diff --git "a/experiment/rwkv-x-exp/v5-memory/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/rwkv-x-exp/v5-memory/v5-L96-D1024-E1e-1-ctx4k-part3.ipynb" "b/experiment/rwkv-x-exp/v5-memory/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/rwkv-x-exp/v5-memory/v5-L96-D1024-E1e-1-ctx4k-part3.ipynb" deleted file mode 100644--- "a/experiment/rwkv-x-exp/v5-memory/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/rwkv-x-exp/v5-memory/v5-L96-D1024-E1e-1-ctx4k-part3.ipynb" +++ /dev/null @@ -1,261885 +0,0 @@ -{ - "cells": [ - { - "attachments": {}, - "cell_type": "markdown", - "id": "ebe40958", - "metadata": { - "papermill": { - "duration": 0.003251, - "end_time": "2023-08-31T21:57:50.593195", - "exception": false, - "start_time": "2023-08-31T21:57:50.589944", - "status": "completed" - }, - "tags": [] - }, - "source": [ - "# RWKV v5 / embedding init-range 1e-01 / 4k\n", - "\n", - "- 96 layers\n", - "- 1024 embedding size\n", - "\n", - "Going through the modified memory training for v5 models, across various initial embedding model weights\n", - "\n", - "**Note:** This project assumes you have the rwkv-infctx conda env setup" - ] - }, - { - "attachments": {}, - "cell_type": "markdown", - "id": "ebb402ba", - "metadata": { - "papermill": { - "duration": 0.002118, - "end_time": "2023-08-31T21:57:50.597672", - "exception": false, - "start_time": "2023-08-31T21:57:50.595554", - "status": "completed" - }, - "tags": [] - }, - "source": [ - "# Basic Setup" - ] - }, - { - "cell_type": "code", - "execution_count": 1, - "id": "65508084", - "metadata": { - "execution": { - "iopub.execute_input": "2023-08-31T21:57:50.603240Z", - "iopub.status.busy": "2023-08-31T21:57:50.603055Z", - "iopub.status.idle": "2023-08-31T21:57:51.324018Z", - "shell.execute_reply": "2023-08-31T21:57:51.323016Z" - }, - "papermill": { - "duration": 0.725665, - "end_time": "2023-08-31T21:57:51.325689", - "exception": false, - "start_time": "2023-08-31T21:57:50.600024", - "status": "completed" - }, - "tags": [] - }, - "outputs": [], - "source": [ - "# First lets setup the various directories, and init the model\n", - "!mkdir -p ../../../../model/\n", - "!mkdir -p ../../../../datapath/\n", - "!mkdir -p ../../../../checkpoint/" - ] - }, - { - "cell_type": "code", - "execution_count": 2, - "id": "4137a5b3", - "metadata": { - "execution": { - "iopub.execute_input": "2023-08-31T21:57:51.331628Z", - "iopub.status.busy": "2023-08-31T21:57:51.331434Z", - "iopub.status.idle": "2023-08-31T21:57:54.206520Z", - "shell.execute_reply": "2023-08-31T21:57:54.205777Z" - }, - "papermill": { - "duration": 2.880097, - "end_time": "2023-08-31T21:57:54.208336", - "exception": false, - "start_time": "2023-08-31T21:57:51.328239", - "status": "completed" - }, - "tags": [] - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\u001b[33mWARNING: Running pip as the 'root' user can result in broken permissions and conflicting behaviour with the system package manager. It is recommended to use a virtual environment instead: https://pip.pypa.io/warnings/venv\u001b[0m\u001b[33m\r\n", - "\u001b[0m" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r\n", - "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m23.1.2\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m23.2.1\u001b[0m\r\n", - "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpython3.11 -m pip install --upgrade pip\u001b[0m\r\n" - ] - } - ], - "source": [ - "# Additional dependencies for eval stuff\n", - "!pip install -q aiocsv aiofiles" - ] - }, - { - "cell_type": "code", - "execution_count": 3, - "id": "9db7327e", - "metadata": { - "execution": { - "iopub.execute_input": "2023-08-31T21:57:54.214815Z", - "iopub.status.busy": "2023-08-31T21:57:54.214569Z", - "iopub.status.idle": "2023-08-31T21:57:54.221053Z", - "shell.execute_reply": "2023-08-31T21:57:54.220407Z" - }, - "papermill": { - "duration": 0.011029, - "end_time": "2023-08-31T21:57:54.222190", - "exception": false, - "start_time": "2023-08-31T21:57:54.211161", - "status": "completed" - }, - "tags": [] - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "DEEPSPEED_STRAT: deepspeed_stage_1\n", - "ENABLE_WANDB: True\n", - "GPU_DEVICES: auto\n", - "NOTEBOOK_DIR: /actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/notebook/experiment/rwkv-x-exp/v5-memory\n", - "INFERENCE_DIR: /actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/RWKV-v5\n", - "TRAINER_DIR: /actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/RWKV-v5\n", - "PROJECT_DIR: /actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer\n" - ] - } - ], - "source": [ - "DEEPSPEED_STRAT=\"deepspeed_stage_1\"\n", - "GPU_DEVICES=\"auto\"\n", - "ENABLE_WANDB=True\n", - "\n", - "# Layer count and embed dim to start with\n", - "LAYER_COUNT=96\n", - "EMBED_DIM=1024\n", - "\n", - "# Wavnet compatibility?\n", - "RWKV_WAVENET_LAYERS=0\n", - "\n", - "EMBED_SCALE=0.1\n", - "EMBED_SCALE_LABEL=str(EMBED_SCALE).replace(\".\", \"_\")\n", - "\n", - "WANDB_PREFIX=f\"v5-L{LAYER_COUNT}-D{EMBED_DIM}-E{EMBED_SCALE}\"\n", - "FILENAME_PREFIX=f\"v5-L{LAYER_COUNT}-D{EMBED_DIM}-E{EMBED_SCALE_LABEL}\"\n", - "\n", - "print(\"DEEPSPEED_STRAT:\", DEEPSPEED_STRAT)\n", - "print(\"ENABLE_WANDB:\", ENABLE_WANDB)\n", - "print(\"GPU_DEVICES:\", GPU_DEVICES)\n", - "\n", - "if ENABLE_WANDB:\n", - " WANDB_MODE=\"online\"\n", - "else:\n", - " WANDB_MODE=\"disabled\"\n", - "\n", - "# Computing the notebook, and various paths\n", - "import os\n", - "NOTEBOOK_DIR=os.path.dirname(os.path.abspath(\"__file__\"))\n", - "PROJECT_DIR=os.path.abspath(os.path.join(NOTEBOOK_DIR, \"../../../../\"))\n", - "TRAINER_DIR=os.path.abspath(os.path.join(PROJECT_DIR, \"./RWKV-v5/\"))\n", - "INFERENCE_DIR=os.path.abspath(os.path.join(PROJECT_DIR, \"./RWKV-v5/\"))\n", - "\n", - "print(\"NOTEBOOK_DIR:\", NOTEBOOK_DIR)\n", - "print(\"INFERENCE_DIR:\", INFERENCE_DIR)\n", - "print(\"TRAINER_DIR:\", TRAINER_DIR)\n", - "print(\"PROJECT_DIR:\", PROJECT_DIR)" - ] - }, - { - "cell_type": "code", - "execution_count": 4, - "id": "2c64df74", - "metadata": { - "execution": { - "iopub.execute_input": "2023-08-31T21:57:54.228179Z", - "iopub.status.busy": "2023-08-31T21:57:54.228014Z", - "iopub.status.idle": "2023-08-31T21:58:42.524078Z", - "shell.execute_reply": "2023-08-31T21:58:42.523147Z" - }, - "papermill": { - "duration": 48.301166, - "end_time": "2023-08-31T21:58:42.526006", - "exception": false, - "start_time": "2023-08-31T21:57:54.224840", - "status": "completed" - }, - "tags": [] - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "--2023-08-31 21:57:54-- https://huggingface.co/rwkv-x-dev/rwkv-x-playground/resolve/main/experiment/rwkv-x-exp/v5-memory/v5-L96-D1024-E0_1-mem-ctx-512.pth\r\n", - "Resolving huggingface.co (huggingface.co)... " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "52.85.242.84, 52.85.242.16, 52.85.242.8, ...\r\n", - "Connecting to huggingface.co (huggingface.co)|52.85.242.84|:443... connected.\r\n", - "HTTP request sent, awaiting response... " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "302 Found\r\n", - "Location: https://cdn-lfs.huggingface.co/repos/2e/f7/2ef78555202aa92abdbdf476ce3d0fd5a8b15f7245edf0b80d4d30572355f30d/893167b0eb69142597da713f1d1a3b7c14cedbd34e677e45adc13979ae756e67?response-content-disposition=attachment%3B+filename*%3DUTF-8%27%27v5-L96-D1024-E0_1-mem-ctx-512.pth%3B+filename%3D%22v5-L96-D1024-E0_1-mem-ctx-512.pth%22%3B&Expires=1693778274&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTY5Mzc3ODI3NH19LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy5odWdnaW5nZmFjZS5jby9yZXBvcy8yZS9mNy8yZWY3ODU1NTIwMmFhOTJhYmRiZGY0NzZjZTNkMGZkNWE4YjE1ZjcyNDVlZGYwYjgwZDRkMzA1NzIzNTVmMzBkLzg5MzE2N2IwZWI2OTE0MjU5N2RhNzEzZjFkMWEzYjdjMTRjZWRiZDM0ZTY3N2U0NWFkYzEzOTc5YWU3NTZlNjc%7EcmVzcG9uc2UtY29udGVudC1kaXNwb3NpdGlvbj0qIn1dfQ__&Signature=JD%7EsMmgqXtvAia5xWxOmrxJJ9tKU0Q3A1gQs41xamphNueZo1cxy07Gl%7ErYfrqYu2W8ERL%7E2h8HKUjyWDy1B7d6SNaLpMJs3t67q57-LfOTK11BsZUGYGii2HMl6tIMJQcChEHUfHujEOZ62QxNls0ETIL3U--Qn5%7E2AFAp1q5sMVngSNWSgN3X991uejYeR9tWVSFE1-iH%7E0h8TG4KjEhRYsjROpeLXkKExHKyz2vulh5gA6I103LDJdNTQ3y%7EXUGp6KRMlegIdpchJmoxoilnMOcHSWwyaY7Qf2veeYouQicgavUFrrJEMIMj-L%7EuJXlf%7EM24zwQ274ro5CJhvOA__&Key-Pair-Id=KVTP0A1DKRTAX [following]\r\n", - "--2023-08-31 21:57:54-- https://cdn-lfs.huggingface.co/repos/2e/f7/2ef78555202aa92abdbdf476ce3d0fd5a8b15f7245edf0b80d4d30572355f30d/893167b0eb69142597da713f1d1a3b7c14cedbd34e677e45adc13979ae756e67?response-content-disposition=attachment%3B+filename*%3DUTF-8%27%27v5-L96-D1024-E0_1-mem-ctx-512.pth%3B+filename%3D%22v5-L96-D1024-E0_1-mem-ctx-512.pth%22%3B&Expires=1693778274&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTY5Mzc3ODI3NH19LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy5odWdnaW5nZmFjZS5jby9yZXBvcy8yZS9mNy8yZWY3ODU1NTIwMmFhOTJhYmRiZGY0NzZjZTNkMGZkNWE4YjE1ZjcyNDVlZGYwYjgwZDRkMzA1NzIzNTVmMzBkLzg5MzE2N2IwZWI2OTE0MjU5N2RhNzEzZjFkMWEzYjdjMTRjZWRiZDM0ZTY3N2U0NWFkYzEzOTc5YWU3NTZlNjc%7EcmVzcG9uc2UtY29udGVudC1kaXNwb3NpdGlvbj0qIn1dfQ__&Signature=JD%7EsMmgqXtvAia5xWxOmrxJJ9tKU0Q3A1gQs41xamphNueZo1cxy07Gl%7ErYfrqYu2W8ERL%7E2h8HKUjyWDy1B7d6SNaLpMJs3t67q57-LfOTK11BsZUGYGii2HMl6tIMJQcChEHUfHujEOZ62QxNls0ETIL3U--Qn5%7E2AFAp1q5sMVngSNWSgN3X991uejYeR9tWVSFE1-iH%7E0h8TG4KjEhRYsjROpeLXkKExHKyz2vulh5gA6I103LDJdNTQ3y%7EXUGp6KRMlegIdpchJmoxoilnMOcHSWwyaY7Qf2veeYouQicgavUFrrJEMIMj-L%7EuJXlf%7EM24zwQ274ro5CJhvOA__&Key-Pair-Id=KVTP0A1DKRTAX\r\n", - "Resolving cdn-lfs.huggingface.co (cdn-lfs.huggingface.co)... " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "108.157.214.82, 108.157.214.31, 108.157.214.7, ...\r\n", - "Connecting to cdn-lfs.huggingface.co (cdn-lfs.huggingface.co)|108.157.214.82|:443... connected.\r\n", - "HTTP request sent, awaiting response... " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "200 OK\r\n", - "Length: 2825978627 (2.6G) [binary/octet-stream]\r\n", - "Saving to: ‘v5-L96-D1024-E0_1-mem-ctx-512.pth’\r\n", - "\r\n", - "\r", - " v5-L96-D1 0%[ ] 0 --.-KB/s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96-D10 0%[ ] 3.83M 19.0MB/s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96-D102 0%[ ] 10.72M 25.5MB/s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96-D1024 0%[ ] 23.43M 36.5MB/s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96-D1024- 1%[ ] 33.54M 39.8MB/s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96-D1024-E 1%[ ] 45.80M 43.0MB/s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96-D1024-E0 2%[ ] 59.71M 47.2MB/s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96-D1024-E0_ 2%[ ] 71.07M 48.5MB/s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96-D1024-E0_1 3%[ ] 81.38M 48.8MB/s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96-D1024-E0_1- 3%[ ] 95.36M 51.0MB/s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "v5-L96-D1024-E0_1-m 4%[ ] 109.14M 52.7MB/s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "5-L96-D1024-E0_1-me 4%[ ] 118.34M 52.1MB/s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "-L96-D1024-E0_1-mem 4%[ ] 133.63M 53.9MB/s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "L96-D1024-E0_1-mem- 5%[> ] 146.71M 54.7MB/s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "96-D1024-E0_1-mem-c 5%[> ] 159.46M 55.4MB/s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "6-D1024-E0_1-mem-ct 6%[> ] 168.00M 54.5MB/s eta 46s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "-D1024-E0_1-mem-ctx 6%[> ] 181.76M 55.4MB/s eta 46s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "D1024-E0_1-mem-ctx- 7%[> ] 191.94M 57.9MB/s eta 46s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "1024-E0_1-mem-ctx-5 7%[> ] 204.83M 59.0MB/s eta 46s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "024-E0_1-mem-ctx-51 8%[> ] 216.37M 59.2MB/s eta 46s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "24-E0_1-mem-ctx-512 8%[> ] 228.26M 60.0MB/s eta 44s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "4-E0_1-mem-ctx-512. 