{ "cells": [ { "attachments": {}, "cell_type": "markdown", "id": "3c5b6775", "metadata": { "papermill": { "duration": 0.00287, "end_time": "2023-09-02T08:17:40.732250", "exception": false, "start_time": "2023-09-02T08:17:40.729380", "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": "7417031e", "metadata": { "papermill": { "duration": 0.001894, "end_time": "2023-09-02T08:17:40.736387", "exception": false, "start_time": "2023-09-02T08:17:40.734493", "status": "completed" }, "tags": [] }, "source": [ "# Basic Setup" ] }, { "cell_type": "code", "execution_count": 1, "id": "7dd08e5d", "metadata": { "execution": { "iopub.execute_input": "2023-09-02T08:17:40.740971Z", "iopub.status.busy": "2023-09-02T08:17:40.740793Z", "iopub.status.idle": "2023-09-02T08:17:41.465322Z", "shell.execute_reply": "2023-09-02T08:17:41.464404Z" }, "papermill": { "duration": 0.729083, "end_time": "2023-09-02T08:17:41.467263", "exception": false, "start_time": "2023-09-02T08:17:40.738180", "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": "2c269f4b", "metadata": { "execution": { "iopub.execute_input": "2023-09-02T08:17:41.472725Z", "iopub.status.busy": "2023-09-02T08:17:41.472531Z", "iopub.status.idle": "2023-09-02T08:17:44.315963Z", "shell.execute_reply": "2023-09-02T08:17:44.315112Z" }, "papermill": { "duration": 2.84766, "end_time": "2023-09-02T08:17:44.317345", "exception": false, "start_time": "2023-09-02T08:17:41.469685", "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": "4676bca0", "metadata": { "execution": { "iopub.execute_input": "2023-09-02T08:17:44.323118Z", "iopub.status.busy": "2023-09-02T08:17:44.322905Z", "iopub.status.idle": "2023-09-02T08:17:44.329820Z", "shell.execute_reply": "2023-09-02T08:17:44.329256Z" }, "papermill": { "duration": 0.011189, "end_time": "2023-09-02T08:17:44.331013", "exception": false, "start_time": "2023-09-02T08:17:44.319824", "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": "3891e174", "metadata": { "execution": { "iopub.execute_input": "2023-09-02T08:17:44.336458Z", "iopub.status.busy": "2023-09-02T08:17:44.335784Z", "iopub.status.idle": "2023-09-02T08:18:19.201904Z", "shell.execute_reply": "2023-09-02T08:18:19.201058Z" }, "papermill": { "duration": 34.870711, "end_time": "2023-09-02T08:18:19.203806", "exception": false, "start_time": "2023-09-02T08:17:44.333095", "status": "completed" }, "tags": [] }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "--2023-09-02 08:17:44-- https://huggingface.co/rwkv-x-dev/rwkv-x-playground/resolve/main/experiment/rwkv-x-exp/v5-memory/v5-L96-D1024-E0_1-mem-ctx-4k.pth\r\n", "Resolving huggingface.co (huggingface.co)... " ] }, { "name": "stdout", "output_type": "stream", "text": [ "18.165.122.120, 18.165.122.11, 18.165.122.101, ...\r\n", "Connecting to huggingface.co (huggingface.co)|18.165.122.120|: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/20fb328bd798a1e23967f80661a0b6a277f1d45ed2d90760cec68d32dfcbd516?response-content-disposition=attachment%3B+filename*%3DUTF-8%27%27v5-L96-D1024-E0_1-mem-ctx-4k.pth%3B+filename%3D%22v5-L96-D1024-E0_1-mem-ctx-4k.pth%22%3B&Expires=1693901864&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTY5MzkwMTg2NH19LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy5odWdnaW5nZmFjZS5jby9yZXBvcy8yZS9mNy8yZWY3ODU1NTIwMmFhOTJhYmRiZGY0NzZjZTNkMGZkNWE4YjE1ZjcyNDVlZGYwYjgwZDRkMzA1NzIzNTVmMzBkLzIwZmIzMjhiZDc5OGExZTIzOTY3ZjgwNjYxYTBiNmEyNzdmMWQ0NWVkMmQ5MDc2MGNlYzY4ZDMyZGZjYmQ1MTY%7EcmVzcG9uc2UtY29udGVudC1kaXNwb3NpdGlvbj0qIn1dfQ__&Signature=bnyjsA3VVJU4wI0tk8PC3pfpnk7Oa0u0pxhcIQ417SNdUho1CMMHokk1jUzmy7OHED7yBWU1RpBUEQRQ7OQRrrhmBagStwst2oNLKlhR7t3cT%7EiU5w3cYkf72VvJYN9bEN3xAgGPmCGZs1j4nZsgG2nn0ndiAHBRIgS3Wh2BCHQhozow-egs3DmLpoZBLLA73DJmGZtK66ASfb8CBCOW8vmkhon-Ca2D5ahZ3jiLdSuAdSFRpAopE31T4pAUOit5qjwhcIgkPkpQRhEDa2qSwSOj32tOJVr9QdzPSShTSh1%7EFZj4qsC5GDLnMWYVU4rSBeWIAgbSPreacy6HcTiNPA__&Key-Pair-Id=KVTP0A1DKRTAX [following]\r\n", "--2023-09-02 08:17:44-- https://cdn-lfs.huggingface.co/repos/2e/f7/2ef78555202aa92abdbdf476ce3d0fd5a8b15f7245edf0b80d4d30572355f30d/20fb328bd798a1e23967f80661a0b6a277f1d45ed2d90760cec68d32dfcbd516?response-content-disposition=attachment%3B+filename*%3DUTF-8%27%27v5-L96-D1024-E0_1-mem-ctx-4k.pth%3B+filename%3D%22v5-L96-D1024-E0_1-mem-ctx-4k.pth%22%3B&Expires=1693901864&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTY5MzkwMTg2NH19LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy5odWdnaW5nZmFjZS5jby9yZXBvcy8yZS9mNy8yZWY3ODU1NTIwMmFhOTJhYmRiZGY0NzZjZTNkMGZkNWE4YjE1ZjcyNDVlZGYwYjgwZDRkMzA1NzIzNTVmMzBkLzIwZmIzMjhiZDc5OGExZTIzOTY3ZjgwNjYxYTBiNmEyNzdmMWQ0NWVkMmQ5MDc2MGNlYzY4ZDMyZGZjYmQ1MTY%7EcmVzcG9uc2UtY29udGVudC1kaXNwb3NpdGlvbj0qIn1dfQ__&Signature=bnyjsA3VVJU4wI0tk8PC3pfpnk7Oa0u0pxhcIQ417SNdUho1CMMHokk1jUzmy7OHED7yBWU1RpBUEQRQ7OQRrrhmBagStwst2oNLKlhR7t3cT%7EiU5w3cYkf72VvJYN9bEN3xAgGPmCGZs1j4nZsgG2nn0ndiAHBRIgS3Wh2BCHQhozow-egs3DmLpoZBLLA73DJmGZtK66ASfb8CBCOW8vmkhon-Ca2D5ahZ3jiLdSuAdSFRpAopE31T4pAUOit5qjwhcIgkPkpQRhEDa2qSwSOj32tOJVr9QdzPSShTSh1%7EFZj4qsC5GDLnMWYVU4rSBeWIAgbSPreacy6HcTiNPA__&Key-Pair-Id=KVTP0A1DKRTAX\r\n", "Resolving cdn-lfs.huggingface.co (cdn-lfs.huggingface.co)... " ] }, { "name": "stdout", "output_type": "stream", "text": [ "108.156.22.7, 108.156.22.119, 108.156.22.122, ...\r\n", "Connecting to cdn-lfs.huggingface.co (cdn-lfs.huggingface.co)|108.156.22.7|:443... connected.\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "HTTP request sent, awaiting response... " ] }, { "name": "stdout", "output_type": "stream", "text": [ "200 OK\r\n", "Length: 2825976699 (2.6G) [binary/octet-stream]\r\n", "Saving to: ‘v5-L96-D1024-E0_1-mem-ctx-4k.pth’\r\n", "\r\n", "\r", " v5-L96-D1 0%[ ] 0 --.-KB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L96-D10 0%[ ] 8.45M 42.3MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L96-D102 0%[ ] 23.67M 59.1MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L96-D1024 1%[ ] 40.87M 66.5MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L96-D1024- 2%[ ] 58.70M 72.0MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L96-D1024-E 2%[ ] 71.97M 70.4MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L96-D1024-E0 3%[ ] 91.07M 74.5MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L96-D1024-E0_ 4%[ ] 107.95M 74.9MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L96-D1024-E0_1 4%[ ] 126.40M 77.0MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L96-D1024-E0_1- 5%[> ] 143.40M 77.8MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "v5-L96-D1024-E0_1-m 5%[> ] 157.45M 76.3MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "5-L96-D1024-E0_1-me 6%[> ] 175.71M 77.6MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-L96-D1024-E0_1-mem 7%[> ] 191.85M 77.8MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "L96-D1024-E0_1-mem- 7%[> ] 210.12M 78.8MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "96-D1024-E0_1-mem-c 8%[> ] 226.21M 78.6MB/s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "6-D1024-E0_1-mem-ct 9%[> ] 242.89M 78.9MB/s eta 31s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-D1024-E0_1-mem-ctx 9%[> ] 257.63M 78.6MB/s eta 31s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "D1024-E0_1-mem-ctx- 10%[=> ] 272.39M 81.2MB/s eta 31s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "1024-E0_1-mem-ctx-4 10%[=> ] 290.09M 81.6MB/s eta 31s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "024-E0_1-mem-ctx-4k 11%[=> ] 304.75M 80.3MB/s eta 31s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "24-E0_1-mem-ctx-4k. 11%[=> ] 320.18M 80.8MB/s eta 30s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "4-E0_1-mem-ctx-4k.p 12%[=> ] 336.66M 81.2MB/s eta 30s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-E0_1-mem-ctx-4k.pt 13%[=> ] 351.68M 80.5MB/s eta 30s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "E0_1-mem-ctx-4k.pth 13%[=> ] 369.76M 80.3MB/s eta 30s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "0_1-mem-ctx-4k.pth 14%[=> ] 387.95M 80.8MB/s eta 30s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "_1-mem-ctx-4k.pth 14%[=> ] 404.18M 81.2MB/s eta 29s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "1-mem-ctx-4k.pth 15%[==> ] 421.43M 82.1MB/s eta 29s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-mem-ctx-4k.pth 16%[==> ] 438.99M 82.2MB/s eta 29s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "mem-ctx-4k.pth 16%[==> ] 455.68M 82.1MB/s eta 29s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "em-ctx-4k.pth 17%[==> ] 473.01M 82.3MB/s eta 29s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "m-ctx-4k.pth 18%[==> ] 490.98M 83.1MB/s eta 27s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-ctx-4k.pth 18%[==> ] 507.20M 82.4MB/s eta 27s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "ctx-4k.pth 19%[==> ] 526.38M 84.1MB/s eta 27s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "tx-4k.pth 20%[===> ] 543.79M 84.7MB/s eta 27s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "x-4k.pth 20%[===> ] 561.04M 84.2MB/s eta 27s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-4k.pth 21%[===> ] 577.79M 85.6MB/s eta 26s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "4k.pth 22%[===> ] 596.59M 86.7MB/s eta 26s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "k.pth 22%[===> ] 613.84M 87.0MB/s eta 26s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", ".pth 23%[===> ] 627.67M 85.6MB/s eta 26s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "pth 23%[===> ] 644.28M 85.5MB/s eta 26s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "th 24%[===> ] 659.18M 84.5MB/s eta 25s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "h 25%[====> ] 676.73M 84.5MB/s eta 25s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 25%[====> ] 693.28M 84.7MB/s eta 25s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v 26%[====> ] 709.40M 83.8MB/s eta 25s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5 26%[====> ] 725.10M 83.1MB/s eta 25s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5- 27%[====> ] 740.41M 82.4MB/s eta 24s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L 28%[====> ] 757.51M 81.8MB/s eta 24s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L9 28%[====> ] 775.08M 81.9MB/s eta 24s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L96 29%[====> ] 792.10M 81.9MB/s eta 24s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L96- 30%[=====> ] 809.64M 82.6MB/s eta 24s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L96-D 30%[=====> ] 826.48M 81.6MB/s eta 23s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L96-D1 31%[=====> ] 840.59M 80.9MB/s eta 23s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L96-D10 31%[=====> ] 854.87M 80.1MB/s eta 23s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L96-D102 32%[=====> ] 865.43M 78.0MB/s eta 23s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L96-D1024 32%[=====> ] 878.40M 77.3MB/s eta 23s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L96-D1024- 33%[=====> ] 892.03M 76.4MB/s eta 23s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L96-D1024-E 33%[=====> ] 906.48M 76.3MB/s eta 23s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L96-D1024-E0 34%[=====> ] 923.51M 76.7MB/s eta 23s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L96-D1024-E0_ 34%[=====> ] 941.87M 77.1MB/s eta 23s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L96-D1024-E0_1 35%[======> ] 958.91M 77.2MB/s eta 23s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L96-D1024-E0_1- 36%[======> ] 975.34M 77.0MB/s eta 21s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "v5-L96-D1024-E0_1-m 36%[======> ] 990.92M 77.6MB/s eta 21s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "5-L96-D1024-E0_1-me 37%[======> ] 1001M 75.0MB/s eta 21s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-L96-D1024-E0_1-mem 37%[======> ] 1006M 71.4MB/s eta 21s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "L96-D1024-E0_1-mem- 37%[======> ] 1023M 70.7MB/s eta 21s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "96-D1024-E0_1-mem-c 38%[======> ] 1.02G 71.4MB/s eta 21s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "6-D1024-E0_1-mem-ct 39%[======> ] 1.03G 71.8MB/s eta 21s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-D1024-E0_1-mem-ctx 39%[======> ] 1.05G 73.1MB/s eta 21s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "D1024-E0_1-mem-ctx- 40%[=======> ] 1.07G 73.2MB/s eta 21s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "1024-E0_1-mem-ctx-4 41%[=======> ] 1.08G 75.9MB/s eta 21s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "024-E0_1-mem-ctx-4k 41%[=======> ] 1.10G 77.0MB/s eta 20s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "24-E0_1-mem-ctx-4k. 42%[=======> ] 1.12G 79.0MB/s eta 20s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "4-E0_1-mem-ctx-4k.p 43%[=======> ] 1.13G 78.6MB/s eta 20s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-E0_1-mem-ctx-4k.pt 43%[=======> ] 1.15G 79.1MB/s eta 20s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "E0_1-mem-ctx-4k.pth 44%[=======> ] 1.17G 79.1MB/s eta 20s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "0_1-mem-ctx-4k.pth 45%[========> ] 1.19G 78.5MB/s eta 19s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "_1-mem-ctx-4k.pth 45%[========> ] 1.20G 78.5MB/s eta 19s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "1-mem-ctx-4k.pth 46%[========> ] 1.22G 79.6MB/s eta 19s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-mem-ctx-4k.pth 46%[========> ] 1.24G 83.2MB/s eta 19s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "mem-ctx-4k.pth 47%[========> ] 1.25G 85.4MB/s eta 19s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "em-ctx-4k.pth 48%[========> ] 1.27G 85.5MB/s eta 17s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "m-ctx-4k.pth 48%[========> ] 1.29G 84.8MB/s eta 17s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-ctx-4k.pth 49%[========> ] 1.30G 85.6MB/s eta 17s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "ctx-4k.pth 50%[=========> ] 1.32G 85.4MB/s eta 17s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "tx-4k.pth 50%[=========> ] 1.34G 86.1MB/s eta 17s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "x-4k.pth 51%[=========> ] 1.36G 84.9MB/s eta 16s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-4k.pth 52%[=========> ] 1.37G 83.3MB/s eta 16s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "4k.pth 52%[=========> ] 1.39G 83.3MB/s eta 16s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "k.pth 53%[=========> ] 1.41G 83.3MB/s eta 16s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", ".pth 54%[=========> ] 1.42G 82.9MB/s eta 16s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "pth 54%[=========> ] 1.44G 83.4MB/s eta 15s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "th 55%[==========> ] 1.46G 83.0MB/s eta 15s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "h 56%[==========> ] 1.47G 82.7MB/s eta 15s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 56%[==========> ] 1.49G 81.8MB/s eta 15s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v 57%[==========> ] 1.51G 82.7MB/s eta 15s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5 57%[==========> ] 1.53G 83.2MB/s eta 14s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5- 58%[==========> ] 1.54G 82.7MB/s eta 14s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L 59%[==========> ] 1.56G 82.6MB/s eta 14s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L9 59%[==========> ] 1.57G 81.7MB/s eta 14s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L96 60%[===========> ] 1.59G 82.8MB/s eta 14s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L96- 61%[===========> ] 1.61G 83.0MB/s eta 13s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L96-D 61%[===========> ] 1.63G 82.9MB/s eta 13s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L96-D1 62%[===========> ] 1.65G 83.9MB/s eta 13s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L96-D10 63%[===========> ] 1.66G 85.0MB/s eta 13s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L96-D102 63%[===========> ] 1.68G 84.4MB/s eta 13s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L96-D1024 64%[===========> ] 1.70G 84.5MB/s eta 12s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L96-D1024- 65%[============> ] 1.71G 85.4MB/s eta 12s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L96-D1024-E 65%[============> ] 1.73G 85.8MB/s eta 12s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L96-D1024-E0 66%[============> ] 1.75G 86.0MB/s eta 12s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L96-D1024-E0_ 67%[============> ] 1.76G 84.8MB/s eta 12s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L96-D1024-E0_1 67%[============> ] 1.77G 82.0MB/s eta 11s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L96-D1024-E0_1- 67%[============> ] 1.79G 81.3MB/s eta 11s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "v5-L96-D1024-E0_1-m 68%[============> ] 1.79G 77.4MB/s eta 11s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "5-L96-D1024-E0_1-me 68%[============> ] 1.80G 76.1MB/s eta 11s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-L96-D1024-E0_1-mem 68%[============> ] 1.81G 74.0MB/s eta 11s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "L96-D1024-E0_1-mem- 69%[============> ] 1.83G 72.6MB/s eta 10s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "96-D1024-E0_1-mem-c 70%[=============> ] 1.85G 72.8MB/s eta 10s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "6-D1024-E0_1-mem-ct 70%[=============> ] 1.86G 72.5MB/s eta 10s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-D1024-E0_1-mem-ctx 71%[=============> ] 1.88G 71.6MB/s eta 10s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "D1024-E0_1-mem-ctx- 72%[=============> ] 