 1.86G 60.1MB/s eta 66s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5 33%[=====> ] 1.88G 61.6MB/s eta 66s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5- 33%[=====> ] 1.88G 60.3MB/s eta 66s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E 33%[=====> ] 1.90G 60.8MB/s eta 66s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0 33%[=====> ] 1.91G 59.2MB/s eta 66s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_ 34%[=====> ] 1.93G 59.0MB/s eta 64s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1 34%[=====> ] 1.94G 61.9MB/s eta 64s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1- 34%[=====> ] 1.97G 61.8MB/s eta 64s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1-m 35%[======> ] 1.98G 59.1MB/s eta 64s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1-me 35%[======> ] 2.00G 57.4MB/s eta 63s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1-mem 35%[======> ] 2.01G 58.6MB/s eta 63s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1-mem- 35%[======> ] 2.03G 60.6MB/s eta 63s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1-mem-c 36%[======> ] 2.05G 62.3MB/s eta 63s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "EWR-1B5-E0_1-mem-ct 36%[======> ] 2.06G 60.9MB/s eta 63s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "WR-1B5-E0_1-mem-ctx 36%[======> ] 2.08G 63.2MB/s eta 61s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "R-1B5-E0_1-mem-ctx- 36%[======> ] 2.09G 64.8MB/s eta 61s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-1B5-E0_1-mem-ctx-8 37%[======> ] 2.10G 63.8MB/s eta 61s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "1B5-E0_1-mem-ctx-8k 37%[======> ] 2.12G 64.0MB/s eta 61s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "B5-E0_1-mem-ctx-8k. 37%[======> ] 2.13G 64.6MB/s eta 60s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "5-E0_1-mem-ctx-8k.p 38%[======> ] 2.15G 64.6MB/s eta 60s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-E0_1-mem-ctx-8k.pt 38%[======> ] 2.16G 63.1MB/s eta 60s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "E0_1-mem-ctx-8k.pth 38%[======> ] 2.17G 63.0MB/s eta 60s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "0_1-mem-ctx-8k.pth 38%[======> ] 2.17G 59.8MB/s eta 60s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "_1-mem-ctx-8k.pth 38%[======> ] 2.19G 58.1MB/s eta 60s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "1-mem-ctx-8k.pth 39%[======> ] 2.21G 56.9MB/s eta 60s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-mem-ctx-8k.pth 39%[======> ] 2.22G 59.8MB/s eta 60s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "mem-ctx-8k.pth 39%[======> ] 2.24G 62.8MB/s eta 60s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "em-ctx-8k.pth 39%[======> ] 2.25G 60.7MB/s eta 60s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "m-ctx-8k.pth 40%[=======> ] 2.26G 63.2MB/s eta 58s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-ctx-8k.pth 40%[=======> ] 2.28G 63.0MB/s eta 58s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "ctx-8k.pth 40%[=======> ] 2.31G 64.9MB/s eta 58s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "tx-8k.pth 41%[=======> ] 2.32G 63.9MB/s eta 58s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "x-8k.pth 41%[=======> ] 2.33G 63.3MB/s eta 58s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-8k.pth 41%[=======> ] 2.34G 62.2MB/s eta 57s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "8k.pth 41%[=======> ] 2.35G 60.1MB/s eta 57s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "k.pth 42%[=======> ] 2.37G 64.0MB/s eta 57s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", ".pth 42%[=======> ] 2.38G 63.1MB/s eta 57s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "pth 42%[=======> ] 2.40G 63.1MB/s eta 56s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "th 42%[=======> ] 2.41G 62.3MB/s eta 56s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "h 42%[=======> ] 2.41G 61.0MB/s eta 56s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 42%[=======> ] 2.42G 61.6MB/s eta 56s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " E 43%[=======> ] 2.43G 58.4MB/s eta 56s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EW 43%[=======> ] 2.44G 57.0MB/s eta 55s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR 43%[=======> ] 2.46G 55.1MB/s eta 55s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR- 43%[=======> ] 2.47G 54.6MB/s eta 55s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1 44%[=======> ] 2.49G 55.4MB/s eta 55s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B 44%[=======> ] 2.51G 54.5MB/s eta 54s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5 44%[=======> ] 2.52G 52.9MB/s eta 54s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5- 44%[=======> ] 2.53G 52.0MB/s eta 54s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E 45%[========> ] 2.55G 54.1MB/s eta 54s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0 45%[========> ] 2.56G 54.3MB/s eta 53s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_ 45%[========> ] 2.58G 54.2MB/s eta 53s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1 45%[========> ] 2.59G 53.5MB/s eta 53s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1- 46%[========> ] 2.61G 55.1MB/s eta 53s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1-m 46%[========> ] 2.62G 54.6MB/s eta 52s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1-me 46%[========> ] 2.64G 57.2MB/s eta 52s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1-mem 46%[========> ] 2.65G 56.7MB/s eta 52s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1-mem- 47%[========> ] 2.67G 56.7MB/s eta 52s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1-mem-c 47%[========> ] 2.67G 54.0MB/s eta 52s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "EWR-1B5-E0_1-mem-ct 47%[========> ] 2.68G 54.5MB/s eta 52s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "WR-1B5-E0_1-mem-ctx 47%[========> ] 2.70G 55.3MB/s eta 52s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "R-1B5-E0_1-mem-ctx- 48%[========> ] 2.71G 54.9MB/s eta 52s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-1B5-E0_1-mem-ctx-8 48%[========> ] 2.73G 55.6MB/s eta 52s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "1B5-E0_1-mem-ctx-8k 48%[========> ] 2.75G 57.7MB/s eta 50s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "B5-E0_1-mem-ctx-8k. 49%[========> ] 2.77G 60.1MB/s eta 50s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "5-E0_1-mem-ctx-8k.p 49%[========> ] 2.79G 62.6MB/s eta 50s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-E0_1-mem-ctx-8k.pt 49%[========> ] 2.80G 62.1MB/s eta 50s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "E0_1-mem-ctx-8k.pth 49%[========> ] 2.81G 60.5MB/s eta 50s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "0_1-mem-ctx-8k.pth 50%[=========> ] 2.83G 59.2MB/s eta 49s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "_1-mem-ctx-8k.pth 50%[=========> ] 2.85G 58.6MB/s eta 49s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "1-mem-ctx-8k.pth 50%[=========> ] 2.86G 59.7MB/s eta 49s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-mem-ctx-8k.pth 50%[=========> ] 2.88G 60.7MB/s eta 49s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "mem-ctx-8k.pth 51%[=========> ] 2.89G 62.7MB/s eta 49s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "em-ctx-8k.pth 51%[=========> ] 2.90G 62.6MB/s eta 47s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "m-ctx-8k.pth 51%[=========> ] 2.92G 63.8MB/s eta 47s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-ctx-8k.pth 52%[=========> ] 2.94G 69.4MB/s eta 47s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "ctx-8k.pth 52%[=========> ] 2.95G 67.2MB/s eta 47s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "tx-8k.pth 52%[=========> ] 2.96G 66.9MB/s eta 47s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "x-8k.pth 52%[=========> ] 2.98G 67.4MB/s eta 46s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-8k.pth 53%[=========> ] 3.00G 66.6MB/s eta 46s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "8k.pth 53%[=========> ] 3.01G 64.8MB/s eta 46s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "k.pth 53%[=========> ] 3.02G 61.8MB/s eta 46s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", ".pth 53%[=========> ] 3.02G 58.7MB/s eta 45s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "pth 53%[=========> ] 3.04G 59.3MB/s eta 45s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "th 54%[=========> ] 3.05G 58.1MB/s eta 45s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "h 54%[=========> ] 3.07G 57.3MB/s eta 45s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 54%[=========> ] 3.08G 57.6MB/s eta 44s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " E 55%[==========> ] 3.11G 59.3MB/s eta 44s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EW 55%[==========> ] 3.11G 59.0MB/s eta 44s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR 55%[==========> ] 3.14G 61.7MB/s eta 44s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR- 55%[==========> ] 3.14G 61.5MB/s eta 44s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1 55%[==========> ] 3.15G 58.4MB/s eta 43s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B 56%[==========> ] 3.17G 59.0MB/s eta 43s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5 56%[==========> ] 3.19G 58.9MB/s eta 43s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5- 56%[==========> ] 3.20G 59.0MB/s eta 43s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E 56%[==========> ] 3.21G 57.7MB/s eta 43s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0 57%[==========> ] 3.22G 57.2MB/s eta 42s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_ 57%[==========> ] 3.23G 56.4MB/s eta 42s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1 57%[==========> ] 3.25G 59.6MB/s eta 42s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1- 57%[==========> ] 3.26G 59.3MB/s eta 42s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1-m 58%[==========> ] 3.28G 58.9MB/s eta 41s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1-me 58%[==========> ] 3.29G 60.7MB/s eta 41s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1-mem 58%[==========> ] 3.31G 59.8MB/s eta 41s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1-mem- 58%[==========> ] 3.32G 57.6MB/s eta 41s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1-mem-c 59%[==========> ] 3.34G 54.6MB/s eta 40s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "EWR-1B5-E0_1-mem-ct 59%[==========> ] 3.35G 56.0MB/s eta 40s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "WR-1B5-E0_1-mem-ctx 59%[==========> ] 3.37G 56.1MB/s eta 40s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "R-1B5-E0_1-mem-ctx- 59%[==========> ] 3.38G 56.4MB/s eta 40s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-1B5-E0_1-mem-ctx-8 60%[===========> ] 3.40G 55.8MB/s eta 39s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "1B5-E0_1-mem-ctx-8k 60%[===========> ] 3.41G 57.9MB/s eta 39s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "B5-E0_1-mem-ctx-8k. 60%[===========> ] 3.42G 58.1MB/s eta 39s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "5-E0_1-mem-ctx-8k.p 60%[===========> ] 3.43G 57.3MB/s eta 39s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-E0_1-mem-ctx-8k.pt 61%[===========> ] 3.45G 60.7MB/s eta 39s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "E0_1-mem-ctx-8k.pth 61%[===========> ] 3.46G 61.2MB/s eta 38s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "0_1-mem-ctx-8k.pth 61%[===========> ] 3.47G 58.5MB/s eta 38s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "_1-mem-ctx-8k.pth 61%[===========> ] 3.49G 61.9MB/s eta 38s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "1-mem-ctx-8k.pth 62%[===========> ] 3.50G 59.6MB/s eta 38s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-mem-ctx-8k.pth 62%[===========> ] 3.51G 59.7MB/s eta 38s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "mem-ctx-8k.pth 62%[===========> ] 3.52G 58.4MB/s eta 37s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "em-ctx-8k.pth 62%[===========> ] 3.55G 58.3MB/s eta 37s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "m-ctx-8k.pth 63%[===========> ] 3.56G 58.9MB/s eta 37s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-ctx-8k.pth 63%[===========> ] 3.58G 61.0MB/s eta 37s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "ctx-8k.pth 63%[===========> ] 3.59G 59.7MB/s eta 35s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "tx-8k.pth 63%[===========> ] 3.61G 62.3MB/s eta 35s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "x-8k.pth 64%[===========> ] 3.62G 61.7MB/s eta 35s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-8k.pth 64%[===========> ] 3.65G 64.8MB/s eta 35s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "8k.pth 64%[===========> ] 3.65G 64.6MB/s eta 35s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "k.pth 64%[===========> ] 3.66G 60.3MB/s eta 34s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", ".pth 65%[============> ] 3.67G 61.6MB/s eta 34s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "pth 65%[============> ] 3.68G 60.6MB/s eta 34s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "th 65%[============> ] 3.70G 61.4MB/s eta 34s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "h 65%[============> ] 3.71G 60.5MB/s eta 34s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 66%[============> ] 3.72G 60.7MB/s eta 33s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " E 66%[============> ] 3.74G 60.1MB/s eta 33s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EW 66%[============> ] 3.75G 60.4MB/s eta 33s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR 66%[============> ] 3.76G 60.2MB/s eta 33s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR- 66%[============> ] 3.77G 57.2MB/s eta 33s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1 67%[============> ] 3.79G 60.2MB/s eta 32s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B 67%[============> ] 3.80G 57.8MB/s eta 32s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5 67%[============> ] 3.83G 60.2MB/s eta 32s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5- 68%[============> ] 3.84G 60.5MB/s eta 32s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E 68%[============> ] 3.85G 58.6MB/s eta 31s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0 68%[============> ] 3.87G 58.6MB/s eta 31s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_ 68%[============> ] 3.88G 59.9MB/s eta 31s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1 69%[============> ] 3.90G 60.3MB/s eta 31s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1- 69%[============> ] 3.90G 57.2MB/s eta 31s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1-m 69%[============> ] 3.92G 59.1MB/s eta 30s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1-me 69%[============> ] 3.95G 61.3MB/s eta 30s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1-mem 70%[=============> ] 3.96G 61.8MB/s eta 30s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1-mem- 70%[=============> ] 3.98G 61.4MB/s eta 30s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1-mem-c 70%[=============> ] 3.99G 63.5MB/s eta 28s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "EWR-1B5-E0_1-mem-ct 71%[=============> ] 4.01G 64.4MB/s eta 28s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "WR-1B5-E0_1-mem-ctx 71%[=============> ] 4.03G 65.3MB/s eta 28s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "R-1B5-E0_1-mem-ctx- 71%[=============> ] 4.04G 60.4MB/s eta 28s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-1B5-E0_1-mem-ctx-8 71%[=============> ] 4.05G 58.8MB/s eta 27s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "1B5-E0_1-mem-ctx-8k 71%[=============> ] 4.05G 57.0MB/s eta 27s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "B5-E0_1-mem-ctx-8k. 72%[=============> ] 4.07G 57.3MB/s eta 27s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "5-E0_1-mem-ctx-8k.p 72%[=============> ] 4.08G 56.8MB/s eta 27s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-E0_1-mem-ctx-8k.pt 72%[=============> ] 4.09G 56.5MB/s eta 27s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "E0_1-mem-ctx-8k.pth 72%[=============> ] 4.10G 55.3MB/s eta 27s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "0_1-mem-ctx-8k.pth 72%[=============> ] 4.11G 54.9MB/s eta 27s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "_1-mem-ctx-8k.pth 73%[=============> ] 4.13G 58.7MB/s eta 27s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "1-mem-ctx-8k.pth 73%[=============> ] 4.14G 58.0MB/s eta 27s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-mem-ctx-8k.pth 73%[=============> ] 4.16G 56.7MB/s eta 27s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "mem-ctx-8k.pth 73%[=============> ] 4.17G 56.0MB/s eta 25s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "em-ctx-8k.pth 74%[=============> ] 4.18G 52.3MB/s eta 25s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "m-ctx-8k.pth 74%[=============> ] 4.19G 53.2MB/s eta 25s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-ctx-8k.pth 74%[=============> ] 4.21G 52.5MB/s eta 25s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "ctx-8k.pth 74%[=============> ] 4.22G 51.5MB/s eta 25s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "tx-8k.pth 74%[=============> ] 4.23G 52.1MB/s eta 24s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "x-8k.pth 75%[==============> ] 4.25G 53.7MB/s eta 24s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-8k.pth 75%[==============> ] 4.26G 53.8MB/s eta 24s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "8k.pth 75%[==============> ] 4.28G 56.1MB/s eta 24s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "k.pth 76%[==============> ] 4.30G 59.0MB/s eta 23s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", ".pth 76%[==============> ] 4.32G 61.1MB/s eta 23s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "pth 76%[==============> ] 4.33G 61.3MB/s eta 23s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "th 77%[==============> ] 4.35G 60.6MB/s eta 23s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "h 77%[==============> ] 4.37G 58.6MB/s eta 22s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 77%[==============> ] 4.38G 59.4MB/s eta 22s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " E 77%[==============> ] 4.40G 59.9MB/s eta 22s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EW 78%[==============> ] 4.41G 61.4MB/s eta 22s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR 78%[==============> ] 4.42G 63.3MB/s eta 21s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR- 78%[==============> ] 4.44G 62.6MB/s eta 21s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1 78%[==============> ] 4.46G 62.5MB/s eta 21s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B 79%[==============> ] 4.47G 62.5MB/s eta 21s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5 79%[==============> ] 4.48G 64.9MB/s eta 21s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5- 79%[==============> ] 4.50G 65.2MB/s eta 20s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E 79%[==============> ] 4.51G 62.3MB/s eta 20s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0 80%[===============> ] 4.52G 62.7MB/s eta 20s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_ 80%[===============> ] 4.55G 64.9MB/s eta 20s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1 80%[===============> ] 4.56G 65.7MB/s eta 20s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1- 81%[===============> ] 4.57G 62.9MB/s eta 18s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1-m 81%[===============> ] 4.59G 60.8MB/s eta 18s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1-me 81%[===============> ] 4.60G 62.4MB/s eta 18s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1-mem 81%[===============> ] 4.62G 63.8MB/s eta 18s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1-mem- 82%[===============> ] 4.63G 65.1MB/s eta 17s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1-mem-c 82%[===============> ] 4.65G 63.3MB/s eta 17s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "EWR-1B5-E0_1-mem-ct 82%[===============> ] 4.68G 65.4MB/s eta 17s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "WR-1B5-E0_1-mem-ctx 83%[===============> ] 4.69G 66.3MB/s eta 17s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "R-1B5-E0_1-mem-ctx- 83%[===============> ] 4.70G 65.5MB/s eta 17s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-1B5-E0_1-mem-ctx-8 83%[===============> ] 4.71G 63.6MB/s eta 16s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "1B5-E0_1-mem-ctx-8k 83%[===============> ] 4.72G 63.2MB/s eta 16s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "B5-E0_1-mem-ctx-8k. 83%[===============> ] 4.74G 64.0MB/s eta 16s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "5-E0_1-mem-ctx-8k.p 84%[===============> ] 4.74G 63.0MB/s eta 16s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-E0_1-mem-ctx-8k.pt 84%[===============> ] 4.75G 60.2MB/s eta 16s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "E0_1-mem-ctx-8k.pth 84%[===============> ] 4.77G 56.0MB/s eta 15s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "0_1-mem-ctx-8k.pth 84%[===============> ] 4.78G 56.7MB/s eta 15s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "_1-mem-ctx-8k.pth 85%[================> ] 4.80G 60.8MB/s eta 15s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "1-mem-ctx-8k.pth 85%[================> ] 4.83G 62.1MB/s eta 15s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-mem-ctx-8k.pth 85%[================> ] 4.84G 60.7MB/s eta 14s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "mem-ctx-8k.pth 86%[================> ] 4.86G 56.9MB/s eta 14s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "em-ctx-8k.pth 86%[================> ] 4.88G 58.5MB/s eta 14s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "m-ctx-8k.pth 86%[================> ] 4.89G 58.3MB/s eta 14s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-ctx-8k.pth 86%[================> ] 4.90G 60.5MB/s eta 14s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "ctx-8k.pth 87%[================> ] 4.92G 60.0MB/s eta 12s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "tx-8k.pth 87%[================> ] 4.93G 59.4MB/s eta 12s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "x-8k.pth 87%[================> ] 4.95G 59.1MB/s eta 12s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-8k.pth 