9%[> ] 242.89M 61.0MB/s eta 44s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "-E0_1-mem-ctx-512.p 9%[> ] 253.08M 60.3MB/s eta 44s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "E0_1-mem-ctx-512.pt 9%[> ] 265.75M 60.2MB/s eta 44s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "0_1-mem-ctx-512.pth 10%[=> ] 276.96M 59.9MB/s eta 44s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "_1-mem-ctx-512.pth 10%[=> ] 292.39M 61.5MB/s eta 42s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "1-mem-ctx-512.pth 11%[=> ] 304.31M 60.8MB/s eta 42s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "-mem-ctx-512.pth 11%[=> ] 318.00M 61.6MB/s eta 42s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "mem-ctx-512.pth 12%[=> ] 331.02M 60.8MB/s eta 42s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "em-ctx-512.pth 12%[=> ] 345.48M 61.1MB/s eta 42s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "m-ctx-512.pth 13%[=> ] 353.27M 59.9MB/s eta 41s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "-ctx-512.pth 13%[=> ] 366.94M 61.0MB/s eta 41s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "ctx-512.pth 14%[=> ] 378.82M 60.9MB/s eta 41s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "tx-512.pth 14%[=> ] 389.97M 60.7MB/s eta 41s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "x-512.pth 14%[=> ] 403.29M 61.3MB/s eta 41s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "-512.pth 15%[==> ] 416.44M 61.0MB/s eta 39s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "512.pth 15%[==> ] 428.14M 61.0MB/s eta 39s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "12.pth 16%[==> ] 437.77M 60.5MB/s eta 39s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "2.pth 16%[==> ] 449.14M 60.1MB/s eta 39s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - ".pth 17%[==> ] 463.27M 60.3MB/s eta 39s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "pth 17%[==> ] 476.37M 59.7MB/s eta 38s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "th 18%[==> ] 491.04M 59.9MB/s eta 38s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "h 18%[==> ] 505.26M 60.4MB/s eta 38s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " 19%[==> ] 517.72M 59.2MB/s eta 38s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v 19%[==> ] 527.85M 58.4MB/s eta 38s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5 20%[===> ] 542.46M 60.4MB/s eta 37s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5- 20%[===> ] 553.68M 60.1MB/s eta 37s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L 20%[===> ] 565.89M 59.8MB/s eta 37s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L9 21%[===> ] 577.69M 59.5MB/s eta 37s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96 21%[===> ] 590.93M 59.3MB/s eta 37s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96- 22%[===> ] 606.10M 60.2MB/s eta 35s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96-D 22%[===> ] 610.08M 57.7MB/s eta 35s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96-D1 22%[===> ] 617.99M 56.4MB/s eta 35s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96-D10 23%[===> ] 633.58M 58.1MB/s eta 35s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96-D102 24%[===> ] 647.01M 59.0MB/s eta 35s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96-D1024 24%[===> ] 659.04M 58.7MB/s eta 35s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96-D1024- 24%[===> ] 668.97M 57.2MB/s eta 35s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96-D1024-E 25%[====> ] 684.61M 58.4MB/s eta 35s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96-D1024-E0 25%[====> ] 693.83M 57.5MB/s eta 35s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96-D1024-E0_ 26%[====> ] 704.54M 56.6MB/s eta 35s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96-D1024-E0_1 26%[====> ] 719.90M 56.7MB/s eta 34s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96-D1024-E0_1- 27%[====> ] 731.53M 56.9MB/s eta 34s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "v5-L96-D1024-E0_1-m 27%[====> ] 744.29M 57.3MB/s eta 34s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "5-L96-D1024-E0_1-me 28%[====> ] 755.07M 56.1MB/s eta 34s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "-L96-D1024-E0_1-mem 28%[====> ] 767.07M 56.2MB/s eta 34s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "L96-D1024-E0_1-mem- 28%[====> ] 777.22M 54.7MB/s eta 33s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "96-D1024-E0_1-mem-c 29%[====> ] 788.64M 55.0MB/s eta 33s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "6-D1024-E0_1-mem-ct 29%[====> ] 801.82M 59.0MB/s eta 33s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "-D1024-E0_1-mem-ctx 30%[=====> ] 811.88M 57.4MB/s eta 33s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "D1024-E0_1-mem-ctx- 30%[=====> ] 824.06M 57.1MB/s eta 33s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "1024-E0_1-mem-ctx-5 31%[=====> ] 839.12M 56.6MB/s eta 32s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "024-E0_1-mem-ctx-51 31%[=====> ] 851.85M 57.1MB/s eta 32s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "24-E0_1-mem-ctx-512 32%[=====> ] 865.35M 56.9MB/s eta 32s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "4-E0_1-mem-ctx-512. 32%[=====> ] 877.59M 57.5MB/s eta 32s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "-E0_1-mem-ctx-512.p 32%[=====> ] 889.21M 58.6MB/s eta 32s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "E0_1-mem-ctx-512.pt 33%[=====> ] 902.22M 58.3MB/s eta 31s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "0_1-mem-ctx-512.pth 33%[=====> ] 914.63M 58.6MB/s eta 31s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "_1-mem-ctx-512.pth 34%[=====> ] 926.11M 57.7MB/s eta 31s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "1-mem-ctx-512.pth 34%[=====> ] 939.43M 58.6MB/s eta 31s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "-mem-ctx-512.pth 35%[======> ] 952.47M 59.3MB/s eta 31s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "mem-ctx-512.pth 35%[======> ] 964.43M 59.2MB/s eta 30s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "em-ctx-512.pth 36%[======> ] 977.88M 59.9MB/s eta 30s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "m-ctx-512.pth 36%[======> ] 988.32M 59.0MB/s eta 30s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "-ctx-512.pth 37%[======> ] 1000M 59.3MB/s eta 30s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "ctx-512.pth 37%[======> ] 1013M 59.5MB/s eta 30s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "tx-512.pth 38%[======> ] 1.00G 58.7MB/s eta 29s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "x-512.pth 38%[======> ] 1.02G 60.1MB/s eta 29s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "-512.pth 39%[======> ] 1.03G 59.6MB/s eta 29s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "512.pth 39%[======> ] 1.04G 58.8MB/s eta 29s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "12.pth 39%[======> ] 1.05G 59.1MB/s eta 29s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "2.pth 40%[=======> ] 1.06G 58.9MB/s eta 28s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - ".pth 40%[=======> ] 1.07G 58.1MB/s eta 28s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "pth 41%[=======> ] 1.08G 57.4MB/s eta 28s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "th 41%[=======> ] 1.09G 57.7MB/s eta 28s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "h 41%[=======> ] 1.10G 56.3MB/s eta 28s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " 42%[=======> ] 1.11G 55.3MB/s eta 27s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v 42%[=======> ] 1.12G 55.4MB/s eta 27s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5 43%[=======> ] 1.14G 57.6MB/s eta 27s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5- 43%[=======> ] 1.16G 60.1MB/s eta 27s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L 44%[=======> ] 1.17G 59.0MB/s eta 27s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L9 44%[=======> ] 1.17G 55.0MB/s eta 26s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96 44%[=======> ] 1.17G 52.1MB/s eta 26s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96- 45%[========> ] 1.18G 51.4MB/s eta 26s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96-D 45%[========> ] 1.20G 51.9MB/s eta 26s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96-D1 45%[========> ] 1.21G 51.4MB/s eta 26s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96-D10 46%[========> ] 1.22G 51.7MB/s eta 25s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96-D102 46%[========> ] 1.24G 52.4MB/s eta 25s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96-D1024 47%[========> ] 1.24G 52.0MB/s eta 25s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96-D1024- 47%[========> ] 1.25G 51.5MB/s eta 25s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96-D1024-E 47%[========> ] 1.26G 51.0MB/s eta 25s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96-D1024-E0 48%[========> ] 1.27G 50.5MB/s eta 25s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96-D1024-E0_ 48%[========> ] 1.28G 50.0MB/s eta 25s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96-D1024-E0_1 48%[========> ] 1.29G 49.4MB/s eta 25s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96-D1024-E0_1- 49%[========> ] 1.30G 46.8MB/s eta 25s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "v5-L96-D1024-E0_1-m 49%[========> ] 1.31G 47.6MB/s eta 25s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "5-L96-D1024-E0_1-me 50%[=========> ] 1.33G 48.1MB/s eta 24s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "-L96-D1024-E0_1-mem 50%[=========> ] 1.34G 51.3MB/s eta 24s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "L96-D1024-E0_1-mem- 51%[=========> ] 1.35G 55.1MB/s eta 24s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "96-D1024-E0_1-mem-c 51%[=========> ] 1.36G 54.6MB/s eta 24s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "6-D1024-E0_1-mem-ct 52%[=========> ] 1.37G 54.9MB/s eta 24s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "-D1024-E0_1-mem-ctx 52%[=========> ] 1.38G 55.9MB/s eta 22s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "D1024-E0_1-mem-ctx- 53%[=========> ] 1.40G 55.4MB/s eta 22s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "1024-E0_1-mem-ctx-5 53%[=========> ] 1.41G 55.2MB/s eta 22s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "024-E0_1-mem-ctx-51 54%[=========> ] 1.42G 56.7MB/s eta 22s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "24-E0_1-mem-ctx-512 54%[=========> ] 1.43G 56.5MB/s eta 22s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "4-E0_1-mem-ctx-512. 54%[=========> ] 1.45G 58.1MB/s eta 21s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "-E0_1-mem-ctx-512.p 55%[==========> ] 1.46G 60.3MB/s eta 21s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "E0_1-mem-ctx-512.pt 55%[==========> ] 1.47G 60.6MB/s eta 21s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "0_1-mem-ctx-512.pth 56%[==========> ] 1.48G 61.2MB/s eta 21s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "_1-mem-ctx-512.pth 56%[==========> ] 1.50G 60.8MB/s eta 21s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "1-mem-ctx-512.pth 57%[==========> ] 1.51G 59.9MB/s eta 20s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "-mem-ctx-512.pth 57%[==========> ] 1.52G 60.5MB/s eta 20s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "mem-ctx-512.pth 58%[==========> ] 1.53G 59.9MB/s eta 20s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "em-ctx-512.pth 58%[==========> ] 1.54G 59.8MB/s eta 20s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "m-ctx-512.pth 59%[==========> ] 1.55G 58.7MB/s eta 20s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "-ctx-512.pth 59%[==========> ] 1.57G 58.1MB/s eta 19s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "ctx-512.pth 60%[===========> ] 1.58G 58.8MB/s eta 19s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "tx-512.pth 60%[===========> ] 1.59G 59.6MB/s eta 19s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "x-512.pth 60%[===========> ] 1.60G 59.0MB/s eta 19s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "-512.pth 61%[===========> ] 1.62G 59.6MB/s eta 19s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "512.pth 61%[===========> ] 1.62G 59.3MB/s eta 18s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "12.pth 62%[===========> ] 1.64G 58.6MB/s eta 18s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "2.pth 62%[===========> ] 1.65G 58.9MB/s eta 18s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - ".pth 63%[===========> ] 1.66G 59.5MB/s eta 18s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "pth 63%[===========> ] 1.68G 58.7MB/s eta 18s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "th 64%[===========> ] 1.69G 58.6MB/s eta 17s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "h 64%[===========> ] 1.70G 58.8MB/s eta 17s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " 64%[===========> ] 1.71G 58.8MB/s eta 17s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v 65%[============> ] 1.72G 58.8MB/s eta 17s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5 65%[============> ] 1.73G 57.7MB/s eta 17s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5- 65%[============> ] 1.74G 56.0MB/s eta 16s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L 66%[============> ] 1.74G 52.9MB/s eta 16s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L9 