diff --git "a/experiment/rwkv-x-exp/v5-r3-memory/L6-D2560-E1e-1-ctx4k/stage3.ipynb" "b/experiment/rwkv-x-exp/v5-r3-memory/L6-D2560-E1e-1-ctx4k/stage3.ipynb" --- "a/experiment/rwkv-x-exp/v5-r3-memory/L6-D2560-E1e-1-ctx4k/stage3.ipynb" +++ "b/experiment/rwkv-x-exp/v5-r3-memory/L6-D2560-E1e-1-ctx4k/stage3.ipynb" @@ -3,13 +3,13 @@ { "attachments": {}, "cell_type": "markdown", - "id": "219a53fb", + "id": "5efa5cf6", "metadata": { "papermill": { - "duration": 0.004385, - "end_time": "2023-09-13T19:02:32.553797", + "duration": 0.004315, + "end_time": "2023-09-13T21:43:19.771432", "exception": false, - "start_time": "2023-09-13T19:02:32.549412", + "start_time": "2023-09-13T21:43:19.767117", "status": "completed" }, "tags": [] @@ -25,13 +25,13 @@ { "attachments": {}, "cell_type": "markdown", - "id": "e73cb2f6", + "id": "3f94c3fe", "metadata": { "papermill": { - "duration": 0.002807, - "end_time": "2023-09-13T19:02:32.559744", + "duration": 0.002697, + "end_time": "2023-09-13T21:43:19.777118", "exception": false, - "start_time": "2023-09-13T19:02:32.556937", + "start_time": "2023-09-13T21:43:19.774421", "status": "completed" }, "tags": [] @@ -43,19 +43,19 @@ { "cell_type": "code", "execution_count": 1, - "id": "1d1252f7", + "id": "4c9a0a0b", "metadata": { "execution": { - "iopub.execute_input": "2023-09-13T19:02:32.564654Z", - "iopub.status.busy": "2023-09-13T19:02:32.564113Z", - "iopub.status.idle": "2023-09-13T19:02:33.435512Z", - "shell.execute_reply": "2023-09-13T19:02:33.434663Z" + "iopub.execute_input": "2023-09-13T21:43:19.781369Z", + "iopub.status.busy": "2023-09-13T21:43:19.781083Z", + "iopub.status.idle": "2023-09-13T21:43:20.655752Z", + "shell.execute_reply": "2023-09-13T21:43:20.654921Z" }, "papermill": { - "duration": 0.87593, - "end_time": "2023-09-13T19:02:33.437575", + "duration": 0.87905, + "end_time": "2023-09-13T21:43:20.657671", "exception": false, - "start_time": "2023-09-13T19:02:32.561645", + "start_time": "2023-09-13T21:43:19.778621", "status": "completed" }, "tags": [] @@ -83,19 +83,19 @@ { "cell_type": "code", "execution_count": 2, - "id": "b994a9a1", + "id": "3054f355", "metadata": { "execution": { - "iopub.execute_input": "2023-09-13T19:02:33.444255Z", - "iopub.status.busy": "2023-09-13T19:02:33.443997Z", - "iopub.status.idle": "2023-09-13T19:02:35.556431Z", - "shell.execute_reply": "2023-09-13T19:02:35.555653Z" + "iopub.execute_input": "2023-09-13T21:43:20.664999Z", + "iopub.status.busy": "2023-09-13T21:43:20.664744Z", + "iopub.status.idle": "2023-09-13T21:43:22.809995Z", + "shell.execute_reply": "2023-09-13T21:43:22.809266Z" }, "papermill": { - "duration": 2.117639, - "end_time": "2023-09-13T19:02:35.558459", + "duration": 2.15121, + "end_time": "2023-09-13T21:43:22.812140", "exception": false, - "start_time": "2023-09-13T19:02:33.440820", + "start_time": "2023-09-13T21:43:20.660930", "status": "completed" }, "tags": [] @@ -118,19 +118,19 @@ { "cell_type": "code", "execution_count": 3, - "id": "d509963e", + "id": "cb2a6c86", "metadata": { "execution": { - "iopub.execute_input": "2023-09-13T19:02:35.566137Z", - "iopub.status.busy": "2023-09-13T19:02:35.565789Z", - "iopub.status.idle": "2023-09-13T19:02:35.574538Z", - "shell.execute_reply": "2023-09-13T19:02:35.574003Z" + "iopub.execute_input": "2023-09-13T21:43:22.819682Z", + "iopub.status.busy": "2023-09-13T21:43:22.819442Z", + "iopub.status.idle": "2023-09-13T21:43:22.828417Z", + "shell.execute_reply": "2023-09-13T21:43:22.827850Z" }, "papermill": { - "duration": 0.01433, - "end_time": "2023-09-13T19:02:35.576116", + "duration": 0.014595, + "end_time": "2023-09-13T21:43:22.830049", "exception": false, - "start_time": "2023-09-13T19:02:35.561786", + "start_time": "2023-09-13T21:43:22.815454", "status": "completed" }, "tags": [] @@ -197,19 +197,19 @@ { "cell_type": "code", "execution_count": 4, - "id": "1d025793", + "id": "9e3a24cf", "metadata": { "execution": { - "iopub.execute_input": "2023-09-13T19:02:35.583154Z", - "iopub.status.busy": "2023-09-13T19:02:35.583006Z", - "iopub.status.idle": "2023-09-13T19:02:36.296504Z", - "shell.execute_reply": "2023-09-13T19:02:36.295637Z" + "iopub.execute_input": "2023-09-13T21:43:22.837873Z", + "iopub.status.busy": "2023-09-13T21:43:22.837614Z", + "iopub.status.idle": "2023-09-13T21:43:23.592874Z", + "shell.execute_reply": "2023-09-13T21:43:23.592085Z" }, "papermill": { - "duration": 0.71891, - "end_time": "2023-09-13T19:02:36.298255", + "duration": 0.761153, + "end_time": "2023-09-13T21:43:23.594701", "exception": false, - "start_time": "2023-09-13T19:02:35.579345", + "start_time": "2023-09-13T21:43:22.833548", "status": "completed" }, "tags": [] @@ -219,7 +219,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "--2023-09-13 19:02:35-- https://huggingface.co/rwkv-x-dev/rwkv-x-playground/resolve/main/experiment/rwkv-x-exp/v5-r3-memory/L6-D2560-E1e-1-ctx4k/v5r3-L12-D2560-E0_1-mem-ctx-512.pth\r\n", + "--2023-09-13 21:43:22-- https://huggingface.co/rwkv-x-dev/rwkv-x-playground/resolve/main/experiment/rwkv-x-exp/v5-r3-memory/L6-D2560-E1e-1-ctx4k/v5r3-L12-D2560-E0_1-mem-ctx-512.pth\r\n", "Resolving huggingface.co (huggingface.co)... 13.33.33.20, 13.33.33.55, 13.33.33.110, ...\r\n", "Connecting to huggingface.co (huggingface.co)|13.33.33.20|:443... connected.\r\n", "HTTP request sent, awaiting response... " @@ -230,7 +230,7 @@ "output_type": "stream", "text": [ "404 Not Found\r\n", - "2023-09-13 19:02:35 ERROR 404: Not Found.\r\n", + "2023-09-13 21:43:23 ERROR 404: Not Found.\r\n", "\r\n" ] }, @@ -239,8 +239,8 @@ "output_type": "stream", "text": [ "total 10K\r\n", - "drwxr-xr-x 2 root root 2 Sep 13 19:02 .\r\n", - "drwxr-xr-x 20 root root 24 Sep 13 19:02 ..\r\n" + "drwxr-xr-x 2 root root 2 Sep 13 21:43 .\r\n", + "drwxr-xr-x 20 root root 24 Sep 13 21:43 ..\r\n" ] } ], @@ -255,13 +255,13 @@ }, { "cell_type": "markdown", - "id": "3d413898", + "id": "d046d1e0", "metadata": { "papermill": { - "duration": 0.00337, - "end_time": "2023-09-13T19:02:36.305351", + "duration": 0.003341, + "end_time": "2023-09-13T21:43:23.601885", "exception": false, - "start_time": "2023-09-13T19:02:36.301981", + "start_time": "2023-09-13T21:43:23.598544", "status": "completed" }, "tags": [] @@ -275,19 +275,19 @@ { "cell_type": "code", "execution_count": 5, - "id": "4b593663", + "id": "c2fb4c25", "metadata": { "execution": { - "iopub.execute_input": "2023-09-13T19:02:36.311981Z", - "iopub.status.busy": "2023-09-13T19:02:36.311731Z", - "iopub.status.idle": "2023-09-13T19:02:59.792866Z", - "shell.execute_reply": "2023-09-13T19:02:59.792387Z" + "iopub.execute_input": "2023-09-13T21:43:23.608478Z", + "iopub.status.busy": "2023-09-13T21:43:23.608215Z", + "iopub.status.idle": "2023-09-13T21:43:47.016389Z", + "shell.execute_reply": "2023-09-13T21:43:47.015749Z" }, "papermill": { - "duration": 23.516383, - "end_time": "2023-09-13T19:02:59.825166", + "duration": 23.441437, + "end_time": "2023-09-13T21:43:47.046834", "exception": false, - "start_time": "2023-09-13T19:02:36.308783", + "start_time": "2023-09-13T21:43:23.605397", "status": "completed" }, "tags": [] @@ -311,847 +311,847 @@ "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 25 max words, 100 samples - at ../dataset/gen-word-25-count.jsonl\n" + "Generated JSONL file with - 15 max words, 100 samples - at ../dataset/gen-word-15-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 15 max words, 100 samples - at ../dataset/gen-word-15-count.jsonl\n" + "Generated JSONL file with - 50 max words, 100 samples - at ../dataset/gen-word-50-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 10 max words, 100 samples - at ../dataset/gen-word-10-count.jsonl\n" + "Generated JSONL file with - 75 max words, 100 samples - at ../dataset/gen-word-75-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 35 max words, 100 samples - at ../dataset/gen-word-35-count.jsonl\n" + "Generated JSONL file with - 30 max words, 100 samples - at ../dataset/gen-word-30-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 65 max words, 100 samples - at ../dataset/gen-word-65-count.jsonl\n" + "Generated JSONL file with - 10 max words, 100 samples - at ../dataset/gen-word-10-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 5 max words, 100 samples - at ../dataset/gen-word-5-count.jsonl\n" + "Generated a single JSONL file with 870 samples (10 token repeat) - 30 max words - at ../dataset/shuffle-word-30-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 60 max words, 100 samples - at ../dataset/gen-word-60-count.jsonl\n" + "Generated JSONL file with - 25 max words, 100 samples - at ../dataset/gen-word-25-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 30 max words, 100 samples - at ../dataset/gen-word-30-count.jsonl\n" + "Generated JSONL file with - 35 max words, 100 samples - at ../dataset/gen-word-35-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 45 max words, 100 samples - at ../dataset/gen-word-45-count.jsonl\n" + "Generated a single JSONL file with 1060 samples (10 token repeat) - 25 max words - at ../dataset/shuffle-word-25-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 70 max words, 100 samples - at ../dataset/gen-word-70-count.jsonl\n" + "Generated a single JSONL file with 1766 samples (10 token repeat) - 15 max words - at ../dataset/shuffle-word-15-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 