87%[================> ] 4.96G 60.6MB/s eta 12s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "8k.pth 88%[================> ] 4.99G 63.2MB/s eta 11s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "k.pth 88%[================> ] 5.01G 63.3MB/s eta 11s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", ".pth 88%[================> ] 5.01G 57.9MB/s eta 11s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "pth 89%[================> ] 5.03G 59.8MB/s eta 11s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "th 89%[================> ] 5.04G 60.3MB/s eta 11s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "h 89%[================> ] 5.05G 56.5MB/s eta 10s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 89%[================> ] 5.07G 56.9MB/s eta 10s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " E 90%[=================> ] 5.08G 56.4MB/s eta 10s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EW 90%[=================> ] 5.10G 57.6MB/s eta 10s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR 90%[=================> ] 5.11G 56.0MB/s eta 9s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR- 90%[=================> ] 5.12G 55.5MB/s eta 9s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1 90%[=================> ] 5.13G 56.8MB/s eta 9s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B 91%[=================> ] 5.14G 55.0MB/s eta 9s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5 91%[=================> ] 5.15G 54.6MB/s eta 9s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5- 91%[=================> ] 5.17G 54.1MB/s eta 8s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E 91%[=================> ] 5.17G 51.3MB/s eta 8s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0 91%[=================> ] 5.19G 50.3MB/s eta 8s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_ 92%[=================> ] 5.20G 51.1MB/s eta 8s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1 92%[=================> ] 5.21G 53.3MB/s eta 7s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1- 92%[=================> ] 5.24G 56.3MB/s eta 7s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1-m 93%[=================> ] 5.26G 55.1MB/s eta 7s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1-me 93%[=================> ] 5.27G 57.5MB/s eta 7s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1-mem 93%[=================> ] 5.29G 58.3MB/s eta 7s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1-mem- 93%[=================> ] 5.30G 58.3MB/s eta 6s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " EWR-1B5-E0_1-mem-c 94%[=================> ] 5.32G 58.8MB/s eta 6s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "EWR-1B5-E0_1-mem-ct 94%[=================> ] 5.33G 59.2MB/s eta 6s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "WR-1B5-E0_1-mem-ctx 94%[=================> ] 5.35G 60.8MB/s eta 6s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "R-1B5-E0_1-mem-ctx- 95%[==================> ] 5.36G 61.8MB/s eta 6s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-1B5-E0_1-mem-ctx-8 95%[==================> ] 5.38G 61.8MB/s eta 5s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "1B5-E0_1-mem-ctx-8k 95%[==================> ] 5.39G 60.5MB/s eta 5s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "B5-E0_1-mem-ctx-8k. 95%[==================> ] 5.41G 61.4MB/s eta 5s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "5-E0_1-mem-ctx-8k.p 96%[==================> ] 5.42G 62.4MB/s eta 5s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-E0_1-mem-ctx-8k.pt 96%[==================> ] 5.44G 61.7MB/s eta 4s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "E0_1-mem-ctx-8k.pth 96%[==================> ] 5.45G 60.3MB/s eta 4s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "0_1-mem-ctx-8k.pth 96%[==================> ] 5.47G 58.9MB/s eta 4s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "_1-mem-ctx-8k.pth 97%[==================> ] 5.48G 56.8MB/s eta 4s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "1-mem-ctx-8k.pth 97%[==================> ] 5.50G 56.2MB/s eta 3s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-mem-ctx-8k.pth 97%[==================> ] 5.51G 54.8MB/s eta 3s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "mem-ctx-8k.pth 97%[==================> ] 5.52G 54.3MB/s eta 3s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "em-ctx-8k.pth 97%[==================> ] 5.53G 52.5MB/s eta 3s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "m-ctx-8k.pth 98%[==================> ] 5.54G 52.4MB/s eta 2s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-ctx-8k.pth 98%[==================> ] 5.56G 52.3MB/s eta 2s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "ctx-8k.pth 98%[==================> ] 5.57G 52.1MB/s eta 2s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "tx-8k.pth 98%[==================> ] 5.58G 49.7MB/s eta 2s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "x-8k.pth 99%[==================> ] 5.59G 50.4MB/s eta 2s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-8k.pth 99%[==================> ] 5.61G 55.0MB/s eta 1s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "8k.pth 99%[==================> ] 5.63G 55.0MB/s eta 1s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "k.pth 99%[==================> ] 5.64G 56.1MB/s eta 1s \r", "EWR-1B5-E0_1-mem-ct 100%[===================>] 5.64G 56.3MB/s in 98s \r\n", "\r\n", "2023-08-26 13:29:16 (59.2 MB/s) - ‘EWR-1B5-E0_1-mem-ctx-8k.pth’ saved [6060483163/6060483163]\r\n", "\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "--2023-08-26 13:29:16-- https://huggingface.co./picocreator/RWKV-x-playground/resolve/main/V5-16k/v5-L6-D2048-E0_1-mem-ctx-8k.pth\r\n", "Resolving huggingface.co (huggingface.co)... 18.154.227.67, 18.154.227.7, 18.154.227.87, ...\r\n", "Connecting to huggingface.co (huggingface.co)|18.154.227.67|:443... connected.\r\n", "HTTP request sent, awaiting response... 302 Found\r\n", "Location: https://cdn-lfs.huggingface.co/repos/69/e5/69e55a6299441d3070ee1690632f8d12440ea004de9c6a51b873ccd49ea78ea0/87b64f45529c2049a8b044b7e7c0338a9ede8ba8259d17d987d8e73f8a34fd75?response-content-disposition=attachment%3B+filename*%3DUTF-8%27%27v5-L6-D2048-E0_1-mem-ctx-8k.pth%3B+filename%3D%22v5-L6-D2048-E0_1-mem-ctx-8k.pth%22%3B&Expires=1693315756&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTY5MzMxNTc1Nn19LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy5odWdnaW5nZmFjZS5jby9yZXBvcy82OS9lNS82OWU1NWE2Mjk5NDQxZDMwNzBlZTE2OTA2MzJmOGQxMjQ0MGVhMDA0ZGU5YzZhNTFiODczY2NkNDllYTc4ZWEwLzg3YjY0ZjQ1NTI5YzIwNDlhOGIwNDRiN2U3YzAzMzhhOWVkZThiYTgyNTlkMTdkOTg3ZDhlNzNmOGEzNGZkNzU%7EcmVzcG9uc2UtY29udGVudC1kaXNwb3NpdGlvbj0qIn1dfQ__&Signature=nQ-K9pUZqkf3Qb-X5VycpSsb2NBCdUjo2I2d1pYB%7EE1ldNGTAfgN6a9qOGn5UuHtD8nAyITD6NgR95cqWgn2AqAUWCTWcqYBc7tuhVIPmbwrYHUwl6FJ52hjrRPmxZngcRQu2Lbg7PXij9qDfqdh1r%7E6z05NRVnGTQ0GkZQQb3maRu5uC9d83DSC88AmR371N2AwiH3t5VUs8w80YL%7E90nAIoeoBsBaMEATtt8k6x6KER-NDZ2fmKLch4cTHxIDGPEaYOKnFyimPy5PWpFC8WYAoGlCE6jLa5P5eXpArLXCNScNiYp4tGyNmcA80Pf9TN9E6UZ-PfU7LwjmrUR2hKg__&Key-Pair-Id=KVTP0A1DKRTAX [following]\r\n", "--2023-08-26 13:29:16-- https://cdn-lfs.huggingface.co/repos/69/e5/69e55a6299441d3070ee1690632f8d12440ea004de9c6a51b873ccd49ea78ea0/87b64f45529c2049a8b044b7e7c0338a9ede8ba8259d17d987d8e73f8a34fd75?response-content-disposition=attachment%3B+filename*%3DUTF-8%27%27v5-L6-D2048-E0_1-mem-ctx-8k.pth%3B+filename%3D%22v5-L6-D2048-E0_1-mem-ctx-8k.pth%22%3B&Expires=1693315756&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTY5MzMxNTc1Nn19LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy5odWdnaW5nZmFjZS5jby9yZXBvcy82OS9lNS82OWU1NWE2Mjk5NDQxZDMwNzBlZTE2OTA2MzJmOGQxMjQ0MGVhMDA0ZGU5YzZhNTFiODczY2NkNDllYTc4ZWEwLzg3YjY0ZjQ1NTI5YzIwNDlhOGIwNDRiN2U3YzAzMzhhOWVkZThiYTgyNTlkMTdkOTg3ZDhlNzNmOGEzNGZkNzU%7EcmVzcG9uc2UtY29udGVudC1kaXNwb3NpdGlvbj0qIn1dfQ__&Signature=nQ-K9pUZqkf3Qb-X5VycpSsb2NBCdUjo2I2d1pYB%7EE1ldNGTAfgN6a9qOGn5UuHtD8nAyITD6NgR95cqWgn2AqAUWCTWcqYBc7tuhVIPmbwrYHUwl6FJ52hjrRPmxZngcRQu2Lbg7PXij9qDfqdh1r%7E6z05NRVnGTQ0GkZQQb3maRu5uC9d83DSC88AmR371N2AwiH3t5VUs8w80YL%7E90nAIoeoBsBaMEATtt8k6x6KER-NDZ2fmKLch4cTHxIDGPEaYOKnFyimPy5PWpFC8WYAoGlCE6jLa5P5eXpArLXCNScNiYp4tGyNmcA80Pf9TN9E6UZ-PfU7LwjmrUR2hKg__&Key-Pair-Id=KVTP0A1DKRTAX\r\n", "Resolving cdn-lfs.huggingface.co (cdn-lfs.huggingface.co)... 108.138.64.121, 108.138.64.111, 108.138.64.36, ...\r\n", "Connecting to cdn-lfs.huggingface.co (cdn-lfs.huggingface.co)|108.138.64.121|: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: 1066508293 (1017M) [binary/octet-stream]\r\n", "Saving to: ‘v5-L6-D2048-E0_1-mem-ctx-8k.pth’\r\n", "\r\n", "\r", " v5-L6-D20 0%[ ] 0 --.-KB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D204 1%[ ] 15.26M 59.8MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048 2%[ ] 30.00M 60.8MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048- 4%[ ] 45.26M 63.8MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048-E 4%[ ] 45.90M 48.9MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048-E0 5%[> ] 60.52M 47.1MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048-E0_ 7%[> ] 75.78M 50.3MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048-E0_1 8%[> ] 86.07M 50.4MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048-E0_1- 9%[> ] 96.66M 50.7MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048-E0_1-m 10%[=> ] 106.81M 50.2MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "v5-L6-D2048-E0_1-me 12%[=> ] 127.07M 54.6MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "5-L6-D2048-E0_1-mem 14%[=> ] 151.05M 59.7MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-L6-D2048-E0_1-mem- 15%[==> ] 161.83M 59.3MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "L6-D2048-E0_1-mem-c 16%[==> ] 167.85M 56.4MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "6-D2048-E0_1-mem-ct 18%[==> ] 183.10M 53.6MB/s eta 16s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-D2048-E0_1-mem-ctx 19%[==> ] 198.36M 54.4MB/s eta 16s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "D2048-E0_1-mem-ctx- 21%[===> ] 213.62M 54.5MB/s eta 16s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "2048-E0_1-mem-ctx-8 21%[===> ] 219.93M 51.6MB/s eta 16s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "048-E0_1-mem-ctx-8k 22%[===> ] 229.84M 52.4MB/s eta 16s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "48-E0_1-mem-ctx-8k. 23%[===> ] 242.32M 50.5MB/s eta 15s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "8-E0_1-mem-ctx-8k.p 25%[====> ] 258.89M 53.4MB/s eta 15s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-E0_1-mem-ctx-8k.pt 26%[====> ] 274.14M 53.7MB/s eta 15s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "E0_1-mem-ctx-8k.pth 28%[====> ] 289.40M 55.0MB/s eta 15s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "0_1-mem-ctx-8k.pth 29%[====> ] 296.23M 54.0MB/s eta 15s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "_1-mem-ctx-8k.pth 30%[=====> ] 305.18M 54.5MB/s eta 14s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "1-mem-ctx-8k.pth 33%[=====> ] 335.69M 57.8MB/s eta 14s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-mem-ctx-8k.pth 35%[======> ] 357.26M 57.6MB/s eta 14s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "mem-ctx-8k.pth 36%[======> ] 376.17M 58.0MB/s eta 14s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "em-ctx-8k.pth 37%[======> ] 381.47M 56.0MB/s eta 14s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "m-ctx-8k.pth 39%[======> ] 396.73M 55.5MB/s eta 11s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-ctx-8k.pth 40%[=======> ] 410.16M 55.5MB/s eta 11s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "ctx-8k.pth 41%[=======> ] 426.73M 57.1MB/s eta 11s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "tx-8k.pth 42%[=======> ] 436.06M 59.8MB/s eta 11s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "x-8k.pth 43%[=======> ] 442.51M 57.7MB/s eta 11s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-8k.pth 45%[========> ] 465.45M 62.0MB/s eta 10s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "8k.pth 46%[========> ] 473.02M 61.3MB/s eta 10s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "k.pth 48%[========> ] 488.28M 64.5MB/s eta 10s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", ".pth 49%[========> ] 503.03M 64.2MB/s eta 10s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "pth 51%[=========> ] 518.80M 65.1MB/s eta 10s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "th 52%[=========> ] 535.97M 65.2MB/s eta 8s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "h 54%[=========> ] 549.31M 67.0MB/s eta 8s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 55%[==========> ] 564.06M 67.8MB/s eta 8s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v 57%[==========> ] 579.83M 59.7MB/s eta 8s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5 58%[==========> ] 595.09M 60.2MB/s eta 7s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5- 60%[===========> ] 610.35M 60.2MB/s eta 7s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L 61%[===========> ] 625.61M 59.7MB/s eta 7s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6 63%[===========> ] 640.87M 57.7MB/s eta 7s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6- 64%[===========> ] 655.62M 57.6MB/s eta 6s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D 65%[============> ] 667.88M 56.7MB/s eta 6s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2 65%[============> ] 669.55M 55.9MB/s eta 6s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D20 67%[============> ] 686.13M 55.7MB/s eta 6s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D204 69%[============> ] 701.90M 53.6MB/s eta 6s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048 70%[=============> ] 717.16M 52.7MB/s eta 5s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048- 72%[=============> ] 732.42M 53.9MB/s eta 5s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048-E 73%[=============> ] 747.69M 53.1MB/s eta 5s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048-E0 75%[==============> ] 762.94M 52.9MB/s eta 5s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048-E0_ 76%[==============> ] 777.68M 53.0MB/s eta 5s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048-E0_1 77%[==============> ] 792.94M 53.8MB/s eta 4s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048-E0_1- 79%[==============> ] 808.20M 54.2MB/s eta 4s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D2048-E0_1-m 81%[===============> ] 823.97M 53.3MB/s eta 4s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "v5-L6-D2048-E0_1-me 82%[===============> ] 839.23M 53.4MB/s eta 4s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "5-L6-D2048-E0_1-mem 84%[===============> ] 854.49M 55.2MB/s eta 3s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-L6-D2048-E0_1-mem- 86%[================> ] 882.15M 58.6MB/s eta 3s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "L6-D2048-E0_1-mem-c 86%[================> ] 884.49M 58.0MB/s eta 3s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "6-D2048-E0_1-mem-ct 88%[================> ] 899.75M 59.7MB/s eta 3s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-D2048-E0_1-mem-ctx 89%[================> ] 915.01M 61.3MB/s eta 3s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "D2048-E0_1-mem-ctx- 91%[=================> ] 928.95M 60.5MB/s eta 2s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "2048-E0_1-mem-ctx-8 93%[=================> ] 946.04M 61.1MB/s eta 2s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "048-E0_1-mem-ctx-8k 94%[=================> ] 961.30M 59.8MB/s eta 2s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "48-E0_1-mem-ctx-8k. 96%[==================> ] 976.55M 62.9MB/s eta 2s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "8-E0_1-mem-ctx-8k.p 97%[==================> ] 993.88M 62.0MB/s eta 0s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-E0_1-mem-ctx-8k.pt 98%[==================> ] 1002M 60.7MB/s eta 0s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "E0_1-mem-ctx-8k.pth 99%[==================> ] 1007M 57.6MB/s eta 0s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "0_1-mem-ctx-8k.pth 99%[==================> ] 1016M 56.2MB/s eta 0s \r", "v5-L6-D2048-E0_1-me 100%[===================>] 1017M 56.5MB/s in 18s \r\n", "\r\n", "2023-08-26 13:29:35 (56.7 MB/s) - ‘v5-L6-D2048-E0_1-mem-ctx-8k.pth’ saved [1066508293/1066508293]\r\n", "\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "--2023-08-26 13:29:35-- https://huggingface.co./picocreator/RWKV-x-playground/resolve/main/V5-16k/v5-L6-D4096-E0_1-mem-ctx-8k.pth\r\n", "Resolving huggingface.co (huggingface.co)... 18.154.227.69, 18.154.227.87, 18.154.227.7, ...\r\n", "Connecting to huggingface.co (huggingface.co)|18.154.227.69|: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/69/e5/69e55a6299441d3070ee1690632f8d12440ea004de9c6a51b873ccd49ea78ea0/5f93b1f6f6f7fb2193130a3a51f8ed41a0541b1b5eab100ca9318c8218d481fa?response-content-disposition=attachment%3B+filename*%3DUTF-8%27%27v5-L6-D4096-E0_1-mem-ctx-8k.pth%3B+filename%3D%22v5-L6-D4096-E0_1-mem-ctx-8k.pth%22%3B&Expires=1693315775&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTY5MzMxNTc3NX19LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy5odWdnaW5nZmFjZS5jby9yZXBvcy82OS9lNS82OWU1NWE2Mjk5NDQxZDMwNzBlZTE2OTA2MzJmOGQxMjQ0MGVhMDA0ZGU5YzZhNTFiODczY2NkNDllYTc4ZWEwLzVmOTNiMWY2ZjZmN2ZiMjE5MzEzMGEzYTUxZjhlZDQxYTA1NDFiMWI1ZWFiMTAwY2E5MzE4YzgyMThkNDgxZmE%7EcmVzcG9uc2UtY29udGVudC1kaXNwb3NpdGlvbj0qIn1dfQ__&Signature=0PAV9vjTAoSaKMEFt4ra050ppnm5%7EebPodEspDpM%7Egvrid9e19xm4sLLXhnWRGgm63iOJ2eZykOhOquOiG9HtoO5NACC2I3xGt4x8Ti%7Eujc0ObTE8Ks9NcRCIrd2B5DeiQANgL-qAUZfh5hj9MGOyy7MMQZNET%7E7eTFHVGLpB2ijJYbdQPjUO5qF0ZHho9T6avOAi8AyTLlwAfXXldcR7JLX1DLCMWgzZXFvv8AP2i6QgstOqEZ8MX5W%7ESS0mwHkJMhtC234TiouvTE0GcZV7ErFMjAats%7EOPqJj6pp9oh3azAdUqXR%7EBRTlZIZCe5E5oTkBzS3m33LT7cRt5cVSSw__&Key-Pair-Id=KVTP0A1DKRTAX [following]\r\n", "--2023-08-26 13:29:35-- https://cdn-lfs.huggingface.co/repos/69/e5/69e55a6299441d3070ee1690632f8d12440ea004de9c6a51b873ccd49ea78ea0/5f93b1f6f6f7fb2193130a3a51f8ed41a0541b1b5eab100ca9318c8218d481fa?response-content-disposition=attachment%3B+filename*%3DUTF-8%27%27v5-L6-D4096-E0_1-mem-ctx-8k.pth%3B+filename%3D%22v5-L6-D4096-E0_1-mem-ctx-8k.pth%22%3B&Expires=1693315775&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTY5MzMxNTc3NX19LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy5odWdnaW5nZmFjZS5jby9yZXBvcy82OS9lNS82OWU1NWE2Mjk5NDQxZDMwNzBlZTE2OTA2MzJmOGQxMjQ0MGVhMDA0ZGU5YzZhNTFiODczY2NkNDllYTc4ZWEwLzVmOTNiMWY2ZjZmN2ZiMjE5MzEzMGEzYTUxZjhlZDQxYTA1NDFiMWI1ZWFiMTAwY2E5MzE4YzgyMThkNDgxZmE%7EcmVzcG9uc2UtY29udGVudC1kaXNwb3NpdGlvbj0qIn1dfQ__&Signature=0PAV9vjTAoSaKMEFt4ra050ppnm5%7EebPodEspDpM%7Egvrid9e19xm4sLLXhnWRGgm63iOJ2eZykOhOquOiG9HtoO5NACC2I3xGt4x8Ti%7Eujc0ObTE8Ks9NcRCIrd2B5DeiQANgL-qAUZfh5hj9MGOyy7MMQZNET%7E7eTFHVGLpB2ijJYbdQPjUO5qF0ZHho9T6avOAi8AyTLlwAfXXldcR7JLX1DLCMWgzZXFvv8AP2i6QgstOqEZ8MX5W%7ESS0mwHkJMhtC234TiouvTE0GcZV7ErFMjAats%7EOPqJj6pp9oh3azAdUqXR%7EBRTlZIZCe5E5oTkBzS3m33LT7cRt5cVSSw__&Key-Pair-Id=KVTP0A1DKRTAX\r\n", "Resolving cdn-lfs.huggingface.co (cdn-lfs.huggingface.co)... 108.138.64.49, 108.138.64.36, 108.138.64.111, ...\r\n", "Connecting to cdn-lfs.huggingface.co (cdn-lfs.huggingface.co)|108.138.64.49|:443... connected.\r\n", "HTTP request sent, awaiting response... " ] }, { "name": "stdout", "output_type": "stream", "text": [ "200 OK\r\n", "Length: 3441599237 (3.2G) [binary/octet-stream]\r\n", "Saving to: ‘v5-L6-D4096-E0_1-mem-ctx-8k.pth’\r\n", "\r\n", "\r", " v5-L6-D40 0%[ ] 0 --.