66%[============> ] 1.75G 52.5MB/s eta 16s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96 66%[============> ] 1.76G 51.7MB/s eta 16s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96- 67%[============> ] 1.77G 51.3MB/s eta 16s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96-D 67%[============> ] 1.79G 52.2MB/s eta 15s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96-D1 68%[============> ] 1.80G 53.0MB/s eta 15s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96-D10 68%[============> ] 1.81G 52.9MB/s eta 15s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96-D102 69%[============> ] 1.82G 51.3MB/s eta 15s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96-D1024 69%[============> ] 1.83G 51.5MB/s eta 15s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96-D1024- 70%[=============> ] 1.85G 52.3MB/s eta 14s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96-D1024-E 70%[=============> ] 1.86G 52.5MB/s eta 14s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96-D1024-E0 71%[=============> ] 1.87G 53.5MB/s eta 14s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96-D1024-E0_ 71%[=============> ] 1.88G 53.6MB/s eta 14s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96-D1024-E0_1 71%[=============> ] 1.89G 53.4MB/s eta 14s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96-D1024-E0_1- 72%[=============> ] 1.90G 54.6MB/s eta 13s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "v5-L96-D1024-E0_1-m 72%[=============> ] 1.92G 58.0MB/s eta 13s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "5-L96-D1024-E0_1-me 73%[=============> ] 1.93G 58.7MB/s eta 13s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "-L96-D1024-E0_1-mem 73%[=============> ] 1.94G 59.9MB/s eta 13s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "L96-D1024-E0_1-mem- 74%[=============> ] 1.95G 60.0MB/s eta 13s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "96-D1024-E0_1-mem-c 74%[=============> ] 1.96G 59.1MB/s eta 12s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "6-D1024-E0_1-mem-ct 75%[==============> ] 1.97G 58.7MB/s eta 12s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "-D1024-E0_1-mem-ctx 75%[==============> ] 1.99G 58.8MB/s eta 12s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "D1024-E0_1-mem-ctx- 75%[==============> ] 2.00G 59.2MB/s eta 12s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "1024-E0_1-mem-ctx-5 76%[==============> ] 2.01G 60.0MB/s eta 12s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "024-E0_1-mem-ctx-51 76%[==============> ] 2.02G 59.3MB/s eta 11s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "24-E0_1-mem-ctx-512 77%[==============> ] 2.04G 60.0MB/s eta 11s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "4-E0_1-mem-ctx-512. 77%[==============> ] 2.05G 59.3MB/s eta 11s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "-E0_1-mem-ctx-512.p 78%[==============> ] 2.06G 59.9MB/s eta 11s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "E0_1-mem-ctx-512.pt 78%[==============> ] 2.07G 59.6MB/s eta 11s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "0_1-mem-ctx-512.pth 79%[==============> ] 2.09G 61.7MB/s eta 10s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "_1-mem-ctx-512.pth 79%[==============> ] 2.10G 60.7MB/s eta 10s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "1-mem-ctx-512.pth 80%[===============> ] 2.11G 60.4MB/s eta 10s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "-mem-ctx-512.pth 80%[===============> ] 2.12G 61.1MB/s eta 10s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "mem-ctx-512.pth 81%[===============> ] 2.13G 61.2MB/s eta 10s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "em-ctx-512.pth 81%[===============> ] 2.15G 61.6MB/s eta 9s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "m-ctx-512.pth 82%[===============> ] 2.16G 63.1MB/s eta 9s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "-ctx-512.pth 82%[===============> ] 2.17G 62.5MB/s eta 9s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "ctx-512.pth 82%[===============> ] 2.18G 61.3MB/s eta 9s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "tx-512.pth 83%[===============> ] 2.19G 61.4MB/s eta 9s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "x-512.pth 83%[===============> ] 2.20G 60.9MB/s eta 8s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "-512.pth 84%[===============> ] 2.22G 61.6MB/s eta 8s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "512.pth 84%[===============> ] 2.23G 61.2MB/s eta 8s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "12.pth 85%[================> ] 2.24G 61.4MB/s eta 8s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "2.pth 85%[================> ] 2.25G 61.3MB/s eta 8s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - ".pth 86%[================> ] 2.27G 61.3MB/s eta 6s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "pth 86%[================> ] 2.27G 59.1MB/s eta 6s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "th 86%[================> ] 2.29G 60.4MB/s eta 6s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "h 87%[================> ] 2.30G 58.9MB/s eta 6s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " 87%[================> ] 2.31G 58.9MB/s eta 6s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v 88%[================> ] 2.32G 59.2MB/s eta 6s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5 88%[================> ] 2.33G 59.3MB/s eta 6s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5- 88%[================> ] 2.34G 57.1MB/s eta 6s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L 89%[================> ] 2.35G 56.9MB/s eta 6s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L9 89%[================> ] 2.37G 57.3MB/s eta 6s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96 89%[================> ] 2.37G 53.8MB/s eta 5s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96- 90%[=================> ] 2.38G 53.6MB/s eta 5s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96-D 91%[=================> ] 2.40G 54.2MB/s eta 5s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96-D1 91%[=================> ] 2.41G 54.8MB/s eta 5s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96-D10 91%[=================> ] 2.42G 54.3MB/s eta 5s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96-D102 92%[=================> ] 2.43G 54.2MB/s eta 4s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96-D1024 92%[=================> ] 2.44G 54.5MB/s eta 4s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96-D1024- 93%[=================> ] 2.46G 55.5MB/s eta 4s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96-D1024-E 93%[=================> ] 2.47G 57.0MB/s eta 4s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96-D1024-E0 94%[=================> ] 2.48G 55.0MB/s eta 4s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96-D1024-E0_ 94%[=================> ] 2.49G 55.6MB/s eta 3s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96-D1024-E0_1 95%[==================> ] 2.50G 55.3MB/s eta 3s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - " v5-L96-D1024-E0_1- 95%[==================> ] 2.51G 56.0MB/s eta 3s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "v5-L96-D1024-E0_1-m 96%[==================> ] 2.53G 57.0MB/s eta 3s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "5-L96-D1024-E0_1-me 96%[==================> ] 2.53G 55.4MB/s eta 3s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "-L96-D1024-E0_1-mem 96%[==================> ] 2.54G 57.5MB/s eta 2s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "L96-D1024-E0_1-mem- 97%[==================> ] 2.55G 58.3MB/s eta 2s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "96-D1024-E0_1-mem-c 97%[==================> ] 2.56G 56.0MB/s eta 2s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "6-D1024-E0_1-mem-ct 97%[==================> ] 2.57G 54.8MB/s eta 2s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "-D1024-E0_1-mem-ctx 98%[==================> ] 2.58G 55.3MB/s eta 2s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "D1024-E0_1-mem-ctx- 98%[==================> ] 2.60G 57.0MB/s eta 1s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "1024-E0_1-mem-ctx-5 99%[==================> ] 2.61G 56.8MB/s eta 1s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "024-E0_1-mem-ctx-51 99%[==================> ] 2.63G 57.4MB/s eta 1s " - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "v5-L96-D1024-E0_1-m 100%[===================>] 2.63G 56.8MB/s in 47s \r\n", - "\r\n", - "2023-08-31 21:58:42 (57.3 MB/s) - ‘v5-L96-D1024-E0_1-mem-ctx-512.pth’ saved [2825978627/2825978627]\r\n", - "\r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "total 2.7G\r\n", - "drwxr-xr-x 2 root root 55 Aug 31 21:57 .\r\n", - "drwxr-xr-x 19 root root 4.0K Aug 31 21:57 ..\r\n", - "-rw-r--r-- 1 root root 2.7G Aug 30 15:41 v5-L96-D1024-E0_1-mem-ctx-512.pth\r\n" - ] - } - ], - "source": [ - "# Download the model directly (stop gap till HF sync issues is resolved)\n", - "!cd \"{TRAINER_DIR}\" && cd \"../model/\" && \\\n", - " wget -nc \"https://huggingface.co/rwkv-x-dev/rwkv-x-playground/resolve/main/experiment/rwkv-x-exp/v5-memory/{FILENAME_PREFIX}-mem-ctx-512.pth\"\n", - "\n", - "!cd \"{TRAINER_DIR}\" && cd \"../model/\" && \\\n", - " ls -alh ." - ] - }, - { - "cell_type": "markdown", - "id": "08cbb280", - "metadata": { - "papermill": { - "duration": 0.0134, - "end_time": "2023-08-31T21:58:42.553999", - "exception": false, - "start_time": "2023-08-31T21:58:42.540599", - "status": "completed" - }, - "tags": [] - }, - "source": [ - "## Tune 3 : Low ctx size (1024), memory training\n", - "\n", - "- Tune 3: Low ctx size (1024), Scaling up !" - ] - }, - { - "cell_type": "code", - "execution_count": 5, - "id": "b56747ca", - "metadata": { - "execution": { - "iopub.execute_input": "2023-08-31T21:58:42.583027Z", - "iopub.status.busy": "2023-08-31T21:58:42.582816Z", - "iopub.status.idle": "2023-08-31T21:58:43.139180Z", - "shell.execute_reply": "2023-08-31T21:58:43.138323Z" - }, - "papermill": { - "duration": 0.600143, - "end_time": "2023-08-31T21:58:43.167557", - "exception": false, - "start_time": "2023-08-31T21:58:42.567414", - "status": "completed" - }, - "tags": [] - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "## Generating word reptition dataset ##\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 2 max words, 400 samples - at ../dataset/word-2-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 5 max words, 400 samples - at ../dataset/gen-word-5-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 40 max words, 400 samples - at ../dataset/gen-word-40-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 15 max words, 400 samples - at ../dataset/gen-word-15-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 10 max words, 400 samples - at ../dataset/gen-word-10-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 652 samples (10 token repeat) - 40 max words - at ../dataset/shuffle-word-40-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 35 max words, 400 samples - at ../dataset/gen-word-35-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 590 samples (10 token repeat) - 45 max words - at ../dataset/shuffle-word-45-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 25 max words, 400 samples - at ../dataset/gen-word-25-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 1304 samples (10 token repeat) - 20 max words - at ../dataset/shuffle-word-20-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 55 max words, 800 samples - at ../dataset/gen-word-55-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 1062 samples (10 token repeat) - 25 max words - at ../dataset/shuffle-word-25-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 80 max words, 800 samples - at ../dataset/gen-word-80-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 1779 samples (10 token repeat) - 15 max words - at ../dataset/shuffle-word-15-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 2602 samples (10 token repeat) - 10 max words - at ../dataset/shuffle-word-10-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 877 samples (10 token repeat) - 30 max words - at ../dataset/shuffle-word-30-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 1056 samples (20 token repeat) - 50 max words - at ../dataset/shuffle-word-50-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 806 samples (20 token repeat) - 65 max words - at ../dataset/shuffle-word-65-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 60 max words, 800 samples - at ../dataset/gen-word-60-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 716 