100 max words, 100 samples - at ../dataset/gen-word-100-count.jsonl\n" + "Generated JSONL file with - 55 max words, 100 samples - at ../dataset/gen-word-55-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 50 max words, 100 samples - at ../dataset/gen-word-50-count.jsonl\n" + "Generated JSONL file with - 95 max words, 100 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) - 2900 max words - at ../dataset/shuffle-word-2900-count.jsonl\n" + "Generated JSONL file with - 40 max words, 100 samples - at ../dataset/gen-word-40-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated a single JSONL file with 445 samples (10 token repeat) - 60 max words - at ../dataset/shuffle-word-60-count.jsonl\n" + "Generated JSONL file with - 80 max words, 100 samples - at ../dataset/gen-word-80-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 55 max words, 100 samples - at ../dataset/gen-word-55-count.jsonl\n" + "Generated JSONL file with - 60 max words, 100 samples - at ../dataset/gen-word-60-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 80 max words, 100 samples - at ../dataset/gen-word-80-count.jsonl\n" + "Generated a single JSONL file with 374 samples (10 token repeat) - 70 max words - at ../dataset/shuffle-word-70-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 75 max words, 100 samples - at ../dataset/gen-word-75-count.jsonl\n" + "Generated JSONL file with - 45 max words, 100 samples - at ../dataset/gen-word-45-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated a single JSONL file with 655 samples (10 token repeat) - 40 max words - at ../dataset/shuffle-word-40-count.jsonl\n" + "Generated a single JSONL file with 763 samples (10 token repeat) - 35 max words - at ../dataset/shuffle-word-35-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 95 max words, 100 samples - at ../dataset/gen-word-95-count.jsonl\n" + "Generated a single JSONL file with 348 samples (10 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 522 samples (10 token repeat) - 50 max words - at ../dataset/shuffle-word-50-count.jsonl\n" + "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 2623 samples (10 token repeat) - 10 max words - at ../dataset/shuffle-word-10-count.jsonl\n" + "Generated a single JSONL file with 665 samples (10 token repeat) - 40 max words - at ../dataset/shuffle-word-40-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 85 max words, 100 samples - at ../dataset/gen-word-85-count.jsonl\n" + "Generated a single JSONL file with 586 samples (10 token repeat) - 45 max words - at ../dataset/shuffle-word-45-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated a single JSONL file with 873 samples (10 token repeat) - 30 max words - at ../dataset/shuffle-word-30-count.jsonl\n" + "Generated a single JSONL file with 2613 samples (10 token repeat) - 10 max words - at ../dataset/shuffle-word-10-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated a single JSONL file with 333 samples (10 token repeat) - 80 max words - at ../dataset/shuffle-word-80-count.jsonl\n" + "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 410 samples (10 token repeat) - 65 max words - at ../dataset/shuffle-word-65-count.jsonl\n" + "Generated a single JSONL file with 100 samples (20 token repeat) - 600 max words - at ../dataset/shuffle-word-600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated a single JSONL file with 305 samples (10 token repeat) - 90 max words - at ../dataset/shuffle-word-90-count.jsonl\n" + "Generated a single JSONL file with 5601 samples (10 token repeat) - 5 max words - at ../dataset/shuffle-word-5-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated a single JSONL file with 1065 samples (10 token repeat) - 25 max words - at ../dataset/shuffle-word-25-count.jsonl\n" + "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 a single JSONL file with 590 samples (10 token repeat) - 45 max words - at ../dataset/shuffle-word-45-count.jsonl\n" + "Generated a single JSONL file with 51 samples (20 token repeat) - 1300 max words - at ../dataset/shuffle-word-1300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated a single JSONL file with 1306 samples (10 token repeat) - 20 max words - at ../dataset/shuffle-word-20-count.jsonl\n" + "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 267 samples (10 token repeat) - 100 max words - at ../dataset/shuffle-word-100-count.jsonl\n" + "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 a single JSONL file with 757 samples (10 token repeat) - 35 max words - at ../dataset/shuffle-word-35-count.jsonl\n" + "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 271 samples (20 token repeat) - 200 max words - at ../dataset/shuffle-word-200-count.jsonl\n" + "Generated a single JSONL file with 80 samples (20 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 309 samples (10 token repeat) - 85 max words - at ../dataset/shuffle-word-85-count.jsonl\n" + "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 a single JSONL file with 278 samples (10 token repeat) - 95 max words - at ../dataset/shuffle-word-95-count.jsonl\n" + "Generated a single JSONL file with 63 samples (20 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 142 samples (20 token repeat) - 400 max words - at ../dataset/shuffle-word-400-count.jsonl\n" + "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) - 3700 max words - at ../dataset/shuffle-word-3700-count.jsonl\n" + "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 350 samples (10 token repeat) - 75 max words - at ../dataset/shuffle-word-75-count.jsonl\n" + "Generated a single JSONL file with 38 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 20 samples (20 token repeat) - 6300 max words - at ../dataset/shuffle-word-6300-count.jsonl\n" + "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 a single JSONL file with 377 samples (10 token repeat) - 70 max words - at ../dataset/shuffle-word-70-count.jsonl\n" + "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) - 6000 max words - at ../dataset/shuffle-word-6000-count.jsonl\n" + "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 184 samples (20 token repeat) - 300 max words - at ../dataset/shuffle-word-300-count.jsonl\n" + "Generated a single JSONL file with 257 samples (10 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 20 samples (20 token repeat) - 7600 max words - at ../dataset/shuffle-word-7600-count.jsonl\n" + "Generated JSONL file with - 5 max words, 100 samples - at ../dataset/gen-word-5-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" + "Generated a single JSONL file with 185 samples (20 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 60 samples (20 token repeat) - 1100 max words - at ../dataset/shuffle-word-1100-count.jsonl\n" + "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 a single JSONL file with 20 samples (20 token repeat) - 7500 max words - at ../dataset/shuffle-word-7500-count.jsonl\n" + "Generated a single JSONL file with 117 samples (20 token repeat) - 500 max words - at ../dataset/shuffle-word-500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated a single JSONL file with 1780 samples (10 token repeat) - 15 max words - at ../dataset/shuffle-word-15-count.jsonl\n" + "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 a single JSONL file with 487 samples (10 token repeat) - 55 max words - at ../dataset/shuffle-word-55-count.jsonl\n" + "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 a single JSONL file with 113 samples (20 token repeat) - 500 max words - at ../dataset/shuffle-word-500-count.jsonl\n" + "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 60 samples (20 token repeat) - 1000 max words - at ../dataset/shuffle-word-1000-count.jsonl\n" + "Generated JSONL file with - 65 max words, 100 samples - at ../dataset/gen-word-65-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 90 max words, 100 samples - at ../dataset/gen-word-90-count.jsonl\n" + "Generated JSONL file with - 70 max words, 100 samples - at ../dataset/gen-word-70-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" + "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 64 samples (20 token repeat) - 900 max words - at ../dataset/shuffle-word-900-count.jsonl\n" + "Generated JSONL file with - 85 max words, 100 samples - at ../dataset/gen-word-85-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" + "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 a single JSONL file with 40 samples (20 token repeat) - 2000 max words - at ../dataset/shuffle-word-2000-count.jsonl\n" + "Generated a single JSONL file with 293 samples (10 token repeat) - 90 max words - at ../dataset/shuffle-word-90-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" + "Generated a single JSONL file with 1301 samples (10 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 20 samples (20 token repeat) - 7400 max words - at ../dataset/shuffle-word-7400-count.jsonl\n" + "Generated a single JSONL file with 318 samples (10 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 40 samples (20 token repeat) - 1700 max words - at ../dataset/shuffle-word-1700-count.jsonl\n" + "Generated JSONL file with - 100 max words, 100 samples - at ../dataset/gen-word-100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 40 max