-KB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D409 0%[ ] 14.45M 72.2MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D4096 0%[ ] 30.00M 69.8MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D4096- 1%[ ] 45.78M 62.5MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D4096-E 1%[ ] 63.10M 66.9MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D4096-E0 2%[ ] 76.29M 62.0MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D4096-E0_ 2%[ ] 91.55M 61.2MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D4096-E0_1 3%[ ] 106.81M 61.9MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D4096-E0_1- 3%[ ] 122.07M 61.9MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D4096-E0_1-m 4%[ ] 137.33M 61.2MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "v5-L6-D4096-E0_1-me 4%[ ] 152.59M 59.0MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "5-L6-D4096-E0_1-mem 5%[> ] 167.85M 59.2MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-L6-D4096-E0_1-mem- 5%[> ] 183.10M 59.3MB/s eta 52s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "L6-D4096-E0_1-mem-c 6%[> ] 200.07M 60.9MB/s eta 52s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "6-D4096-E0_1-mem-ct 6%[> ] 213.62M 61.3MB/s eta 52s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-D4096-E0_1-mem-ctx 6%[> ] 228.36M 61.9MB/s eta 52s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "D4096-E0_1-mem-ctx- 7%[> ] 231.28M 58.9MB/s eta 52s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "4096-E0_1-mem-ctx-8 7%[> ] 245.59M 59.4MB/s eta 51s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "096-E0_1-mem-ctx-8k 7%[> ] 259.40M 59.2MB/s eta 51s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "96-E0_1-mem-ctx-8k. 8%[> ] 274.66M 54.8MB/s eta 51s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "6-E0_1-mem-ctx-8k.p 8%[> ] 289.92M 54.4MB/s eta 51s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-E0_1-mem-ctx-8k.pt 9%[> ] 303.43M 56.3MB/s eta 52s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "E0_1-mem-ctx-8k.pth 9%[> ] 320.43M 56.5MB/s eta 52s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "0_1-mem-ctx-8k.pth 10%[=> ] 335.69M 51.5MB/s eta 52s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "_1-mem-ctx-8k.pth 10%[=> ] 350.95M 54.7MB/s eta 52s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "1-mem-ctx-8k.pth 11%[=> ] 373.65M 55.9MB/s eta 49s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-mem-ctx-8k.pth 11%[=> ] 381.47M 55.3MB/s eta 49s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "mem-ctx-8k.pth 12%[=> ] 396.22M 54.8MB/s eta 49s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "em-ctx-8k.pth 12%[=> ] 410.16M 53.9MB/s eta 49s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "m-ctx-8k.pth 13%[=> ] 426.73M 54.2MB/s eta 50s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-ctx-8k.pth 13%[=> ] 434.90M 52.6MB/s eta 50s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "ctx-8k.pth 13%[=> ] 442.51M 50.9MB/s eta 50s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "tx-8k.pth 13%[=> ] 457.76M 50.4MB/s eta 50s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "x-8k.pth 14%[=> ] 485.65M 56.9MB/s eta 48s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-8k.pth 15%[==> ] 503.54M 57.4MB/s eta 48s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "8k.pth 15%[==> ] 518.80M 54.0MB/s eta 48s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "k.pth 16%[==> ] 533.54M 55.1MB/s eta 48s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", ".pth 16%[==> ] 542.02M 54.1MB/s eta 48s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "pth 16%[==> ] 549.31M 54.7MB/s eta 48s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "th 17%[==> ] 564.58M 52.2MB/s eta 48s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "h 17%[==> ] 573.01M 50.2MB/s eta 48s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 17%[==> ] 582.65M 51.6MB/s eta 48s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v 18%[==> ] 595.09M 49.7MB/s eta 49s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5 18%[==> ] 609.84M 52.8MB/s eta 49s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5- 18%[==> ] 612.47M 50.4MB/s eta 49s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L 19%[==> ] 625.09M 47.8MB/s eta 49s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6 19%[==> ] 635.59M 49.6MB/s eta 49s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6- 19%[==> ] 640.87M 47.2MB/s eta 49s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D 19%[==> ] 656.13M 48.2MB/s eta 49s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D4 20%[===> ] 671.38M 44.8MB/s eta 49s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D40 20%[===> ] 686.64M 44.8MB/s eta 49s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D409 21%[===> ] 706.19M 47.9MB/s eta 48s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D4096 21%[===> ] 717.16M 47.2MB/s eta 48s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D4096- 22%[===> ] 732.42M 46.3MB/s eta 48s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D4096-E 22%[===> ] 745.86M 46.4MB/s eta 48s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D4096-E0 23%[===> ] 759.61M 48.3MB/s eta 47s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D4096-E0_ 23%[===> ] 767.09M 48.3MB/s eta 47s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D4096-E0_1 23%[===> ] 778.20M 48.2MB/s eta 47s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D4096-E0_1- 24%[===> ] 793.46M 49.1MB/s eta 47s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D4096-E0_1-m 24%[===> ] 808.71M 49.6MB/s eta 46s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "v5-L6-D4096-E0_1-me 25%[====> ] 823.46M 51.8MB/s eta 46s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "5-L6-D4096-E0_1-mem 25%[====> ] 839.23M 53.6MB/s eta 46s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-L6-D4096-E0_1-mem- 26%[====> ] 854.49M 52.4MB/s eta 46s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "L6-D4096-E0_1-mem-c 26%[====> ] 874.75M 54.5MB/s eta 45s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "6-D4096-E0_1-mem-ct 27%[====> ] 888.17M 57.6MB/s eta 45s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-D4096-E0_1-mem-ctx 27%[====> ] 900.27M 56.0MB/s eta 45s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "D4096-E0_1-mem-ctx- 27%[====> ] 915.53M 56.1MB/s eta 45s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "4096-E0_1-mem-ctx-8 28%[====> ] 930.78M 55.9MB/s eta 45s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "096-E0_1-mem-ctx-8k 28%[====> ] 946.04M 55.5MB/s eta 43s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "96-E0_1-mem-ctx-8k. 29%[====> ] 963.36M 57.9MB/s eta 43s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "6-E0_1-mem-ctx-8k.p 29%[====> ] 967.61M 56.2MB/s eta 43s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-E0_1-mem-ctx-8k.pt 29%[====> ] 976.05M 56.5MB/s eta 43s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "E0_1-mem-ctx-8k.pth 30%[=====> ] 988.87M 56.9MB/s eta 43s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "0_1-mem-ctx-8k.pth 30%[=====> ] 1002M 56.3MB/s eta 42s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "_1-mem-ctx-8k.pth 30%[=====> ] 1007M 55.5MB/s eta 42s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "1-mem-ctx-8k.pth 31%[=====> ] 1.00G 54.9MB/s eta 42s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-mem-ctx-8k.pth 31%[=====> ] 1.01G 55.9MB/s eta 42s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "mem-ctx-8k.pth 32%[=====> ] 1.03G 55.6MB/s eta 41s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "em-ctx-8k.pth 32%[=====> ] 1.04G 55.3MB/s eta 41s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "m-ctx-8k.pth 32%[=====> ] 1.04G 50.9MB/s eta 41s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-ctx-8k.pth 32%[=====> ] 1.06G 50.5MB/s eta 41s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "ctx-8k.pth 33%[=====> ] 1.07G 50.0MB/s eta 41s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "tx-8k.pth 33%[=====> ] 1.08G 47.6MB/s eta 41s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "x-8k.pth 33%[=====> ] 1.09G 47.3MB/s eta 41s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-8k.pth 34%[=====> ] 1.10G 46.2MB/s eta 41s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "8k.pth 34%[=====> ] 1.12G 46.2MB/s eta 41s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "k.pth 35%[======> ] 1.13G 47.4MB/s eta 40s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", ".pth 35%[======> ] 1.15G 50.8MB/s eta 40s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "pth 36%[======> ] 1.16G 52.5MB/s eta 40s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "th 36%[======> ] 1.16G 49.3MB/s eta 40s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "h 36%[======> ] 1.18G 49.9MB/s eta 40s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 37%[======> ] 1.19G 48.9MB/s eta 39s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v 37%[======> ] 1.21G 49.5MB/s eta 39s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5 37%[======> ] 1.21G 46.1MB/s eta 39s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5- 38%[======> ] 1.23G 50.5MB/s eta 39s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L 38%[======> ] 1.24G 49.0MB/s eta 39s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6 39%[======> ] 1.25G 50.9MB/s eta 38s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6- 39%[======> ] 1.26G 52.1MB/s eta 38s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D 39%[======> ] 1.27G 49.5MB/s eta 38s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D4 39%[======> ] 1.28G 50.0MB/s eta 38s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D40 40%[=======> ] 1.29G 50.0MB/s eta 37s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D409 40%[=======> ] 1.31G 48.3MB/s eta 37s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D4096 41%[=======> ] 1.32G 47.8MB/s eta 37s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D4096- 41%[=======> ] 1.33G 45.3MB/s eta 37s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D4096-E 41%[=======> ] 1.34G 46.9MB/s eta 36s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D4096-E0 42%[=======> ] 1.36G 47.6MB/s eta 36s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D4096-E0_ 42%[=======> ] 1.37G 51.0MB/s eta 36s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D4096-E0_1 43%[=======> ] 1.38G 49.1MB/s eta 36s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D4096-E0_1- 43%[=======> ] 1.39G 45.8MB/s eta 36s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D4096-E0_1-m 43%[=======> ] 1.40G 46.1MB/s eta 35s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "v5-L6-D4096-E0_1-me 44%[=======> ] 1.42G 48.0MB/s eta 35s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "5-L6-D4096-E0_1-mem 44%[=======> ] 1.43G 47.6MB/s eta 35s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-L6-D4096-E0_1-mem- 45%[========> ] 1.45G 48.4MB/s eta 35s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "L6-D4096-E0_1-mem-c 45%[========> ] 1.46G 50.4MB/s eta 35s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "6-D4096-E0_1-mem-ct 45%[========> ] 1.46G 47.4MB/s eta 34s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-D4096-E0_1-mem-ctx 46%[========> ] 1.47G 49.5MB/s eta 34s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "D4096-E0_1-mem-ctx- 46%[========> ] 1.49G 51.1MB/s eta 34s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "4096-E0_1-mem-ctx-8 46%[========> ] 1.50G 51.9MB/s eta 34s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "096-E0_1-mem-ctx-8k 47%[========> ] 1.52G 53.6MB/s eta 33s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "96-E0_1-mem-ctx-8k. 47%[========> ] 1.53G 52.3MB/s eta 33s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "6-E0_1-mem-ctx-8k.p 48%[========> ] 1.55G 50.6MB/s eta 33s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-E0_1-mem-ctx-8k.pt 48%[========> ] 1.55G 50.5MB/s eta 33s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "E0_1-mem-ctx-8k.pth 48%[========> ] 1.56G 50.3MB/s eta 32s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "0_1-mem-ctx-8k.pth 49%[========> ] 1.58G 53.0MB/s eta 32s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "_1-mem-ctx-8k.pth 49%[========> ] 1.59G 53.6MB/s eta 32s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "1-mem-ctx-8k.pth 50%[=========> ] 1.61G 54.7MB/s eta 32s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-mem-ctx-8k.pth 50%[=========> ] 1.62G 51.3MB/s eta 31s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "mem-ctx-8k.pth 51%[=========> ] 1.64G 52.6MB/s eta 31s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "em-ctx-8k.pth 51%[=========> ] 1.66G 55.2MB/s eta 31s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "m-ctx-8k.pth 52%[=========> ] 1.67G 54.2MB/s eta 31s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-ctx-8k.pth 52%[=========> ] 1.68G 54.9MB/s eta 30s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "ctx-8k.pth 52%[=========> ] 1.70G 52.2MB/s eta 30s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "tx-8k.pth 53%[=========> ] 1.71G 53.8MB/s eta 30s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "x-8k.pth 53%[=========> ] 1.71G 50.7MB/s eta 30s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-8k.pth 53%[=========> ] 1.73G 51.9MB/s eta 29s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "8k.pth 54%[=========> ] 1.74G 51.9MB/s eta 29s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "k.pth 54%[=========> ] 1.76G 54.8MB/s eta 29s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", ".pth 55%[==========> ] 1.77G 55.4MB/s eta 29s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "pth 55%[==========> ] 1.79G 55.1MB/s eta 29s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "th 56%[==========> ] 1.80G 55.7MB/s eta 27s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "h 56%[==========> ] 1.82G 57.3MB/s eta 27s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 56%[==========> ] 1.82G 53.5MB/s eta 27s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v 57%[==========> ] 1.83G 52.6MB/s eta 27s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5 57%[==========> ] 1.85G 55.3MB/s eta 27s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5- 58%[==========> ] 1.86G 54.3MB/s eta 26s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L 58%[==========> ] 1.86G 50.9MB/s eta 26s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6 58%[==========> ] 1.88G 50.6MB/s eta 26s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6- 59%[==========> ] 1.89G 51.7MB/s eta 26s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D 59%[==========> ] 1.91G 51.6MB/s eta 25s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D4 59%[==========> ] 1.92G 50.9MB/s eta 25s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D40 60%[===========> ] 1.93G 51.7MB/s eta 25s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D409 60%[===========> ] 1.94G 50.8MB/s eta 25s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D4096 60%[===========> ] 1.95G 52.2MB/s eta 25s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D4096- 61%[===========> ] 1.97G 51.5MB/s eta 25s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D4096-E 61%[===========> ] 1.98G 50.4MB/s eta 25s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D4096-E0 62%[===========> ] 2.00G 49.6MB/s eta 25s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D4096-E0_ 62%[===========> ] 2.01G 49.4MB/s eta 23s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D4096-E0_1 63%[===========> ] 2.03G 48.8MB/s eta 23s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D4096-E0_1- 63%[===========> ] 2.04G 51.1MB/s eta 23s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D4096-E0_1-m 63%[===========> ] 2.05G 50.6MB/s eta 23s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "v5-L6-D4096-E0_1-me 64%[===========> ] 2.06G 50.5MB/s eta 23s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "5-L6-D4096-E0_1-mem 64%[===========> ] 2.07G 51.2MB/s eta 22s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-L6-D4096-E0_1-mem- 64%[===========> ] 2.08G 51.2MB/s eta 22s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "L6-D4096-E0_1-mem-c 65%[============> ] 2.09G 48.9MB/s eta 22s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "6-D4096-E0_1-mem-ct 65%[============> ] 2.10G 48.0MB/s eta 22s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-D4096-E0_1-mem-ctx 66%[============> ] 2.12G 50.3MB/s eta 22s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "D4096-E0_1-mem-ctx- 66%[============> ] 2.13G 50.1MB/s eta 21s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "4096-E0_1-mem-ctx-8 66%[============> ] 2.14G 50.9MB/s eta 21s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "096-E0_1-mem-ctx-8k 67%[============> ] 2.16G 52.8MB/s eta 21s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "96-E0_1-mem-ctx-8k. 67%[============> ] 2.17G 54.8MB/s eta 21s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "6-E0_1-mem-ctx-8k.p 67%[============> ] 2.17G 52.1MB/s eta 21s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-E0_1-mem-ctx-8k.pt 68%[============> ] 2.19G 52.9MB/s eta 20s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "E0_1-mem-ctx-8k.pth 68%[============> ] 2.19G 49.6MB/s eta 20s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "0_1-mem-ctx-8k.pth 68%[============> ] 2.20G 51.2MB/s eta 20s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "_1-mem-ctx-8k.pth 69%[============> ] 2.21G 49.2MB/s eta 20s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "1-mem-ctx-8k.pth 69%[============> ] 2.22G 47.1MB/s eta 20s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-mem-ctx-8k.pth 69%[============> ] 2.23G 49.6MB/s eta 19s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "mem-ctx-8k.pth 70%[=============> ] 2.25G 49.0MB/s eta 19s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "em-ctx-8k.pth 70%[=============> ] 2.26G 48.8MB/s eta 19s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "m-ctx-8k.pth 71%[=============> ] 2.28G 49.2MB/s eta 19s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-ctx-8k.pth 71%[=============> ] 2.29G 52.0MB/s eta 18s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "ctx-8k.pth 72%[=============> ] 2.31G 51.0MB/s eta 18s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "tx-8k.pth 72%[=============> ] 2.32G 51.4MB/s eta 18s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "x-8k.pth 72%[=============> ] 2.34G 50.6MB/s eta 18s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-8k.pth 73%[=============> ] 2.35G 50.3MB/s eta 17s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "8k.pth 73%[=============> ] 2.35G 49.2MB/s eta 17s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "k.pth 73%[=============> ] 2.37G 49.4MB/s eta 17s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", ".pth 74%[=============> ] 2.38G 50.2MB/s eta 17s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "pth 74%[=============> ] 2.39G 48.5MB/s eta 17s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "th 74%[=============> ] 2.40G 47.0MB/s eta 16s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "h 75%[==============> ] 2.41G 47.5MB/s eta 16s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 75%[==============> ] 2.41G 46.8MB/s eta 16s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v 75%[==============> ] 2.41G 45.5MB/s eta 16s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5 76%[==============> ] 2.44G 49.9MB/s eta 16s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5- 76%[==============> ] 2.44G 46.5MB/s eta 15s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L 76%[==============> ] 2.46G 46.8MB/s eta 15s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6 76%[==============> ] 2.46G 45.3MB/s eta 15s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6- 77%[==============> ] 2.47G 44.0MB/s eta 15s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D 77%[==============> ] 2.49G 46.3MB/s eta 15s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D4 77%[==============> ] 2.50G 45.0MB/s eta 14s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D40 78%[==============> ] 2.51G 45.7MB/s eta 14s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D409 78%[==============> ] 2.52G 46.3MB/s eta 14s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D4096 79%[==============> ] 2.53G 45.4MB/s eta 14s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D4096- 79%[==============> ] 2.55G 45.6MB/s eta 14s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D4096-E 79%[==============> ] 2.56G 48.4MB/s eta 13s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D4096-E0 80%[===============> ] 2.58G 48.2MB/s eta 13s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D4096-E0_ 80%[===============> ] 2.58G 46.9MB/s eta 13s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D4096-E0_1 80%[===============> ] 2.59G 49.3MB/s eta 13s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D4096-E0_1- 81%[===============> ] 2.61G 45.2MB/s eta 12s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D4096-E0_1-m 81%[===============> ] 2.62G 48.9MB/s eta 12s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "v5-L6-D4096-E0_1-me 82%[===============> ] 2.64G 48.9MB/s eta 12s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "5-L6-D4096-E0_1-mem 82%[===============> ] 2.65G 49.2MB/s eta 12s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-L6-D4096-E0_1-mem- 83%[===============> ] 2.67G 49.8MB/s eta 12s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "L6-D4096-E0_1-mem-c 83%[===============> ] 2.68G 50.8MB/s eta 10s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "6-D4096-E0_1-mem-ct 84%[===============> ] 2.70G 50.6MB/s eta 10s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-D4096-E0_1-mem-ctx 84%[===============> ] 2.70G 50.0MB/s eta 10s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "D4096-E0_1-mem-ctx- 84%[===============> ] 2.71G 49.3MB/s eta 10s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "4096-E0_1-mem-ctx-8 85%[================> ] 2.73G 49.5MB/s eta 10s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "096-E0_1-mem-ctx-8k 85%[================> ] 2.74G 52.1MB/s eta 9s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "96-E0_1-mem-ctx-8k. 86%[================> ] 2.76G 51.2MB/s eta 9s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "6-E0_1-mem-ctx-8k.p 86%[================> ] 2.77G 53.9MB/s eta 9s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-E0_1-mem-ctx-8k.pt 86%[================> ] 2.77G 50.2MB/s eta 9s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "E0_1-mem-ctx-8k.pth 87%[================> ] 2.80G 54.7MB/s eta 8s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "0_1-mem-ctx-8k.pth 87%[================> ] 2.82G 57.2MB/s eta 8s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "_1-mem-ctx-8k.pth 88%[================> ] 2.83G 57.9MB/s eta 8s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "1-mem-ctx-8k.pth 88%[================> ] 2.84G 56.5MB/s eta 8s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-mem-ctx-8k.pth 89%[================> ] 2.86G 57.9MB/s eta 8s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "mem-ctx-8k.pth 89%[================> ] 2.86G 56.1MB/s eta 7s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "em-ctx-8k.pth 89%[================> ] 2.88G 55.1MB/s eta 7s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "m-ctx-8k.pth 90%[=================> ] 2.89G 55.6MB/s eta 7s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-ctx-8k.pth 90%[=================> ] 2.89G 53.6MB/s eta 7s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "ctx-8k.pth 90%[=================> ] 2.91G 54.0MB/s eta 7s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "tx-8k.pth 91%[=================> ] 2.92G 57.0MB/s eta 6s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "x-8k.pth 91%[=================> ] 2.94G 57.0MB/s eta 6s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-8k.pth 91%[=================> ] 2.94G 54.9MB/s eta 6s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "8k.pth 91%[=================> ] 2.95G 53.2MB/s eta 6s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "k.pth 92%[=================> ] 2.95G 48.8MB/s eta 6s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", ".pth 92%[=================> ] 2.96G 51.8MB/s eta 5s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "pth 92%[=================> ] 2.97G 51.1MB/s eta 5s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "th 92%[=================> ] 2.98G 50.6MB/s eta 5s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "h 92%[=================> ] 2.98G 44.5MB/s eta 5s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 93%[=================> ] 2.99G 46.9MB/s eta 5s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v 93%[=================> ] 3.01G 44.4MB/s eta 4s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5 94%[=================> ] 3.02G 44.4MB/s eta 4s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5- 94%[=================> ] 3.04G 45.9MB/s eta 4s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L 95%[==================> ] 3.05G 45.5MB/s eta 4s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6 95%[==================> ] 3.07G 48.1MB/s eta 3s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6- 96%[==================> ] 3.08G 47.2MB/s eta 3s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D 96%[==================> ] 3.10G 