samples (20 token repeat) - 75 max words - at ../dataset/shuffle-word-75-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 50 max words, 800 samples - at ../dataset/gen-word-50-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 880 samples (20 token repeat) - 60 max words - at ../dataset/shuffle-word-60-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 948 samples (20 token repeat) - 55 max words - at ../dataset/shuffle-word-55-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 748 samples (20 token repeat) - 70 max words - at ../dataset/shuffle-word-70-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 380 samples (20 token repeat) - 115 max words - at ../dataset/shuffle-word-115-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 5578 samples (10 token repeat) - 5 max words - at ../dataset/shuffle-word-5-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 670 samples (20 token repeat) - 80 max words - at ../dataset/shuffle-word-80-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 65 max words, 800 samples - at ../dataset/gen-word-65-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 415 samples (20 token repeat) - 105 max words - at ../dataset/shuffle-word-105-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 30 max words, 400 samples - at ../dataset/gen-word-30-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 291 samples (20 token repeat) - 160 max words - at ../dataset/shuffle-word-160-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 345 samples (20 token repeat) - 130 max words - at ../dataset/shuffle-word-130-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 45 max words, 400 samples - at ../dataset/gen-word-45-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 20 max words, 400 samples - at ../dataset/gen-word-20-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 368 samples (20 token repeat) - 120 max words - at ../dataset/shuffle-word-120-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 564 samples (20 token repeat) - 95 max words - at ../dataset/shuffle-word-95-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 752 samples (10 token repeat) - 35 max words - at ../dataset/shuffle-word-35-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 537 samples (20 token repeat) - 100 max words - at ../dataset/shuffle-word-100-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 70 max words, 800 samples - at ../dataset/gen-word-70-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 358 samples (20 token repeat) - 125 max words - at ../dataset/shuffle-word-125-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 95 max words, 800 samples - at ../dataset/gen-word-95-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 105 max words, 800 samples - at ../dataset/gen-word-105-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 130 max words, 800 samples - at ../dataset/gen-word-130-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 85 max words, 800 samples - at ../dataset/gen-word-85-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 619 samples (20 token repeat) - 85 max words - at ../dataset/shuffle-word-85-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 203 samples (20 token repeat) - 215 max words - at ../dataset/shuffle-word-215-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 593 samples (20 token repeat) - 90 max words - at ../dataset/shuffle-word-90-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 100 max words, 800 samples - at ../dataset/gen-word-100-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 192 samples (20 token repeat) - 240 max words - at ../dataset/shuffle-word-240-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 141 samples (20 token repeat) - 395 max words - at ../dataset/shuffle-word-395-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 218 samples (20 token repeat) - 205 max words - at ../dataset/shuffle-word-205-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 208 samples (20 token repeat) - 210 max words - at ../dataset/shuffle-word-210-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 140 samples (20 token repeat) - 380 max words - at ../dataset/shuffle-word-380-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 117 samples (20 token repeat) - 430 max words - at ../dataset/shuffle-word-430-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 277 samples (20 token repeat) - 200 max words - at ../dataset/shuffle-word-200-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 125 max words, 800 samples - at ../dataset/gen-word-125-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 301 samples (20 token repeat) - 155 max words - at ../dataset/shuffle-word-155-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 197 samples (20 token repeat) - 235 max words - at ../dataset/shuffle-word-235-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 117 samples (20 token repeat) - 435 max words - at ../dataset/shuffle-word-435-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 180 max words, 800 samples - at ../dataset/gen-word-180-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 116 samples (20 token repeat) - 450 max words - at ../dataset/shuffle-word-450-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 120 samples (20 token repeat) - 420 max words - at ../dataset/shuffle-word-420-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 170 max words, 800 samples - at ../dataset/gen-word-170-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 139 samples (20 token repeat) - 370 max words - at ../dataset/shuffle-word-370-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 118 samples (20 token repeat) - 475 max words - at ../dataset/shuffle-word-475-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 140 samples (20 token repeat) - 390 max words - at ../dataset/shuffle-word-390-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 120 samples (20 token repeat) - 405 max words - at ../dataset/shuffle-word-405-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 100 samples (20 token repeat) - 510 max words - at ../dataset/shuffle-word-510-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 143 samples (20 token repeat) - 315 max words - at ../dataset/shuffle-word-315-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 142 samples (20 token repeat) - 320 max words - at ../dataset/shuffle-word-320-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 75 max words, 800 samples - at ../dataset/gen-word-75-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 118 samples (20 token repeat) - 485 max words - at ../dataset/shuffle-word-485-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 145 samples (20 token repeat) - 305 max words - at ../dataset/shuffle-word-305-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 115 samples (20 token repeat) - 465 max words - at ../dataset/shuffle-word-465-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 289 samples (20 token repeat) - 165 max words - at ../dataset/shuffle-word-165-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 100 samples (20 token repeat) - 540 max words - at ../dataset/shuffle-word-540-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 118 samples (20 token repeat) - 440 max words - at ../dataset/shuffle-word-440-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 140 samples (20 token repeat) - 335 max words - at ../dataset/shuffle-word-335-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 189 samples (20 token repeat) - 245 max words - at ../dataset/shuffle-word-245-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 200 samples (20 token repeat) - 225 max words - at ../dataset/shuffle-word-225-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 141 samples (20 token repeat) - 350 max words - at ../dataset/shuffle-word-350-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 100 samples (20 token repeat) - 515 max words - at ../dataset/shuffle-word-515-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 184 samples (20 token repeat) - 270 max words - at ../dataset/shuffle-word-270-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 90 max words, 800 samples - at ../dataset/gen-word-90-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 140 samples (20 token repeat) - 355 max words - at ../dataset/shuffle-word-355-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 278 samples (20 token repeat) - 180 max words - at ../dataset/shuffle-word-180-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 278 samples (20 token repeat) - 175 max words - at ../dataset/shuffle-word-175-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 145 max words, 800 samples - at ../dataset/gen-word-145-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 276 samples (20 token repeat) - 185 max words - at ../dataset/shuffle-word-185-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 143 samples (20 token repeat) - 400 max words - at ../dataset/shuffle-word-400-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 110 max words, 800 samples - at ../dataset/gen-word-110-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 287 samples (20 token repeat) - 170 max words - at ../dataset/shuffle-word-170-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 185 samples (20 token repeat) - 295 max words - at ../dataset/shuffle-word-295-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 141 samples (20 token repeat) - 345 max words - at ../dataset/shuffle-word-345-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 100 samples (20 token repeat) - 505 max words - at ../dataset/shuffle-word-505-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 145 samples (20 token repeat) - 325 max words - at ../dataset/shuffle-word-325-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 100 samples (20 token repeat) - 545 max words - at ../dataset/shuffle-word-545-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 118 samples (20 token repeat) - 425 max words - at ../dataset/shuffle-word-425-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 143 samples (20 token repeat) - 330 max words - at ../dataset/shuffle-word-330-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 200 samples (20 token repeat) - 220 max words - at ../dataset/shuffle-word-220-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 142 samples (20 token repeat) - 340 max words - at ../dataset/shuffle-word-340-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 100 samples (20 token repeat) - 520 max words - at ../dataset/shuffle-word-520-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 160 max words, 800 samples - at ../dataset/gen-word-160-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 398 samples (20 token repeat) - 110 max words - at ../dataset/shuffle-word-110-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 319 samples (20 token repeat) - 145 max words - at ../dataset/shuffle-word-145-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 188 samples (20 token repeat) - 250 max words - at ../dataset/shuffle-word-250-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 141 samples (20 token repeat) - 375 max words - at ../dataset/shuffle-word-375-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 99 samples (20 token repeat) - 535 max words - at ../dataset/shuffle-word-535-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 215 max words, 800 samples - at ../dataset/gen-word-215-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 189 samples (20 token repeat) - 255 max words - at ../dataset/shuffle-word-255-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 186 samples (20 token repeat) - 275 max words - at ../dataset/shuffle-word-275-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 186 samples (20 token repeat) - 290 max words - at ../dataset/shuffle-word-290-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 155 max words, 800 samples - at ../dataset/gen-word-155-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 100 samples (20 token repeat) - 530 max words - at ../dataset/shuffle-word-530-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 335 samples (20 token repeat) - 135 max words - at ../dataset/shuffle-word-135-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 117 samples (20 token repeat) - 445 max words - at ../dataset/shuffle-word-445-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 220 max words, 800 samples - at ../dataset/gen-word-220-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 305 samples (20 token repeat) - 150 max words - at ../dataset/shuffle-word-150-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 187 