words, 100 samples - at ../dataset/gen-word-40-count.jsonl\n" + "Generated JSONL file with - 90 max words, 100 samples - at ../dataset/gen-word-90-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated a single JSONL file with 34 samples (20 token repeat) - 2500 max words - at ../dataset/shuffle-word-2500-count.jsonl\n" + "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) - 6600 max words - at ../dataset/shuffle-word-6600-count.jsonl\n" + "Generated a single JSONL file with 330 samples (10 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 21 samples (20 token repeat) - 2800 max words - at ../dataset/shuffle-word-2800-count.jsonl\n" + "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 30 samples (20 token repeat) - 2600 max words - at ../dataset/shuffle-word-2600-count.jsonl\n" + "Generated a single JSONL file with 283 samples (10 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 20 samples (20 token repeat) - 4100 max words - at ../dataset/shuffle-word-4100-count.jsonl\n" + "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 20 samples (20 token repeat) - 7000 max words - at ../dataset/shuffle-word-7000-count.jsonl\n" + "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 20 samples (20 token repeat) - 3000 max words - at ../dataset/shuffle-word-3000-count.jsonl\n" + "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 a single JSONL file with 534 samples (20 token repeat) - 100 max words - at ../dataset/shuffle-word-100-count.jsonl\n" + "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 a single JSONL file with 22 samples (20 token repeat) - 2700 max words - at ../dataset/shuffle-word-2700-count.jsonl\n" + "Generated a single JSONL file with 60 samples (20 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 20 samples (20 token repeat) - 4800 max words - at ../dataset/shuffle-word-4800-count.jsonl\n" + "Generated a single JSONL file with 447 samples (10 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 40 samples (20 token repeat) - 1900 max words - at ../dataset/shuffle-word-1900-count.jsonl\n" + "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) - 4000 max words - at ../dataset/shuffle-word-4000-count.jsonl\n" + "Generated a single JSONL file with 477 samples (10 token repeat) - 55 max words - at ../dataset/shuffle-word-55-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 5100 max words - at ../dataset/shuffle-word-5100-count.jsonl\n" + "Generated a single JSONL file with 408 samples (10 token repeat) - 65 max words - at ../dataset/shuffle-word-65-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" + "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 a single JSONL file with 20 samples (20 token repeat) - 6100 max words - at ../dataset/shuffle-word-6100-count.jsonl\n" + "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 20 samples (20 token repeat) - 5400 max words - at ../dataset/shuffle-word-5400-count.jsonl\n" + "Generated a single JSONL file with 80 samples (20 token repeat) - 800 max words - at ../dataset/shuffle-word-800-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" + "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 20 samples (20 token repeat) - 7900 max words - at ../dataset/shuffle-word-7900-count.jsonl\n" + "Generated a single JSONL file with 275 samples (20 token repeat) - 200 max words - at ../dataset/shuffle-word-200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated a single JSONL file with 81 samples (20 token repeat) - 700 max words - at ../dataset/shuffle-word-700-count.jsonl\n" + "Generated a single JSONL file with 40 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) - 3600 max words - at ../dataset/shuffle-word-3600-count.jsonl\n" + "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 a single JSONL file with 80 samples (20 token repeat) - 800 max words - at ../dataset/shuffle-word-800-count.jsonl\n" + "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 20 samples (20 token repeat) - 4200 max words - at ../dataset/shuffle-word-4200-count.jsonl\n" + "Generated a single JSONL file with 531 samples (10 token repeat) - 50 max words - at ../dataset/shuffle-word-50-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated a single JSONL file with 40 samples (20 token repeat) - 1500 max words - at ../dataset/shuffle-word-1500-count.jsonl\n" + "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 20 samples (20 token repeat) - 3500 max words - at ../dataset/shuffle-word-3500-count.jsonl\n" + "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 a single JSONL file with 20 samples (20 token repeat) - 5200 max words - at ../dataset/shuffle-word-5200-count.jsonl\n" + "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 20 samples (20 token repeat) - 7100 max words - at ../dataset/shuffle-word-7100-count.jsonl\n" + "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 a single JSONL file with 20 samples (20 token repeat) - 7200 max words - at ../dataset/shuffle-word-7200-count.jsonl\n" + "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) - 3900 max words - at ../dataset/shuffle-word-3900-count.jsonl\n" + "Generated a single JSONL file with 140 samples (20 token repeat) - 400 max words - at ../dataset/shuffle-word-400-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" + "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) - 6800 max words - at ../dataset/shuffle-word-6800-count.jsonl\n" + "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 a single JSONL file with 20 samples (20 token repeat) - 5700 max words - at ../dataset/shuffle-word-5700-count.jsonl\n" + "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 a single JSONL file with 20 samples (20 token repeat) - 3300 max words - at ../dataset/shuffle-word-3300-count.jsonl\n" + "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 40 samples (20 token repeat) - 1600 max words - at ../dataset/shuffle-word-1600-count.jsonl\n" + "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 a single JSONL file with 100 samples (20 token repeat) - 600 max words - at ../dataset/shuffle-word-600-count.jsonl\n" + "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) - 8000 max words - at ../dataset/shuffle-word-8000-count.jsonl\n" + "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 a single JSONL file with 40 samples (20 token repeat) - 2300 max words - at ../dataset/shuffle-word-2300-count.jsonl\n" + "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 a single JSONL file with 40 samples (20 token repeat) - 1800 max words - at ../dataset/shuffle-word-1800-count.jsonl\n" + "Generated a single JSONL file with 532 samples (20 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 20 samples (20 token repeat) - 3400 max words - at ../dataset/shuffle-word-3400-count.jsonl\n" + "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 20 samples (20 token repeat) - 7300 max words - at ../dataset/shuffle-word-7300-count.jsonl\n" + "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 20 samples (20 token repeat) - 7800 max words - at ../dataset/shuffle-word-7800-count.jsonl\n" + "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 54 samples (20 token repeat) - 1300 max words - at ../dataset/shuffle-word-1300-count.jsonl\n" + "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 a single JSONL file with 20 samples (20 token repeat) - 3800 max words - at ../dataset/shuffle-word-3800-count.jsonl\n" + "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) - 4700 max words - at ../dataset/shuffle-word-4700-count.jsonl\n" + "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 a single JSONL file with 20 samples (20 token repeat) - 6500 max words - at ../dataset/shuffle-word-6500-count.jsonl\n" + "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 a single JSONL file with 20 samples (20 token repeat) - 5900 max words - at ../dataset/shuffle-word-5900-count.jsonl\n" + "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 20 samples (20 token repeat) - 6700 max words - at ../dataset/shuffle-word-6700-count.jsonl\n" + "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 20 samples (20 token repeat) - 3200 max words - at ../dataset/shuffle-word-3200-count.jsonl\n" + "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 20 samples (20 token repeat) - 6900 max words - at ../dataset/shuffle-word-6900-count.jsonl\n" + "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 a single JSONL file with 20 samples (20 token repeat) - 4400 max words - at ../dataset/shuffle-word-4400-count.jsonl\n" + "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 20 samples (20 token repeat) - 6400 max words - at ../dataset/shuffle-word-6400-count.jsonl\n" + "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 a single JSONL file with 20 samples (20 token repeat) - 5600 max words - at ../dataset/shuffle-word-5600-count.jsonl\n" + "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) - 6200 max words - at ../dataset/shuffle-word-6200-count.jsonl\n" + "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 20 samples (20 token repeat) - 4900 max words - at ../dataset/shuffle-word-4900-count.jsonl\n" + "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 a single JSONL file with 20 samples (20 token repeat) - 7700 max words - at ../dataset/shuffle-word-7700-count.jsonl\n" + "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 a single JSONL file with 20 samples (20 token repeat) - 5500 max words - at ../dataset/shuffle-word-5500-count.jsonl\n" + "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 20 samples (20 token repeat) - 5000 max words - at ../dataset/shuffle-word-5000-count.jsonl\n" + "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 a single JSONL file with 20 samples (20 token repeat) - 4500 max words - at ../dataset/shuffle-word-4500-count.jsonl\n" + "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 a single JSONL file with 40 samples (20 token repeat) - 1400 max words - at ../dataset/shuffle-word-1400-count.jsonl\n" + "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 20 samples (20 token repeat) - 5300 max words - at ../dataset/shuffle-word-5300-count.jsonl\n" + "Generated a single JSONL file with 26 samples (20 token repeat) - 2600 max words - at ../dataset/shuffle-word-2600-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" + "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 5566 samples (10 token repeat) - 5 max words - at ../dataset/shuffle-word-5-count.jsonl\n" + "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 JSONL file with - 100 max words, 2000 samples - at ../dataset/gen-word-100-count.jsonl\n" + "Generated JSONL file with - 200 max words, 2000 samples - at ../dataset/gen-word-200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 200 max words, 2000 samples - at ../dataset/gen-word-200-count.jsonl\n" + "Generated JSONL file with - 100 max words, 2000 samples - at ../dataset/gen-word-100-count.jsonl\n" ] }, { @@ -1165,28 +1165,28 @@ "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 400 max words, 2000 samples - at ../dataset/gen-word-400-count.jsonl\n" + "Generated JSONL file with - 800 max words, 2000 samples - at ../dataset/gen-word-800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 800 max words, 2000 samples - at ../dataset/gen-word-800-count.jsonl\n" + "Generated JSONL file with - 400 max words, 2000 samples - at ../dataset/gen-word-400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 600 max words, 2000 samples - at ../dataset/gen-word-600-count.jsonl\n" + "Generated JSONL file with - 500 max words, 2000 samples - at ../dataset/gen-word-500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 500 max words, 2000 samples - at ../dataset/gen-word-500-count.jsonl\n" + "Generated JSONL file with - 600 max words, 2000 samples - at ../dataset/gen-word-600-count.jsonl\n" ] }, { @@ -1200,70 +1200,70 @@ "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 900 max words, 2000 samples - at ../dataset/gen-word-900-count.jsonl\n" + "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 - 1000 max words, 2000 samples - at ../dataset/gen-word-1000-count.jsonl\n" + "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 - 1300 max words, 2000 samples - at ../dataset/gen-word-1300-count.jsonl\n" + "Generated JSONL file with - 1000 max words, 2000 samples - at ../dataset/gen-word-1000-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" + "Generated JSONL file with - 900 max words, 2000 samples - at ../dataset/gen-word-900-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" + "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 - 1500 max words, 2000 samples - at ../dataset/gen-word-1500-count.jsonl\n" + "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 - 1200 max words, 2000 samples - at ../dataset/gen-word-1200-count.jsonl\n" + "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 - 2200 max words, 2000 samples - at ../dataset/gen-word-2200-count.jsonl\n" + "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 - 2100 max words, 2000 samples - at ../dataset/gen-word-2100-count.jsonl\n" + "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 - 2000 max words, 2000 samples - at ../dataset/gen-word-2000-count.jsonl\n" + "Generated JSONL file with - 1500 max words, 2000 samples - at ../dataset/gen-word-1500-count.jsonl\n" ] }, { @@ -1277,147 +1277,147 @@ "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 1900 max words, 2000 samples - at ../dataset/gen-word-1900-count.jsonl\n" + "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" + "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" + "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 - 1600 max words, 2000 samples - at ../dataset/gen-word-1600-count.jsonl\n" + "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 - 3300 max words, 2000 samples - at ../dataset/gen-word-3300-count.jsonl\n" + "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 - 2700 max words, 2000 samples - at ../dataset/gen-word-2700-count.jsonl\n" + "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 - 2400 max words, 2000 samples - at ../dataset/gen-word-2400-count.jsonl\n" + "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 - 3100 max words, 2000 samples - at ../dataset/gen-word-3100-count.jsonl\n" + "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 - 2600 max words, 2000 samples - at ../dataset/gen-word-2600-count.jsonl\n" + "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 - 3000 max words, 2000 samples - at ../dataset/gen-word-3000-count.jsonl\n" + "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 - 2900 max words, 2000 samples - at ../dataset/gen-word-2900-count.jsonl\n" + "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 - 3700 max words, 2000 samples - at ../dataset/gen-word-3700-count.jsonl\n" + "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 - 2500 max words, 2000 samples - at ../dataset/gen-word-2500-count.jsonl\n" + "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 - 2800 max words, 2000 samples - at ../dataset/gen-word-2800-count.jsonl\n" + "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 - 3200 max words, 2000 samples - at ../dataset/gen-word-3200-count.jsonl\n" + "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 - 3400 max words, 2000 samples - at ../dataset/gen-word-3400-count.jsonl\n" + "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 - 4300 max words, 2000 samples - at ../dataset/gen-word-4300-count.jsonl\n" + "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 - 5900 max words, 2000 samples - at ../dataset/gen-word-5900-count.jsonl\n" + "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 - 4400 max words, 2000 samples - at ../dataset/gen-word-4400-count.jsonl\n" + "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 - 4600 max words, 2000 samples - at ../dataset/gen-word-4600-count.jsonl\n" + "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 - 6900 max words, 2000 samples - at ../dataset/gen-word-6900-count.jsonl\n" + "Generated JSONL file with - 3500 max words, 2000 samples - at ../dataset/gen-word-3500-count.jsonl\n" ] }, { @@ -1431,77 +1431,77 @@ "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 4100 max words, 2000 samples - at ../dataset/gen-word-4100-count.jsonl\n" + "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 - 4900 max words, 2000 samples - at ../dataset/gen-word-4900-count.jsonl\n" + "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 - 4500 max words, 2000 samples - at ../dataset/gen-word-4500-count.jsonl\n" + "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 - 4000 max words, 2000 samples - at ../dataset/gen-word-4000-count.jsonl\n" + "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 - 3500 max words, 2000 samples - at ../dataset/gen-word-3500-count.jsonl\n" + "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 - 3600 max words, 2000 samples - at ../dataset/gen-word-3600-count.jsonl\n" + "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 - 3800 max words, 2000 samples - at ../dataset/gen-word-3800-count.jsonl\n" + "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 - 6000 max words, 2000 samples - at ../dataset/gen-word-6000-count.jsonl\n" + "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 - 5100 max words, 2000 samples - at ../dataset/gen-word-5100-count.jsonl\n" + "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 - 5500 max words, 2000 samples - at ../dataset/gen-word-5500-count.jsonl\n" + "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 - 4200 max words, 2000 samples - at ../dataset/gen-word-4200-count.jsonl\n" + "Generated JSONL file with - 3900 max words, 2000 samples - at ../dataset/gen-word-3900-count.jsonl\n" ] }, { @@ -1515,112 +1515,112 @@ "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 3900 max words, 2000 samples - at ../dataset/gen-word-3900-count.jsonl\n" + "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 - 5200 max words, 2000 samples - at ../dataset/gen-word-5200-count.jsonl\n" + "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 - 6500 max words, 2000 samples - at ../dataset/gen-word-6500-count.jsonl\n" + "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 - 6800 max words, 2000 samples - at ../dataset/gen-word-6800-count.jsonl\n" + "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 - 5400 max words, 2000 samples - at ../dataset/gen-word-5400-count.jsonl\n" + "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 - 6700 max words, 2000 samples - at ../dataset/gen-word-6700-count.jsonl\n" + "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 - 