46.6MB/s eta 3s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D4 97%[==================> ] 3.11G 45.8MB/s eta 3s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D40 97%[==================> ] 3.13G 46.7MB/s eta 2s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D409 97%[==================> ] 3.13G 45.6MB/s eta 2s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D4096 98%[==================> ] 3.15G 48.4MB/s eta 2s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D4096- 98%[==================> ] 3.16G 50.4MB/s eta 2s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D4096-E 98%[==================> ] 3.16G 48.0MB/s eta 2s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D4096-E0 99%[==================> ] 3.17G 49.5MB/s eta 1s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D4096-E0_ 99%[==================> ] 3.19G 50.4MB/s eta 1s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L6-D4096-E0_1 99%[==================> ] 3.20G 53.9MB/s eta 1s \r", "v5-L6-D4096-E0_1-me 100%[===================>] 3.21G 53.9MB/s in 64s \r\n", "\r\n", "2023-08-26 13:30:39 (51.4 MB/s) - ‘v5-L6-D4096-E0_1-mem-ctx-8k.pth’ saved [3441599237/3441599237]\r\n", "\r\n" ] } ], "source": [ "# Lets download the custom models\n", "!mkdir -p ../../../model/\n", "!cd ../../../model/ && wget -nc \"https://huggingface.co./picocreator/memory-size-experiment-for-rwkv/resolve/main/RWKV-v5-baseline/BaseV5-C-Tune5.pth\"\n", "!cd ../../../model/ && wget -nc \"https://huggingface.co./picocreator/RWKV-x-playground/resolve/main/V5-16k/EWR-1B5-E0_1-mem-ctx-8k.pth\"\n", "!cd ../../../model/ && wget -nc \"https://huggingface.co./picocreator/RWKV-x-playground/resolve/main/V5-16k/v5-L6-D2048-E0_1-mem-ctx-8k.pth\"\n", "!cd ../../../model/ && wget -nc \"https://huggingface.co./picocreator/RWKV-x-playground/resolve/main/V5-16k/v5-L6-D4096-E0_1-mem-ctx-8k.pth\"" ] }, { "cell_type": "code", "execution_count": 2, "id": "fbaa4381", "metadata": { "execution": { "iopub.execute_input": "2023-08-26T13:30:39.660558Z", "iopub.status.busy": "2023-08-26T13:30:39.659105Z", "iopub.status.idle": "2023-08-26T13:30:39.915027Z", "shell.execute_reply": "2023-08-26T13:30:39.914129Z" }, "papermill": { "duration": 0.309269, "end_time": "2023-08-26T13:30:39.917097", "exception": false, "start_time": "2023-08-26T13:30:39.607828", "status": "completed" }, "tags": [] }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "total 16G\r\n", "-rw-r--r-- 1 root root 5.7G Aug 11 12:48 BaseV5-C-Tune5.pth\r\n", "-rw-r--r-- 1 root root 5.7G Aug 17 14:38 EWR-1B5-E0_1-mem-ctx-8k.pth\r\n", "-rw-r--r-- 1 root root 1018M Aug 19 08:33 v5-L6-D2048-E0_1-mem-ctx-8k.pth\r\n", "-rw-r--r-- 1 root root 3.3G Aug 20 14:58 v5-L6-D4096-E0_1-mem-ctx-8k.pth\r\n" ] } ], "source": [ "!ls -lh ../../../model/" ] }, { "cell_type": "code", "execution_count": 3, "id": "d97d8780", "metadata": { "execution": { "iopub.execute_input": "2023-08-26T13:30:40.012919Z", "iopub.status.busy": "2023-08-26T13:30:40.012535Z", "iopub.status.idle": "2023-08-26T13:30:40.265417Z", "shell.execute_reply": "2023-08-26T13:30:40.264441Z" }, "papermill": { "duration": 0.303594, "end_time": "2023-08-26T13:30:40.267576", "exception": false, "start_time": "2023-08-26T13:30:39.963982", "status": "completed" }, "tags": [] }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "/usr/bin/sh: 1: python: not found\r\n" ] } ], "source": [ "!python -m pip install aiocsv aiofiles" ] }, { "cell_type": "markdown", "id": "84e31882", "metadata": { "papermill": { "duration": 0.046789, "end_time": "2023-08-26T13:30:40.361168", "exception": false, "start_time": "2023-08-26T13:30:40.314379", "status": "completed" }, "tags": [] }, "source": [ "# 1B5 V5 benchmark" ] }, { "cell_type": "code", "execution_count": 4, "id": "b787699a", "metadata": { "execution": { "iopub.execute_input": "2023-08-26T13:30:40.457229Z", "iopub.status.busy": "2023-08-26T13:30:40.456877Z", "iopub.status.idle": "2023-08-26T13:31:50.055322Z", "shell.execute_reply": "2023-08-26T13:31:50.054422Z" }, "papermill": { "duration": 69.64913, "end_time": "2023-08-26T13:31:50.057468", "exception": false, "start_time": "2023-08-26T13:30:40.408338", "status": "completed" }, "tags": [] }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[2023-08-26 13:30:44,674] [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": [ "###\r\n", "### Model validation start ###\r\n", "###\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 5 tokens : 100.0% similarity, with 5 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 10 tokens : 100.0% similarity, with 10 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 15 tokens : 100.0% similarity, with 15 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 20 tokens : 100.0% similarity, with 20 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 25 tokens : 100.0% similarity, with 25 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 30 tokens : 100.0% similarity, with 30 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 35 tokens : 100.0% similarity, with 35 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 40 tokens : 100.0% similarity, with 40 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 45 tokens : 100.0% similarity, with 45 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 50 tokens : 100.0% similarity, with 50 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 55 tokens : 100.0% similarity, with 55 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 60 tokens : 100.0% similarity, with 60 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 65 tokens : 100.0% similarity, with 65 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 70 tokens : 100.0% similarity, with 70 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 75 tokens : 100.0% similarity, with 75 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 80 tokens : 100.0% similarity, with 80 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 85 tokens : 100.0% similarity, with 85 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 90 tokens : 100.0% similarity, with 90 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 95 tokens : 100.0% similarity, with 95 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 100 tokens : 100.0% similarity, with 100 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 105 tokens : 100.0% similarity, with 105 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 110 tokens : 100.0% similarity, with 110 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 115 tokens : 100.0% similarity, with 115 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 120 tokens : 100.0% similarity, with 120 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 125 tokens : 100.0% similarity, with 125 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 130 tokens : 100.0% similarity, with 130 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 135 tokens : 100.0% similarity, with 135 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 140 tokens : 100.0% similarity, with 140 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 145 tokens : 100.0% similarity, with 145 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 150 tokens : 100.0% similarity, with 150 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 160 tokens : 100.0% similarity, with 160 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 170 tokens : 100.0% similarity, with 170 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 180 tokens : 100.0% similarity, with 180 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 190 tokens : 99.47368421052632% similarity, with 189 matched token, and 1 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 200 tokens : 100.0% similarity, with 200 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 210 tokens : 100.0% similarity, with 210 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 220 tokens : 100.0% similarity, with 220 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 230 tokens : 100.0% similarity, with 230 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 240 tokens : 100.0% similarity, with 240 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 250 tokens : 100.0% similarity, with 250 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 260 tokens : 100.0% similarity, with 260 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 270 tokens : 100.0% similarity, with 270 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 280 tokens : 99.64285714285714% similarity, with 279 matched token, and 1 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 290 tokens : 100.0% similarity, with 290 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 300 tokens : 99.66666666666667% similarity, with 299 matched token, and 1 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 325 tokens : 100.0% similarity, with 325 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 350 tokens : 100.0% similarity, with 350 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 375 tokens : 99.46666666666667% similarity, with 373 matched token, and 2 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 400 tokens : 99.75% similarity, with 399 matched token, and 1 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 425 tokens : 99.76470588235294% similarity, with 424 matched token, and 1 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 450 tokens : 99.55555555555556% similarity, with 448 matched token, and 2 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 475 tokens : 99.36842105263159% similarity, with 472 matched token, and 3 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 500 tokens : 99.6% similarity, with 498 matched token, and 2 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 525 tokens : 99.61904761904762% similarity, with 523 matched token, and 2 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 550 tokens : 99.27272727272727% similarity, with 546 matched token, and 4 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 575 tokens : 99.30434782608695% similarity, with 571 matched token, and 4 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 600 tokens : 99.33333333333333% similarity, with 596 matched token, and 4 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 625 tokens : 99.03999999999999% similarity, with 619 matched token, and 6 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 650 tokens : 99.07692307692308% similarity, with 644 matched token, and 6 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 675 tokens : 99.11111111111111% similarity, with 669 matched token, and 6 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 700 tokens : 99.0% similarity, with 693 matched token, and 7 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 750 tokens : 99.06666666666666% similarity, with 743 matched token, and 7 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 800 tokens : 99.0% similarity, with 792 matched token, and 8 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 850 tokens : 99.05882352941177% similarity, with 842 matched token, and 8 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 900 tokens : 99.0% similarity, with 891 matched token, and 9 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 950 tokens : 99.1578947368421% similarity, with 942 matched token, and 8 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 1000 tokens : 99.2% similarity, with 992 matched token, and 8 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Finished baseline model to eval output predictive matching (aka 0 memory?), for 1000 tokens\r\n", "###\r\n", "### Model validation end ###\r\n", "###\r\n" ] } ], "source": [ "!python3 ./memory_script/eval_v5_memory_guided.py \"../../../model/BaseV5-C-Tune5.pth\" \"./logs/BaseV5-C-Tune5-1k.csv\"" ] }, { "cell_type": "code", "execution_count": 5, "id": "633f1f79", "metadata": { "execution": { "iopub.execute_input": "2023-08-26T13:31:50.161177Z", "iopub.status.busy": "2023-08-26T13:31:50.160355Z", "iopub.status.idle": "2023-08-26T13:36:16.812262Z", "shell.execute_reply": "2023-08-26T13:36:16.811318Z" }, "papermill": { "duration": 266.706426, "end_time": "2023-08-26T13:36:16.814332", "exception": false, "start_time": "2023-08-26T13:31:50.107906", "status": "completed" }, "tags": [] }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[2023-08-26 13:31:54,664] [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": [ "###\r\n", "### Model validation start ###\r\n", "###\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 1100 tokens : 98.63636363636363% similarity, with 1085 matched token, and 15 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 1150 tokens : 98.52173913043478% similarity, with 1133 matched token, and 17 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 1200 tokens : 98.75% similarity, with 1185 matched token, and 15 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 1250 tokens : 98.72% similarity, with 1234 matched token, and 16 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 1300 tokens : 98.61538461538461% similarity, with 1282 matched token, and 18 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 1350 tokens : 98.44444444444444% similarity, with 1329 matched token, and 21 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 1400 tokens : 98.5% similarity, with 1379 matched token, and 21 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 1450 tokens : 98.20689655172414% similarity, with 1424 matched token, and 26 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 1500 tokens : 97.86666666666667% similarity, with 1468 matched token, and 32 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 1550 tokens : 97.67741935483872% similarity, with 1514 matched token, and 36 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 1600 tokens : 97.8125% similarity, with 1565 matched token, and 35 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 1650 tokens : 97.57575757575758% similarity, with 1610 matched token, and 40 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 1700 tokens : 97.6470588235294% similarity, with 1660 matched token, and 40 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 1750 tokens : 97.94285714285714% similarity, with 1714 matched token, and 36 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 1800 tokens : 97.72222222222223% similarity, with 1759 matched token, and 41 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 1850 tokens : 96.86486486486487% similarity, with 1792 matched token, and 58 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 1900 tokens : 96.36842105263158% similarity, with 1831 matched token, and 69 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 1950 tokens : 95.23076923076923% similarity, with 1857 matched token, and 93 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 2000 tokens : 94.75% similarity, with 1895 matched token, and 105 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 2050 tokens : 93.26829268292684% similarity, with 1912 matched token, and 138 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 2100 tokens : 91.33333333333333% similarity, with 1918 matched token, and 182 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 2150 tokens : 90.13953488372093% similarity, with 1938 matched token, and 212 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 2200 tokens : 88.81818181818181% similarity, with 1954 matched token, and 246 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 2250 tokens : 86.62222222222222% similarity, with 1949 matched token, and 301 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 2300 tokens : 84.82608695652173% similarity, with 1951 matched token, and 349 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 2350 tokens : 82.08510638297872% similarity, with 1929 matched token, and 421 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 2400 tokens : 80.625% similarity, with 1935 matched token, and 465 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 2450 tokens : 78.61224489795919% similarity, with 1926 matched token, and 524 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 2500 tokens : 77.08% similarity, with 1927 matched token, and 573 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 2550 tokens : 75.25490196078431% similarity, with 1919 matched token, and 631 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 2600 tokens : 73.88461538461539% similarity, with 1921 matched token, and 679 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 2650 tokens : 72.71698113207547% similarity, with 1927 matched token, and 723 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 2700 tokens : 71.4074074074074% similarity, with 1928 matched token, and 772 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 2750 tokens : 70.10909090909091% similarity, with 1928 matched token, and 822 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 2800 tokens : 68.85714285714286% similarity, with 1928 matched token, and 872 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 2850 tokens : 67.89473684210526% similarity, with 1935 matched token, and 915 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 2900 tokens : 66.6896551724138% similarity, with 1934 matched token, and 966 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 2950 tokens : 65.62711864406779% similarity, with 1936 matched token, and 1014 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 3000 tokens : 64.4% similarity, with 1932 matched token, and 1068 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 3050 tokens : 63.31147540983607% similarity, with 1931 matched token, and 1119 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 3100 tokens : 62.096774193548384% similarity, with 1925 matched token, and 1175 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 3150 tokens : 61.17460317460317% similarity, with 1927 matched token, and 1223 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 3200 tokens : 60.21875% similarity, with 1927 matched token, and 1273 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 3250 tokens : 59.199999999999996% similarity, with 1924 matched token, and 1326 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 3300 tokens : 58.18181818181818% similarity, with 1920 matched token, and 1380 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 3350 tokens : 57.134328358208954% similarity, with 1914 matched token, and 1436 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 3400 tokens : 56.294117647058826% similarity, with 1914 matched token, and 1486 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 3450 tokens : 55.362318840579704% similarity, with 1910 matched token, and 1540 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 3500 tokens : 54.400000000000006% similarity, with 1904 matched token, and 1596 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 3550 tokens : 53.54929577464789% similarity, with 1901 matched token, and 1649 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 3600 tokens : 52.77777777777778% similarity, with 1900 matched token, and 1700 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 3650 tokens : 51.89041095890411% similarity, with 1894 matched token, and 1756 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 3700 tokens : 51.054054054054056% similarity, with 1889 matched token, and 1811 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 3750 tokens : 50.18666666666667% similarity, with 1882 matched token, and 1868 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 3800 tokens : 49.31578947368421% similarity, with 1874 matched token, and 1926 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 3850 tokens : 48.51948051948052% similarity, with 1868 matched token, and 1982 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 3900 tokens : 47.53846153846154% similarity, with 1854 matched token, and 2046 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 3950 tokens : 46.607594936708864% similarity, with 1841 matched token, and 2109 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 4000 tokens : 45.574999999999996% similarity, with 1823 matched token, and 2177 token mismatch\r\n", "###\r\n", "### Model validation end ###\r\n", "###\r\n" ] } ], "source": [ "!python3 ./memory_script/eval_v5_memory_guided.py \"../../../model/BaseV5-C-Tune5.pth\" \"./logs/BaseV5-C-Tune5-4k.csv\" 1100 4000" ] }, { "cell_type": "code", "execution_count": 6, "id": "f78a7cce", "metadata": { "execution": { "iopub.execute_input": "2023-08-26T13:36:16.924786Z", "iopub.status.busy": "2023-08-26T13:36:16.924015Z", "iopub.status.idle": "2023-08-26T14:38:59.194602Z", "shell.execute_reply": "2023-08-26T14:38:59.193661Z" }, "papermill": { "duration": 3762.328534, "end_time": "2023-08-26T14:38:59.196991", "exception": false, "start_time": "2023-08-26T13:36:16.868457", "status": "completed" }, "tags": [] }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[2023-08-26 13:36:21,464] [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": [ "###\r\n", "### Model validation start ###\r\n", "###\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 4100 tokens : 43.97560975609756% similarity, with 1803 matched token, and 2297 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 4200 tokens : 42.142857142857146% similarity, with 1770 matched token, and 2430 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 4300 tokens : 40.27906976744186% similarity, with 1732 matched token, and 2568 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 4400 tokens : 38.27272727272727% similarity, with 1684 matched token, and 2716 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 4500 tokens : 35.8% similarity, with 1611 matched token, and 2889 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 4600 tokens : 33.71739130434783% similarity, with 1551 matched token, and 3049 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 4700 tokens : 31.06382978723404% similarity, with 1460 matched token, and 3240 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 4800 tokens : 28.375% similarity, with 1362 matched token, and 3438 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 4900 tokens : 25.857142857142858% similarity, with 1267 matched token, and 3633 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 5000 tokens : 23.04% similarity, with 1152 matched token, and 3848 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 5100 tokens : 20.784313725490197% similarity, with 1060 matched token, and 4040 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 