1.89G 72.0MB/s eta 10s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "1024-E0_1-mem-ctx-4 72%[=============> ] 1.91G 72.3MB/s eta 9s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "024-E0_1-mem-ctx-4k 73%[=============> ] 1.93G 72.5MB/s eta 9s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "24-E0_1-mem-ctx-4k. 73%[=============> ] 1.94G 72.2MB/s eta 9s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "4-E0_1-mem-ctx-4k.p 74%[=============> ] 1.96G 71.5MB/s eta 9s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-E0_1-mem-ctx-4k.pt 75%[==============> ] 1.97G 70.5MB/s eta 9s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "E0_1-mem-ctx-4k.pth 75%[==============> ] 1.99G 72.3MB/s eta 8s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "0_1-mem-ctx-4k.pth 76%[==============> ] 2.01G 73.9MB/s eta 8s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "_1-mem-ctx-4k.pth 76%[==============> ] 2.02G 73.8MB/s eta 8s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "1-mem-ctx-4k.pth 77%[==============> ] 2.04G 79.5MB/s eta 8s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-mem-ctx-4k.pth 78%[==============> ] 2.05G 79.3MB/s eta 8s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "mem-ctx-4k.pth 78%[==============> ] 2.07G 80.6MB/s eta 7s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "em-ctx-4k.pth 79%[==============> ] 2.08G 79.4MB/s eta 7s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "m-ctx-4k.pth 79%[==============> ] 2.10G 79.7MB/s eta 7s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-ctx-4k.pth 80%[===============> ] 2.12G 80.6MB/s eta 7s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "ctx-4k.pth 81%[===============> ] 2.13G 80.3MB/s eta 7s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "tx-4k.pth 81%[===============> ] 2.15G 80.4MB/s eta 6s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "x-4k.pth 82%[===============> ] 2.17G 79.9MB/s eta 6s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-4k.pth 82%[===============> ] 2.18G 78.9MB/s eta 6s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "4k.pth 83%[===============> ] 2.20G 79.9MB/s eta 6s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "k.pth 84%[===============> ] 2.21G 80.1MB/s eta 6s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", ".pth 84%[===============> ] 2.23G 78.9MB/s eta 5s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "pth 85%[================> ] 2.24G 78.7MB/s eta 5s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "th 85%[================> ] 2.26G 78.7MB/s eta 5s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "h 86%[================> ] 2.27G 79.2MB/s eta 5s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 87%[================> ] 2.29G 79.7MB/s eta 5s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v 87%[================> ] 2.31G 79.9MB/s eta 4s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5 88%[================> ] 2.32G 80.5MB/s eta 4s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5- 88%[================> ] 2.34G 81.6MB/s eta 4s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L 89%[================> ] 2.36G 80.4MB/s eta 4s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L9 90%[=================> ] 2.37G 79.3MB/s eta 4s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L96 90%[=================> ] 2.39G 79.5MB/s eta 3s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L96- 91%[=================> ] 2.40G 79.5MB/s eta 3s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L96-D 92%[=================> ] 2.42G 79.8MB/s eta 3s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L96-D1 92%[=================> ] 2.44G 79.4MB/s eta 3s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L96-D10 93%[=================> ] 2.45G 79.8MB/s eta 3s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L96-D102 93%[=================> ] 2.46G 78.4MB/s eta 2s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L96-D1024 94%[=================> ] 2.48G 80.3MB/s eta 2s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L96-D1024- 94%[=================> ] 2.50G 80.0MB/s eta 2s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L96-D1024-E 95%[==================> ] 2.51G 79.2MB/s eta 2s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L96-D1024-E0 95%[==================> ] 2.53G 77.4MB/s eta 2s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L96-D1024-E0_ 96%[==================> ] 2.54G 77.6MB/s eta 1s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L96-D1024-E0_1 97%[==================> ] 2.56G 78.4MB/s eta 1s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " v5-L96-D1024-E0_1- 97%[==================> ] 2.57G 74.5MB/s eta 1s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "v5-L96-D1024-E0_1-m 97%[==================> ] 2.58G 73.8MB/s eta 1s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "5-L96-D1024-E0_1-me 98%[==================> ] 2.59G 73.5MB/s eta 1s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "-L96-D1024-E0_1-mem 98%[==================> ] 2.60G 72.5MB/s eta 0s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "L96-D1024-E0_1-mem- 99%[==================> ] 2.62G 72.3MB/s eta 0s " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "v5-L96-D1024-E0_1-m 100%[===================>] 2.63G 72.1MB/s in 34s \r\n", "\r\n", "2023-09-02 08:18:18 (79.2 MB/s) - ‘v5-L96-D1024-E0_1-mem-ctx-4k.pth’ saved [2825976699/2825976699]\r\n", "\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "total 2.7G\r\n", "drwxr-xr-x 2 root root 54 Sep 2 08:17 .\r\n", "drwxr-xr-x 19 root root 4.0K Sep 2 08:17 ..\r\n", "-rw-r--r-- 1 root root 2.7G Sep 2 05:37 v5-L96-D1024-E0_1-mem-ctx-4k.pth\r\n" ] } ], "source": [ "# Download the model directly (stop gap till HF sync issues is resolved)\n", "!cd \"{TRAINER_DIR}\" && cd \"../model/\" && \\\n", " wget -nc \"https://huggingface.co/rwkv-x-dev/rwkv-x-playground/resolve/main/experiment/rwkv-x-exp/v5-memory/{FILENAME_PREFIX}-mem-ctx-4k.pth\"\n", "\n", "!cd \"{TRAINER_DIR}\" && cd \"../model/\" && \\\n", " ls -alh ." ] }, { "cell_type": "markdown", "id": "477caa1a", "metadata": { "papermill": { "duration": 0.010045, "end_time": "2023-09-02T08:18:19.226002", "exception": false, "start_time": "2023-09-02T08:18:19.215957", "status": "completed" }, "tags": [] }, "source": [ "## Tune 6 : Ramping up the ctx size (8192), memory training\n", "\n", "- Tune 6: Large ctx size (8192), Scaling up!" ] }, { "cell_type": "code", "execution_count": 5, "id": "60b9e5c0", "metadata": { "execution": { "iopub.execute_input": "2023-09-02T08:18:19.250836Z", "iopub.status.busy": "2023-09-02T08:18:19.250263Z", "iopub.status.idle": "2023-09-02T08:18:26.397768Z", "shell.execute_reply": "2023-09-02T08:18:26.397070Z" }, "papermill": { "duration": 7.24077, "end_time": "2023-09-02T08:18:26.476912", "exception": false, "start_time": "2023-09-02T08:18:19.236142", "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, 50 samples - at ../dataset/word-2-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 45 max words, 50 samples - at ../dataset/gen-word-45-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 25 max words, 50 samples - at ../dataset/gen-word-25-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 85 samples (1 token repeat) - 30 max words - at ../dataset/shuffle-word-30-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 30 max words, 50 samples - at ../dataset/gen-word-30-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 35 max words, 50 samples - at ../dataset/gen-word-35-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 20 max words, 50 samples - at ../dataset/gen-word-20-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 77 samples (1 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 174 samples (1 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 65 samples (1 token repeat) - 40 max words - at ../dataset/shuffle-word-40-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 107 samples (1 token repeat) - 25 max words - at ../dataset/shuffle-word-25-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 40 max words, 50 samples - at ../dataset/gen-word-40-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 5 max words, 50 samples - at ../dataset/gen-word-5-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 49 samples (1 token repeat) - 55 max words - at ../dataset/shuffle-word-55-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 60 max words, 50 samples - at ../dataset/gen-word-60-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 53 samples (1 token repeat) - 50 max words - at ../dataset/shuffle-word-50-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 10 max words, 50 samples - at ../dataset/gen-word-10-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 59 samples (1 token repeat) - 45 max words - at ../dataset/shuffle-word-45-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 15 max words, 50 samples - at ../dataset/gen-word-15-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 55 max words, 50 samples - at ../dataset/gen-word-55-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 75 max words, 50 samples - at ../dataset/gen-word-75-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 41 samples (1 token repeat) - 65 max words - at ../dataset/shuffle-word-65-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 50 max words, 50 samples - at ../dataset/gen-word-50-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 131 samples (1 token repeat) - 20 max words - at ../dataset/shuffle-word-20-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 42 samples (1 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 557 samples (1 token repeat) - 5 max words - at ../dataset/shuffle-word-5-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 259 samples (1 token repeat) - 10 max words - at ../dataset/shuffle-word-10-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 90 max words, 50 samples - at ../dataset/gen-word-90-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 70 max words, 50 samples - at ../dataset/gen-word-70-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 28 samples (1 token repeat) - 90 max words - at ../dataset/shuffle-word-90-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 65 max words, 50 samples - at ../dataset/gen-word-65-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 38 samples (1 token repeat) - 70 max words - at ../dataset/shuffle-word-70-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 36 samples (1 token repeat) - 75 max words - at ../dataset/shuffle-word-75-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 28 samples (1 token repeat) - 95 max words - at ../dataset/shuffle-word-95-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 15 samples (1 token repeat) - 165 max words - at ../dataset/shuffle-word-165-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 15 samples (1 token repeat) - 155 max words - at ../dataset/shuffle-word-155-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 80 max words, 50 samples - at ../dataset/gen-word-80-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 150 max words, 50 samples - at ../dataset/gen-word-150-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 17 samples (1 token repeat) - 135 max words - at ../dataset/shuffle-word-135-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 330 max words, 50 samples - at ../dataset/gen-word-330-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 14 samples (1 token repeat) - 190 max words - at ../dataset/shuffle-word-190-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 9 samples (1 token repeat) - 265 max words - at ../dataset/shuffle-word-265-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 14 samples (1 token repeat) - 175 max words - at ../dataset/shuffle-word-175-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 21 samples (1 token repeat) - 105 max words - at ../dataset/shuffle-word-105-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 6 samples (1 token repeat) - 500 max words - at ../dataset/shuffle-word-500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 180 max words, 50 samples - at ../dataset/gen-word-180-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 100 max words, 50 samples - at ../dataset/gen-word-100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 105 max words, 50 samples - at ../dataset/gen-word-105-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 265 max words, 50 samples - at ../dataset/gen-word-265-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 280 max words, 50 samples - at ../dataset/gen-word-280-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 85 max words, 50 samples - at ../dataset/gen-word-85-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 18 samples (1 token repeat) - 120 max words - at ../dataset/shuffle-word-120-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 18 samples (1 token repeat) - 125 max words - at ../dataset/shuffle-word-125-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 140 max words, 50 samples - at ../dataset/gen-word-140-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 160 max words, 50 samples - at ../dataset/gen-word-160-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 7 samples (1 token repeat) - 310 max words - at ../dataset/shuffle-word-310-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 7 samples (1 token repeat) - 305 max words - at ../dataset/shuffle-word-305-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 390 max words, 50 samples - at ../dataset/gen-word-390-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 230 max words, 50 samples - at ../dataset/gen-word-230-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 225 max words, 50 samples - at ../dataset/gen-word-225-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 175 max words, 50 samples - at ../dataset/gen-word-175-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 190 max words, 50 samples - at ../dataset/gen-word-190-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 35 samples (1 token repeat) - 80 max words - at ../dataset/shuffle-word-80-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 14 samples (1 token repeat) - 160 max words - at ../dataset/shuffle-word-160-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 360 max words, 50 samples - at ../dataset/gen-word-360-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 9 samples (1 token repeat) - 290 max words - at ../dataset/shuffle-word-290-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 10 samples (1 token repeat) - 220 max words - at ../dataset/shuffle-word-220-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 315 max words, 50 samples - at ../dataset/gen-word-315-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 195 max words, 50 samples - at ../dataset/gen-word-195-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 185 max words, 50 samples - at ../dataset/gen-word-185-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 165 max words, 50 samples - at ../dataset/gen-word-165-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 5 samples (1 token repeat) - 550 max words - at ../dataset/shuffle-word-550-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 11 samples (1 token repeat) - 205 max words - at ../dataset/shuffle-word-205-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 515 max words, 50 samples - at ../dataset/gen-word-515-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 16 samples (1 token repeat) - 140 max words - at ../dataset/shuffle-word-140-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 170 max words, 50 samples - at ../dataset/gen-word-170-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 6 samples (1 token repeat) - 435 max words - at ../dataset/shuffle-word-435-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 11 samples (1 token repeat) - 210 max words - at ../dataset/shuffle-word-210-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 325 max words, 50 samples - at ../dataset/gen-word-325-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 250 max words, 50 samples - at ../dataset/gen-word-250-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 7 samples (1 token repeat) - 315 max words - at ../dataset/shuffle-word-315-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 9 samples (1 token repeat) - 300 max words - at ../dataset/shuffle-word-300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 5 samples (1 token repeat) - 570 max words - at ../dataset/shuffle-word-570-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 17 samples (1 token repeat) - 130 max words - at ../dataset/shuffle-word-130-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 20 samples (1 token repeat) - 110 max words - at ../dataset/shuffle-word-110-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 5 samples (1 token repeat) - 525 max words - at ../dataset/shuffle-word-525-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 14 samples (1 token repeat) - 200 max words - at ../dataset/shuffle-word-200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 320 max words, 50 samples - at ../dataset/gen-word-320-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 19 samples (1 token repeat) - 115 max words - at ../dataset/shuffle-word-115-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 28 samples (1 token repeat) - 100 max words - at ../dataset/shuffle-word-100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 7 samples (1 token repeat) - 350 max words - at ../dataset/shuffle-word-350-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 125 max words, 50 samples - at ../dataset/gen-word-125-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 14 samples (1 token repeat) - 180 max words - at ../dataset/shuffle-word-180-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 530 max words, 50 samples - at ../dataset/gen-word-530-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 135 max words, 50 samples - at ../dataset/gen-word-135-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 615 max words, 50 samples - at ../dataset/gen-word-615-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 16 samples (1 token repeat) - 145 max words - at ../dataset/shuffle-word-145-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 14 samples (1 token repeat) - 195 max words - at ../dataset/shuffle-word-195-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 4 samples (1 token repeat) - 640 max words - at ../dataset/shuffle-word-640-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 9 samples (1 token repeat) - 295 max words - at ../dataset/shuffle-word-295-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 7 samples (1 token repeat) - 390 max words - at ../dataset/shuffle-word-390-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 565 max words, 50 samples - at ../dataset/gen-word-565-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 10 samples (1 token repeat) - 230 max words - at ../dataset/shuffle-word-230-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 205 max words, 50 samples - at ../dataset/gen-word-205-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 4 samples (1 token repeat) - 735 max words - at ../dataset/shuffle-word-735-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 4 samples (1 token repeat) - 610 max words - at ../dataset/shuffle-word-610-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 9 samples (1 token repeat) - 270 max words - at ../dataset/shuffle-word-270-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 495 max words, 50 samples - at ../dataset/gen-word-495-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 855 max words, 50 samples - at ../dataset/gen-word-855-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 905 max words, 50 samples - at ../dataset/gen-word-905-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 240 max words, 50 samples - at ../dataset/gen-word-240-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 560 max words, 50 samples - at ../dataset/gen-word-560-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 405 max words, 50 samples - at ../dataset/gen-word-405-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 440 max words, 50 samples - at ../dataset/gen-word-440-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 7 samples (1 token repeat) - 385 max words - at ../dataset/shuffle-word-385-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 15 samples (1 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 4 samples (1 token repeat) - 775 max words - at ../dataset/shuffle-word-775-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 10 samples (1 token repeat) - 235 max words - at ../dataset/shuffle-word-235-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 6 samples (1 token repeat) - 410 max words - at ../dataset/shuffle-word-410-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 5 samples (1 token repeat) - 595 max words - at ../dataset/shuffle-word-595-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 4 samples (1 token repeat) - 765 max words - at ../dataset/shuffle-word-765-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 245 max words, 50 samples - at ../dataset/gen-word-245-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 4 samples (1 token repeat) - 665 max words - at ../dataset/shuffle-word-665-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 7 samples (1 token repeat) - 360 max words - at ../dataset/shuffle-word-360-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 295 max words, 50 samples - at ../dataset/gen-word-295-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 7 samples (1 token repeat) - 380 max words - at ../dataset/shuffle-word-380-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 3 samples (1 token repeat) - 830 max words - at ../dataset/shuffle-word-830-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 215 max words, 50 samples - at ../dataset/gen-word-215-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 6 samples (1 token repeat) - 460 max words - at ../dataset/shuffle-word-460-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 975 max words, 50 samples - at ../dataset/gen-word-975-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 525 max words, 50 samples - at ../dataset/gen-word-525-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 4 samples (1 token repeat) - 645 max words - at ../dataset/shuffle-word-645-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 4 samples (1 token repeat) - 825 max words - at ../dataset/shuffle-word-825-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 535 max words, 50 samples - at ../dataset/gen-word-535-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 4 samples (1 token repeat) - 725 max words - at ../dataset/shuffle-word-725-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 10 samples (1 token repeat) - 215 max words - at ../dataset/shuffle-word-215-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 725 max words, 50 samples - at ../dataset/gen-word-725-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 8 samples (1 token repeat) - 320 max words - at ../dataset/shuffle-word-320-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 290 max words, 50 samples - at ../dataset/gen-word-290-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 3 samples (1 token repeat) - 935 max words - at ../dataset/shuffle-word-935-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 32 samples (1 token repeat) - 85 max words - at ../dataset/shuffle-word-85-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 3 samples (1 token repeat) - 990 max words - at ../dataset/shuffle-word-990-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 485 max words, 50 samples - at ../dataset/gen-word-485-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 625 max words, 50 samples - at ../dataset/gen-word-625-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 665 max words, 50 samples - at ../dataset/gen-word-665-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 4 samples (1 token repeat) - 630 max words - at ../dataset/shuffle-word-630-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 6 samples (1 token repeat) - 475 max words - at ../dataset/shuffle-word-475-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 5 samples (1 token repeat) - 515 max words - at ../dataset/shuffle-word-515-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 7 samples (1 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 9 samples (1 token repeat) - 280 max words - at ../dataset/shuffle-word-280-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 955 max words, 50 samples - at ../dataset/gen-word-955-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 3 samples (1 token repeat) - 980 max words - at ../dataset/shuffle-word-980-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 9 samples (1 token repeat) - 285 max words - at ../dataset/shuffle-word-285-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 675 max words, 50 samples - at ../dataset/gen-word-675-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 5 samples (1 token repeat) - 560 max words - at ../dataset/shuffle-word-560-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 4 samples (1 token repeat) - 790 max words - at ../dataset/shuffle-word-790-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 4 samples (1 token repeat) - 680 max words - at ../dataset/shuffle-word-680-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 6 samples (1 token repeat) - 430 max words - at ../dataset/shuffle-word-430-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 5 samples (1 token repeat) - 580 max words - at ../dataset/shuffle-word-580-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 130 max words, 50 samples - at ../dataset/gen-word-130-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 20 samples (20 token repeat) - 5700 max words - at ../dataset/shuffle-word-5700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 220 max words, 50 samples - at ../dataset/gen-word-220-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 4 samples (1 token repeat) - 705 max words - at ../dataset/shuffle-word-705-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 310 max words, 50 samples - at ../dataset/gen-word-310-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 490 max words, 50 samples - at ../dataset/gen-word-490-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 595 max words, 50 samples - at ../dataset/gen-word-595-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 350 max words, 50 samples - at ../dataset/gen-word-350-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 40 samples (20 token repeat) - 2100 max words - at ../dataset/shuffle-word-2100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 890 max words, 50 samples - at ../dataset/gen-word-890-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 475 max words, 50 samples - at ../dataset/gen-word-475-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 20 samples (20 token repeat) - 7400 max words - at ../dataset/shuffle-word-7400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 10 samples (1 token repeat) - 225 max words - at ../dataset/shuffle-word-225-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 3 samples (1 token repeat) - 885 max words - at ../dataset/shuffle-word-885-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 3 samples (1 token repeat) - 970 max words - at ../dataset/shuffle-word-970-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 970 max words, 50 samples - at ../dataset/gen-word-970-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 120 max words, 50 samples - at ../dataset/gen-word-120-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 9 samples (1 token repeat) - 250 max words - at ../dataset/shuffle-word-250-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 650 max words, 50 samples - at ../dataset/gen-word-650-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 4 samples (1 token repeat) - 740 max words - at ../dataset/shuffle-word-740-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 20 samples (20 token repeat) - 5900 max words - at ../dataset/shuffle-word-5900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 4 samples (1 token repeat) - 660 max words - at ../dataset/shuffle-word-660-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 285 max words, 50 samples - at ../dataset/gen-word-285-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 3 samples (1 token repeat) - 900 max words - at ../dataset/shuffle-word-900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 3 samples (1 token repeat) - 960 max words - at ../dataset/shuffle-word-960-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 300 max words, 50 samples - at ../dataset/gen-word-300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 14 samples (1 token repeat) - 170 max words - at ../dataset/shuffle-word-170-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 4 samples (1 token repeat) - 750 max words - at ../dataset/shuffle-word-750-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 6 samples (1 token repeat) - 490 max words - at ../dataset/shuffle-word-490-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 260 max words, 50 samples - at ../dataset/gen-word-260-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 20 samples (20 token repeat) - 5100 max words - at ../dataset/shuffle-word-5100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 5 samples (1 token repeat) - 600 max words - at ../dataset/shuffle-word-600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 935 max words, 50 samples - at ../dataset/gen-word-935-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 4 samples (1 token repeat) - 655 max words - at ../dataset/shuffle-word-655-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 20 samples (20 token repeat) - 5000 max words - at ../dataset/shuffle-word-5000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 7 samples (1 token repeat) - 335 max words - at ../dataset/shuffle-word-335-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 6 samples (1 token repeat) - 440 max words - at ../dataset/shuffle-word-440-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 3 samples (1 token repeat) - 915 max words - at ../dataset/shuffle-word-915-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 20 samples (20 token repeat) - 5600 max words - at ../dataset/shuffle-word-5600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 4 samples (1 token repeat) - 720 max words - at ../dataset/shuffle-word-720-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 4 samples (1 token repeat) - 615 max words - at ../dataset/shuffle-word-615-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 4 samples (1 token repeat) - 650 max words - at ../dataset/shuffle-word-650-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 20 samples (20 token repeat) - 4600 max words - at ../dataset/shuffle-word-4600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 7 samples (1 token repeat) - 345 max words - at ../dataset/shuffle-word-345-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 40 samples (20 token repeat) - 1600 max words - at ../dataset/shuffle-word-1600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 6 samples (1 token repeat) - 415 max words - at ../dataset/shuffle-word-415-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 4 samples (1 token repeat) - 715 max words - at ../dataset/shuffle-word-715-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 740 max words, 50 samples - at ../dataset/gen-word-740-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 380 max words, 50 samples - at ../dataset/gen-word-380-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 4 samples (1 token repeat) - 670 max words - at ../dataset/shuffle-word-670-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 4 samples (1 token repeat) - 795 max words - at ../dataset/shuffle-word-795-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 155 max words, 50 samples - at ../dataset/gen-word-155-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 3 samples (1 token repeat) - 850 max words - at ../dataset/shuffle-word-850-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 20 samples (20 token repeat) - 4900 max words - at ../dataset/shuffle-word-4900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 7 samples (1 token repeat) - 370 max words - at ../dataset/shuffle-word-370-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 210 max words, 50 samples - at ../dataset/gen-word-210-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 3 samples (1 token repeat) - 985 max words - at ../dataset/shuffle-word-985-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 40 samples (20 token repeat) - 1700 max words - at ../dataset/shuffle-word-1700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 815 max words, 50 samples - at ../dataset/gen-word-815-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 20 samples (20 token repeat) - 7000 max words - at ../dataset/shuffle-word-7000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 940 max words, 50 samples - at ../dataset/gen-word-940-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 6 samples (1 token repeat) - 405 max words - at ../dataset/shuffle-word-405-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 335 max words, 50 samples - at ../dataset/gen-word-335-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 20 samples (20 token repeat) - 3700 max words - at ../dataset/shuffle-word-3700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 555 max words, 50 samples - at ../dataset/gen-word-555-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 20 samples (20 token repeat) - 7300 max words - at ../dataset/shuffle-word-7300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 37 samples (20 token repeat) - 2500 max words - at ../dataset/shuffle-word-2500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 4 samples (1 token repeat) - 690 max words - at ../dataset/shuffle-word-690-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 520 max words, 50 samples - at ../dataset/gen-word-520-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 7 samples (1 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 7 samples (1 token repeat) - 330 max words - at ../dataset/shuffle-word-330-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 10 samples (1 token repeat) - 240 max words - at ../dataset/shuffle-word-240-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 705 max words, 50 samples - at ../dataset/gen-word-705-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 600 max words, 50 samples - at ../dataset/gen-word-600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 145 max words, 50 samples - at ../dataset/gen-word-145-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 20 samples (20 token repeat) - 5500 max words - at ../dataset/shuffle-word-5500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 570 max words, 50 samples - at ../dataset/gen-word-570-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 6 samples (1 token repeat) - 470 max words - at ../dataset/shuffle-word-470-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 9 samples (1 token repeat) - 245 