4700 max words, 2000 samples - at ../dataset/gen-word-4700-count.jsonl\n" + "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 - 5000 max words, 2000 samples - at ../dataset/gen-word-5000-count.jsonl\n" + "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 - 5600 max words, 2000 samples - at ../dataset/gen-word-5600-count.jsonl\n" + "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 - 5800 max words, 2000 samples - at ../dataset/gen-word-5800-count.jsonl\n" + "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 - 6300 max words, 2000 samples - at ../dataset/gen-word-6300-count.jsonl\n" + "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 - 5700 max words, 2000 samples - at ../dataset/gen-word-5700-count.jsonl\n" + "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 - 6200 max words, 2000 samples - at ../dataset/gen-word-6200-count.jsonl\n" + "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 - 6100 max words, 2000 samples - at ../dataset/gen-word-6100-count.jsonl\n" + "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 - 6600 max words, 2000 samples - at ../dataset/gen-word-6600-count.jsonl\n" + "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 - 7700 max words, 2000 samples - at ../dataset/gen-word-7700-count.jsonl\n" + "Generated JSONL file with - 6400 max words, 2000 samples - at ../dataset/gen-word-6400-count.jsonl\n" ] }, { @@ -1634,70 +1634,70 @@ "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 8000 max words, 2000 samples - at ../dataset/gen-word-8000-count.jsonl\n" + "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" + "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 - 7800 max words, 2000 samples - at ../dataset/gen-word-7800-count.jsonl\n" + "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" + "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 - 6400 max words, 2000 samples - at ../dataset/gen-word-6400-count.jsonl\n" + "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 - 7200 max words, 2000 samples - at ../dataset/gen-word-7200-count.jsonl\n" + "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 - 7300 max words, 2000 samples - at ../dataset/gen-word-7300-count.jsonl\n" + "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 - 7000 max words, 2000 samples - at ../dataset/gen-word-7000-count.jsonl\n" + "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" + "Generated JSONL file with - 7700 max words, 2000 samples - at ../dataset/gen-word-7700-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" + "Generated JSONL file with - 8000 max words, 2000 samples - at ../dataset/gen-word-8000-count.jsonl\n" ] }, { @@ -1711,1393 +1711,1393 @@ "name": "stdout", "output_type": "stream", "text": [ - "total 2.4G\n" + "total 2.5G\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 21K Sep 13 19:02 gen-word-10-count.jsonl\n" + "-rw-r--r-- 1 root root 20K Sep 13 21:43 gen-word-10-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 2.1M Sep 13 19:02 gen-word-100-count.jsonl\n" + "-rw-r--r-- 1 root root 2.1M Sep 13 21:43 gen-word-100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 20M Sep 13 19:02 gen-word-1000-count.jsonl\n" + "-rw-r--r-- 1 root root 20M Sep 13 21:43 gen-word-1000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 22M Sep 13 19:02 gen-word-1100-count.jsonl\n" + "-rw-r--r-- 1 root root 22M Sep 13 21:43 gen-word-1100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 23M Sep 13 19:02 gen-word-1200-count.jsonl\n" + "-rw-r--r-- 1 root root 23M Sep 13 21:43 gen-word-1200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 25M Sep 13 19:02 gen-word-1300-count.jsonl\n" + "-rw-r--r-- 1 root root 25M Sep 13 21:43 gen-word-1300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 27M Sep 13 19:02 gen-word-1400-count.jsonl\n" + "-rw-r--r-- 1 root root 27M Sep 13 21:43 gen-word-1400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 25K Sep 13 19:02 gen-word-15-count.jsonl\n" + "-rw-r--r-- 1 root root 25K Sep 13 21:43 gen-word-15-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 29M Sep 13 19:02 gen-word-1500-count.jsonl\n" + "-rw-r--r-- 1 root root 29M Sep 13 21:43 gen-word-1500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 31M Sep 13 19:02 gen-word-1600-count.jsonl\n" + "-rw-r--r-- 1 root root 31M Sep 13 21:43 gen-word-1600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 33M Sep 13 19:02 gen-word-1700-count.jsonl\n" + "-rw-r--r-- 1 root root 33M Sep 13 21:43 gen-word-1700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 35M Sep 13 19:02 gen-word-1800-count.jsonl\n" + "-rw-r--r-- 1 root root 35M Sep 13 21:43 gen-word-1800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 37M Sep 13 19:02 gen-word-1900-count.jsonl\n" + "-rw-r--r-- 1 root root 37M Sep 13 21:43 gen-word-1900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 30K Sep 13 19:02 gen-word-20-count.jsonl\n" + "-rw-r--r-- 1 root root 30K Sep 13 21:43 gen-word-20-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 4.0M Sep 13 19:02 gen-word-200-count.jsonl\n" + "-rw-r--r-- 1 root root 4.0M Sep 13 21:43 gen-word-200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 39M Sep 13 19:02 gen-word-2000-count.jsonl\n" + "-rw-r--r-- 1 root root 39M Sep 13 21:43 gen-word-2000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 41M Sep 13 19:02 gen-word-2100-count.jsonl\n" + "-rw-r--r-- 1 root root 41M Sep 13 21:43 gen-word-2100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 42M Sep 13 19:02 gen-word-2200-count.jsonl\n" + "-rw-r--r-- 1 root root 42M Sep 13 21:43 gen-word-2200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 44M Sep 13 19:02 gen-word-2300-count.jsonl\n" + "-rw-r--r-- 1 root root 44M Sep 13 21:43 gen-word-2300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 46M Sep 13 19:02 gen-word-2400-count.jsonl\n" + "-rw-r--r-- 1 root root 46M Sep 13 21:43 gen-word-2400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 35K Sep 13 19:02 gen-word-25-count.jsonl\n" + "-rw-r--r-- 1 root root 34K Sep 13 21:43 gen-word-25-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 48M Sep 13 19:02 gen-word-2500-count.jsonl\n" + "-rw-r--r-- 1 root root 48M Sep 13 21:43 gen-word-2500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 50M Sep 13 19:02 gen-word-2600-count.jsonl\n" + "-rw-r--r-- 1 root root 50M Sep 13 21:43 gen-word-2600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 52M Sep 13 19:02 gen-word-2700-count.jsonl\n" + "-rw-r--r-- 1 root root 52M Sep 13 21:43 gen-word-2700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 54M Sep 13 19:02 gen-word-2800-count.jsonl\n" + "-rw-r--r-- 1 root root 54M Sep 13 21:43 gen-word-2800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 56M Sep 13 19:02 gen-word-2900-count.jsonl\n" + "-rw-r--r-- 1 root root 56M Sep 13 21:43 gen-word-2900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 40K Sep 13 19:02 gen-word-30-count.jsonl\n" + "-rw-r--r-- 1 root root 41K Sep 13 21:43 gen-word-30-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 5.9M Sep 13 19:02 gen-word-300-count.jsonl\n" + "-rw-r--r-- 1 root root 5.9M Sep 13 21:43 gen-word-300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 58M Sep 13 19:02 gen-word-3000-count.jsonl\n" + "-rw-r--r-- 1 root root 58M Sep 13 21:43 gen-word-3000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 60M Sep 13 19:02 gen-word-3100-count.jsonl\n" + "-rw-r--r-- 1 root root 60M Sep 13 21:43 gen-word-3100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 62M Sep 13 19:02 gen-word-3200-count.jsonl\n" + "-rw-r--r-- 1 root root 62M Sep 13 21:43 gen-word-3200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 63M Sep 13 19:02 gen-word-3300-count.jsonl\n" + "-rw-r--r-- 1 root root 63M Sep 13 21:43 gen-word-3300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 65M Sep 13 19:02 gen-word-3400-count.jsonl\n" + "-rw-r--r-- 1 root root 65M Sep 13 21:43 gen-word-3400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 44K Sep 13 19:02 gen-word-35-count.jsonl\n" + "-rw-r--r-- 1 root root 46K Sep 13 21:43 gen-word-35-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 67M Sep 13 19:02 gen-word-3500-count.jsonl\n" + "-rw-r--r-- 1 root root 67M Sep 13 21:43 gen-word-3500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 69M Sep 13 19:02 gen-word-3600-count.jsonl\n" + "-rw-r--r-- 1 root root 69M Sep 13 21:43 gen-word-3600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 71M Sep 13 19:02 gen-word-3700-count.jsonl\n" + "-rw-r--r-- 1 root root 71M Sep 13 21:43 gen-word-3700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 73M Sep 13 19:02 gen-word-3800-count.jsonl\n" + "-rw-r--r-- 1 root root 73M Sep 13 21:43 gen-word-3800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 75M Sep 13 19:02 gen-word-3900-count.jsonl\n" + "-rw-r--r-- 1 root root 75M Sep 13 21:43 gen-word-3900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 50K Sep 13 19:02 gen-word-40-count.jsonl\n" + "-rw-r--r-- 1 root root 50K Sep 13 21:43 gen-word-40-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 7.8M Sep 13 19:02 gen-word-400-count.jsonl\n" + "-rw-r--r-- 1 root root 7.9M Sep 13 21:43 gen-word-400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 77M Sep 13 19:02 gen-word-4000-count.jsonl\n" + "-rw-r--r-- 1 root root 77M Sep 13 21:43 