5200 tokens : 18.5% similarity, with 962 matched token, and 4238 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 5300 tokens : 16.88679245283019% similarity, with 895 matched token, and 4405 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 5400 tokens : 15.24074074074074% similarity, with 823 matched token, and 4577 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 5500 tokens : 13.436363636363636% similarity, with 739 matched token, and 4761 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 5600 tokens : 11.607142857142858% similarity, with 650 matched token, and 4950 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 5700 tokens : 10.385964912280702% similarity, with 592 matched token, and 5108 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 5800 tokens : 9.327586206896552% similarity, with 541 matched token, and 5259 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 5900 tokens : 8.305084745762711% similarity, with 490 matched token, and 5410 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 6000 tokens : 7.466666666666668% similarity, with 448 matched token, and 5552 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 6100 tokens : 6.672131147540984% similarity, with 407 matched token, and 5693 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 6200 tokens : 6.048387096774194% similarity, with 375 matched token, and 5825 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 6300 tokens : 5.65079365079365% similarity, with 356 matched token, and 5944 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 6400 tokens : 5.328125% similarity, with 341 matched token, and 6059 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 6500 tokens : 4.984615384615385% similarity, with 324 matched token, and 6176 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 6600 tokens : 4.6818181818181825% similarity, with 309 matched token, and 6291 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 6700 tokens : 4.447761194029851% similarity, with 298 matched token, and 6402 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 6800 tokens : 4.25% similarity, with 289 matched token, and 6511 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 6900 tokens : 4.08695652173913% similarity, with 282 matched token, and 6618 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 7000 tokens : 4.0% similarity, with 280 matched token, and 6720 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 7100 tokens : 3.943661971830986% similarity, with 280 matched token, and 6820 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 7200 tokens : 3.763888888888889% similarity, with 271 matched token, and 6929 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 7300 tokens : 3.767123287671233% similarity, with 275 matched token, and 7025 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 7400 tokens : 3.689189189189189% similarity, with 273 matched token, and 7127 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 7500 tokens : 3.64% similarity, with 273 matched token, and 7227 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 7600 tokens : 3.578947368421052% similarity, with 272 matched token, and 7328 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 7700 tokens : 3.5844155844155843% similarity, with 276 matched token, and 7424 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 7800 tokens : 3.5512820512820515% similarity, with 277 matched token, and 7523 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 7900 tokens : 3.468354430379747% similarity, with 274 matched token, and 7626 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 8000 tokens : 3.4250000000000003% similarity, with 274 matched token, and 7726 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 8100 tokens : 3.419753086419753% similarity, with 277 matched token, and 7823 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 8200 tokens : 3.414634146341464% similarity, with 280 matched token, and 7920 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 8300 tokens : 3.36144578313253% similarity, with 279 matched token, and 8021 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 8400 tokens : 3.3690476190476186% similarity, with 283 matched token, and 8117 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 8500 tokens : 3.3411764705882354% similarity, with 284 matched token, and 8216 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 8600 tokens : 3.3488372093023258% similarity, with 288 matched token, and 8312 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 8700 tokens : 3.3678160919540225% similarity, with 293 matched token, and 8407 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 8800 tokens : 3.3295454545454546% similarity, with 293 matched token, and 8507 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 8900 tokens : 3.348314606741573% similarity, with 298 matched token, and 8602 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 9000 tokens : 3.3333333333333335% similarity, with 300 matched token, and 8700 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 9100 tokens : 3.3406593406593412% similarity, with 304 matched token, and 8796 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 9200 tokens : 3.3260869565217392% similarity, with 306 matched token, and 8894 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 9300 tokens : 3.3010752688172045% similarity, with 307 matched token, and 8993 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 9400 tokens : 3.2978723404255317% similarity, with 310 matched token, and 9090 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 9500 tokens : 3.3157894736842106% similarity, with 315 matched token, and 9185 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 9600 tokens : 3.3229166666666665% similarity, with 319 matched token, and 9281 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 9700 tokens : 3.3195876288659796% similarity, with 322 matched token, and 9378 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 9800 tokens : 3.316326530612245% similarity, with 325 matched token, and 9475 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 9900 tokens : 3.3333333333333335% similarity, with 330 matched token, and 9570 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 10000 tokens : 3.37% similarity, with 337 matched token, and 9663 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 10100 tokens : 3.3762376237623766% similarity, with 341 matched token, and 9759 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 10200 tokens : 3.3725490196078427% similarity, with 344 matched token, and 9856 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 10300 tokens : 3.349514563106796% similarity, with 345 matched token, and 9955 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 10400 tokens : 3.355769230769231% similarity, with 349 matched token, and 10051 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 10500 tokens : 3.371428571428572% similarity, with 354 matched token, and 10146 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 10600 tokens : 3.3584905660377355% similarity, with 356 matched token, and 10244 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 10700 tokens : 3.392523364485981% similarity, with 363 matched token, and 10337 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 10800 tokens : 3.4074074074074074% similarity, with 368 matched token, and 10432 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 10900 tokens : 3.3853211009174315% similarity, with 369 matched token, and 10531 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 11000 tokens : 3.4000000000000004% similarity, with 374 matched token, and 10626 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 11100 tokens : 3.3963963963963963% similarity, with 377 matched token, and 10723 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 11200 tokens : 3.3839285714285716% similarity, with 379 matched token, and 10821 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 11300 tokens : 3.4070796460176993% similarity, with 385 matched token, and 10915 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 11400 tokens : 3.43859649122807% similarity, with 392 matched token, and 11008 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 11500 tokens : 3.4434782608695653% similarity, with 396 matched token, and 11104 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 11600 tokens : 3.4568965517241383% similarity, with 401 matched token, and 11199 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 11700 tokens : 3.4444444444444446% similarity, with 403 matched token, and 11297 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 11800 tokens : 3.457627118644068% similarity, with 408 matched token, and 11392 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 11900 tokens : 3.46218487394958% similarity, with 412 matched token, and 11488 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 12000 tokens : 3.4750000000000005% similarity, with 417 matched token, and 11583 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 12100 tokens : 3.487603305785124% similarity, with 422 matched token, and 11678 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 12200 tokens : 3.475409836065574% similarity, with 424 matched token, and 11776 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 12300 tokens : 3.487804878048781% similarity, with 429 matched token, and 11871 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 12400 tokens : 3.491935483870968% similarity, with 433 matched token, and 11967 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 12500 tokens : 3.488% similarity, with 436 matched token, and 12064 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 12600 tokens : 3.484126984126984% similarity, with 439 matched token, and 12161 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 12700 tokens : 3.4881889763779523% similarity, with 443 matched token, and 12257 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 12800 tokens : 3.484375% similarity, with 446 matched token, and 12354 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 12900 tokens : 3.488372093023256% similarity, with 450 matched token, and 12450 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 13000 tokens : 3.5000000000000004% similarity, with 455 matched token, and 12545 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 13100 tokens : 3.5038167938931295% similarity, with 459 matched token, and 12641 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 13200 tokens : 3.5000000000000004% similarity, with 462 matched token, and 12738 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 13300 tokens : 3.488721804511278% similarity, with 464 matched token, and 12836 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 13400 tokens : 3.514925373134328% similarity, with 471 matched token, and 12929 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 13500 tokens : 3.503703703703704% similarity, with 473 matched token, and 13027 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 13600 tokens : 3.514705882352941% similarity, with 478 matched token, and 13122 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 13700 tokens : 3.510948905109489% similarity, with 481 matched token, and 13219 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 13800 tokens : 3.5144927536231885% similarity, with 485 matched token, and 13315 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 13900 tokens : 3.5251798561151078% similarity, with 490 matched token, and 13410 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 14000 tokens : 3.55% similarity, with 497 matched token, and 13503 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 14100 tokens : 3.546099290780142% similarity, with 500 matched token, and 13600 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 14200 tokens : 3.535211267605634% similarity, with 502 matched token, and 13698 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 14300 tokens : 3.5454545454545454% similarity, with 507 matched token, and 13793 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 14400 tokens : 3.5555555555555554% similarity, with 512 matched token, and 13888 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 14500 tokens : 3.537931034482759% similarity, with 513 matched token, and 13987 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 14600 tokens : 3.5273972602739727% similarity, with 515 matched token, and 14085 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 14700 tokens : 3.5646258503401365% similarity, with 524 matched token, and 14176 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 14800 tokens : 3.5472972972972974% similarity, with 525 matched token, and 14275 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 14900 tokens : 3.550335570469799% similarity, with 529 matched token, and 14371 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 15000 tokens : 3.5533333333333332% similarity, with 533 matched token, and 14467 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 15100 tokens : 3.576158940397351% similarity, with 540 matched token, and 14560 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 15200 tokens : 3.56578947368421% similarity, with 542 matched token, and 14658 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 15300 tokens : 3.5490196078431375% similarity, with 543 matched token, and 14757 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 15400 tokens : 3.551948051948052% similarity, with 547 matched token, and 14853 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 15500 tokens : 3.5483870967741935% similarity, with 550 matched token, and 14950 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 15600 tokens : 3.5448717948717947% similarity, with 553 matched token, and 15047 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 15700 tokens : 3.5605095541401273% similarity, with 559 matched token, and 15141 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 15800 tokens : 3.5506329113924053% similarity, with 561 matched token, and 15239 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 15900 tokens : 3.547169811320755% similarity, with 564 matched token, and 15336 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 16000 tokens : 3.5437499999999997% similarity, with 567 matched token, and 15433 token mismatch\r\n", "###\r\n", "### Model validation end ###\r\n", "###\r\n" ] } ], "source": [ "!python3 ./memory_script/eval_v5_memory_guided.py \"../../../model/BaseV5-C-Tune5.pth\" \"./logs/BaseV5-C-Tune5-16k.csv\" 4100 16000" ] }, { "cell_type": "markdown", "id": "cfbf5b3d", "metadata": { "papermill": { "duration": 0.061671, "end_time": "2023-08-26T14:38:59.320285", "exception": false, "start_time": "2023-08-26T14:38:59.258614", "status": "completed" }, "tags": [] }, "source": [ "# EWR V5 benchmark" ] }, { "cell_type": "code", "execution_count": 7, "id": "60d86655", "metadata": { "execution": { "iopub.execute_input": "2023-08-26T14:38:59.445569Z", "iopub.status.busy": "2023-08-26T14:38:59.444939Z", "iopub.status.idle": "2023-08-26T14:39:05.718059Z", "shell.execute_reply": "2023-08-26T14:39:05.716844Z" }, "papermill": { "duration": 6.338733, "end_time": "2023-08-26T14:39:05.720399", "exception": false, "start_time": "2023-08-26T14:38:59.381666", "status": "completed" }, "tags": [] }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[2023-08-26 14:39:03,924] [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/notebook/experiment/memory-bench/./memory_script/eval_v5_memory_guided.py\", line 366, in \r\n", " asyncio.run(main_function())\r\n", " File \"/usr/lib/python3.10/asyncio/runners.py\", line 44, in run\r\n", " return loop.run_until_complete(main)\r\n", " File \"/usr/lib/python3.10/asyncio/base_events.py\", line 649, in run_until_complete\r\n", " return future.result()\r\n", " File \"/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/notebook/experiment/memory-bench/./memory_script/eval_v5_memory_guided.py\", line 58, in main_function\r\n", " model = SimpleRWKV(model_path, device=\"cuda\")\r\n", " File \"/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/RWKV-v5/src/model.py\", line 1378, 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 553, in __init__\r\n", " raise ValueError(f\"load_model file '{load_model}' does not exist\")\r\n", "ValueError: load_model file '../../../model/EWR-1B5-E0_1.pth' does not exist\r\n" ] } ], "source": [ "!python3 ./memory_script/eval_v5_memory_guided.py \"../../../model/EWR-1B5-E0_1.pth\" \"./logs/v5-EWR-1B5-E0_1-1k.csv\"" ] }, { "cell_type": "code", "execution_count": 8, "id": "851be2b7", "metadata": { "execution": { "iopub.execute_input": "2023-08-26T14:39:05.838572Z", "iopub.status.busy": "2023-08-26T14:39:05.837927Z", "iopub.status.idle": "2023-08-26T14:39:12.062651Z", "shell.execute_reply": "2023-08-26T14:39:12.061734Z" }, "papermill": { "duration": 6.287262, "end_time": "2023-08-26T14:39:12.065659", "exception": false, "start_time": "2023-08-26T14:39:05.778397", "status": "completed" }, "tags": [] }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[2023-08-26 14:39:10,148] [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/notebook/experiment/memory-bench/./memory_script/eval_v5_memory_guided.py\", line 366, in \r\n", " asyncio.run(main_function())\r\n", " File \"/usr/lib/python3.10/asyncio/runners.py\", line 44, in run\r\n", " return loop.run_until_complete(main)\r\n", " File \"/usr/lib/python3.10/asyncio/base_events.py\", line 649, in run_until_complete\r\n", " return future.result()\r\n", " File \"/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/notebook/experiment/memory-bench/./memory_script/eval_v5_memory_guided.py\", line 58, in main_function\r\n", " model = SimpleRWKV(model_path, device=\"cuda\")\r\n", " File \"/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/RWKV-v5/src/model.py\", line 1378, 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 553, in __init__\r\n", " raise ValueError(f\"load_model file '{load_model}' does not exist\")\r\n", "ValueError: load_model file '../../../model/EWR-1B5-E0_1.pth' does not exist\r\n" ] } ], "source": [ "!python3 ./memory_script/eval_v5_memory_guided.py \"../../../model/EWR-1B5-E0_1.pth\" \"./logs/v5-EWR-1B5-E0_1-4k.csv\" 1100 4000" ] }, { "cell_type": "code", "execution_count": 9, "id": "e6022677", "metadata": { "execution": { "iopub.execute_input": "2023-08-26T14:39:12.215332Z", "iopub.status.busy": "2023-08-26T14:39:12.214878Z", "iopub.status.idle": "2023-08-26T14:39:18.967986Z", "shell.execute_reply": "2023-08-26T14:39:18.967070Z" }, "papermill": { "duration": 6.823866, "end_time": "2023-08-26T14:39:18.970264", "exception": false, "start_time": "2023-08-26T14:39:12.146398", "status": "completed" }, "tags": [] }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[2023-08-26 14:39:16,784] [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/notebook/experiment/memory-bench/./memory_script/eval_v5_memory_guided.py\", line 366, in \r\n", " asyncio.run(main_function())\r\n", " File \"/usr/lib/python3.10/asyncio/runners.py\", line 44, in run\r\n", " return loop.run_until_complete(main)\r\n", " File \"/usr/lib/python3.10/asyncio/base_events.py\", line 649, in run_until_complete\r\n", " return future.result()\r\n", " File \"/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/notebook/experiment/memory-bench/./memory_script/eval_v5_memory_guided.py\", line 58, in main_function\r\n", " model = SimpleRWKV(model_path, device=\"cuda\")\r\n", " File \"/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/RWKV-v5/src/model.py\", line 1378, in __init__\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ " self.model = RWKV(**model_config)\r\n", " File \"/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/RWKV-v5/src/model.py\", line 553, in __init__\r\n", " raise ValueError(f\"load_model file '{load_model}' does not exist\")\r\n", "ValueError: load_model file '../../../model/EWR-1B5-E0_1.pth' does not exist\r\n" ] } ], "source": [ "!python3 ./memory_script/eval_v5_memory_guided.py \"../../../model/EWR-1B5-E0_1.pth\" \"./logs/v5-EWR-1B5-E0_1-16k.csv\" 4100 16000" ] }, { "cell_type": "markdown", "id": "29d656b6", "metadata": { "papermill": { "duration": 0.061957, "end_time": "2023-08-26T14:39:19.094552", "exception": false, "start_time": "2023-08-26T14:39:19.032595", "status": "completed" }, "tags": [] }, "source": [ "# v5-L6-D2048-E0_1-mem-ctx-8k.pth" ] }, { "cell_type": "code", "execution_count": 10, "id": "04f299aa", "metadata": { "execution": { "iopub.execute_input": "2023-08-26T14:39:19.221229Z", "iopub.status.busy": "2023-08-26T14:39:19.220475Z", "iopub.status.idle": "2023-08-26T14:40:15.430273Z", "shell.execute_reply": "2023-08-26T14:40:15.428492Z" }, "papermill": { "duration": 56.276274, "end_time": "2023-08-26T14:40:15.432948", "exception": false, "start_time": "2023-08-26T14:39:19.156674", "status": "completed" }, "tags": [] }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[2023-08-26 14:39:23,732] [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": [ "###\r\n", "### Model validation start ###\r\n", "###\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 5 tokens : 100.0% similarity, with 5 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 10 tokens : 100.0% similarity, with 10 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 15 tokens : 100.0% similarity, with 15 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 20 tokens : 100.0% similarity, with 20 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 25 tokens : 100.0% similarity, with 25 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 30 tokens : 100.0% similarity, with 30 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 35 tokens : 100.0% similarity, with 35 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 40 tokens : 100.0% similarity, with 40 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 45 tokens : 100.0% similarity, with 45 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 50 tokens : 100.0% similarity, with 50 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 55 tokens : 98.18181818181819% similarity, with 54 matched token, and 1 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 60 tokens : 100.0% similarity, with 60 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 65 tokens : 98.46153846153847% similarity, with 64 matched token, and 1 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 70 tokens : 