samples (20 token repeat) - 265 max words - at ../dataset/shuffle-word-265-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 200 samples (20 token repeat) - 230 max words - at ../dataset/shuffle-word-230-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 186 samples (20 token repeat) - 300 max words - at ../dataset/shuffle-word-300-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 225 max words, 800 samples - at ../dataset/gen-word-225-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 120 max words, 800 samples - at ../dataset/gen-word-120-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 270 samples (20 token repeat) - 195 max words - at ../dataset/shuffle-word-195-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 115 max words, 800 samples - at ../dataset/gen-word-115-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 140 samples (20 token repeat) - 360 max words - at ../dataset/shuffle-word-360-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 118 samples (20 token repeat) - 455 max words - at ../dataset/shuffle-word-455-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 274 samples (20 token repeat) - 190 max words - at ../dataset/shuffle-word-190-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 116 samples (20 token repeat) - 460 max words - at ../dataset/shuffle-word-460-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 183 samples (20 token repeat) - 280 max words - at ../dataset/shuffle-word-280-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 115 samples (20 token repeat) - 495 max words - at ../dataset/shuffle-word-495-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 180 samples (20 token repeat) - 285 max words - at ../dataset/shuffle-word-285-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 100 samples (20 token repeat) - 525 max words - at ../dataset/shuffle-word-525-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 120 samples (20 token repeat) - 415 max words - at ../dataset/shuffle-word-415-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 119 samples (20 token repeat) - 410 max words - at ../dataset/shuffle-word-410-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 140 max words, 800 samples - at ../dataset/gen-word-140-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 143 samples (20 token repeat) - 310 max words - at ../dataset/shuffle-word-310-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 324 samples (20 token repeat) - 140 max words - at ../dataset/shuffle-word-140-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 210 max words, 800 samples - at ../dataset/gen-word-210-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 205 max words, 800 samples - at ../dataset/gen-word-205-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 118 samples (20 token repeat) - 470 max words - at ../dataset/shuffle-word-470-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 250 max words, 800 samples - at ../dataset/gen-word-250-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 115 samples (20 token repeat) - 480 max words - at ../dataset/shuffle-word-480-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 140 samples (20 token repeat) - 385 max words - at ../dataset/shuffle-word-385-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 245 max words, 800 samples - at ../dataset/gen-word-245-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 165 max words, 800 samples - at ../dataset/gen-word-165-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 116 samples (20 token repeat) - 500 max words - at ../dataset/shuffle-word-500-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 115 samples (20 token repeat) - 490 max words - at ../dataset/shuffle-word-490-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 185 samples (20 token repeat) - 260 max words - at ../dataset/shuffle-word-260-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 150 max words, 800 samples - at ../dataset/gen-word-150-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 185 max words, 800 samples - at ../dataset/gen-word-185-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 135 max words, 800 samples - at ../dataset/gen-word-135-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 100 samples (20 token repeat) - 550 max words - at ../dataset/shuffle-word-550-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 200 max words, 800 samples - at ../dataset/gen-word-200-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 240 max words, 800 samples - at ../dataset/gen-word-240-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated a single JSONL file with 143 samples (20 token repeat) - 365 max words - at ../dataset/shuffle-word-365-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 330 max words, 800 samples - at ../dataset/gen-word-330-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 255 max words, 800 samples - at ../dataset/gen-word-255-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 350 max words, 800 samples - at ../dataset/gen-word-350-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 290 max words, 800 samples - at ../dataset/gen-word-290-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 345 max words, 800 samples - at ../dataset/gen-word-345-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 190 max words, 800 samples - at ../dataset/gen-word-190-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 295 max words, 800 samples - at ../dataset/gen-word-295-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 320 max words, 800 samples - at ../dataset/gen-word-320-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 415 max words, 800 samples - at ../dataset/gen-word-415-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 230 max words, 800 samples - at ../dataset/gen-word-230-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 395 max words, 800 samples - at ../dataset/gen-word-395-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 260 max words, 800 samples - at ../dataset/gen-word-260-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 265 max words, 800 samples - at ../dataset/gen-word-265-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 275 max words, 800 samples - at ../dataset/gen-word-275-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 175 max words, 800 samples - at ../dataset/gen-word-175-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 355 max words, 800 samples - at ../dataset/gen-word-355-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 195 max words, 800 samples - at ../dataset/gen-word-195-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 270 max words, 800 samples - at ../dataset/gen-word-270-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 370 max words, 800 samples - at ../dataset/gen-word-370-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 285 max words, 800 samples - at ../dataset/gen-word-285-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 235 max words, 800 samples - at ../dataset/gen-word-235-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 505 max words, 800 samples - at ../dataset/gen-word-505-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 365 max words, 800 samples - at ../dataset/gen-word-365-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 450 max words, 800 samples - at ../dataset/gen-word-450-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 280 max words, 800 samples - at ../dataset/gen-word-280-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 315 max words, 800 samples - at ../dataset/gen-word-315-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 300 max words, 800 samples - at ../dataset/gen-word-300-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 305 max words, 800 samples - at ../dataset/gen-word-305-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 385 max words, 800 samples - at ../dataset/gen-word-385-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 430 max words, 800 samples - at ../dataset/gen-word-430-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 360 max words, 800 samples - at ../dataset/gen-word-360-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 525 max words, 800 samples - at ../dataset/gen-word-525-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 340 max words, 800 samples - at ../dataset/gen-word-340-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 405 max words, 800 samples - at ../dataset/gen-word-405-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 420 max words, 800 samples - at ../dataset/gen-word-420-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 390 max words, 800 samples - at ../dataset/gen-word-390-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 495 max words, 800 samples - at ../dataset/gen-word-495-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 500 max words, 800 samples - at ../dataset/gen-word-500-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 375 max words, 800 samples - at ../dataset/gen-word-375-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 325 max words, 800 samples - at ../dataset/gen-word-325-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 520 max words, 800 samples - at ../dataset/gen-word-520-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 310 max words, 800 samples - at ../dataset/gen-word-310-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 410 max words, 800 samples - at ../dataset/gen-word-410-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 380 max words, 800 samples - at ../dataset/gen-word-380-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 460 max words, 800 samples - at ../dataset/gen-word-460-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 400 max words, 800 samples - at ../dataset/gen-word-400-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 470 max words, 800 samples - at ../dataset/gen-word-470-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 335 max words, 800 samples - at ../dataset/gen-word-335-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 530 max words, 800 samples - at ../dataset/gen-word-530-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 540 max words, 800 samples - at ../dataset/gen-word-540-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 485 max words, 800 samples - at ../dataset/gen-word-485-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 550 max words, 800 samples - at ../dataset/gen-word-550-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 435 max words, 800 samples - at ../dataset/gen-word-435-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 425 max words, 800 samples - at ../dataset/gen-word-425-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 455 max words, 800 samples - at ../dataset/gen-word-455-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 465 max words, 800 samples - at ../dataset/gen-word-465-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 510 max words, 800 samples - at ../dataset/gen-word-510-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 490 max words, 800 samples - at ../dataset/gen-word-490-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 445 max words, 800 samples - at ../dataset/gen-word-445-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 545 max words, 800 samples - at ../dataset/gen-word-545-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 480 max words, 800 samples - at ../dataset/gen-word-480-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 440 max words, 800 samples - at ../dataset/gen-word-440-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 475 max words, 800 samples - at ../dataset/gen-word-475-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 515 max words, 800 samples - at ../dataset/gen-word-515-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Generated JSONL file with - 535 max words, 800 samples - at ../dataset/gen-word-535-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "## Done ##\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "total 297M\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "drwxr-xr-x 2 root root 12K Aug 31 21:58 .\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "drwxr-xr-x 14 root root 302 Aug 31 21:58 ..