gen-word-4000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 79M Sep 13 19:02 gen-word-4100-count.jsonl\n" + "-rw-r--r-- 1 root root 78M Sep 13 21:43 gen-word-4100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 80M Sep 13 19:02 gen-word-4200-count.jsonl\n" + "-rw-r--r-- 1 root root 80M Sep 13 21:43 gen-word-4200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 82M Sep 13 19:02 gen-word-4300-count.jsonl\n" + "-rw-r--r-- 1 root root 82M Sep 13 21:43 gen-word-4300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 84M Sep 13 19:02 gen-word-4400-count.jsonl\n" + "-rw-r--r-- 1 root root 84M Sep 13 21:43 gen-word-4400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 54K Sep 13 19:02 gen-word-45-count.jsonl\n" + "-rw-r--r-- 1 root root 55K Sep 13 21:43 gen-word-45-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 86M Sep 13 19:02 gen-word-4500-count.jsonl\n" + "-rw-r--r-- 1 root root 86M Sep 13 21:43 gen-word-4500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 88M Sep 13 19:02 gen-word-4600-count.jsonl\n" + "-rw-r--r-- 1 root root 88M Sep 13 21:43 gen-word-4600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 90M Sep 13 19:02 gen-word-4700-count.jsonl\n" + "-rw-r--r-- 1 root root 90M Sep 13 21:43 gen-word-4700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 92M Sep 13 19:02 gen-word-4800-count.jsonl\n" + "-rw-r--r-- 1 root root 92M Sep 13 21:43 gen-word-4800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 94M Sep 13 19:02 gen-word-4900-count.jsonl\n" + "-rw-r--r-- 1 root root 94M Sep 13 21:43 gen-word-4900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 15K Sep 13 19:02 gen-word-5-count.jsonl\n" + "-rw-r--r-- 1 root root 15K Sep 13 21:43 gen-word-5-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 58K Sep 13 19:02 gen-word-50-count.jsonl\n" + "-rw-r--r-- 1 root root 58K Sep 13 21:43 gen-word-50-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 9.8M Sep 13 19:02 gen-word-500-count.jsonl\n" + "-rw-r--r-- 1 root root 9.7M Sep 13 21:43 gen-word-500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 96M Sep 13 19:02 gen-word-5000-count.jsonl\n" + "-rw-r--r-- 1 root root 96M Sep 13 21:43 gen-word-5000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 98M Sep 13 19:02 gen-word-5100-count.jsonl\n" + "-rw-r--r-- 1 root root 98M Sep 13 21:43 gen-word-5100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 99M Sep 13 19:02 gen-word-5200-count.jsonl\n" + "-rw-r--r-- 1 root root 99M Sep 13 21:43 gen-word-5200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 101M Sep 13 19:02 gen-word-5300-count.jsonl\n" + "-rw-r--r-- 1 root root 101M Sep 13 21:43 gen-word-5300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 103M Sep 13 19:02 gen-word-5400-count.jsonl\n" + "-rw-r--r-- 1 root root 103M Sep 13 21:43 gen-word-5400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 64K Sep 13 19:02 gen-word-55-count.jsonl\n" + "-rw-r--r-- 1 root root 62K Sep 13 21:43 gen-word-55-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 105M Sep 13 19:02 gen-word-5500-count.jsonl\n" + "-rw-r--r-- 1 root root 105M Sep 13 21:43 gen-word-5500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 107M Sep 13 19:02 gen-word-5600-count.jsonl\n" + "-rw-r--r-- 1 root root 107M Sep 13 21:43 gen-word-5600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 109M Sep 13 19:02 gen-word-5700-count.jsonl\n" + "-rw-r--r-- 1 root root 109M Sep 13 21:43 gen-word-5700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 111M Sep 13 19:02 gen-word-5800-count.jsonl\n" + "-rw-r--r-- 1 root root 111M Sep 13 21:43 gen-word-5800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 113M Sep 13 19:02 gen-word-5900-count.jsonl\n" + "-rw-r--r-- 1 root root 113M Sep 13 21:43 gen-word-5900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 70K Sep 13 19:02 gen-word-60-count.jsonl\n" + "-rw-r--r-- 1 root root 65K Sep 13 21:43 gen-word-60-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 12M Sep 13 19:02 gen-word-600-count.jsonl\n" + "-rw-r--r-- 1 root root 12M Sep 13 21:43 gen-word-600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 115M Sep 13 19:02 gen-word-6000-count.jsonl\n" + "-rw-r--r-- 1 root root 115M Sep 13 21:43 gen-word-6000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 117M Sep 13 19:02 gen-word-6100-count.jsonl\n" + "-rw-r--r-- 1 root root 117M Sep 13 21:43 gen-word-6100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 118M Sep 13 19:02 gen-word-6200-count.jsonl\n" + "-rw-r--r-- 1 root root 118M Sep 13 21:43 gen-word-6200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 120M Sep 13 19:02 gen-word-6300-count.jsonl\n" + "-rw-r--r-- 1 root root 120M Sep 13 21:43 gen-word-6300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 122M Sep 13 19:02 gen-word-6400-count.jsonl\n" + "-rw-r--r-- 1 root root 122M Sep 13 21:43 gen-word-6400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 75K Sep 13 19:02 gen-word-65-count.jsonl\n" + "-rw-r--r-- 1 root root 72K Sep 13 21:43 gen-word-65-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 124M Sep 13 19:02 gen-word-6500-count.jsonl\n" + "-rw-r--r-- 1 root root 124M Sep 13 21:43 gen-word-6500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 126M Sep 13 19:02 gen-word-6600-count.jsonl\n" + "-rw-r--r-- 1 root root 126M Sep 13 21:43 gen-word-6600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 128M Sep 13 19:02 gen-word-6700-count.jsonl\n" + "-rw-r--r-- 1 root root 128M Sep 13 21:43 gen-word-6700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 130M Sep 13 19:02 gen-word-6800-count.jsonl\n" + "-rw-r--r-- 1 root root 130M Sep 13 21:43 gen-word-6800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 132M Sep 13 19:02 gen-word-6900-count.jsonl\n" + "-rw-r--r-- 1 root root 132M Sep 13 21:43 gen-word-6900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 79K Sep 13 19:02 gen-word-70-count.jsonl\n" + "-rw-r--r-- 1 root root 79K Sep 13 21:43 gen-word-70-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 14M Sep 13 19:02 gen-word-700-count.jsonl\n" + "-rw-r--r-- 1 root root 14M Sep 13 21:43 gen-word-700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 134M Sep 13 19:02 gen-word-7000-count.jsonl\n" + "-rw-r--r-- 1 root root 134M Sep 13 21:43 gen-word-7000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 135M Sep 13 19:02 gen-word-7100-count.jsonl\n" + "-rw-r--r-- 1 root root 136M Sep 13 21:43 gen-word-7100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 137M Sep 13 19:02 gen-word-7200-count.jsonl\n" + "-rw-r--r-- 1 root root 137M Sep 13 21:43 gen-word-7200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 139M Sep 13 19:02 gen-word-7300-count.jsonl\n" + "-rw-r--r-- 1 root root 139M Sep 13 21:43 gen-word-7300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 141M Sep 13 19:02 gen-word-7400-count.jsonl\n" + "-rw-r--r-- 1 root root 141M Sep 13 21:43 gen-word-7400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 84K Sep 13 19:02 gen-word-75-count.jsonl\n" + "-rw-r--r-- 1 root root 83K Sep 13 21:43 gen-word-75-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 143M Sep 13 19:02 gen-word-7500-count.jsonl\n" + "-rw-r--r-- 1 root root 143M Sep 13 21:43 gen-word-7500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 145M Sep 13 19:02 gen-word-7600-count.jsonl\n" + "-rw-r--r-- 1 root root 145M Sep 13 21:43 gen-word-7600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 147M Sep 13 19:02 gen-word-7700-count.jsonl\n" + "-rw-r--r-- 1 root root 147M Sep 13 21:43 gen-word-7700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 149M Sep 13 19:02 gen-word-7800-count.jsonl\n" + "-rw-r--r-- 1 root root 149M Sep 13 21:43 gen-word-7800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 151M Sep 13 19:02 gen-word-7900-count.jsonl\n" + "-rw-r--r-- 1 root root 151M Sep 13 21:43 gen-word-7900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 87K Sep 13 19:02 gen-word-80-count.jsonl\n" + "-rw-r--r-- 1 root root 87K Sep 13 21:43 gen-word-80-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 16M Sep 13 19:02 gen-word-800-count.jsonl\n" + "-rw-r--r-- 1 root root 16M Sep 13 21:43 gen-word-800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 153M Sep 13 19:02 gen-word-8000-count.jsonl\n" + "-rw-r--r-- 1 root root 153M Sep 13 21:43 gen-word-8000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 94K Sep 13 19:02 gen-word-85-count.jsonl\n" + "-rw-r--r-- 1 root root 92K Sep 13 21:43 gen-word-85-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 101K Sep 13 19:02 gen-word-90-count.jsonl\n" + "-rw-r--r-- 1 root root 95K Sep 13 21:43 gen-word-90-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 18M Sep 13 19:02 gen-word-900-count.jsonl\n" + "-rw-r--r-- 1 root root 18M Sep 13 21:43 gen-word-900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 105K Sep 13 19:02 gen-word-95-count.jsonl\n" + "-rw-r--r-- 1 root root 99K Sep 13 21:43 gen-word-95-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 520K Sep 13 19:02 shuffle-word-10-count.jsonl\n" + "-rw-r--r-- 1 root root 519K Sep 13 21:43 shuffle-word-10-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 574K Sep 13 19:02 shuffle-word-100-count.jsonl\n" + "-rw-r--r-- 1 root root 561K Sep 13 21:43 shuffle-word-100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 