98.57142857142858% similarity, with 69 matched token, and 1 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 75 tokens : 98.66666666666667% similarity, with 74 matched token, and 1 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 80 tokens : 100.0% similarity, with 80 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 85 tokens : 100.0% similarity, with 85 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 90 tokens : 97.77777777777777% similarity, with 88 matched token, and 2 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 95 tokens : 100.0% similarity, with 95 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 100 tokens : 99.0% similarity, with 99 matched token, and 1 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 105 tokens : 99.04761904761905% similarity, with 104 matched token, and 1 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 110 tokens : 99.0909090909091% similarity, with 109 matched token, and 1 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 115 tokens : 99.1304347826087% similarity, with 114 matched token, and 1 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 120 tokens : 99.16666666666667% similarity, with 119 matched token, and 1 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 125 tokens : 99.2% similarity, with 124 matched token, and 1 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 130 tokens : 99.23076923076923% similarity, with 129 matched token, and 1 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 135 tokens : 99.25925925925925% similarity, with 134 matched token, and 1 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 140 tokens : 99.28571428571429% similarity, with 139 matched token, and 1 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 145 tokens : 99.3103448275862% similarity, with 144 matched token, and 1 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 150 tokens : 99.33333333333333% similarity, with 149 matched token, and 1 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 160 tokens : 99.375% similarity, with 159 matched token, and 1 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 170 tokens : 99.41176470588235% similarity, with 169 matched token, and 1 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 180 tokens : 99.44444444444444% similarity, with 179 matched token, and 1 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 190 tokens : 97.89473684210527% similarity, with 186 matched token, and 4 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 200 tokens : 98.5% similarity, with 197 matched token, and 3 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 210 tokens : 98.09523809523809% similarity, with 206 matched token, and 4 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 220 tokens : 96.36363636363636% similarity, with 212 matched token, and 8 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 230 tokens : 97.3913043478261% similarity, with 224 matched token, and 6 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 240 tokens : 97.5% similarity, with 234 matched token, and 6 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 250 tokens : 97.6% similarity, with 244 matched token, and 6 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 260 tokens : 97.3076923076923% similarity, with 253 matched token, and 7 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 270 tokens : 97.03703703703704% similarity, with 262 matched token, and 8 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 280 tokens : 95.35714285714286% similarity, with 267 matched token, and 13 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 290 tokens : 95.17241379310344% similarity, with 276 matched token, and 14 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 300 tokens : 95.33333333333334% similarity, with 286 matched token, and 14 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 325 tokens : 95.6923076923077% similarity, with 311 matched token, and 14 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 350 tokens : 95.14285714285714% similarity, with 333 matched token, and 17 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 375 tokens : 93.60000000000001% similarity, with 351 matched token, and 24 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 400 tokens : 91.75% similarity, with 367 matched token, and 33 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 425 tokens : 91.76470588235294% similarity, with 390 matched token, and 35 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 450 tokens : 89.77777777777777% similarity, with 404 matched token, and 46 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 475 tokens : 89.47368421052632% similarity, with 425 matched token, and 50 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 500 tokens : 88.8% similarity, with 444 matched token, and 56 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 525 tokens : 87.80952380952381% similarity, with 461 matched token, and 64 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 550 tokens : 86.72727272727273% similarity, with 477 matched token, and 73 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 575 tokens : 86.08695652173914% similarity, with 495 matched token, and 80 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 600 tokens : 85.66666666666667% similarity, with 514 matched token, and 86 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 625 tokens : 84.48% similarity, with 528 matched token, and 97 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 650 tokens : 83.23076923076923% similarity, with 541 matched token, and 109 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 675 tokens : 82.07407407407408% similarity, with 554 matched token, and 121 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 700 tokens : 81.0% similarity, with 567 matched token, and 133 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 750 tokens : 78.53333333333333% similarity, with 589 matched token, and 161 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 800 tokens : 76.75% similarity, with 614 matched token, and 186 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 850 tokens : 73.76470588235294% similarity, with 627 matched token, and 223 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 900 tokens : 71.44444444444444% similarity, with 643 matched token, and 257 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 950 tokens : 68.84210526315789% similarity, with 654 matched token, and 296 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 1000 tokens : 67.5% similarity, with 675 matched token, and 325 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Finished baseline model to eval output predictive matching (aka 0 memory?), for 1000 tokens\r\n", "###\r\n", "### Model validation end ###\r\n", "###\r\n" ] } ], "source": [ "!python3 ./memory_script/eval_v5_memory_guided.py \"../../../model/v5-L6-D2048-E0_1-mem-ctx-8k.pth\" \"./logs/v5-L6-D2048-E0_1-1k.csv\"" ] }, { "cell_type": "code", "execution_count": 11, "id": "cd974aff", "metadata": { "execution": { "iopub.execute_input": "2023-08-26T14:40:15.563705Z", "iopub.status.busy": "2023-08-26T14:40:15.561980Z", "iopub.status.idle": "2023-08-26T14:44:23.290770Z", "shell.execute_reply": "2023-08-26T14:44:23.289849Z" }, "papermill": { "duration": 247.796902, "end_time": "2023-08-26T14:44:23.293511", "exception": false, "start_time": "2023-08-26T14:40:15.496609", "status": "completed" }, "tags": [] }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[2023-08-26 14:40:19,891] [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": [ "###\r\n", "### Model validation start ###\r\n", "###\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 1100 tokens : 61.0% similarity, with 671 matched token, and 429 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 1150 tokens : 58.26086956521739% similarity, with 670 matched token, and 480 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 1200 tokens : 56.49999999999999% similarity, with 678 matched token, and 522 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 1250 tokens : 54.400000000000006% similarity, with 680 matched token, and 570 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 1300 tokens : 51.92307692307693% similarity, with 675 matched token, and 625 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 1350 tokens : 50.2962962962963% similarity, with 679 matched token, and 671 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 1400 tokens : 48.214285714285715% similarity, with 675 matched token, and 725 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 1450 tokens : 45.03448275862069% similarity, with 653 matched token, and 797 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 1500 tokens : 43.06666666666666% similarity, with 646 matched token, and 854 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 1550 tokens : 41.80645161290323% similarity, with 648 matched token, and 902 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 1600 tokens : 41.1875% similarity, with 659 matched token, and 941 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 1650 tokens : 39.45454545454545% similarity, with 651 matched token, and 999 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 1700 tokens : 38.1764705882353% similarity, with 649 matched token, and 1051 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 1750 tokens : 36.22857142857143% similarity, with 634 matched token, and 1116 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 1800 tokens : 35.44444444444444% similarity, with 638 matched token, and 1162 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 1850 tokens : 33.2972972972973% similarity, with 616 matched token, and 1234 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 1900 tokens : 32.26315789473684% similarity, with 613 matched token, and 1287 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 1950 tokens : 31.538461538461537% similarity, with 615 matched token, and 1335 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 2000 tokens : 30.7% similarity, with 614 matched token, and 1386 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 2050 tokens : 30.097560975609756% similarity, with 617 matched token, and 1433 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 2100 tokens : 29.19047619047619% similarity, with 613 matched token, and 1487 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 2150 tokens : 28.55813953488372% similarity, with 614 matched token, and 1536 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 2200 tokens : 28.000000000000004% similarity, with 616 matched token, and 1584 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 2250 tokens : 27.28888888888889% similarity, with 614 matched token, and 1636 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 2300 tokens : 26.608695652173914% similarity, with 612 matched token, and 1688 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 2350 tokens : 26.04255319148936% similarity, with 612 matched token, and 1738 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 2400 tokens : 25.5% similarity, with 612 matched token, and 1788 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 2450 tokens : 24.816326530612244% similarity, with 608 matched token, and 1842 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 2500 tokens : 24.2% similarity, with 605 matched token, and 1895 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 2550 tokens : 23.72549019607843% similarity, with 605 matched token, and 1945 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 2600 tokens : 23.23076923076923% similarity, with 604 matched token, and 1996 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 2650 tokens : 22.754716981132077% similarity, with 603 matched token, and 2047 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 2700 tokens : 22.25925925925926% similarity, with 601 matched token, and 2099 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 2750 tokens : 21.818181818181817% similarity, with 600 matched token, and 2150 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 2800 tokens : 21.392857142857142% similarity, with 599 matched token, and 2201 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 2850 tokens : 21.157894736842106% similarity, with 603 matched token, and 2247 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 2900 tokens : 20.655172413793103% similarity, with 599 matched token, and 2301 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 2950 tokens : 20.271186440677965% similarity, with 598 matched token, and 2352 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 3000 tokens : 19.8% similarity, with 594 matched token, and 2406 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 3050 tokens : 19.540983606557376% similarity, with 596 matched token, and 2454 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 3100 tokens : 19.225806451612904% similarity, with 596 matched token, and 2504 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 3150 tokens : 18.88888888888889% similarity, with 595 matched token, and 2555 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 3200 tokens : 18.53125% similarity, with 593 matched token, and 2607 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 3250 tokens : 18.246153846153845% similarity, with 593 matched token, and 2657 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 3300 tokens : 17.84848484848485% similarity, with 589 matched token, and 2711 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 3350 tokens : 17.522388059701495% similarity, with 587 matched token, and 2763 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 3400 tokens : 17.352941176470587% similarity, with 590 matched token, and 2810 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 3450 tokens : 16.956521739130434% similarity, with 585 matched token, and 2865 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 3500 tokens : 16.57142857142857% similarity, with 580 matched token, and 2920 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 3550 tokens : 16.366197183098592% similarity, with 581 matched token, and 2969 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 3600 tokens : 16.0% similarity, with 576 matched token, and 3024 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 3650 tokens : 15.890410958904111% similarity, with 580 matched token, and 3070 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 3700 tokens : 15.513513513513514% similarity, with 574 matched token, and 3126 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 3750 tokens : 15.306666666666665% similarity, with 574 matched token, and 3176 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 3800 tokens : 15.078947368421053% similarity, with 573 matched token, and 3227 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 3850 tokens : 14.779220779220777% similarity, with 569 matched token, and 3281 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 3900 tokens : 14.666666666666666% similarity, with 572 matched token, and 3328 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 3950 tokens : 14.253164556962025% similarity, with 563 matched token, and 3387 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 4000 tokens : 13.875000000000002% similarity, with 555 matched token, and 3445 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "###\r\n", "### Model validation end ###\r\n", "###\r\n" ] } ], "source": [ "!python3 ./memory_script/eval_v5_memory_guided.py \"../../../model/v5-L6-D2048-E0_1-mem-ctx-8k.pth\" \"./logs/v5-L6-D2048-E0_1-4k.csv\" 1100 4000" ] }, { "cell_type": "code", "execution_count": 12, "id": "55c4b231", "metadata": { "execution": { "iopub.execute_input": "2023-08-26T14:44:23.524751Z", "iopub.status.busy": "2023-08-26T14:44:23.524350Z", "iopub.status.idle": "2023-08-26T15:43:52.551775Z", "shell.execute_reply": "2023-08-26T15:43:52.550592Z" }, "papermill": { "duration": 3569.18119, "end_time": "2023-08-26T15:43:52.554057", "exception": false, "start_time": "2023-08-26T14:44:23.372867", "status": "completed" }, "tags": [] }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[2023-08-26 14:44:28,120] [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": [ "###\r\n", "### Model validation start ###\r\n", "###\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 4100 tokens : 13.463414634146343% similarity, with 552 matched token, and 3548 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 4200 tokens : 12.523809523809524% similarity, with 526 matched token, and 3674 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 4300 tokens : 11.906976744186046% similarity, with 512 matched token, and 3788 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 4400 tokens : 10.795454545454545% similarity, with 475 matched token, and 3925 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 4500 tokens : 9.911111111111111% similarity, with 446 matched token, and 4054 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 4600 tokens : 8.76086956521739% similarity, with 403 matched token, and 4197 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 4700 tokens : 8.085106382978724% similarity, with 380 matched token, and 4320 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 4800 tokens : 7.208333333333333% similarity, with 346 matched token, and 4454 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 4900 tokens : 6.346938775510204% similarity, with 311 matched token, and 4589 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 5000 tokens : 5.46% similarity, with 273 matched token, and 4727 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 5100 tokens : 4.980392156862745% similarity, with 254 matched token, and 4846 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 5200 tokens : 4.5% similarity, with 234 matched token, and 4966 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 5300 tokens : 4.3584905660377355% similarity, with 231 matched token, and 5069 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 5400 tokens : 4.12962962962963% similarity, with 223 matched token, and 5177 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 5500 tokens : 4.018181818181818% similarity, with 221 matched token, and 5279 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 5600 tokens : 3.8214285714285716% similarity, with 214 matched token, and 5386 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 5700 tokens : 3.736842105263158% similarity, with 213 matched token, and 5487 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 5800 tokens : 3.6551724137931036% similarity, with 212 matched token, and 5588 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 5900 tokens : 3.6610169491525424% similarity, with 216 matched token, and 5684 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 6000 tokens : 3.5333333333333337% similarity, with 212 matched token, and 5788 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 6100 tokens : 3.540983606557377% similarity, with 216 matched token, and 5884 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 6200 tokens : 3.516129032258065% similarity, with 218 matched token, and 5982 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 6300 tokens : 3.492063492063492% similarity, with 220 matched token, and 6080 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 6400 tokens : 3.453125% similarity, with 221 matched token, and 6179 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 6500 tokens : 3.4615384615384617% similarity, with 225 matched token, and 6275 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 6600 tokens : 3.4393939393939394% similarity, with 227 matched token, and 6373 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 6700 tokens : 3.4477611940298503% similarity, with 231 matched token, and 6469 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 6800 tokens : 3.426470588235294% similarity, with 233 matched token, and 6567 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 6900 tokens : 3.4637681159420293% similarity, with 239 matched token, and 6661 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 7000 tokens : 3.4428571428571426% similarity, with 241 matched token, and 6759 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 7100 tokens : 3.4225352112676055% similarity, with 243 matched token, and 6857 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 7200 tokens : 3.3888888888888893% similarity, with 244 matched token, and 6956 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 7300 tokens : 3.4109589041095894% similarity, with 249 matched token, and 7051 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 7400 tokens : 3.4054054054054053% similarity, with 252 matched token, and 7148 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 7500 tokens : 3.4133333333333336% similarity, with 256 matched token, and 7244 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 7600 tokens : 3.421052631578948% similarity, with 260 matched token, and 7340 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 7700 tokens : 3.428571428571429% similarity, with 264 matched token, and 7436 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 7800 tokens : 3.4102564102564106% similarity, with 266 matched token, and 7534 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 7900 tokens : 3.4177215189873418% similarity, with 270 matched token, and 7630 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 8000 tokens : 3.4125% similarity, with 273 matched token, and 7727 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 8100 tokens : 3.45679012345679% similarity, with 280 matched token, and 7820 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 8200 tokens : 3.439024390243903% similarity, with 282 matched token, and 7918 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 8300 tokens : 3.4216867469879517% similarity, with 284 matched token, and 8016 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 8400 tokens : 3.4166666666666665% similarity, with 287 matched token, and 8113 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 8500 tokens : 3.458823529411765% similarity, with 294 matched token, and 8206 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 8600 tokens : 3.4534883720930236% similarity, with 297 matched token, and 8303 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 8700 tokens : 3.4482758620689653% similarity, with 300 matched token, and 8400 