\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 78K Aug 31 21:58 gen-word-10-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 858K Aug 31 21:58 gen-word-100-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 895K Aug 31 21:58 gen-word-105-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 936K Aug 31 21:58 gen-word-110-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 968K Aug 31 21:58 gen-word-115-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 1008K Aug 31 21:58 gen-word-120-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 1.1M Aug 31 21:58 gen-word-125-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 1.1M Aug 31 21:58 gen-word-130-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 1.2M Aug 31 21:58 gen-word-135-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 1.2M Aug 31 21:58 gen-word-140-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 1.2M Aug 31 21:58 gen-word-145-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 98K Aug 31 21:58 gen-word-15-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 1.3M Aug 31 21:58 gen-word-150-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 1.3M Aug 31 21:58 gen-word-155-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 1.3M Aug 31 21:58 gen-word-160-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 1.4M Aug 31 21:58 gen-word-165-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 1.4M Aug 31 21:58 gen-word-170-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 1.4M Aug 31 21:58 gen-word-175-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 1.5M Aug 31 21:58 gen-word-180-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 1.5M Aug 31 21:58 gen-word-185-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 1.6M Aug 31 21:58 gen-word-190-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 1.6M Aug 31 21:58 gen-word-195-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 118K Aug 31 21:58 gen-word-20-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 1.6M Aug 31 21:58 gen-word-200-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 1.7M Aug 31 21:58 gen-word-205-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 1.7M Aug 31 21:58 gen-word-210-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 1.7M Aug 31 21:58 gen-word-215-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 1.8M Aug 31 21:58 gen-word-220-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 1.8M Aug 31 21:58 gen-word-225-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 1.9M Aug 31 21:58 gen-word-230-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 1.9M Aug 31 21:58 gen-word-235-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 2.0M Aug 31 21:58 gen-word-240-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 2.0M Aug 31 21:58 gen-word-245-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 138K Aug 31 21:58 gen-word-25-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 2.0M Aug 31 21:58 gen-word-250-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 2.1M Aug 31 21:58 gen-word-255-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 2.1M Aug 31 21:58 gen-word-260-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 2.1M Aug 31 21:58 gen-word-265-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 2.2M Aug 31 21:58 gen-word-270-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 2.2M Aug 31 21:58 gen-word-275-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 2.2M Aug 31 21:58 gen-word-280-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 2.3M Aug 31 21:58 gen-word-285-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 2.3M Aug 31 21:58 gen-word-290-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 2.4M Aug 31 21:58 gen-word-295-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 156K Aug 31 21:58 gen-word-30-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 2.4M Aug 31 21:58 gen-word-300-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 2.5M Aug 31 21:58 gen-word-305-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 2.5M Aug 31 21:58 gen-word-310-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 2.5M Aug 31 21:58 gen-word-315-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 2.6M Aug 31 21:58 gen-word-320-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 2.6M Aug 31 21:58 gen-word-325-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 2.6M Aug 31 21:58 gen-word-330-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 2.7M Aug 31 21:58 gen-word-335-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 2.7M Aug 31 21:58 gen-word-340-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 2.7M Aug 31 21:58 gen-word-345-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 177K Aug 31 21:58 gen-word-35-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 2.8M Aug 31 21:58 gen-word-350-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 2.8M Aug 31 21:58 gen-word-355-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 2.9M Aug 31 21:58 gen-word-360-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 2.9M Aug 31 21:58 gen-word-365-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 2.9M Aug 31 21:58 gen-word-370-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 3.0M Aug 31 21:58 gen-word-375-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 3.0M Aug 31 21:58 gen-word-380-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 3.0M Aug 31 21:58 gen-word-385-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 3.1M Aug 31 21:58 gen-word-390-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 3.1M Aug 31 21:58 gen-word-395-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 196K Aug 31 21:58 gen-word-40-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 3.1M Aug 31 21:58 gen-word-400-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 3.2M Aug 31 21:58 gen-word-405-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 3.3M Aug 31 21:58 gen-word-410-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 3.3M Aug 31 21:58 gen-word-415-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 3.3M Aug 31 21:58 gen-word-420-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 3.3M Aug 31 21:58 gen-word-425-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 3.4M Aug 31 21:58 gen-word-430-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 3.4M Aug 31 21:58 gen-word-435-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 3.5M Aug 31 21:58 gen-word-440-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 3.5M Aug 31 21:58 gen-word-445-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 216K Aug 31 21:58 gen-word-45-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 3.5M Aug 31 21:58 gen-word-450-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 3.6M Aug 31 21:58 gen-word-455-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 3.6M Aug 31 21:58 gen-word-460-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 3.6M Aug 31 21:58 gen-word-465-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 3.7M Aug 31 21:58 gen-word-470-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 3.7M Aug 31 21:58 gen-word-475-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 3.8M Aug 31 21:58 gen-word-480-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 3.8M Aug 31 21:58 gen-word-485-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 3.8M Aug 31 21:58 gen-word-490-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 3.9M Aug 31 21:58 gen-word-495-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 59K Aug 31 21:58 gen-word-5-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 472K Aug 31 21:58 gen-word-50-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 3.9M Aug 31 21:58 gen-word-500-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 4.0M Aug 31 21:58 gen-word-505-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 4.0M Aug 31 21:58 gen-word-510-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 4.0M Aug 31 21:58 gen-word-515-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 4.1M Aug 31 21:58 gen-word-520-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 4.1M Aug 31 21:58 gen-word-525-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 4.2M Aug 31 21:58 gen-word-530-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 4.2M Aug 31 21:58 gen-word-535-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 4.2M Aug 31 21:58 gen-word-540-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 4.3M Aug 31 21:58 gen-word-545-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 509K Aug 31 21:58 gen-word-55-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 4.3M Aug 31 21:58 gen-word-550-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 545K Aug 31 21:58 gen-word-60-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 578K Aug 31 21:58 gen-word-65-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 624K Aug 31 21:58 gen-word-70-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 658K Aug 31 21:58 gen-word-75-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 710K Aug 31 21:58 gen-word-80-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 738K Aug 31 21:58 gen-word-85-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 772K Aug 31 21:58 gen-word-90-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 809K Aug 31 21:58 gen-word-95-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 523K Aug 31 21:58 shuffle-word-10-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 567K Aug 31 21:58 shuffle-word-100-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 557K Aug 31 21:58 shuffle-word-105-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 556K Aug 31 21:58 shuffle-word-110-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 551K Aug 31 21:58 shuffle-word-115-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 552K Aug 31 21:58 shuffle-word-120-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 555K Aug 31 21:58 shuffle-word-125-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 547K Aug 31 21:58 shuffle-word-130-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 547K Aug 31 21:58 shuffle-word-135-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 540K Aug 31 21:58 shuffle-word-140-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 547K Aug 31 21:58 shuffle-word-145-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 433K Aug 31 21:58 shuffle-word-15-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 544K Aug 31 21:58 shuffle-word-150-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 541K Aug 31 21:58 shuffle-word-155-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 541K Aug 31 21:58 shuffle-word-160-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 541K Aug 31 21:58 shuffle-word-165-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 545K Aug 31 21:58 shuffle-word-170-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 545K Aug 31 21:58 shuffle-word-175-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 541K Aug 31 21:58 shuffle-word-180-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 539K Aug 31 21:58 shuffle-word-185-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 540K Aug 31 21:58 shuffle-word-190-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 540K Aug 31 21:58 shuffle-word-195-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 393K Aug 31 21:58 shuffle-word-20-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 544K Aug 31 21:58 shuffle-word-200-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 537K Aug 31 21:58 shuffle-word-205-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 540K Aug 31 21:58 shuffle-word-210-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 537K Aug 31 21:58 shuffle-word-215-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 535K Aug 31 21:58 shuffle-word-220-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 532K Aug 31 21:58 shuffle-word-225-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 536K Aug 31 21:58 shuffle-word-230-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 534K Aug 31 21:58 shuffle-word-235-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 533K Aug 31 21:58 shuffle-word-240-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 533K Aug 31 21:58 shuffle-word-245-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 357K Aug 31 21:58 shuffle-word-25-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 534K Aug 31 21:58 shuffle-word-250-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 534K Aug 31 21:58 shuffle-word-255-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 534K Aug 31 21:58 shuffle-word-260-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 534K Aug 31 21:58 shuffle-word-265-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 532K Aug 31 21:58 shuffle-word-270-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 534K Aug 31 21:58 shuffle-word-275-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 533K Aug 31 21:58 shuffle-word-280-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 533K