max words - at ../dataset/shuffle-word-245-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 630 max words, 50 samples - at ../dataset/gen-word-630-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 9 samples (1 token repeat) - 260 max words - at ../dataset/shuffle-word-260-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 765 max words, 50 samples - at ../dataset/gen-word-765-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 660 max words, 50 samples - at ../dataset/gen-word-660-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 575 max words, 50 samples - at ../dataset/gen-word-575-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 5 samples (1 token repeat) - 545 max words - at ../dataset/shuffle-word-545-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 20 samples (20 token repeat) - 7900 max words - at ../dataset/shuffle-word-7900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 3 samples (1 token repeat) - 955 max words - at ../dataset/shuffle-word-955-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 500 max words, 50 samples - at ../dataset/gen-word-500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 9 samples (1 token repeat) - 255 max words - at ../dataset/shuffle-word-255-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 5 samples (1 token repeat) - 530 max words - at ../dataset/shuffle-word-530-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 235 max words, 50 samples - at ../dataset/gen-word-235-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 5 samples (1 token repeat) - 585 max words - at ../dataset/shuffle-word-585-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 6 samples (1 token repeat) - 445 max words - at ../dataset/shuffle-word-445-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 20 samples (20 token repeat) - 5200 max words - at ../dataset/shuffle-word-5200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 845 max words, 50 samples - at ../dataset/gen-word-845-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 41 samples (20 token repeat) - 1400 max words - at ../dataset/shuffle-word-1400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 20 samples (20 token repeat) - 6500 max words - at ../dataset/shuffle-word-6500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 4 samples (1 token repeat) - 755 max words - at ../dataset/shuffle-word-755-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 5 samples (1 token repeat) - 540 max words - at ../dataset/shuffle-word-540-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 4 samples (1 token repeat) - 625 max words - at ../dataset/shuffle-word-625-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 20 samples (20 token repeat) - 4300 max words - at ../dataset/shuffle-word-4300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 200 max words, 50 samples - at ../dataset/gen-word-200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 755 max words, 50 samples - at ../dataset/gen-word-755-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 770 max words, 50 samples - at ../dataset/gen-word-770-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 5 samples (1 token repeat) - 535 max words - at ../dataset/shuffle-word-535-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 465 max words, 50 samples - at ../dataset/gen-word-465-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 700 max words, 50 samples - at ../dataset/gen-word-700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 7 samples (1 token repeat) - 355 max words - at ../dataset/shuffle-word-355-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 610 max words, 50 samples - at ../dataset/gen-word-610-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 20 samples (20 token repeat) - 6900 max words - at ../dataset/shuffle-word-6900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 895 max words, 50 samples - at ../dataset/gen-word-895-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 860 max words, 50 samples - at ../dataset/gen-word-860-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 20 samples (20 token repeat) - 2900 max words - at ../dataset/shuffle-word-2900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 5 samples (1 token repeat) - 465 max words - at ../dataset/shuffle-word-465-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 3 samples (1 token repeat) - 895 max words - at ../dataset/shuffle-word-895-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 6 samples (1 token repeat) - 420 max words - at ../dataset/shuffle-word-420-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 20 samples (20 token repeat) - 4500 max words - at ../dataset/shuffle-word-4500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 20 samples (20 token repeat) - 7600 max words - at ../dataset/shuffle-word-7600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 4 samples (1 token repeat) - 760 max words - at ../dataset/shuffle-word-760-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 505 max words, 50 samples - at ../dataset/gen-word-505-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 795 max words, 50 samples - at ../dataset/gen-word-795-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 40 samples (20 token repeat) - 1800 max words - at ../dataset/shuffle-word-1800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 3 samples (1 token repeat) - 730 max words - at ../dataset/shuffle-word-730-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 4 samples (1 token repeat) - 605 max words - at ../dataset/shuffle-word-605-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 270 max words, 50 samples - at ../dataset/gen-word-270-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 5 samples (1 token repeat) - 565 max words - at ../dataset/shuffle-word-565-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 60 samples (20 token repeat) - 1100 max words - at ../dataset/shuffle-word-1100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 20 samples (20 token repeat) - 6800 max words - at ../dataset/shuffle-word-6800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 20 samples (20 token repeat) - 4700 max words - at ../dataset/shuffle-word-4700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 960 max words, 50 samples - at ../dataset/gen-word-960-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 965 max words, 50 samples - at ../dataset/gen-word-965-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 6 samples (1 token repeat) - 450 max words - at ../dataset/shuffle-word-450-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 410 max words, 50 samples - at ../dataset/gen-word-410-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 4 samples (1 token repeat) - 745 max words - at ../dataset/shuffle-word-745-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 20 samples (20 token repeat) - 7500 max words - at ../dataset/shuffle-word-7500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 3 samples (1 token repeat) - 835 max words - at ../dataset/shuffle-word-835-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 20 samples (20 token repeat) - 6600 max words - at ../dataset/shuffle-word-6600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 3 samples (1 token repeat) - 995 max words - at ../dataset/shuffle-word-995-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 7 samples (1 token repeat) - 365 max words - at ../dataset/shuffle-word-365-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 3 samples (1 token repeat) - 875 max words - at ../dataset/shuffle-word-875-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 840 max words, 50 samples - at ../dataset/gen-word-840-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 6 samples (1 token repeat) - 425 max words - at ../dataset/shuffle-word-425-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 5 samples (1 token repeat) - 575 max words - at ../dataset/shuffle-word-575-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 5 samples (1 token repeat) - 520 max words - at ../dataset/shuffle-word-520-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 785 max words, 50 samples - at ../dataset/gen-word-785-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 640 max words, 50 samples - at ../dataset/gen-word-640-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 4 samples (1 token repeat) - 675 max words - at ../dataset/shuffle-word-675-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 580 max words, 50 samples - at ../dataset/gen-word-580-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 435 max words, 50 samples - at ../dataset/gen-word-435-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 7 samples (1 token repeat) - 375 max words - at ../dataset/shuffle-word-375-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 305 max words, 50 samples - at ../dataset/gen-word-305-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 275 max words, 50 samples - at ../dataset/gen-word-275-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 6 samples (1 token repeat) - 485 max words - at ../dataset/shuffle-word-485-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 760 max words, 50 samples - at ../dataset/gen-word-760-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 20 samples (20 token repeat) - 7200 max words - at ../dataset/shuffle-word-7200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 3 samples (1 token repeat) - 1000 max words - at ../dataset/shuffle-word-1000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 3 samples (1 token repeat) - 920 max words - at ../dataset/shuffle-word-920-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 635 max words, 50 samples - at ../dataset/gen-word-635-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 5 samples (1 token repeat) - 505 max words - at ../dataset/shuffle-word-505-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 455 max words, 50 samples - at ../dataset/gen-word-455-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 3 samples (1 token repeat) - 815 max words - at ../dataset/shuffle-word-815-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 115 max words, 50 samples - at ../dataset/gen-word-115-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 3 samples (1 token repeat) - 820 max words - at ../dataset/shuffle-word-820-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 685 max words, 50 samples - at ../dataset/gen-word-685-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 20 samples (20 token repeat) - 3200 max words - at ../dataset/shuffle-word-3200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 345 max words, 50 samples - at ../dataset/gen-word-345-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 20 samples (20 token repeat) - 6200 max words - at ../dataset/shuffle-word-6200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 40 samples (20 token repeat) - 1900 max words - at ../dataset/shuffle-word-1900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 255 max words, 50 samples - at ../dataset/gen-word-255-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 690 max words, 50 samples - at ../dataset/gen-word-690-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 805 max words, 50 samples - at ../dataset/gen-word-805-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 3 samples (1 token repeat) - 905 max words - at ../dataset/shuffle-word-905-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 385 max words, 50 samples - at ../dataset/gen-word-385-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 110 max words, 50 samples - at ../dataset/gen-word-110-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 13 samples (1 token repeat) - 185 max words - at ../dataset/shuffle-word-185-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 9 samples (1 token repeat) - 275 max words - at ../dataset/shuffle-word-275-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 20 samples (20 token repeat) - 3000 max words - at ../dataset/shuffle-word-3000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 400 max words, 50 samples - at ../dataset/gen-word-400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 3 samples (1 token repeat) - 925 max words - at ../dataset/shuffle-word-925-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 620 max words, 50 samples - at ../dataset/gen-word-620-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 375 max words, 50 samples - at ../dataset/gen-word-375-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 4 samples (1 token repeat) - 770 max words - at ../dataset/shuffle-word-770-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 3 samples (1 token repeat) - 910 max words - at ../dataset/shuffle-word-910-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 3 samples (1 token repeat) - 890 max words - at ../dataset/shuffle-word-890-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 20 samples (20 token repeat) - 6000 max words - at ../dataset/shuffle-word-6000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 20 samples (20 token repeat) - 5300 max words - at ../dataset/shuffle-word-5300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 20 samples (20 token repeat) - 3300 max words - at ../dataset/shuffle-word-3300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 365 max words, 50 samples - at ../dataset/gen-word-365-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 950 max words, 50 samples - at ../dataset/gen-word-950-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 3 samples (1 token repeat) - 945 max words - at ../dataset/shuffle-word-945-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 95 max words, 50 samples - at ../dataset/gen-word-95-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 20 samples (20 token repeat) - 6700 max words - at ../dataset/shuffle-word-6700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 420 max words, 50 samples - at ../dataset/gen-word-420-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 415 max words, 50 samples - at ../dataset/gen-word-415-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 820 max words, 50 samples - at ../dataset/gen-word-820-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 590 max words, 50 samples - at ../dataset/gen-word-590-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 3 samples (1 token repeat) - 965 max words - at ../dataset/shuffle-word-965-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 6 samples (1 token repeat) - 495 max words - at ../dataset/shuffle-word-495-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 40 samples (20 token repeat) - 2300 max words - at ../dataset/shuffle-word-2300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 780 max words, 50 samples - at ../dataset/gen-word-780-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 585 max words, 50 samples - at ../dataset/gen-word-585-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 450 max words, 50 samples - at ../dataset/gen-word-450-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 3 samples (1 token repeat) - 930 max words - at ../dataset/shuffle-word-930-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 40 samples (20 token repeat) - 2200 max words - at ../dataset/shuffle-word-2200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 4 samples (1 token repeat) - 700 max words - at ../dataset/shuffle-word-700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 7 samples (1 token repeat) - 400 max words - at ../dataset/shuffle-word-400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 990 max words, 50 samples - at ../dataset/gen-word-990-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 355 max words, 50 samples - at ../dataset/gen-word-355-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 3 samples (1 token repeat) - 940 max words - at ../dataset/shuffle-word-940-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 545 max words, 50 samples - at ../dataset/gen-word-545-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 20 samples (20 token repeat) - 3800 max words - at ../dataset/shuffle-word-3800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 745 max words, 50 samples - at ../dataset/gen-word-745-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 720 max words, 50 samples - at ../dataset/gen-word-720-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 4 samples (1 token repeat) - 710 max words - at ../dataset/shuffle-word-710-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 20 samples (20 token repeat) - 3500 max words - at ../dataset/shuffle-word-3500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 20 samples (20 token repeat) - 4800 max words - at ../dataset/shuffle-word-4800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 510 max words, 50 samples - at ../dataset/gen-word-510-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 5 samples (1 token repeat) - 555 max words - at ../dataset/shuffle-word-555-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 5 samples (1 token repeat) - 510 max words - at ../dataset/shuffle-word-510-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 370 max words, 50 samples - at ../dataset/gen-word-370-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 425 max words, 50 samples - at ../dataset/gen-word-425-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 20 samples (20 token repeat) - 3600 max words - at ../dataset/shuffle-word-3600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 655 max words, 50 samples - at ../dataset/gen-word-655-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 925 max words, 50 samples - at ../dataset/gen-word-925-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 4 samples (1 token repeat) - 865 max words - at ../dataset/shuffle-word-865-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 3 samples (1 token repeat) - 860 max words - at ../dataset/shuffle-word-860-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 4 samples (1 token repeat) - 785 max words - at ../dataset/shuffle-word-785-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 20 samples (20 token repeat) - 7100 max words - at ../dataset/shuffle-word-7100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 550 max words, 50 samples - at ../dataset/gen-word-550-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 5 samples (1 token repeat) - 590 max words - at ../dataset/shuffle-word-590-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 1000 max words, 50 samples - at ../dataset/gen-word-1000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 430 max words, 50 samples - at ../dataset/gen-word-430-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 445 max words, 50 samples - at ../dataset/gen-word-445-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 20 samples (20 token repeat) - 6300 max words - at ../dataset/shuffle-word-6300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 20 samples (20 token repeat) - 6400 max words - at ../dataset/shuffle-word-6400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 3 samples (1 token repeat) - 810 max words - at ../dataset/shuffle-word-810-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 3 samples (1 token repeat) - 950 max words - at ../dataset/shuffle-word-950-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 470 max words, 50 samples - at ../dataset/gen-word-470-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 775 max words, 50 samples - at ../dataset/gen-word-775-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 540 max words, 50 samples - at ../dataset/gen-word-540-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 20 samples (20 token repeat) - 3900 max words - at ../dataset/shuffle-word-3900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 750 max words, 50 samples - at ../dataset/gen-word-750-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 920 max words, 50 samples - at ../dataset/gen-word-920-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 3 samples (1 token repeat) - 805 max words - at ../dataset/shuffle-word-805-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 850 max words, 50 samples - at ../dataset/gen-word-850-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 3 samples (1 token repeat) - 855 max words - at ../dataset/shuffle-word-855-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 885 max words, 50 samples - at ../dataset/gen-word-885-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 4 samples (1 token repeat) - 685 max words - at ../dataset/shuffle-word-685-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 20 samples (20 token repeat) - 5800 max words - at ../dataset/shuffle-word-5800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 340 max words, 50 samples - at ../dataset/gen-word-340-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 4 samples (1 token repeat) - 780 max words - at ../dataset/shuffle-word-780-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 20 samples (20 token repeat) - 7800 max words - at ../dataset/shuffle-word-7800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 48 samples (20 token repeat) - 1300 max words - at ../dataset/shuffle-word-1300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 680 max words, 50 samples - at ../dataset/gen-word-680-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 3 samples (1 token repeat) - 975 max words - at ../dataset/shuffle-word-975-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 3 samples (1 token repeat) - 870 max words - at ../dataset/shuffle-word-870-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 4 samples (1 token repeat) - 840 max words - at ../dataset/shuffle-word-840-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 695 max words, 50 samples - at ../dataset/gen-word-695-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 870 max words, 50 samples - at ../dataset/gen-word-870-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 670 max words, 50 samples - at ../dataset/gen-word-670-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 25 samples (20 token repeat) - 2700 max words - at ../dataset/shuffle-word-2700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 4 samples (1 token repeat) - 695 max words - at ../dataset/shuffle-word-695-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 4 samples (1 token repeat) - 620 max words - at ../dataset/shuffle-word-620-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 645 max words, 50 samples - at ../dataset/gen-word-645-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 3 samples (1 token repeat) - 845 max words - at ../dataset/shuffle-word-845-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 20 samples (20 token repeat) - 3100 max words - at ../dataset/shuffle-word-3100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 4 samples (1 token repeat) - 800 max words - at ../dataset/shuffle-word-800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 460 max words, 50 samples - at ../dataset/gen-word-460-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 710 max words, 50 samples - at ../dataset/gen-word-710-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 3 samples (1 token repeat) - 880 max words - at ../dataset/shuffle-word-880-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 7 samples (1 token repeat) - 340 max words - at ../dataset/shuffle-word-340-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 930 max words, 50 samples - at ../dataset/gen-word-930-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 945 max words, 50 samples - at ../dataset/gen-word-945-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 735 max words, 50 samples - at ../dataset/gen-word-735-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 6 samples (1 token repeat) - 480 max words - at ../dataset/shuffle-word-480-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 830 max words, 50 samples - at ../dataset/gen-word-830-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 20 samples (20 token repeat) - 3400 max words - at ../dataset/shuffle-word-3400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 865 max words, 50 samples - at ../dataset/gen-word-865-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 6 samples (1 token repeat) - 455 max words - at ../dataset/shuffle-word-455-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 395 max words, 50 samples - at ../dataset/gen-word-395-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 20 samples (20 token repeat) - 4000 max words - at ../dataset/shuffle-word-4000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 825 max words, 50 samples - at ../dataset/gen-word-825-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 790 max words, 50 samples - at ../dataset/gen-word-790-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 715 max words, 50 samples - at ../dataset/gen-word-715-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 4 samples (1 token repeat) - 635 max words - at ../dataset/shuffle-word-635-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 835 max words, 50 samples - at ../dataset/gen-word-835-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 875 max words, 50 samples - at ../dataset/gen-word-875-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 40 samples (20 token repeat) - 2000 max words - at ../dataset/shuffle-word-2000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 20 samples (20 token repeat) - 4100 max words - at ../dataset/shuffle-word-4100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 880 max words, 50 samples - at ../dataset/gen-word-880-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 60 samples (20 token repeat) - 1200 max words - at ../dataset/shuffle-word-1200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 20 samples (20 token repeat) - 7700 max words - at ../dataset/shuffle-word-7700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 20 samples (20 token repeat) - 5400 max words - at ../dataset/shuffle-word-5400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 20 samples (20 token repeat) - 8000 max words - at ../dataset/shuffle-word-8000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 20 samples (20 token repeat) - 4400 max words - at ../dataset/shuffle-word-4400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 605 max words, 50 samples - at ../dataset/gen-word-605-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 800 max words, 50 samples - at ../dataset/gen-word-800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 985 max words, 50 samples - at ../dataset/gen-word-985-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 40 samples (20 token repeat) - 2400 max words - at ../dataset/shuffle-word-2400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 20 samples (20 token repeat) - 2800 max words - at ../dataset/shuffle-word-2800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 900 max words, 50 samples - at ../dataset/gen-word-900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 480 max words, 50 samples - at ../dataset/gen-word-480-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 730 max words, 50 samples - at ../dataset/gen-word-730-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 980 max words, 50 samples - at ../dataset/gen-word-980-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 33 samples (20 token repeat) - 2600 max words - at ../dataset/shuffle-word-2600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 810 max words, 50 samples - at ../dataset/gen-word-810-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 910 max words, 50 samples - at ../dataset/gen-word-910-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 915 max words, 50 samples - at ../dataset/gen-word-915-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 20 samples (20 token repeat) - 4200 max words - at ../dataset/shuffle-word-4200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 20 samples (20 token repeat) - 6100 max words - at ../dataset/shuffle-word-6100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated a single JSONL file with 40 samples (20 token repeat) - 1500 max words - at ../dataset/shuffle-word-1500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 995 max words, 50 samples - at ../dataset/gen-word-995-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 1100 max words, 2000 samples - at ../dataset/gen-word-1100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 1200 max words, 2000 samples - at ../dataset/gen-word-1200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 1300 max words, 2000 samples - at ../dataset/gen-word-1300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 1800 max words, 2000 samples - at ../dataset/gen-word-1800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 1500 max words, 2000 samples - at ../dataset/gen-word-1500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 1900 max words, 2000 samples - at ../dataset/gen-word-1900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 1700 max words, 2000 samples - at ../dataset/gen-word-1700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 1600 max words, 2000 samples - at ../dataset/gen-word-1600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 2000 max words, 2000 samples - at ../dataset/gen-word-2000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 1400 max words, 2000 samples - at ../dataset/gen-word-1400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 2100 max words, 2000 samples - at ../dataset/gen-word-2100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 2200 max words, 2000 samples - at ../dataset/gen-word-2200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 2600 max words, 2000 samples - at ../dataset/gen-word-2600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 2400 max words, 2000 samples - at ../dataset/gen-word-2400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 2500 max words, 2000 samples - at ../dataset/gen-word-2500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 2800 max words, 2000 samples - at ../dataset/gen-word-2800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 3000 max words, 2000 samples - at ../dataset/gen-word-3000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 3100 max words, 2000 samples - at ../dataset/gen-word-3100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 2700 max words, 2000 samples - at ../dataset/gen-word-2700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 3700 max words, 2000 samples - at ../dataset/gen-word-3700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 3400 max words, 2000 samples - at ../dataset/gen-word-3400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 3300 max words, 2000 samples - at ../dataset/gen-word-3300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 2300 max words, 2000 samples - at ../dataset/gen-word-2300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 3200 max words, 2000 samples - at ../dataset/gen-word-3200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 3800 max words, 2000 samples - at ../dataset/gen-word-3800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 4100 max words, 2000 samples - at ../dataset/gen-word-4100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 3600 max words, 2000 samples - at ../dataset/gen-word-3600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 2900 max words, 2000 samples - at ../dataset/gen-word-2900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 3500 max words, 2000 samples - at ../dataset/gen-word-3500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 4200 max words, 2000 samples - at ../dataset/gen-word-4200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 3900 max words, 2000 samples - at ../dataset/gen-word-3900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 4500 max words, 2000 samples - at ../dataset/gen-word-4500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 4600 max words, 2000 samples - at ../dataset/gen-word-4600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 4300 max words, 2000 samples - at ../dataset/gen-word-4300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 5100 max words, 2000 samples - at ../dataset/gen-word-5100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 4400 max words, 2000 samples - at ../dataset/gen-word-4400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 4700 max words, 2000 samples - at ../dataset/gen-word-4700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 5000 max words, 2000 samples - at ../dataset/gen-word-5000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 4000 max words, 2000 samples - at ../dataset/gen-word-4000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 5500 max words, 2000 samples - at ../dataset/gen-word-5500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 6000 max words, 2000 samples - at ../dataset/gen-word-6000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 6100 max words, 2000 samples - at ../dataset/gen-word-6100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 5400 max words, 2000 samples - at ../dataset/gen-word-5400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 4900 max words, 2000 samples - at ../dataset/gen-word-4900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 5600 max words, 2000 samples - at ../dataset/gen-word-5600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 6200 max words, 2000 samples - at ../dataset/gen-word-6200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 4800 max words, 2000 samples - at ../dataset/gen-word-4800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 5900 max words, 2000 samples - at ../dataset/gen-word-5900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 5800 max words, 2000 samples - at ../dataset/gen-word-5800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 5700 max words, 2000 samples - at ../dataset/gen-word-5700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 6400 max words, 2000 samples - at ../dataset/gen-word-6400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 5200 max words, 2000 samples - at ../dataset/gen-word-5200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 5300 max words, 2000 samples - at ../dataset/gen-word-5300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 6800 max words, 2000 samples - at ../dataset/gen-word-6800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 6300 max words, 2000 samples - at ../dataset/gen-word-6300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 7000 max words, 2000 samples - at ../dataset/gen-word-7000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 6500 max words, 2000 samples - at ../dataset/gen-word-6500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 6900 max words, 2000 samples - at ../dataset/gen-word-6900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 7400 max words, 2000 samples - at ../dataset/gen-word-7400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 6700 max words, 2000 samples - at ../dataset/gen-word-6700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 7300 max words, 2000 samples - at ../dataset/gen-word-7300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 6600 max words, 2000 samples - at ../dataset/gen-word-6600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 7100 max words, 2000 samples - at ../dataset/gen-word-7100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 7200 max words, 2000 samples - at ../dataset/gen-word-7200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 7600 max words, 2000 samples - at ../dataset/gen-word-7600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 7900 max words, 2000 samples - at ../dataset/gen-word-7900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 7500 max words, 2000 samples - at ../dataset/gen-word-7500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 7800 max words, 2000 samples - at ../dataset/gen-word-7800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 8000 max words, 2000 samples - at ../dataset/gen-word-8000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Generated JSONL file with - 7700 max words, 2000 samples - at ../dataset/gen-word-7700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "## Done ##\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "total 6.1G\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 10K Sep 2 08:18 gen-word-10-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 54K Sep 2 08:18 gen-word-100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 489K Sep 2 08:18 gen-word-1000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 59K Sep 2 08:18 gen-word-105-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 57K Sep 2 08:18 gen-word-110-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 22M Sep 2 08:18 gen-word-1100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 61K Sep 2 08:18 gen-word-115-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 63K Sep 2 08:18 gen-word-120-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 23M Sep 2 08:18 gen-word-1200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 64K Sep 2 08:18 gen-word-125-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 66K Sep 2 08:18 gen-word-130-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 25M Sep 2 08:18 gen-word-1300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 68K Sep 2 08:18 gen-word-135-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 72K Sep 2 08:18 gen-word-140-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27M Sep 2 08:18 gen-word-1400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 76K Sep 2 08:18 gen-word-145-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 13K Sep 2 08:18 gen-word-15-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 78K Sep 2 08:18 gen-word-150-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 29M Sep 2 08:18 gen-word-1500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 81K Sep 2 08:18 gen-word-155-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 83K Sep 2 08:18 gen-word-160-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 31M Sep 2 08:18 gen-word-1600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 87K Sep 2 08:18 gen-word-165-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 87K Sep 2 08:18 gen-word-170-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 33M Sep 2 08:18 gen-word-1700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 90K Sep 2 08:18 gen-word-175-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 94K Sep 2 08:18 gen-word-180-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 35M Sep 2 08:18 gen-word-1800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 95K Sep 2 08:18 gen-word-185-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 98K Sep 2 08:18 gen-word-190-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 37M Sep 2 08:18 gen-word-1900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 99K Sep 2 08:18 gen-word-195-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 15K Sep 2 08:18 gen-word-20-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 103K Sep 2 08:18 gen-word-200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 39M Sep 2 08:18 gen-word-2000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 105K Sep 2 08:18 gen-word-205-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 107K Sep 2 08:18 gen-word-210-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 41M Sep 2 08:18 gen-word-2100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 112K Sep 2 08:18 gen-word-215-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 112K Sep 2 08:18 gen-word-220-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 42M Sep 2 08:18 gen-word-2200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 111K Sep 2 08:18 gen-word-225-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 118K Sep 2 08:18 gen-word-230-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 44M Sep 2 08:18 gen-word-2300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 120K Sep 2 08:18 gen-word-235-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 124K Sep 2 08:18 gen-word-240-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 46M Sep 2 08:18 gen-word-2400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 127K Sep 2 08:18 gen-word-245-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 17K Sep 2 08:18 gen-word-25-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 124K Sep 2 08:18 gen-word-250-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 48M Sep 2 08:18 gen-word-2500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 132K Sep 2 08:18 gen-word-255-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 134K Sep 2 08:18 gen-word-260-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 50M Sep 2 08:18 gen-word-2600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 133K Sep 2 08:18 gen-word-265-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 137K Sep 2 08:18 gen-word-270-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 52M Sep 2 08:18 gen-word-2700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 137K Sep 2 08:18 gen-word-275-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 140K Sep 2 08:18 gen-word-280-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 54M Sep 2 08:18 gen-word-2800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 141K Sep 2 08:18 gen-word-285-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 149K Sep 2 08:18 gen-word-290-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 56M Sep 2 08:18 gen-word-2900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 148K Sep 2 08:18 gen-word-295-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 20K Sep 2 08:18 gen-word-30-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 152K Sep 2 08:18 gen-word-300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 58M Sep 2 08:18 gen-word-3000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 149K Sep 2 08:18 gen-word-305-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 158K Sep 2 08:18 gen-word-310-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 60M Sep 2 08:18 gen-word-3100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 161K Sep 2 08:18 gen-word-315-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 159K Sep 2 08:18 gen-word-320-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 62M Sep 2 08:18 gen-word-3200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 163K Sep 2 08:18 gen-word-325-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 166K Sep 2 08:18 gen-word-330-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 63M Sep 2 08:18 gen-word-3300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 173K Sep 2 08:18 gen-word-335-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 173K Sep 2 08:18 gen-word-340-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 65M Sep 2 08:18 gen-word-3400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 174K Sep 2 08:18 gen-word-345-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 22K Sep 2 08:18 gen-word-35-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 177K Sep 2 08:18 gen-word-350-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 67M Sep 2 08:18 gen-word-3500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 177K Sep 2 08:18 gen-word-355-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 177K Sep 2 08:18 gen-word-360-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 69M Sep 2 08:18 gen-word-3600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 183K Sep 2 08:18 gen-word-365-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 187K Sep 2 08:18 gen-word-370-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 71M Sep 2 08:18 gen-word-3700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 187K Sep 2 08:18 gen-word-375-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 188K Sep 2 08:18 gen-word-380-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 73M Sep 2 08:18 gen-word-3800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 191K Sep 2 08:18 gen-word-385-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 199K Sep 2 08:18 gen-word-390-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 75M Sep 2 08:18 gen-word-3900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 198K Sep 2 08:18 gen-word-395-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 25K Sep 2 08:18 gen-word-40-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 202K Sep 2 08:18 gen-word-400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 77M Sep 2 08:18 gen-word-4000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 199K Sep 2 08:18 gen-word-405-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 204K Sep 2 08:18 gen-word-410-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 79M Sep 2 08:18 gen-word-4100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 204K Sep 2 08:18 gen-word-415-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 212K Sep 2 08:18 gen-word-420-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 80M Sep 2 08:18 gen-word-4200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 214K Sep 2 08:18 gen-word-425-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 214K Sep 2 08:18 gen-word-430-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 82M Sep 2 08:18 gen-word-4300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 217K Sep 2 08:18 gen-word-435-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 218K Sep 2 08:18 gen-word-440-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 84M Sep 2 08:18 gen-word-4400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 221K Sep 2 08:18 gen-word-445-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 26K Sep 2 08:18 gen-word-45-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 222K Sep 2 08:18 gen-word-450-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 86M Sep 2 08:18 gen-word-4500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 226K Sep 2 08:18 gen-word-455-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 228K Sep 2 08:18 gen-word-460-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 88M Sep 2 08:18 gen-word-4600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 229K Sep 2 08:18 gen-word-465-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 229K Sep 2 08:18 gen-word-470-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 90M Sep 2 08:18 gen-word-4700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 232K Sep 2 08:18 gen-word-475-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 239K Sep 2 08:18 gen-word-480-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 92M Sep 2 08:18 gen-word-4800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 243K Sep 2 08:18 gen-word-485-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 243K Sep 2 08:18 gen-word-490-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 94M Sep 2 08:18 gen-word-4900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 241K Sep 2 08:18 gen-word-495-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 7.3K Sep 2 08:18 gen-word-5-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 29K Sep 2 08:18 gen-word-50-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 248K Sep 2 08:18 gen-word-500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 96M Sep 2 08:18 gen-word-5000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 254K Sep 2 08:18 gen-word-505-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 249K Sep 2 08:18 gen-word-510-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 98M Sep 2 08:18 gen-word-5100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 254K Sep 2 08:18 gen-word-515-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 257K Sep 2 08:18 gen-word-520-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 99M Sep 2 08:18 gen-word-5200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 261K Sep 2 08:18 gen-word-525-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 263K Sep 2 08:18 gen-word-530-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 101M Sep 2 08:18 gen-word-5300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 261K Sep 2 08:18 gen-word-535-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 274K Sep 2 08:18 gen-word-540-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 103M Sep 2 08:18 gen-word-5400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 268K Sep 2 08:18 gen-word-545-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 31K Sep 2 08:18 gen-word-55-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 272K Sep 2 08:18 gen-word-550-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 105M Sep 2 08:18 gen-word-5500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 274K Sep 2 08:18 gen-word-555-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 275K Sep 2 08:18 gen-word-560-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 107M Sep 2 08:18 gen-word-5600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 281K Sep 2 08:18 gen-word-565-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 288K Sep 2 08:18 gen-word-570-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 109M Sep 2 08:18 gen-word-5700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 285K Sep 2 08:18 gen-word-575-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 285K Sep 2 08:18 gen-word-580-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 111M Sep 2 08:18 gen-word-5800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 290K Sep 2 08:18 gen-word-585-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 291K Sep 2 08:18 gen-word-590-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 113M Sep 2 08:18 gen-word-5900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 297K Sep 2 08:18 gen-word-595-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 34K Sep 2 08:18 gen-word-60-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 292K Sep 2 08:18 gen-word-600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 115M Sep 2 08:18 gen-word-6000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 305K Sep 2 08:18 gen-word-605-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 297K Sep 2 08:18 gen-word-610-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 116M Sep 2 08:18 gen-word-6100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 304K Sep 2 08:18 gen-word-615-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 307K Sep 2 08:18 gen-word-620-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 118M Sep 2 08:18 gen-word-6200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 306K Sep 2 08:18 gen-word-625-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 307K Sep 2 08:18 gen-word-630-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 120M Sep 2 08:18 gen-word-6300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 314K Sep 2 08:18 gen-word-635-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 312K Sep 2 08:18 gen-word-640-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 122M Sep 2 08:18 gen-word-6400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 320K Sep 2 08:18 gen-word-645-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 37K Sep 2 08:18 gen-word-65-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 318K Sep 2 08:18 gen-word-650-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 124M Sep 2 08:18 gen-word-6500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 325K Sep 2 08:18 gen-word-655-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 330K Sep 2 08:18 gen-word-660-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 126M Sep 2 08:18 gen-word-6600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 329K Sep 2 08:18 gen-word-665-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 335K Sep 2 08:18 gen-word-670-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 128M Sep 2 08:18 gen-word-6700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 333K Sep 2 08:18 gen-word-675-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 332K Sep 2 08:18 gen-word-680-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 130M Sep 2 08:18 gen-word-6800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 334K Sep 2 08:18 gen-word-685-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 342K Sep 2 08:18 gen-word-690-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 132M Sep 2 08:18 gen-word-6900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 340K Sep 2 08:18 gen-word-695-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 39K Sep 2 08:18 gen-word-70-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 342K Sep 2 08:18 gen-word-700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 134M Sep 2 08:18 gen-word-7000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 349K Sep 2 08:18 gen-word-705-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 347K Sep 2 08:18 gen-word-710-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 136M Sep 2 08:18 gen-word-7100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 355K Sep 2 08:18 