523K Sep 13 19:02 shuffle-word-1000-count.jsonl\n" + "-rw-r--r-- 1 root root 524K Sep 13 21:43 shuffle-word-1000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 523K Sep 13 19:02 shuffle-word-1100-count.jsonl\n" + "-rw-r--r-- 1 root root 521K Sep 13 21:43 shuffle-word-1100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 522K Sep 13 19:02 shuffle-word-1200-count.jsonl\n" + "-rw-r--r-- 1 root root 523K Sep 13 21:43 shuffle-word-1200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 526K Sep 13 19:02 shuffle-word-1300-count.jsonl\n" + "-rw-r--r-- 1 root root 522K Sep 13 21:43 shuffle-word-1300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 520K Sep 13 19:02 shuffle-word-1400-count.jsonl\n" + "-rw-r--r-- 1 root root 521K Sep 13 21:43 shuffle-word-1400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 432K Sep 13 19:02 shuffle-word-15-count.jsonl\n" + "-rw-r--r-- 1 root root 443K Sep 13 21:43 shuffle-word-15-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 523K Sep 13 19:02 shuffle-word-1500-count.jsonl\n" + "-rw-r--r-- 1 root root 520K Sep 13 21:43 shuffle-word-1500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 522K Sep 13 19:02 shuffle-word-1600-count.jsonl\n" + "-rw-r--r-- 1 root root 520K Sep 13 21:43 shuffle-word-1600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 520K Sep 13 19:02 shuffle-word-1700-count.jsonl\n" + "-rw-r--r-- 1 root root 520K Sep 13 21:43 shuffle-word-1700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 521K Sep 13 19:02 shuffle-word-1800-count.jsonl\n" + "-rw-r--r-- 1 root root 519K Sep 13 21:43 shuffle-word-1800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 522K Sep 13 19:02 shuffle-word-1900-count.jsonl\n" + "-rw-r--r-- 1 root root 520K Sep 13 21:43 shuffle-word-1900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 378K Sep 13 19:02 shuffle-word-20-count.jsonl\n" + "-rw-r--r-- 1 root root 379K Sep 13 21:43 shuffle-word-20-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 541K Sep 13 19:02 shuffle-word-200-count.jsonl\n" + "-rw-r--r-- 1 root root 545K Sep 13 21:43 shuffle-word-200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 520K Sep 13 19:02 shuffle-word-2000-count.jsonl\n" + "-rw-r--r-- 1 root root 522K Sep 13 21:43 shuffle-word-2000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 520K Sep 13 19:02 shuffle-word-2100-count.jsonl\n" + "-rw-r--r-- 1 root root 522K Sep 13 21:43 shuffle-word-2100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 522K Sep 13 19:02 shuffle-word-2200-count.jsonl\n" + "-rw-r--r-- 1 root root 524K Sep 13 21:43 shuffle-word-2200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 518K Sep 13 19:02 shuffle-word-2300-count.jsonl\n" + "-rw-r--r-- 1 root root 519K Sep 13 21:43 shuffle-word-2300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 520K Sep 13 19:02 shuffle-word-2400-count.jsonl\n" + "-rw-r--r-- 1 root root 518K Sep 13 21:43 shuffle-word-2400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 356K Sep 13 19:02 shuffle-word-25-count.jsonl\n" + "-rw-r--r-- 1 root root 349K Sep 13 21:43 shuffle-word-25-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 518K Sep 13 19:02 shuffle-word-2500-count.jsonl\n" + "-rw-r--r-- 1 root root 521K Sep 13 21:43 shuffle-word-2500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 515K Sep 13 19:02 shuffle-word-2600-count.jsonl\n" + "-rw-r--r-- 1 root root 512K Sep 13 21:43 shuffle-word-2600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 511K Sep 13 19:02 shuffle-word-2700-count.jsonl\n" + "-rw-r--r-- 1 root root 513K Sep 13 21:43 shuffle-word-2700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-2800-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 21:43 shuffle-word-2800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-2900-count.jsonl\n" + "-rw-r--r-- 1 root root 508K Sep 13 21:43 shuffle-word-2900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 344K Sep 13 19:02 shuffle-word-30-count.jsonl\n" + "-rw-r--r-- 1 root root 343K Sep 13 21:43 shuffle-word-30-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 535K Sep 13 19:02 shuffle-word-300-count.jsonl\n" + "-rw-r--r-- 1 root root 534K Sep 13 21:43 shuffle-word-300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-3000-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 21:43 shuffle-word-3000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-3100-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 21:43 shuffle-word-3100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-3200-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 21:43 shuffle-word-3200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-3300-count.jsonl\n" + "-rw-r--r-- 1 root root 508K Sep 13 21:43 shuffle-word-3300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 508K Sep 13 19:02 shuffle-word-3400-count.jsonl\n" + "-rw-r--r-- 1 root root 508K Sep 13 21:43 shuffle-word-3400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 332K Sep 13 19:02 shuffle-word-35-count.jsonl\n" + "-rw-r--r-- 1 root root 335K Sep 13 21:43 shuffle-word-35-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 508K Sep 13 19:02 shuffle-word-3500-count.jsonl\n" + "-rw-r--r-- 1 root root 508K Sep 13 21:43 shuffle-word-3500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-3600-count.jsonl\n" + "-rw-r--r-- 1 root root 508K Sep 13 21:43 shuffle-word-3600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-3700-count.jsonl\n" + "-rw-r--r-- 1 root root 508K Sep 13 21:43 shuffle-word-3700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-3800-count.jsonl\n" + "-rw-r--r-- 1 root root 508K Sep 13 21:43 shuffle-word-3800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-3900-count.jsonl\n" + "-rw-r--r-- 1 root root 508K Sep 13 21:43 shuffle-word-3900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 311K Sep 13 19:02 shuffle-word-40-count.jsonl\n" + "-rw-r--r-- 1 root root 323K Sep 13 21:43 shuffle-word-40-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 529K Sep 13 19:02 shuffle-word-400-count.jsonl\n" + "-rw-r--r-- 1 root root 529K Sep 13 21:43 shuffle-word-400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-4000-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 21:43 shuffle-word-4000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-4100-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 21:43 shuffle-word-4100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-4200-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 21:43 shuffle-word-4200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-4300-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 21:43 shuffle-word-4300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 508K Sep 13 19:02 shuffle-word-4400-count.jsonl\n" + "-rw-r--r-- 1 root root 508K Sep 13 21:43 shuffle-word-4400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 305K Sep 13 19:02 shuffle-word-45-count.jsonl\n" + "-rw-r--r-- 1 root root 313K Sep 13 21:43 shuffle-word-45-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-4500-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 21:43 shuffle-word-4500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-4600-count.jsonl\n" + "-rw-r--r-- 1 root root 508K Sep 13 21:43 shuffle-word-4600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 508K Sep 13 19:02 shuffle-word-4700-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 21:43 shuffle-word-4700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 508K Sep 13 19:02 shuffle-word-4800-count.jsonl\n" + "-rw-r--r-- 1 root root 508K Sep 13 21:43 shuffle-word-4800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-4900-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 21:43 shuffle-word-4900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 809K Sep 13 19:02 shuffle-word-5-count.jsonl\n" + "-rw-r--r-- 1 root root 822K Sep 13 21:43 shuffle-word-5-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 313K Sep 13 19:02 shuffle-word-50-count.jsonl\n" + "-rw-r--r-- 1 root root 308K Sep 13 21:43 shuffle-word-50-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 526K Sep 13 19:02 shuffle-word-500-count.jsonl\n" + "-rw-r--r-- 1 root root 528K Sep 13 21:43 shuffle-word-500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 508K Sep 13 19:02 shuffle-word-5000-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 21:43 shuffle-word-5000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-5100-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 21:43 shuffle-word-5100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-5200-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 21:43 shuffle-word-5200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-5300-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 21:43 shuffle-word-5300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-5400-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 21:43 shuffle-word-5400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 306K Sep 13 19:02 shuffle-word-55-count.jsonl\n" + "-rw-r--r-- 1 root root 306K Sep 13 21:43 shuffle-word-55-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 508K Sep 13 19:02 shuffle-word-5500-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 21:43 shuffle-word-5500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 