Aug 31 21:58 shuffle-word-285-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 535K Aug 31 21:58 shuffle-word-290-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 535K Aug 31 21:58 shuffle-word-295-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 349K Aug 31 21:58 shuffle-word-30-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 536K Aug 31 21:58 shuffle-word-300-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 532K Aug 31 21:58 shuffle-word-305-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 529K Aug 31 21:58 shuffle-word-310-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 532K Aug 31 21:58 shuffle-word-315-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 532K Aug 31 21:58 shuffle-word-320-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 532K Aug 31 21:58 shuffle-word-325-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 529K Aug 31 21:58 shuffle-word-330-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 526K Aug 31 21:58 shuffle-word-335-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 527K Aug 31 21:58 shuffle-word-340-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 529K Aug 31 21:58 shuffle-word-345-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 326K Aug 31 21:58 shuffle-word-35-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 528K Aug 31 21:58 shuffle-word-350-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 533K Aug 31 21:58 shuffle-word-355-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 530K Aug 31 21:58 shuffle-word-360-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 530K Aug 31 21:58 shuffle-word-365-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 530K Aug 31 21:58 shuffle-word-370-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 529K Aug 31 21:58 shuffle-word-375-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 531K Aug 31 21:58 shuffle-word-380-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 530K Aug 31 21:58 shuffle-word-385-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 531K Aug 31 21:58 shuffle-word-390-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 529K Aug 31 21:58 shuffle-word-395-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 320K Aug 31 21:58 shuffle-word-40-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 531K Aug 31 21:58 shuffle-word-400-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 528K Aug 31 21:58 shuffle-word-405-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 529K Aug 31 21:58 shuffle-word-410-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 524K Aug 31 21:58 shuffle-word-415-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 526K Aug 31 21:58 shuffle-word-420-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 525K Aug 31 21:58 shuffle-word-425-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 530K Aug 31 21:58 shuffle-word-430-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 526K Aug 31 21:58 shuffle-word-435-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 529K Aug 31 21:58 shuffle-word-440-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 528K Aug 31 21:58 shuffle-word-445-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 314K Aug 31 21:58 shuffle-word-45-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 527K Aug 31 21:58 shuffle-word-450-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 531K Aug 31 21:58 shuffle-word-455-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 526K Aug 31 21:58 shuffle-word-460-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 525K Aug 31 21:58 shuffle-word-465-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 527K Aug 31 21:58 shuffle-word-470-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 525K Aug 31 21:58 shuffle-word-475-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 530K Aug 31 21:58 shuffle-word-480-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 528K Aug 31 21:58 shuffle-word-485-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 525K Aug 31 21:58 shuffle-word-490-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 529K Aug 31 21:58 shuffle-word-495-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 814K Aug 31 21:58 shuffle-word-5-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 621K Aug 31 21:58 shuffle-word-50-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 530K Aug 31 21:58 shuffle-word-500-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 524K Aug 31 21:58 shuffle-word-505-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 528K Aug 31 21:58 shuffle-word-510-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 523K Aug 31 21:58 shuffle-word-515-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 531K Aug 31 21:58 shuffle-word-520-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 530K Aug 31 21:58 shuffle-word-525-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 527K Aug 31 21:58 shuffle-word-530-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 523K Aug 31 21:58 shuffle-word-535-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 524K Aug 31 21:58 shuffle-word-540-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 526K Aug 31 21:58 shuffle-word-545-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 597K Aug 31 21:58 shuffle-word-55-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 526K Aug 31 21:58 shuffle-word-550-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 603K Aug 31 21:58 shuffle-word-60-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 593K Aug 31 21:58 shuffle-word-65-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 580K Aug 31 21:58 shuffle-word-70-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 583K Aug 31 21:58 shuffle-word-75-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 574K Aug 31 21:58 shuffle-word-80-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 574K Aug 31 21:58 shuffle-word-85-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 571K Aug 31 21:58 shuffle-word-90-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 574K Aug 31 21:58 shuffle-word-95-count.jsonl\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "-rw-r--r-- 1 root root 49K Aug 31 21:58 word-2-count.jsonl\n" - ] - } - ], - "source": [ - "%%script bash\n", - "\n", - "########################################\n", - "# Generate the required jsonl dataset\n", - "########################################\n", - "\n", - "# Reset the dataset dir\n", - "mkdir -p ../dataset\n", - "rm -rf ../dataset/*.jsonl\n", - "\n", - "# Generate the various datasets\n", - "echo \"## Generating word reptition dataset ##\"\n", - "\n", - "#\n", - "# We reduce the training set for lower word count - and shift the focus upwards\n", - "#\n", - "python ../memory_script/gen_limited_prompt_completion_jsonl.py ../dataset/word-2-count.jsonl 2 400 &\n", - "for i in {5..45..5} \n", - "do\n", - " python ../memory_script/gen_limited_prompt_completion_jsonl.py ../dataset/gen-word-$i-count.jsonl $i 400 & \n", - " python ../memory_script/shuffle_limited_prompt_completion_jsonl.py ../dataset/shuffle-word-$i-count.jsonl $i 10 & \n", - "done\n", - "\n", - "#\n", - "# Ramping up the 50+ - 510 words dataset\n", - "# \n", - "for i in {50..550..5} \n", - "do\n", - " python ../memory_script/gen_limited_prompt_completion_jsonl.py ../dataset/gen-word-$i-count.jsonl $i 800 & \n", - " python ../memory_script/shuffle_limited_prompt_completion_jsonl.py ../dataset/shuffle-word-$i-count.jsonl $i 20 & \n", - "done\n", - "\n", - "wait\n", - "echo \"## Done ##\"\n", - "\n", - "ls -alh ../dataset/" - ] - }, - { - "cell_type": "code", - "execution_count": 6, - "id": "d333baca", - "metadata": { - "execution": { - "iopub.execute_input": "2023-08-31T21:58:43.238676Z", - "iopub.status.busy": "2023-08-31T21:58:43.238125Z", - "iopub.status.idle": "2023-09-01T02:53:33.810375Z", - "shell.execute_reply": "2023-09-01T02:53:33.808544Z" - }, - "papermill": { - "duration": 17690.609691, - "end_time": "2023-09-01T02:53:33.812814", - "exception": false, - "start_time": "2023-08-31T21:58:43.203123", - "status": "completed" - }, - "tags": [] - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Setting ds_accelerator to cuda (auto detect)\r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "[RWKV.model] Running RWKV model using 'torch-jit' with torch '2.0.1+cu118'\r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "/usr/local/lib/python3.11/dist-packages/lightning/pytorch/cli.py:484: UserWarning: LightningCLI's args parameter is intended to run from within Python like if it were from the command line. To prevent mistakes it is not recommended to provide both args and command line arguments, got: sys.argv[1:]=['fit', '-c', '/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/notebook/experiment/rwkv-x-exp/v5-memory/config-mem-template.yaml', '--trainer.logger.init_args.name=v5-L96-D1024-E0.1 - Mem-Tune ctx-1k (train-ctx=1k, deepspeed_stage_1)', '--trainer.strategy=deepspeed_stage_1', '--trainer.devices=auto', '--trainer.callbacks.init_args.dirpath=../checkpoint/v5-L96-D1024-E0_1-mem-ctx-1k/', '--model.lr_init=4e-4', '--model.lr_final=2e-4', '--data.max_token_size=1024', '--model.ctx_len=1024', '--model.bptt_learning_range=1', '--model.load_model=../model/v5-L96-D1024-E0_1-mem-ctx-512.pth'], args=['fit', '-c', '/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/notebook/experiment/rwkv-x-exp/v5-memory/config-mem-template.yaml', '--trainer.logger.init_args.name=v5-L96-D1024-E0.1 - Mem-Tune ctx-1k (train-ctx=1k, deepspeed_stage_1)', '--trainer.strategy=deepspeed_stage_1', '--trainer.devices=auto', '--trainer.callbacks.init_args.dirpath=../checkpoint/v5-L96-D1024-E0_1-mem-ctx-1k/', '--model.lr_init=4e-4', '--model.lr_final=2e-4', '--data.max_token_size=1024', '--model.ctx_len=1024', '--model.bptt_learning_range=1', '--model.load_model=../model/v5-L96-D1024-E0_1-mem-ctx-512.pth'].\r\n", - " rank_zero_warn(\r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "/usr/local/lib/python3.11/dist-packages/lightning/fabric/utilities/seed.py:39: UserWarning: No seed found, seed set to 552501025\r\n", - " rank_zero_warn(f\"No seed found, seed set to {seed}\")\r\n", - "Global seed set to 552501025\r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\u001b[34m\u001b[1mwandb\u001b[0m: Currently logged in as: \u001b[33mpicocreator\u001b[0m (\u001b[33mrwkv-x-dev\u001b[0m). Use \u001b[1m`wandb login --relogin`\u001b[0m to force relogin\r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\u001b[34m\u001b[1mwandb\u001b[0m: Tracking run with wandb version 0.15.9\r\n", - "\u001b[34m\u001b[1mwandb\u001b[0m: Run data is saved locally in \u001b[35m\u001b[1m./wandb/run-20230831_215849-y5kr73vx\u001b[0m\r\n", - "\u001b[34m\u001b[1mwandb\u001b[0m: Run \u001b[1m`wandb offline`\u001b[0m to turn off syncing.\r\n", - "\u001b[34m\u001b[1mwandb\u001b[0m: Syncing run \u001b[33mv5-L96-D1024-E0.1 - Mem-Tune ctx-1k (train-ctx=1k, deepspeed_stage_1)\u001b[0m\r\n", - "\u001b[34m\u001b[1mwandb\u001b[0m: ⭐️ View project at \u001b[34m\u001b[4mhttps://wandb.ai/rwkv-x-dev/RWKV-X-Experiments\u001b[0m\r\n", - "\u001b[34m\u001b[1mwandb\u001b[0m: 🚀 View run at \u001b[34m\u001b[4mhttps://wandb.ai/rwkv-x-dev/RWKV-X-Experiments/runs/y5kr73vx\u001b[0m\r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "/usr/local/lib/python3.11/dist-packages/lightning/fabric/connector.py:562: UserWarning: bf16 is supported for historical reasons but its usage is discouraged. Please set your precision to bf16-mixed instead!\r\n", - " rank_zero_warn(\r\n", - "GPU available: True (cuda), used: True\r\n", - "TPU available: False, using: 0 TPU cores\r\n", - "IPU available: False, using: 0 IPUs\r\n", - "HPU available: False, using: 0 HPUs\r\n", - "\r\n", - "\r\n", - "[RWKV.Trainer] Applying 'target_batch_size' with the following:\r\n", - " - target_batch_size: 256\r\n", - " - num_nodes: 1\r\n", - " - num_devices: 8\r\n", - " - accumulate_grad_batches: 32\r\n", - " - effective_batch_size: 256\r\n", - "\r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "Resolving data files: 0%| | 0/221 [00:00=12.1), as this is known to have freeze issues\r\n", - "# - The terms used in wandb / the progress bar can be confusing, see the github README.md for beter clarifications\r\n", - "# - When resuming from checkpoint, the estimated time is inaccurate\r\n", - "#\r\n", - "\r\n", - "[RWKV.model] Configuring optimizer with\r\n", - " - lr_init: 4.000e-04 (0.0004)\r\n", - " - lr_final: 2.000e-04 (0.0002)\r\n", - "\r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Detected CUDA files, patching ldflags\r\n", - "Emitting ninja build file /root/.cache/torch_extensions/py311_cu118/fused_adam/build.ninja...