gen-word-715-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 360K Sep 2 08:18 gen-word-720-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 137M Sep 2 08:18 gen-word-7200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 359K Sep 2 08:18 gen-word-725-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 365K Sep 2 08:18 gen-word-730-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 139M Sep 2 08:18 gen-word-7300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 360K Sep 2 08:18 gen-word-735-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 368K Sep 2 08:18 gen-word-740-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 141M Sep 2 08:18 gen-word-7400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 369K Sep 2 08:18 gen-word-745-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 43K Sep 2 08:18 gen-word-75-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 368K Sep 2 08:18 gen-word-750-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 143M Sep 2 08:18 gen-word-7500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 376K Sep 2 08:18 gen-word-755-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 372K Sep 2 08:18 gen-word-760-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 145M Sep 2 08:18 gen-word-7600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 380K Sep 2 08:18 gen-word-765-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 382K Sep 2 08:18 gen-word-770-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 147M Sep 2 08:18 gen-word-7700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 379K Sep 2 08:18 gen-word-775-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 389K Sep 2 08:18 gen-word-780-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 149M Sep 2 08:18 gen-word-7800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 390K Sep 2 08:18 gen-word-785-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 391K Sep 2 08:18 gen-word-790-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 151M Sep 2 08:18 gen-word-7900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 385K Sep 2 08:18 gen-word-795-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 43K Sep 2 08:18 gen-word-80-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 390K Sep 2 08:18 gen-word-800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 153M Sep 2 08:18 gen-word-8000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 389K Sep 2 08:18 gen-word-805-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 396K Sep 2 08:18 gen-word-810-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 398K Sep 2 08:18 gen-word-815-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 406K Sep 2 08:18 gen-word-820-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 410K Sep 2 08:18 gen-word-825-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 410K Sep 2 08:18 gen-word-830-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 415K Sep 2 08:18 gen-word-835-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 418K Sep 2 08:18 gen-word-840-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 420K Sep 2 08:18 gen-word-845-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 46K Sep 2 08:18 gen-word-85-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 420K Sep 2 08:18 gen-word-850-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 425K Sep 2 08:18 gen-word-855-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 421K Sep 2 08:18 gen-word-860-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 424K Sep 2 08:18 gen-word-865-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 428K Sep 2 08:18 gen-word-870-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 434K Sep 2 08:18 gen-word-875-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 437K Sep 2 08:18 gen-word-880-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 438K Sep 2 08:18 gen-word-885-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 443K Sep 2 08:18 gen-word-890-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 435K Sep 2 08:18 gen-word-895-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 49K Sep 2 08:18 gen-word-90-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 451K Sep 2 08:18 gen-word-900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 444K Sep 2 08:18 gen-word-905-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 443K Sep 2 08:18 gen-word-910-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 450K Sep 2 08:18 gen-word-915-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 448K Sep 2 08:18 gen-word-920-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 458K Sep 2 08:18 gen-word-925-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 465K Sep 2 08:18 gen-word-930-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 461K Sep 2 08:18 gen-word-935-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 462K Sep 2 08:18 gen-word-940-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 468K Sep 2 08:18 gen-word-945-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 51K Sep 2 08:18 gen-word-95-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 473K Sep 2 08:18 gen-word-950-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 474K Sep 2 08:18 gen-word-955-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 478K Sep 2 08:18 gen-word-960-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 472K Sep 2 08:18 gen-word-965-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 477K Sep 2 08:18 gen-word-970-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 477K Sep 2 08:18 gen-word-975-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 483K Sep 2 08:18 gen-word-980-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 487K Sep 2 08:18 gen-word-985-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 490K Sep 2 08:18 gen-word-990-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 490K Sep 2 08:18 gen-word-995-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 51K Sep 2 08:18 shuffle-word-10-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 26K Sep 2 08:18 shuffle-word-100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-1000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 29K Sep 2 08:18 shuffle-word-105-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 28K Sep 2 08:18 shuffle-word-110-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 524K Sep 2 08:18 shuffle-word-1100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 29K Sep 2 08:18 shuffle-word-115-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-120-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 522K Sep 2 08:18 shuffle-word-1200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 28K Sep 2 08:18 shuffle-word-125-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 28K Sep 2 08:18 shuffle-word-130-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 520K Sep 2 08:18 shuffle-word-1300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 30K Sep 2 08:18 shuffle-word-135-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 29K Sep 2 08:18 shuffle-word-140-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 518K Sep 2 08:18 shuffle-word-1400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 26K Sep 2 08:18 shuffle-word-145-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 44K Sep 2 08:18 shuffle-word-15-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 28K Sep 2 08:18 shuffle-word-150-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 520K Sep 2 08:18 shuffle-word-1500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 29K Sep 2 08:18 shuffle-word-155-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 28K Sep 2 08:18 shuffle-word-160-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 522K Sep 2 08:18 shuffle-word-1600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 28K Sep 2 08:18 shuffle-word-165-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-170-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 520K Sep 2 08:18 shuffle-word-1700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 28K Sep 2 08:18 shuffle-word-175-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-180-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 520K Sep 2 08:18 shuffle-word-1800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 28K Sep 2 08:18 shuffle-word-185-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-190-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 522K Sep 2 08:18 shuffle-word-1900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-195-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 39K Sep 2 08:18 shuffle-word-20-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 521K Sep 2 08:18 shuffle-word-2000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-205-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 28K Sep 2 08:18 shuffle-word-210-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 521K Sep 2 08:18 shuffle-word-2100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-215-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-220-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 521K Sep 2 08:18 shuffle-word-2200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-225-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-230-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 521K Sep 2 08:18 shuffle-word-2300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-235-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 26K Sep 2 08:18 shuffle-word-240-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 521K Sep 2 08:18 shuffle-word-2400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-245-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 38K Sep 2 08:18 shuffle-word-25-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-250-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 522K Sep 2 08:18 shuffle-word-2500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-255-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 26K Sep 2 08:18 shuffle-word-260-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 518K Sep 2 08:18 shuffle-word-2600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 28K Sep 2 08:18 shuffle-word-265-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-270-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 512K Sep 2 08:18 shuffle-word-2700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-275-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 28K Sep 2 08:18 shuffle-word-280-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 508K Sep 2 08:18 shuffle-word-2800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 28K Sep 2 08:18 shuffle-word-285-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 26K Sep 2 08:18 shuffle-word-290-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 509K Sep 2 08:18 shuffle-word-2900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-295-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 34K Sep 2 08:18 shuffle-word-30-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 28K Sep 2 08:18 shuffle-word-300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 509K Sep 2 08:18 shuffle-word-3000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 26K Sep 2 08:18 shuffle-word-305-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 26K Sep 2 08:18 shuffle-word-310-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 509K Sep 2 08:18 shuffle-word-3100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-315-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-320-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 509K Sep 2 08:18 shuffle-word-3200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-325-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-330-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 509K Sep 2 08:18 shuffle-word-3300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-335-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-340-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 509K Sep 2 08:18 shuffle-word-3400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-345-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 33K Sep 2 08:18 shuffle-word-35-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-350-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 509K Sep 2 08:18 shuffle-word-3500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 28K Sep 2 08:18 shuffle-word-355-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-360-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 508K Sep 2 08:18 shuffle-word-3600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 28K Sep 2 08:18 shuffle-word-365-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-370-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 509K Sep 2 08:18 shuffle-word-3700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 28K Sep 2 08:18 shuffle-word-375-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-380-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 509K Sep 2 08:18 shuffle-word-3800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-385-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 28K Sep 2 08:18 shuffle-word-390-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 509K Sep 2 08:18 shuffle-word-3900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-395-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 32K Sep 2 08:18 shuffle-word-40-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 28K Sep 2 08:18 shuffle-word-400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 508K Sep 2 08:18 shuffle-word-4000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-405-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-410-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 508K Sep 2 08:18 shuffle-word-4100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-415-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-420-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 509K Sep 2 08:18 shuffle-word-4200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-425-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-430-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 509K Sep 2 08:18 shuffle-word-4300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-435-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-440-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 509K Sep 2 08:18 shuffle-word-4400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-445-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 32K Sep 2 08:18 shuffle-word-45-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 28K Sep 2 08:18 shuffle-word-450-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 509K Sep 2 08:18 shuffle-word-4500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 26K Sep 2 08:18 shuffle-word-455-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-460-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 508K Sep 2 08:18 shuffle-word-4600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-465-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-470-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 509K Sep 2 08:18 shuffle-word-4700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-475-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-480-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 509K Sep 2 08:18 shuffle-word-4800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-485-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-490-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 509K Sep 2 08:18 shuffle-word-4900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-495-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 84K Sep 2 08:18 shuffle-word-5-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 31K Sep 2 08:18 shuffle-word-50-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 28K Sep 2 08:18 shuffle-word-500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 509K Sep 2 08:18 shuffle-word-5000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 26K Sep 2 08:18 shuffle-word-505-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-510-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 509K Sep 2 08:18 shuffle-word-5100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 26K Sep 2 08:18 shuffle-word-515-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-520-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 509K Sep 2 08:18 shuffle-word-5200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-525-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-530-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 508K Sep 2 08:18 shuffle-word-5300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-535-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-540-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 509K Sep 2 08:18 shuffle-word-5400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-545-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 31K Sep 2 08:18 shuffle-word-55-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-550-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 509K Sep 2 08:18 shuffle-word-5500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-555-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 26K Sep 2 08:18 shuffle-word-560-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 509K Sep 2 08:18 shuffle-word-5600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 26K Sep 2 08:18 shuffle-word-565-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-570-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 509K Sep 2 08:18 shuffle-word-5700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-575-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 26K Sep 2 08:18 shuffle-word-580-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 