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 8800 tokens : 3.4431818181818183% similarity, with 303 matched token, and 8497 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 8900 tokens : 3.449438202247191% similarity, with 307 matched token, and 8593 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 9000 tokens : 3.4333333333333336% similarity, with 309 matched token, and 8691 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 9100 tokens : 3.4395604395604393% similarity, with 313 matched token, and 8787 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 9200 tokens : 3.4565217391304346% similarity, with 318 matched token, and 8882 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 9300 tokens : 3.4301075268817205% similarity, with 319 matched token, and 8981 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 9400 tokens : 3.393617021276596% similarity, with 319 matched token, and 9081 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 9500 tokens : 3.421052631578948% similarity, with 325 matched token, and 9175 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 9600 tokens : 3.4062500000000004% similarity, with 327 matched token, and 9273 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 9700 tokens : 3.4123711340206184% similarity, with 331 matched token, and 9369 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 9800 tokens : 3.387755102040816% similarity, with 332 matched token, and 9468 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 9900 tokens : 3.414141414141414% similarity, with 338 matched token, and 9562 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 10000 tokens : 3.45% similarity, with 345 matched token, and 9655 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 10100 tokens : 3.455445544554456% similarity, with 349 matched token, and 9751 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 10200 tokens : 3.4509803921568625% similarity, with 352 matched token, and 9848 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 10300 tokens : 3.4368932038834954% similarity, with 354 matched token, and 9946 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 10400 tokens : 3.4423076923076925% similarity, with 358 matched token, and 10042 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 10500 tokens : 3.4571428571428573% similarity, with 363 matched token, and 10137 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 10600 tokens : 3.4528301886792456% similarity, with 366 matched token, and 10234 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 10700 tokens : 3.4766355140186915% similarity, with 372 matched token, and 10328 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 10800 tokens : 3.490740740740741% similarity, with 377 matched token, and 10423 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 10900 tokens : 3.4770642201834865% similarity, with 379 matched token, and 10521 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 11000 tokens : 3.5000000000000004% similarity, with 385 matched token, and 10615 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 11100 tokens : 3.4954954954954953% similarity, with 388 matched token, and 10712 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 11200 tokens : 3.482142857142857% similarity, with 390 matched token, and 10810 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 11300 tokens : 3.4955752212389384% similarity, with 395 matched token, and 10905 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 11400 tokens : 3.543859649122807% similarity, with 404 matched token, and 10996 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 11500 tokens : 3.5391304347826087% similarity, with 407 matched token, and 11093 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 11600 tokens : 3.5603448275862073% similarity, with 413 matched token, and 11187 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 11700 tokens : 3.547008547008547% similarity, with 415 matched token, and 11285 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 11800 tokens : 3.5593220338983054% similarity, with 420 matched token, and 11380 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 11900 tokens : 3.563025210084034% similarity, with 424 matched token, and 11476 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 12000 tokens : 3.5833333333333335% similarity, with 430 matched token, and 11570 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 12100 tokens : 3.5867768595041323% similarity, with 434 matched token, and 11666 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 12200 tokens : 3.5655737704918034% similarity, with 435 matched token, and 11765 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 12300 tokens : 3.585365853658536% similarity, with 441 matched token, and 11859 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 12400 tokens : 3.588709677419355% similarity, with 445 matched token, and 11955 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 12500 tokens : 3.5839999999999996% similarity, with 448 matched token, and 12052 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 12600 tokens : 3.5793650793650795% similarity, with 451 matched token, and 12149 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 12700 tokens : 3.5905511811023625% similarity, with 456 matched token, and 12244 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 12800 tokens : 3.5703125% similarity, with 457 matched token, and 12343 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 12900 tokens : 3.573643410852713% similarity, with 461 matched token, and 12439 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 13000 tokens : 3.5923076923076924% similarity, with 467 matched token, and 12533 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 13100 tokens : 3.572519083969466% similarity, with 468 matched token, and 12632 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 13200 tokens : 3.5757575757575757% similarity, with 472 matched token, and 12728 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 13300 tokens : 3.56390977443609% similarity, with 474 matched token, and 12826 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 13400 tokens : 3.58955223880597% similarity, with 481 matched token, and 12919 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 13500 tokens : 3.5777777777777775% similarity, with 483 matched token, and 13017 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 13600 tokens : 3.5882352941176467% similarity, with 488 matched token, and 13112 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 13700 tokens : 3.576642335766423% similarity, with 490 matched token, and 13210 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 13800 tokens : 3.5797101449275366% similarity, with 494 matched token, and 13306 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 13900 tokens : 3.5899280575539567% similarity, with 499 matched token, and 13401 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 14000 tokens : 3.6142857142857143% similarity, with 506 matched token, and 13494 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 14100 tokens : 3.6099290780141846% similarity, with 509 matched token, and 13591 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 14200 tokens : 3.5985915492957745% similarity, with 511 matched token, and 13689 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 14300 tokens : 3.5944055944055946% similarity, with 514 matched token, and 13786 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 14400 tokens : 3.6111111111111107% similarity, with 520 matched token, and 13880 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 14500 tokens : 3.5999999999999996% similarity, with 522 matched token, and 13978 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 14600 tokens : 3.5890410958904106% similarity, with 524 matched token, and 14076 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 14700 tokens : 3.619047619047619% similarity, with 532 matched token, and 14168 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 14800 tokens : 3.614864864864865% similarity, with 535 matched token, and 14265 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 14900 tokens : 3.604026845637584% similarity, with 537 matched token, and 14363 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 15000 tokens : 3.5999999999999996% similarity, with 540 matched token, and 14460 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 15100 tokens : 3.596026490066225% similarity, with 543 matched token, and 14557 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 15200 tokens : 3.592105263157895% similarity, with 546 matched token, and 14654 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 15300 tokens : 3.594771241830065% similarity, with 550 matched token, and 14750 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 15400 tokens : 3.5909090909090913% similarity, with 553 matched token, and 14847 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 15500 tokens : 3.5806451612903225% similarity, with 555 matched token, and 14945 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 15600 tokens : 3.5897435897435894% similarity, with 560 matched token, and 15040 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 15700 tokens : 3.5923566878980893% similarity, with 564 matched token, and 15136 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 15800 tokens : 3.5822784810126582% similarity, with 566 matched token, and 15234 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 15900 tokens : 3.578616352201258% similarity, with 569 matched token, and 15331 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 16000 tokens : 3.5687499999999996% similarity, with 571 matched token, and 15429 token mismatch\r\n", "###\r\n", "### Model validation end ###\r\n", "###\r\n" ] } ], "source": [ "!python3 ./memory_script/eval_v5_memory_guided.py \"../../../model/v5-L6-D2048-E0_1-mem-ctx-8k.pth\" \"./logs/v5-L6-D2048-E0_1-16k.csv\" 4100 16000" ] }, { "cell_type": "markdown", "id": "9fdb5030", "metadata": { "papermill": { "duration": 0.075748, "end_time": "2023-08-26T15:43:52.704738", "exception": false, "start_time": "2023-08-26T15:43:52.628990", "status": "completed" }, "tags": [] }, "source": [ "# v5-L6-D4096-E0_1-mem-ctx-8k.pth" ] }, { "cell_type": "code", "execution_count": 13, "id": "59ffd864", "metadata": { "execution": { "iopub.execute_input": "2023-08-26T15:43:52.859479Z", "iopub.status.busy": "2023-08-26T15:43:52.858275Z", "iopub.status.idle": "2023-08-26T15:44:58.323128Z", "shell.execute_reply": "2023-08-26T15:44:58.322179Z" }, "papermill": { "duration": 65.543854, "end_time": "2023-08-26T15:44:58.325168", "exception": false, "start_time": "2023-08-26T15:43:52.781314", "status": "completed" }, "tags": [] }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[2023-08-26 15:43:57,356] [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": [ "###\r\n", "### Model validation start ###\r\n", "###\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 5 tokens : 100.0% similarity, with 5 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 10 tokens : 100.0% similarity, with 10 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 15 tokens : 100.0% similarity, with 15 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 20 tokens : 100.0% similarity, with 20 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 25 tokens : 100.0% similarity, with 25 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 30 tokens : 100.0% similarity, with 30 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 35 tokens : 100.0% similarity, with 35 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 40 tokens : 100.0% similarity, with 40 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 45 tokens : 100.0% similarity, with 45 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 50 tokens : 100.0% similarity, with 50 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 55 tokens : 100.0% similarity, with 55 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 60 tokens : 100.0% similarity, with 60 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 65 tokens : 100.0% similarity, with 65 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 70 tokens : 100.0% similarity, with 70 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 75 tokens : 100.0% similarity, with 75 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 80 tokens : 100.0% similarity, with 80 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 85 tokens : 100.0% similarity, with 85 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 90 tokens : 100.0% similarity, with 90 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 95 tokens : 100.0% similarity, with 95 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 100 tokens : 100.0% similarity, with 100 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 105 tokens : 100.0% similarity, with 105 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 110 tokens : 100.0% similarity, with 110 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 115 tokens : 100.0% similarity, with 115 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 120 tokens : 100.0% similarity, with 120 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 125 tokens : 100.0% similarity, with 125 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 130 tokens : 100.0% similarity, with 130 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 135 tokens : 100.0% similarity, with 135 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 140 tokens : 100.0% similarity, with 140 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 145 tokens : 100.0% similarity, with 145 matched token, and 0 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 150 tokens : 99.33333333333333% similarity, with 149 matched token, and 1 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 160 tokens : 99.375% similarity, with 159 matched token, and 1 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 170 tokens : 98.82352941176471% similarity, with 168 matched token, and 2 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 180 tokens : 98.88888888888889% similarity, with 178 matched token, and 2 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 190 tokens : 98.94736842105263% similarity, with 188 matched token, and 2 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 200 tokens : 99.0% similarity, with 198 matched token, and 2 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 210 tokens : 99.04761904761905% similarity, with 208 matched token, and 2 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 220 tokens : 99.0909090909091% similarity, with 218 matched token, and 2 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 230 tokens : 99.1304347826087% similarity, with 228 matched token, and 2 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 240 tokens : 99.58333333333333% similarity, with 239 matched token, and 1 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 250 tokens : 99.2% similarity, with 248 matched token, and 2 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 260 tokens : 99.23076923076923% similarity, with 258 matched token, and 2 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 270 tokens : 98.51851851851852% similarity, with 266 matched token, and 4 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 280 tokens : 98.57142857142858% similarity, with 276 matched token, and 4 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 290 tokens : 98.62068965517241% similarity, with 286 matched token, and 4 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 300 tokens : 98.0% similarity, with 294 matched token, and 6 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 325 tokens : 98.46153846153847% similarity, with 320 matched token, and 5 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 350 tokens : 97.71428571428571% similarity, with 342 matched token, and 8 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 375 tokens : 96.53333333333333% similarity, with 362 matched token, and 13 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 400 tokens : 96.75% similarity, with 387 matched token, and 13 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 425 tokens : 96.47058823529412% similarity, with 410 matched token, and 15 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 450 tokens : 96.0% similarity, with 432 matched token, and 18 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 475 tokens : 95.36842105263158% similarity, with 453 matched token, and 22 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 500 tokens : 93.8% similarity, with 469 matched token, and 31 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 525 tokens : 93.9047619047619% similarity, with 493 matched token, and 32 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 550 tokens : 93.81818181818183% similarity, with 516 matched token, and 34 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 575 tokens : 92.8695652173913% similarity, with 534 matched token, and 41 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 600 tokens : 92.66666666666666% similarity, with 556 matched token, and 44 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 625 tokens : 92.0% similarity, with 575 matched token, and 50 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 650 tokens : 90.46153846153845% similarity, with 588 matched token, and 62 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 675 tokens : 90.96296296296296% similarity, with 614 matched token, and 61 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 700 tokens : 91.0% similarity, with 637 matched token, and 63 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 750 tokens : 89.2% similarity, with 669 matched token, and 81 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 800 tokens : 88.0% similarity, with 704 matched token, and 96 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 850 tokens : 87.52941176470588% similarity, with 744 matched token, and 106 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 900 tokens : 87.66666666666667% similarity, with 789 matched token, and 111 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 950 tokens : 85.78947368421052% similarity, with 815 matched token, and 135 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 1000 tokens : 83.6% similarity, with 836 matched token, and 164 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Finished baseline model to eval output predictive matching (aka 0 memory?), for 1000 tokens\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "###\r\n", "### Model validation end ###\r\n", "###\r\n" ] } ], "source": [ "!python3 ./memory_script/eval_v5_memory_guided.py \"../../../model/v5-L6-D4096-E0_1-mem-ctx-8k.pth\" \"./logs/v5-L6-D4096-E0_1-1k.csv\"" ] }, { "cell_type": "code", "execution_count": 14, "id": "816d4475", "metadata": { "execution": { "iopub.execute_input": "2023-08-26T15:44:58.475082Z", "iopub.status.busy": "2023-08-26T15:44:58.474129Z", "iopub.status.idle": "2023-08-26T15:48:50.587080Z", "shell.execute_reply": "2023-08-26T15:48:50.585908Z" }, "papermill": { "duration": 232.19095, "end_time": "2023-08-26T15:48:50.589477", "exception": false, "start_time": "2023-08-26T15:44:58.398527", "status": "completed" }, "tags": [] }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[2023-08-26 15:45:02,461] [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": [ "###\r\n", "### Model validation start ###\r\n", "###\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 1100 tokens : 80.0909090909091% similarity, with 881 matched token, and 219 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 1150 tokens : 78.34782608695652% similarity, with 901 matched token, and 249 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 1200 tokens : 77.08333333333334% similarity, with 925 matched token, and 275 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 1250 tokens : 74.56% similarity, with 932 matched token, and 318 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 1300 tokens : 73.07692307692307% similarity, with 950 matched token, and 350 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 1350 tokens : 72.5925925925926% similarity, with 980 matched token, and 370 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 1400 tokens : 70.71428571428572% similarity, with 990 matched token, and 410 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 1450 tokens : 68.13793103448276% similarity, with 988 matched token, and 462 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 1500 tokens : 66.0% similarity, with 990 matched token, and 510 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 1550 tokens : 65.48387096774194% similarity, with 1015 matched token, and 535 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 1600 tokens : 63.375% similarity, with 1014 matched token, and 586 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 1650 tokens : 62.24242424242424% similarity, with 1027 matched token, and 623 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 1700 tokens : 60.411764705882355% similarity, with 1027 matched token, and 673 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 1750 tokens : 59.14285714285714% similarity, with 1035 matched token, and 715 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 1800 tokens : 56.388888888888886% similarity, with 1015 matched token, and 785 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 1850 tokens : 55.945945945945944% similarity, with 1035 matched token, and 815 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 1900 tokens : 54.94736842105263% similarity, with 1044 matched token, and 856 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 1950 tokens : 53.230769230769226% similarity, with 1038 matched token, and 912 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 2000 tokens : 52.75% similarity, with 1055 matched token, and 945 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 2050 tokens : 50.926829268292686% similarity, with 1044 matched token, and 1006 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 2100 tokens : 49.57142857142857% similarity, with 1041 matched token, and 1059 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 2150 tokens : 47.72093023255814% similarity, with 1026 matched token, and 1124 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 2200 tokens : 46.409090909090914% similarity, with 1021 matched token, and 