\r\n", - "Building extension module fused_adam...\r\n", - "Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)\r\n", - "ninja: no work to do.\r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Loading extension module fused_adam...\r\n", - "Time to load fused_adam op: 0.07133364677429199 seconds\r\n", - "Loading extension module fused_adam...\r\n", - "Loading extension module fused_adam...\r\n", - "Loading extension module fused_adam...\r\n", - "Time to load fused_adam op: 0.10167789459228516 seconds\r\n", - "Loading extension module fused_adam...\r\n", - "Time to load fused_adam op: 0.1017768383026123 seconds\r\n", - "Time to load fused_adam op: 0.10129690170288086 seconds\r\n", - "Loading extension module fused_adam...\r\n", - "Time to load fused_adam op: 0.1013040542602539 seconds\r\n", - "Time to load fused_adam op: 0.10144639015197754 seconds\r\n", - "Loading extension module fused_adam...\r\n", - "Time to load fused_adam op: 0.10147547721862793 seconds\r\n", - "Loading extension module fused_adam...\r\n", - "Time to load fused_adam op: 0.10201120376586914 seconds\r\n", - "Loading `train_dataloader` to estimate number of stepping batches.\r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "Emitting ninja build file /root/.cache/torch_extensions/py311_cu118/utils/build.ninja...\r\n", - "Building extension module utils...\r\n", - "Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)\r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "ninja: no work to do.\r\n", - "Loading extension module utils...\r\n", - "Time to load utils op: 0.0716085433959961 seconds\r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Loading extension module utils...\r\n", - "Loading extension module utils...\r\n", - "Time to load utils op: 0.1023414134979248 seconds\r\n", - "Loading extension module utils...\r\n", - "Loading extension module utils...\r\n", - "Time to load utils op: 0.10242319107055664 seconds\r\n", - "Time to load utils op: 0.10249185562133789 seconds\r\n", - "Time to load utils op: 0.10365796089172363 seconds\r\n", - "Loading extension module utils...\r\n", - "Time to load utils op: 0.10232424736022949 seconds\r\n", - "Loading extension module utils...\r\n", - "Time to load utils op: 0.10280680656433105 seconds\r\n", - "Loading extension module utils...\r\n", - "Time to load utils op: 0.10291290283203125 seconds\r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Rank: 7 partition count [8, 8] and sizes[(176584448, False), (384, False)] \r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Rank: 2 partition count [8, 8] and sizes[(176584448, False), (384, False)] \r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Rank: 5 partition count [8, 8] and sizes[(176584448, False), (384, False)] \r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Rank: 4 partition count [8, 8] and sizes[(176584448, False), (384, False)] \r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Rank: 0 partition count [8, 8] and sizes[(176584448, False), (384, False)] \r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Rank: 3 partition count [8, 8] and sizes[(176584448, False), (384, False)] \r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Rank: 1 partition count [8, 8] and sizes[(176584448, False), (384, False)] \r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Rank: 6 partition count [8, 8] and sizes[(176584448, False), (384, False)] \r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "No modifications detected for re-loaded extension module utils, skipping build step...\r\n", - "Loading extension module utils...\r\n", - "Time to load utils op: 0.0006060600280761719 seconds\r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "No modifications detected for re-loaded extension module utils, skipping build step...\r\n", - "Loading extension module utils...\r\n", - "No modifications detected for re-loaded extension module utils, skipping build step...\r\n", - "Loading extension module utils...\r\n", - "Time to load utils op: 0.0006058216094970703 seconds\r\n", - "Time to load utils op: 0.0006122589111328125 seconds\r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "No modifications detected for re-loaded extension module utils, skipping build step...\r\n", - "Loading extension module utils...\r\n", - "Time to load utils op: 0.0006463527679443359 seconds\r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "No modifications detected for re-loaded extension module utils, skipping build step...\r\n", - "Loading extension module utils...\r\n", - "Time to load utils op: 0.000640869140625 seconds\r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "No modifications detected for re-loaded extension module utils, skipping build step...\r\n", - "Loading extension module utils...\r\n", - "Time to load utils op: 0.0006463527679443359 seconds\r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "No modifications detected for re-loaded extension module utils, skipping build step...\r\n", - "Loading extension module utils...\r\n", - "Time to load utils op: 0.0006933212280273438 seconds\r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "No modifications detected for re-loaded extension module utils, skipping build step...\r\n", - "Loading extension module utils...\r\n", - "Time to load utils op: 0.0008387565612792969 seconds\r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r\n", - " | Name | Type | Params\r\n", - "--------------------------------------\r\n", - "0 | emb | Embedding | 51.5 M\r\n", - "1 | blocks | ModuleList | 1.3 B \r\n", - "2 | ln_out | LayerNorm | 2.0 K \r\n", - "3 | head | Linear | 51.5 M\r\n", - "--------------------------------------\r\n", - "1.4 B Trainable params\r\n", - "0 Non-trainable params\r\n", - "1.4 B Total params\r\n", - "5,650.715 Total estimated model params size (MB)\r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "Training: 0it [00:00, ?it/s]\r", - "Training: 0%| | 0/15526 [00:00=12.1), as this is known to have freeze issues\r\n", - "# - The terms used in wandb / the progress bar can be confusing, see the github README.md for beter clarifications\r\n", - "# - When resuming from checkpoint, the estimated time is inaccurate\r\n", - "#\r\n", - "\r\n", - "[RWKV.model] Configuring optimizer with\r\n", - " - lr_init: 3.000e-04 (0.0003)\r\n", - " - lr_final: 1.000e-04 (0.0001)\r\n", - "\r\n", - "LOCAL_RANK: 6 - CUDA_VISIBLE_DEVICES: [0,1,2,3,4,5,6,7]\r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "Detected CUDA files, patching ldflags\r\n", - "Emitting ninja build file /root/.cache/torch_extensions/py311_cu118/fused_adam/build.ninja...\r\n", - "Building extension module fused_adam...\r\n", - "Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)\r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "ninja: no work to do.\r\n", - "Loading extension module fused_adam...\r\n", - "Time to load fused_adam op: 0.06886816024780273 seconds\r\n", - "Loading extension module fused_adam...\r\n", - "Loading extension module fused_adam...\r\n", - "Time to load fused_adam op: 0.10180830955505371 seconds\r\n", - "Time to load fused_adam op: 0.10175633430480957 seconds\r\n", - "Loading extension module fused_adam...\r\n", - "Loading extension module fused_adam...\r\n", - "Loading extension module fused_adam...\r\n", - "Time to load fused_adam op: 0.10140442848205566 seconds\r\n", - "Time to load fused_adam op: 0.10190558433532715 seconds\r\n", - "Time to load fused_adam op: 0.10192203521728516 seconds\r\n", - "Loading `train_dataloader` to estimate number of stepping batches.\r\n", - "Loading extension module fused_adam...\r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Time to load fused_adam op: 0.10334587097167969 seconds\r\n", - "Loading extension module fused_adam...\r\n", - "Time to load fused_adam op: 0.10170531272888184 seconds\r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "Emitting ninja build file /root/.cache/torch_extensions/py311_cu118/utils/build.ninja...\r\n", - "Building extension module utils...\r\n", - "Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)\r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "ninja: no work to do.\r\n", - "Loading extension module utils...\r\n", - "Time to load utils op: 0.08224630355834961 seconds\r\n", - "Loading extension module utils...\r\n", - "Time to load utils op: 0.10256481170654297 seconds\r\n", - "Loading extension module utils...\r\n", - "Loading extension module utils...\r\n", - "Time to load utils op: 0.10213708877563477 seconds\r\n", - "Time to load utils op: 0.10302615165710449 seconds\r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Loading extension module utils...\r\n", - "Loading extension module utils...\r\n", - "Time to load utils op: 0.10284805297851562 seconds\r\n", - "Time to load utils op: 0.10296297073364258 seconds\r\n", - "Loading extension module utils...\r\n", - "Time to load utils op: 0.10295629501342773 seconds\r\n", - "Loading extension module utils...\r\n", - "Time to load utils op: 0.10236072540283203 seconds\r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Rank: 2 partition count [8, 8] and sizes[(176584448, False), (384, False)] \r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Rank: 1 partition count [8, 8] and sizes[(176584448, False), (384, False)] \r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Rank: 0 partition count [8, 8] and sizes[(176584448, False), (384, False)] \r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Rank: 6 partition count [8, 8] and sizes[(176584448, False), (384, False)] \r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Rank: 3 partition count [8, 8] and sizes[(176584448, False), (384, False)] \r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Rank: 5 partition count [8, 8] and sizes[(176584448, False), (384, False)] \r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Rank: 4 partition count [8, 8] and sizes[(176584448, False), (384, False)] \r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Rank: 7 partition count [8, 8] and sizes[(176584448, False), (384, False)] \r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "No modifications detected for re-loaded extension module utils, skipping build step...\r\n", - "Loading extension module utils...\r\n", - "Time to load utils op: 0.0009775161743164062 seconds\r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "No modifications detected for re-loaded extension module utils, skipping build step...\r\n", - "Loading extension module utils...\r\n", - "Time to load utils op: 0.000652313232421875 seconds\r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "No modifications detected for re-loaded extension module utils, skipping build step...\r\n", - "Loading extension module utils...\r\n", - "No modifications detected for re-loaded extension module utils, skipping build step...\r\n", - "Loading extension module utils...\r\n", - "No modifications detected for re-loaded extension module utils, skipping build step...\r\n", - "Loading extension module utils...\r\n", - "Time to load utils op: 0.0010175704956054688 seconds\r\n", - "Time to load utils op: 0.0006313323974609375 seconds\r\n", - "Time to load utils op: 0.0006577968597412109 seconds\r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "No modifications detected for re-loaded extension module utils, skipping build step...\r\n", - "Loading extension module utils...\r\n", - "Time to load utils op: 0.0011701583862304688 seconds\r\n", - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "No modifications detected for re-loaded extension module utils, skipping build step...\r\n", - "Loading extension module utils...\r\n", - "Time to load utils op: 0.0011792182922363281 seconds\r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", - "No modifications detected for re-loaded extension module utils, skipping build step...\r\n", - "Loading extension module utils...\r\n", - "Time to load utils op: 0.0008912086486816406 seconds\r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r\n", - " | Name | Type | Params\r\n", - "--------------------------------------\r\n", - "0 | emb | Embedding | 51.5 M\r\n", - "1 | blocks | ModuleList | 1.3 B \r\n", - "2 | ln_out | LayerNorm | 2.0 K \r\n", - "3 | head | Linear | 51.5 M\r\n", - "--------------------------------------\r\n", - "1.4 B Trainable params\r\n", - "0 Non-trainable params\r\n", - "1.4 B Total params\r\n", - "5,650.715 Total estimated model params size (MB)\r\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\r", - "Training: 0it [00:00, ?it/s]\r", - "Training: 0%| | 0/10070 [00:00