509K Sep 2 08:18 shuffle-word-5800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-585-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 26K Sep 2 08:18 shuffle-word-590-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 509K Sep 2 08:18 shuffle-word-5900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-595-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 31K Sep 2 08:18 shuffle-word-60-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 509K Sep 2 08:18 shuffle-word-6000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-605-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-610-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 509K Sep 2 08:18 shuffle-word-6100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-615-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-620-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 508K Sep 2 08:18 shuffle-word-6200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-625-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 26K Sep 2 08:18 shuffle-word-630-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 509K Sep 2 08:18 shuffle-word-6300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 26K Sep 2 08:18 shuffle-word-635-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-640-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 509K Sep 2 08:18 shuffle-word-6400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-645-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 31K Sep 2 08:18 shuffle-word-65-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-650-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 509K Sep 2 08:18 shuffle-word-6500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 26K Sep 2 08:18 shuffle-word-655-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-660-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 509K Sep 2 08:18 shuffle-word-6600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 26K Sep 2 08:18 shuffle-word-665-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-670-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 509K Sep 2 08:18 shuffle-word-6700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 26K Sep 2 08:18 shuffle-word-675-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-680-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 508K Sep 2 08:18 shuffle-word-6800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 26K Sep 2 08:18 shuffle-word-685-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-690-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 508K Sep 2 08:18 shuffle-word-6900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-695-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 30K Sep 2 08:18 shuffle-word-70-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 26K Sep 2 08:18 shuffle-word-700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 509K Sep 2 08:18 shuffle-word-7000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-705-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-710-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 509K Sep 2 08:18 shuffle-word-7100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-715-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-720-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 508K Sep 2 08:18 shuffle-word-7200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 26K Sep 2 08:18 shuffle-word-725-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-730-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 509K Sep 2 08:18 shuffle-word-7300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-735-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 26K Sep 2 08:18 shuffle-word-740-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 509K Sep 2 08:18 shuffle-word-7400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 26K Sep 2 08:18 shuffle-word-745-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 31K Sep 2 08:18 shuffle-word-75-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-750-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 509K Sep 2 08:18 shuffle-word-7500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-755-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-760-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 508K Sep 2 08:18 shuffle-word-7600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-765-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 26K Sep 2 08:18 shuffle-word-770-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 509K Sep 2 08:18 shuffle-word-7700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-775-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-780-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 509K Sep 2 08:18 shuffle-word-7800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-785-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-790-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 509K Sep 2 08:18 shuffle-word-7900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 26K Sep 2 08:18 shuffle-word-795-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 29K Sep 2 08:18 shuffle-word-80-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 509K Sep 2 08:18 shuffle-word-8000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-805-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-810-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 26K Sep 2 08:18 shuffle-word-815-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 26K Sep 2 08:18 shuffle-word-820-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 28K Sep 2 08:18 shuffle-word-825-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-830-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 26K Sep 2 08:18 shuffle-word-835-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-840-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 26K Sep 2 08:18 shuffle-word-845-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 29K Sep 2 08:18 shuffle-word-85-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 26K Sep 2 08:18 shuffle-word-850-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 26K Sep 2 08:18 shuffle-word-855-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-860-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-865-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 26K Sep 2 08:18 shuffle-word-870-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-875-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 26K Sep 2 08:18 shuffle-word-880-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-885-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-890-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-895-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 29K Sep 2 08:18 shuffle-word-90-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 26K Sep 2 08:18 shuffle-word-900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-905-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-910-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-915-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 26K Sep 2 08:18 shuffle-word-920-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 26K Sep 2 08:18 shuffle-word-925-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-930-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 26K Sep 2 08:18 shuffle-word-935-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 26K Sep 2 08:18 shuffle-word-940-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-945-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 29K Sep 2 08:18 shuffle-word-95-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-950-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 26K Sep 2 08:18 shuffle-word-955-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 26K Sep 2 08:18 shuffle-word-960-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-965-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 26K Sep 2 08:18 shuffle-word-970-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 26K Sep 2 08:18 shuffle-word-975-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-980-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-985-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-990-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 27K Sep 2 08:18 shuffle-word-995-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "-rw-r--r-- 1 root root 6.0K Sep 2 08:18 word-2-count.jsonl\n" ] } ], "source": [ "%%script bash\n", "\n", "########################################\n", "# Generate the required jsonl dataset\n", "########################################\n", "\n", "# Reset the dataset dir\n", "mkdir -p ../dataset\n", "rm -rf ../dataset/*.jsonl\n", "\n", "# Generate the various datasets\n", "echo \"## Generating word reptition dataset ##\"\n", "\n", "#\n", "# We reduce the training set for < 50 words - and shift the focus upwards\n", "# (aka 50-100 token * 2 : ~100 - 250 token ctx len)\n", "#\n", "python ../memory_script/gen_limited_prompt_completion_jsonl.py ../dataset/word-2-count.jsonl 2 50 &\n", "for i in {5..1000..5} \n", "do\n", " python ../memory_script/gen_limited_prompt_completion_jsonl.py ../dataset/gen-word-$i-count.jsonl $i 50 & \n", " python ../memory_script/shuffle_limited_prompt_completion_jsonl.py ../dataset/shuffle-word-$i-count.jsonl $i 1 & \n", "done\n", "\n", "#\n", "# Ramping up the 50+ - 4200 words dataset\n", "# \n", "for i in {1100..8000..100} \n", "do\n", " python ../memory_script/gen_limited_prompt_completion_jsonl.py ../dataset/gen-word-$i-count.jsonl $i 2000 & \n", " python ../memory_script/shuffle_limited_prompt_completion_jsonl.py ../dataset/shuffle-word-$i-count.jsonl $i 20 & \n", "done\n", "\n", "wait\n", "echo \"## Done ##\"\n", "\n", "ls -lh ../dataset/" ] }, { "cell_type": "code", "execution_count": 6, "id": "4e120a7c", "metadata": { "execution": { "iopub.execute_input": "2023-09-02T08:18:26.680311Z", "iopub.status.busy": "2023-09-02T08:18:26.680056Z" }, "papermill": { "duration": null, "end_time": null, "exception": false, "start_time": "2023-09-02T08:18:26.618314", "status": "running" }, "tags": [] }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Setting ds_accelerator to cuda (auto detect)\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "[RWKV.model] Running RWKV model using 'torch-jit' with torch '2.0.1+cu118'\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "/usr/local/lib/python3.11/dist-packages/lightning/pytorch/cli.py:484: UserWarning: LightningCLI's args parameter is intended to run from within Python like if it were from the command line. To prevent mistakes it is not recommended to provide both args and command line arguments, got: sys.argv[1:]=['fit', '-c', '/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/notebook/experiment/rwkv-x-exp/v5-memory/config-mem-template.yaml', '--trainer.logger.init_args.name=v5-L96-D1024-E0.1 - Mem-Tune ctx-8k (train-ctx=4k, deepspeed_stage_1)', '--trainer.strategy=deepspeed_stage_1', '--trainer.devices=auto', '--trainer.callbacks.init_args.dirpath=../checkpoint/v5-L96-D1024-E0_1-mem-ctx-8k/', '--model.lr_init=3e-4', '--model.lr_final=1e-4', '--data.max_token_size=8192', '--model.ctx_len=4096', '--model.bptt_learning_range=2', '--model.load_model=../model/v5-L96-D1024-E0_1-mem-ctx-4k.pth'], args=['fit', '-c', '/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/notebook/experiment/rwkv-x-exp/v5-memory/config-mem-template.yaml', '--trainer.logger.init_args.name=v5-L96-D1024-E0.1 - Mem-Tune ctx-8k (train-ctx=4k, deepspeed_stage_1)', '--trainer.strategy=deepspeed_stage_1', '--trainer.devices=auto', '--trainer.callbacks.init_args.dirpath=../checkpoint/v5-L96-D1024-E0_1-mem-ctx-8k/', '--model.lr_init=3e-4', '--model.lr_final=1e-4', '--data.max_token_size=8192', '--model.ctx_len=4096', '--model.bptt_learning_range=2', '--model.load_model=../model/v5-L96-D1024-E0_1-mem-ctx-4k.pth'].\r\n", " rank_zero_warn(\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "/usr/local/lib/python3.11/dist-packages/lightning/fabric/utilities/seed.py:39: UserWarning: No seed found, seed set to 2561877090\r\n", " rank_zero_warn(f\"No seed found, seed set to {seed}\")\r\n", "Global seed set to 2561877090\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\u001b[34m\u001b[1mwandb\u001b[0m: Currently logged in as: \u001b[33mpicocreator\u001b[0m (\u001b[33mrwkv-x-dev\u001b[0m). Use \u001b[1m`wandb login --relogin`\u001b[0m to force relogin\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\u001b[34m\u001b[1mwandb\u001b[0m: Tracking run with wandb version 0.15.9\r\n", "\u001b[34m\u001b[1mwandb\u001b[0m: Run data is saved locally in \u001b[35m\u001b[1m./wandb/run-20230902_081832-8e7vxd6w\u001b[0m\r\n", "\u001b[34m\u001b[1mwandb\u001b[0m: Run \u001b[1m`wandb offline`\u001b[0m to turn off syncing.\r\n", "\u001b[34m\u001b[1mwandb\u001b[0m: Syncing run \u001b[33mv5-L96-D1024-E0.1 - Mem-Tune ctx-8k (train-ctx=4k, deepspeed_stage_1)\u001b[0m\r\n", "\u001b[34m\u001b[1mwandb\u001b[0m: ⭐️ View project at \u001b[34m\u001b[4mhttps://wandb.ai/rwkv-x-dev/RWKV-X-Experiments\u001b[0m\r\n", "\u001b[34m\u001b[1mwandb\u001b[0m: 🚀 View run at \u001b[34m\u001b[4mhttps://wandb.ai/rwkv-x-dev/RWKV-X-Experiments/runs/8e7vxd6w\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%| | 0/541 [00:00=12.1), as this is known to have freeze issues\r\n", "# - The terms used in wandb / the progress bar can be confusing, see the github README.md for beter clarifications\r\n", "# - When resuming from checkpoint, the estimated time is inaccurate\r\n", "#\r\n", "\r\n", "[RWKV.model] Configuring optimizer with\r\n", " - lr_init: 3.000e-04 (0.0003)\r\n", " - lr_final: 1.000e-04 (0.0001)\r\n", "\r\n", "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Detected CUDA files, patching ldflags\r\n", "Emitting ninja build file /root/.cache/torch_extensions/py311_cu118/fused_adam/build.ninja...\r\n", "Building extension module fused_adam...\r\n", "Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)\r\n", "ninja: no work to do.\r\n", "Loading extension module fused_adam...\r\n", "Time to load fused_adam op: 0.0697624683380127 seconds\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Loading extension module fused_adam...\r\n", "Loading extension module fused_adam...\r\n", "Loading extension module fused_adam...\r\n", "Time to load fused_adam op: 0.1018216609954834 seconds\r\n", "Time to load fused_adam op: 0.1012732982635498 seconds\r\n", "Time to load fused_adam op: 0.10108113288879395 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: 0.10145211219787598 seconds\r\n", "Time to load fused_adam op: 0.10141134262084961 seconds\r\n", "Loading extension module fused_adam...\r\n", "Time to load fused_adam op: 0.10147690773010254 seconds\r\n", "Time to load fused_adam op: 0.10164475440979004 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" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Emitting ninja build file /root/.cache/torch_extensions/py311_cu118/utils/build.ninja...\r\n", "Building extension module utils...\r\n", "Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)\r\n", "ninja: no work to do.\r\n", "Loading extension module utils...\r\n", "Time to load utils op: 0.06967592239379883 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: 0.10271096229553223 seconds\r\n", "Time to load utils op: 0.10364270210266113 seconds\r\n", "Loading extension module utils...\r\n", "Loading extension module utils...\r\n", "Time to load utils op: 0.10257887840270996 seconds\r\n", "Time to load utils op: 0.10231256484985352 seconds\r\n", "Loading extension module utils...\r\n", "Time to load utils op: 0.10250520706176758 seconds\r\n", "Loading extension module utils...\r\n", "Loading extension module utils...\r\n", "Time to load utils op: 0.10262155532836914 seconds\r\n", "Time to load utils op: 0.10332131385803223 seconds\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: 2 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: 4 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: 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: 7 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: 0.0010597705841064453 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: 0.0006201267242431641 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", "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", "Time to load utils op: 0.0006339550018310547 seconds\r\n", "No modifications detected for re-loaded extension module utils, skipping build step...\r\n", "Loading extension module utils...\r\n", "Using /root/.cache/torch_extensions/py311_cu118 as PyTorch extensions root...\r\n", "Time to load utils op: 0.0006387233734130859 seconds\r\n", "No modifications detected for re-loaded extension module utils, skipping build step...\r\n", "Loading extension module utils...\r\n", "Time to load utils op: 0.0006029605865478516 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: 0.000637054443359375 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: 0.0006983280181884766 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: 0.0009295940399169922 seconds\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r\n", " | Name | Type | Params\r\n", "--------------------------------------\r\n", "0 | emb | Embedding | 51.5 M\r\n", "1 | blocks | ModuleList | 1.3 B \r\n", "2 | ln_out | LayerNorm | 2.0 K \r\n", "3 | head | Linear | 51.5 M\r\n", "--------------------------------------\r\n", "1.4 B Trainable params\r\n", "0 Non-trainable params\r\n", "1.4 B Total params\r\n", "5,650.715 Total estimated model params size (MB)\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", "Training: 0it [00:00, ?it/s]\r", "Training: 0%| | 0/12318 [00:00