1179 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 2250 tokens : 45.33333333333333% similarity, with 1020 matched token, and 1230 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 2300 tokens : 43.21739130434782% similarity, with 994 matched token, and 1306 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 2350 tokens : 41.65957446808511% similarity, with 979 matched token, and 1371 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 2400 tokens : 40.91666666666667% similarity, with 982 matched token, and 1418 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 2450 tokens : 39.02040816326531% similarity, with 956 matched token, and 1494 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 2500 tokens : 37.92% similarity, with 948 matched token, and 1552 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 2550 tokens : 36.470588235294116% similarity, with 930 matched token, and 1620 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 2600 tokens : 35.46153846153846% similarity, with 922 matched token, and 1678 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 2650 tokens : 34.56603773584906% similarity, with 916 matched token, and 1734 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 2700 tokens : 33.88888888888889% similarity, with 915 matched token, and 1785 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 2750 tokens : 32.654545454545456% similarity, with 898 matched token, and 1852 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 2800 tokens : 31.607142857142854% similarity, with 885 matched token, and 1915 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 2850 tokens : 31.05263157894737% similarity, with 885 matched token, and 1965 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 2900 tokens : 30.10344827586207% similarity, with 873 matched token, and 2027 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 2950 tokens : 29.355932203389827% similarity, with 866 matched token, and 2084 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 3000 tokens : 28.666666666666668% similarity, with 860 matched token, and 2140 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 3050 tokens : 27.77049180327869% similarity, with 847 matched token, and 2203 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 3100 tokens : 27.387096774193548% similarity, with 849 matched token, and 2251 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 3150 tokens : 26.88888888888889% similarity, with 847 matched token, and 2303 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 3200 tokens : 26.34375% similarity, with 843 matched token, and 2357 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 3250 tokens : 25.784615384615385% similarity, with 838 matched token, and 2412 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 3300 tokens : 25.181818181818183% similarity, with 831 matched token, and 2469 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 3350 tokens : 24.44776119402985% similarity, with 819 matched token, and 2531 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 3400 tokens : 24.058823529411764% similarity, with 818 matched token, and 2582 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 3450 tokens : 23.391304347826086% similarity, with 807 matched token, and 2643 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 3500 tokens : 23.0% similarity, with 805 matched token, and 2695 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 3550 tokens : 22.7887323943662% similarity, with 809 matched token, and 2741 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 3600 tokens : 22.47222222222222% similarity, with 809 matched token, and 2791 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 3650 tokens : 22.054794520547947% similarity, with 805 matched token, and 2845 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 3700 tokens : 21.783783783783782% similarity, with 806 matched token, and 2894 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 3750 tokens : 21.52% similarity, with 807 matched token, and 2943 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 3800 tokens : 21.342105263157897% similarity, with 811 matched token, and 2989 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 3850 tokens : 21.038961038961038% similarity, with 810 matched token, and 3040 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 3900 tokens : 20.692307692307693% similarity, with 807 matched token, and 3093 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 3950 tokens : 20.32911392405063% similarity, with 803 matched token, and 3147 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 4000 tokens : 20.05% similarity, with 802 matched token, and 3198 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "###\r\n", "### Model validation end ###\r\n", "###\r\n" ] } ], "source": [ "!python3 ./memory_script/eval_v5_memory_guided.py \"../../../model/v5-L6-D4096-E0_1-mem-ctx-8k.pth\" \"./logs/v5-L6-D4096-E0_1-4k.csv\" 1100 4000" ] }, { "cell_type": "code", "execution_count": 15, "id": "3246699f", "metadata": { "execution": { "iopub.execute_input": "2023-08-26T15:48:50.755698Z", "iopub.status.busy": "2023-08-26T15:48:50.754546Z", "iopub.status.idle": "2023-08-26T16:51:12.767938Z", "shell.execute_reply": "2023-08-26T16:51:12.766985Z" }, "papermill": { "duration": 3742.098954, "end_time": "2023-08-26T16:51:12.770407", "exception": false, "start_time": "2023-08-26T15:48:50.671453", "status": "completed" }, "tags": [] }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[2023-08-26 15:48:55,284] [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": [ "###\r\n", "### Model validation start ###\r\n", "###\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 4100 tokens : 19.439024390243905% similarity, with 797 matched token, and 3303 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 4200 tokens : 18.5% similarity, with 777 matched token, and 3423 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 4300 tokens : 17.906976744186046% similarity, with 770 matched token, and 3530 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 4400 tokens : 17.06818181818182% similarity, with 751 matched token, and 3649 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 4500 tokens : 16.377777777777776% similarity, with 737 matched token, and 3763 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 4600 tokens : 15.65217391304348% similarity, with 720 matched token, and 3880 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 4700 tokens : 14.829787234042552% similarity, with 697 matched token, and 4003 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 4800 tokens : 14.145833333333332% similarity, with 679 matched token, and 4121 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 4900 tokens : 13.204081632653061% similarity, with 647 matched token, and 4253 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 5000 tokens : 12.42% similarity, with 621 matched token, and 4379 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 5100 tokens : 11.470588235294118% similarity, with 585 matched token, and 4515 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 5200 tokens : 10.596153846153847% similarity, with 551 matched token, and 4649 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 5300 tokens : 9.773584905660378% similarity, with 518 matched token, and 4782 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 5400 tokens : 8.666666666666668% similarity, with 468 matched token, and 4932 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 5500 tokens : 7.8909090909090915% similarity, with 434 matched token, and 5066 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 5600 tokens : 7.214285714285714% similarity, with 404 matched token, and 5196 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 5700 tokens : 6.561403508771931% similarity, with 374 matched token, and 5326 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 5800 tokens : 5.931034482758621% similarity, with 344 matched token, and 5456 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 5900 tokens : 5.627118644067797% similarity, with 332 matched token, and 5568 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 6000 tokens : 5.166666666666667% similarity, with 310 matched token, and 5690 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 6100 tokens : 4.836065573770492% similarity, with 295 matched token, and 5805 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 6200 tokens : 4.370967741935484% similarity, with 271 matched token, and 5929 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 6300 tokens : 4.222222222222222% similarity, with 266 matched token, and 6034 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 6400 tokens : 3.9843749999999996% similarity, with 255 matched token, and 6145 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 6500 tokens : 3.8615384615384616% similarity, with 251 matched token, and 6249 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 6600 tokens : 3.7575757575757573% similarity, with 248 matched token, and 6352 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 6700 tokens : 3.7910447761194033% similarity, with 254 matched token, and 6446 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 6800 tokens : 3.6764705882352944% similarity, with 250 matched token, and 6550 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 6900 tokens : 3.6231884057971016% similarity, with 250 matched token, and 6650 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 7000 tokens : 3.571428571428571% similarity, with 250 matched token, and 6750 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 7100 tokens : 3.492957746478873% similarity, with 248 matched token, and 6852 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 7200 tokens : 3.486111111111111% similarity, with 251 matched token, and 6949 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 7300 tokens : 3.493150684931507% similarity, with 255 matched token, and 7045 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 7400 tokens : 3.5000000000000004% similarity, with 259 matched token, and 7141 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 7500 tokens : 3.4266666666666667% similarity, with 257 matched token, and 7243 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 7600 tokens : 3.4342105263157894% similarity, with 261 matched token, and 7339 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 7700 tokens : 3.428571428571429% similarity, with 264 matched token, and 7436 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 7800 tokens : 3.4230769230769234% similarity, with 267 matched token, and 7533 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 7900 tokens : 3.4050632911392404% similarity, with 269 matched token, and 7631 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 8000 tokens : 3.4000000000000004% similarity, with 272 matched token, and 7728 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 8100 tokens : 3.4444444444444446% similarity, with 279 matched token, and 7821 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 8200 tokens : 3.4268292682926833% similarity, with 281 matched token, and 7919 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 8300 tokens : 3.4096385542168677% similarity, with 283 matched token, and 8017 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 8400 tokens : 3.392857142857143% similarity, with 285 matched token, and 8115 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 8500 tokens : 3.4235294117647057% similarity, with 291 matched token, and 8209 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 8600 tokens : 3.4186046511627906% similarity, with 294 matched token, and 8306 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 8700 tokens : 3.425287356321839% similarity, with 298 matched token, and 8402 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 8800 tokens : 3.4090909090909087% similarity, with 300 matched token, and 8500 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 8900 tokens : 3.4269662921348316% similarity, with 305 matched token, and 8595 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 9000 tokens : 3.4111111111111114% similarity, with 307 matched token, and 8693 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 9100 tokens : 3.428571428571429% similarity, with 312 matched token, and 8788 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 9200 tokens : 3.4239130434782608% similarity, with 315 matched token, and 8885 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 9300 tokens : 3.4086021505376345% similarity, with 317 matched token, and 8983 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 9400 tokens : 3.393617021276596% similarity, with 319 matched token, and 9081 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 9500 tokens : 3.4105263157894736% similarity, with 324 matched token, and 9176 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 9600 tokens : 3.4166666666666665% similarity, with 328 matched token, and 9272 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 9700 tokens : 3.4123711340206184% similarity, with 331 matched token, and 9369 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 9800 tokens : 3.4081632653061225% similarity, with 334 matched token, and 9466 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 9900 tokens : 3.424242424242424% similarity, with 339 matched token, and 9561 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 10000 tokens : 3.45% similarity, with 345 matched token, and 9655 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 10100 tokens : 3.4653465346534658% similarity, with 350 matched token, and 9750 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 10200 tokens : 3.4509803921568625% similarity, with 352 matched token, and 9848 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 10300 tokens : 3.4368932038834954% similarity, with 354 matched token, and 9946 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 10400 tokens : 3.4423076923076925% similarity, with 358 matched token, and 10042 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 10500 tokens : 3.4476190476190474% similarity, with 362 matched token, and 10138 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 10600 tokens : 3.443396226415094% similarity, with 365 matched token, and 10235 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 10700 tokens : 3.467289719626168% similarity, with 371 matched token, and 10329 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 10800 tokens : 3.4722222222222223% similarity, with 375 matched token, and 10425 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 10900 tokens : 3.458715596330275% similarity, with 377 matched token, and 10523 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 11000 tokens : 3.481818181818182% similarity, with 383 matched token, and 10617 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 11100 tokens : 3.4774774774774775% similarity, with 386 matched token, and 10714 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 11200 tokens : 3.455357142857143% similarity, with 387 matched token, and 10813 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 11300 tokens : 3.4690265486725664% similarity, with 392 matched token, and 10908 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 11400 tokens : 3.5000000000000004% similarity, with 399 matched token, and 11001 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 11500 tokens : 3.5043478260869563% similarity, with 403 matched token, and 11097 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 11600 tokens : 3.517241379310345% similarity, with 408 matched token, and 11192 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 11700 tokens : 3.5042735042735043% similarity, with 410 matched token, and 11290 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 11800 tokens : 3.516949152542373% similarity, with 415 matched token, and 11385 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 11900 tokens : 3.521008403361345% similarity, with 419 matched token, and 11481 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 12000 tokens : 3.5333333333333337% similarity, with 424 matched token, and 11576 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 12100 tokens : 3.5454545454545454% similarity, with 429 matched token, and 11671 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 12200 tokens : 3.5327868852459017% similarity, with 431 matched token, and 11769 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 12300 tokens : 3.5447154471544713% similarity, with 436 matched token, and 11864 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 12400 tokens : 3.540322580645161% similarity, with 439 matched token, and 11961 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 12500 tokens : 3.5360000000000005% similarity, with 442 matched token, and 12058 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 12600 tokens : 3.5317460317460316% similarity, with 445 matched token, and 12155 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 12700 tokens : 3.543307086614173% similarity, with 450 matched token, and 12250 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 12800 tokens : 3.5312499999999996% similarity, with 452 matched token, and 12348 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 12900 tokens : 3.5348837209302326% similarity, with 456 matched token, and 12444 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 13000 tokens : 3.553846153846154% similarity, with 462 matched token, and 12538 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 13100 tokens : 3.5343511450381677% similarity, with 463 matched token, and 12637 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 13200 tokens : 3.5378787878787876% similarity, with 467 matched token, and 12733 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 13300 tokens : 3.5263157894736845% similarity, with 469 matched token, and 12831 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 13400 tokens : 3.544776119402985% similarity, with 475 matched token, and 12925 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 13500 tokens : 3.5333333333333337% similarity, with 477 matched token, and 13023 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 13600 tokens : 3.5441176470588234% similarity, with 482 matched token, and 13118 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 13700 tokens : 3.5328467153284673% similarity, with 484 matched token, and 13216 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 13800 tokens : 3.5362318840579707% similarity, with 488 matched token, and 13312 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 13900 tokens : 3.5467625899280577% similarity, with 493 matched token, and 13407 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 14000 tokens : 3.564285714285714% similarity, with 499 matched token, and 13501 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 14100 tokens : 3.5602836879432624% similarity, with 502 matched token, and 13598 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 14200 tokens : 3.549295774647887% similarity, with 504 matched token, and 13696 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 14300 tokens : 3.5454545454545454% similarity, with 507 matched token, and 13793 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 14400 tokens : 3.5555555555555554% similarity, with 512 matched token, and 13888 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 14500 tokens : 3.5448275862068965% similarity, with 514 matched token, and 13986 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 14600 tokens : 3.534246575342466% similarity, with 516 matched token, and 14084 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 14700 tokens : 3.5646258503401365% similarity, with 524 matched token, and 14176 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 14800 tokens : 3.5608108108108105% similarity, with 527 matched token, and 14273 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 14900 tokens : 3.557046979865772% similarity, with 530 matched token, and 14370 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 15000 tokens : 3.56% similarity, with 534 matched token, and 14466 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 15100 tokens : 3.556291390728477% similarity, with 537 matched token, and 14563 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 15200 tokens : 3.546052631578948% similarity, with 539 matched token, and 14661 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 15300 tokens : 3.5490196078431375% similarity, with 543 matched token, and 14757 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 15400 tokens : 3.538961038961039% similarity, with 545 matched token, and 14855 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 15500 tokens : 3.535483870967742% similarity, with 548 matched token, and 14952 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 15600 tokens : 3.5384615384615383% similarity, with 552 matched token, and 15048 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 15700 tokens : 3.54140127388535% similarity, with 556 matched token, and 15144 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 15800 tokens : 3.537974683544304% similarity, with 559 matched token, and 15241 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 15900 tokens : 3.528301886792453% similarity, with 561 matched token, and 15339 token mismatch\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Model validation for 16000 tokens : 3.5249999999999995% similarity, with 564 matched token, and 15436 token mismatch\r\n", "###\r\n", "### Model validation end ###\r\n", "###\r\n" ] } ], "source": [ "!python3 ./memory_script/eval_v5_memory_guided.py \"../../../model/v5-L6-D4096-E0_1-mem-ctx-8k.pth\" \"./logs/v5-L6-D4096-E0_1-16k.csv\" 4100 16000" ] } ], "metadata": { "kernelspec": { "display_name": "rwkv-infctx", "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": 12231.801051, "end_time": "2023-08-26T16:51:13.211146", "environment_variables": {}, "exception": null, "input_path": "/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/notebook/experiment/memory-bench/Benchmark-V5.ipynb", "output_path": "/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/memory-bench/Benchmark-V5.ipynb", "parameters": {}, "start_time": "2023-08-26T13:27:21.410095", "version": "2.4.0" } }, "nbformat": 4, "nbformat_minor": 5 }