508K Sep 13 19:02 shuffle-word-5600-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 21:43 shuffle-word-5600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-5700-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 21:43 shuffle-word-5700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 508K Sep 13 19:02 shuffle-word-5800-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 21:43 shuffle-word-5800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-5900-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 21:43 shuffle-word-5900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 299K Sep 13 19:02 shuffle-word-60-count.jsonl\n" + "-rw-r--r-- 1 root root 300K Sep 13 21:43 shuffle-word-60-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 527K Sep 13 19:02 shuffle-word-600-count.jsonl\n" + "-rw-r--r-- 1 root root 528K Sep 13 21:43 shuffle-word-600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-6000-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 21:43 shuffle-word-6000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-6100-count.jsonl\n" + "-rw-r--r-- 1 root root 508K Sep 13 21:43 shuffle-word-6100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-6200-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 21:43 shuffle-word-6200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-6300-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 21:43 shuffle-word-6300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-6400-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 21:43 shuffle-word-6400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 296K Sep 13 19:02 shuffle-word-65-count.jsonl\n" + "-rw-r--r-- 1 root root 299K Sep 13 21:43 shuffle-word-65-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-6500-count.jsonl\n" + "-rw-r--r-- 1 root root 508K Sep 13 21:43 shuffle-word-6500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-6600-count.jsonl\n" + "-rw-r--r-- 1 root root 508K Sep 13 21:43 shuffle-word-6600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-6700-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 21:43 shuffle-word-6700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-6800-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 21:43 shuffle-word-6800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-6900-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 21:43 shuffle-word-6900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 290K Sep 13 19:02 shuffle-word-70-count.jsonl\n" + "-rw-r--r-- 1 root root 291K Sep 13 21:43 shuffle-word-70-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 523K Sep 13 19:02 shuffle-word-700-count.jsonl\n" + "-rw-r--r-- 1 root root 525K Sep 13 21:43 shuffle-word-700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-7000-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 21:43 shuffle-word-7000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-7100-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 21:43 shuffle-word-7100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-7200-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 21:43 shuffle-word-7200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-7300-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 21:43 shuffle-word-7300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 508K Sep 13 19:02 shuffle-word-7400-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 21:43 shuffle-word-7400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 290K Sep 13 19:02 shuffle-word-75-count.jsonl\n" + "-rw-r--r-- 1 root root 289K Sep 13 21:43 shuffle-word-75-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-7500-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 21:43 shuffle-word-7500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-7600-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 21:43 shuffle-word-7600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-7700-count.jsonl\n" + "-rw-r--r-- 1 root root 508K Sep 13 21:43 shuffle-word-7700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-7800-count.jsonl\n" + "-rw-r--r-- 1 root root 508K Sep 13 21:43 shuffle-word-7800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-7900-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 21:43 shuffle-word-7900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 291K Sep 13 19:02 shuffle-word-80-count.jsonl\n" + "-rw-r--r-- 1 root root 288K Sep 13 21:43 shuffle-word-80-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 527K Sep 13 19:02 shuffle-word-800-count.jsonl\n" + "-rw-r--r-- 1 root root 527K Sep 13 21:43 shuffle-word-800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-8000-count.jsonl\n" + "-rw-r--r-- 1 root root 508K Sep 13 21:43 shuffle-word-8000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 289K Sep 13 19:02 shuffle-word-85-count.jsonl\n" + "-rw-r--r-- 1 root root 287K Sep 13 21:43 shuffle-word-85-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 287K Sep 13 19:02 shuffle-word-90-count.jsonl\n" + "-rw-r--r-- 1 root root 288K Sep 13 21:43 shuffle-word-90-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 522K Sep 13 19:02 shuffle-word-900-count.jsonl\n" + "-rw-r--r-- 1 root root 524K Sep 13 21:43 shuffle-word-900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 282K Sep 13 19:02 shuffle-word-95-count.jsonl\n" + "-rw-r--r-- 1 root root 288K Sep 13 21:43 shuffle-word-95-count.jsonl\n" ] } ], @@ -3146,19 +3146,19 @@ { "cell_type": "code", "execution_count": 6, - "id": "4da0b8bc", + "id": "fe8bdefe", "metadata": { "execution": { - "iopub.execute_input": "2023-09-13T19:02:59.859578Z", - "iopub.status.busy": "2023-09-13T19:02:59.859296Z", - "iopub.status.idle": "2023-09-13T19:03:17.314139Z", - "shell.execute_reply": "2023-09-13T19:03:17.313284Z" + "iopub.execute_input": "2023-09-13T21:43:47.086026Z", + "iopub.status.busy": "2023-09-13T21:43:47.085626Z", + "iopub.status.idle": "2023-09-13T21:44:04.543593Z", + "shell.execute_reply": "2023-09-13T21:44:04.542745Z" }, "papermill": { - "duration": 17.474014, - "end_time": "2023-09-13T19:03:17.316238", + "duration": 17.477036, + "end_time": "2023-09-13T21:44:04.545689", "exception": false, - "start_time": "2023-09-13T19:02:59.842224", + "start_time": "2023-09-13T21:43:47.068653", "status": "completed" }, "tags": [] @@ -3168,7 +3168,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "[2023-09-13 19:03:02,731] [INFO] [real_accelerator.py:133:get_accelerator] Setting ds_accelerator to cuda (auto detect)\r\n" + "[2023-09-13 21:43:49,965] [INFO] [real_accelerator.py:133:get_accelerator] Setting ds_accelerator to cuda (auto detect)\r\n" ] }, { @@ -3190,9 +3190,9 @@ "name": "stdout", "output_type": "stream", "text": [ - "/usr/local/lib/python3.10/dist-packages/lightning/fabric/utilities/seed.py:39: UserWarning: No seed found, seed set to 1648783608\r\n", + "/usr/local/lib/python3.10/dist-packages/lightning/fabric/utilities/seed.py:39: UserWarning: No seed found, seed set to 1365345879\r\n", " rank_zero_warn(f\"No seed found, seed set to {seed}\")\r\n", - "Global seed set to 1648783608\r\n" + "Global seed set to 1365345879\r\n" ] }, { @@ -3207,11 +3207,11 @@ "output_type": "stream", "text": [ "\u001b[34m\u001b[1mwandb\u001b[0m: Tracking run with wandb version 0.15.10\r\n", - "\u001b[34m\u001b[1mwandb\u001b[0m: Run data is saved locally in \u001b[35m\u001b[1m./wandb/run-20230913_190305-kiickwj2\u001b[0m\r\n", + "\u001b[34m\u001b[1mwandb\u001b[0m: Run data is saved locally in \u001b[35m\u001b[1m./wandb/run-20230913_214352-oqbu77ao\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[33mv5r3-L12-D2560-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/kiickwj2\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/oqbu77ao\u001b[0m\r\n" ] }, { @@ -3253,10 +3253,10 @@ "name": "stdout", "output_type": "stream", "text": [ - "\u001b[34m\u001b[1mwandb\u001b[0m: 🚀 View run \u001b[33mv5r3-L12-D2560-E0.1 - Mem-Tune ctx-8k (train-ctx=4k, deepspeed_stage_1)\u001b[0m at: \u001b[34m\u001b[4mhttps://wandb.ai/rwkv-x-dev/RWKV-X-Experiments/runs/kiickwj2\u001b[0m\r\n", - "\u001b[34m\u001b[1mwandb\u001b[0m: ️⚡ View job at \u001b[34m\u001b[4mhttps://wandb.ai/rwkv-x-dev/RWKV-X-Experiments/jobs/QXJ0aWZhY3RDb2xsZWN0aW9uOjkzMjg5ODA3/version_details/v49\u001b[0m\r\n", + "\u001b[34m\u001b[1mwandb\u001b[0m: 🚀 View run \u001b[33mv5r3-L12-D2560-E0.1 - Mem-Tune ctx-8k (train-ctx=4k, deepspeed_stage_1)\u001b[0m at: \u001b[34m\u001b[4mhttps://wandb.ai/rwkv-x-dev/RWKV-X-Experiments/runs/oqbu77ao\u001b[0m\r\n", + "\u001b[34m\u001b[1mwandb\u001b[0m: ️⚡ View job at \u001b[34m\u001b[4mhttps://wandb.ai/rwkv-x-dev/RWKV-X-Experiments/jobs/QXJ0aWZhY3RDb2xsZWN0aW9uOjkzMjg5ODA3/version_details/v51\u001b[0m\r\n", "\u001b[34m\u001b[1mwandb\u001b[0m: Synced 5 W&B file(s), 0 media file(s), 2 artifact file(s) and 0 other file(s)\r\n", - "\u001b[34m\u001b[1mwandb\u001b[0m: Find logs at: \u001b[35m\u001b[1m./wandb/run-20230913_190305-kiickwj2/logs\u001b[0m\r\n" + "\u001b[34m\u001b[1mwandb\u001b[0m: Find logs at: \u001b[35m\u001b[1m./wandb/run-20230913_214352-oqbu77ao/logs\u001b[0m\r\n" ] } ], @@ -3282,19 +3282,19 @@ { "cell_type": "code", "execution_count": 7, - "id": "dcf71a84", + "id": "338ebb3a", "metadata": { "execution": { - "iopub.execute_input": "2023-09-13T19:03:17.355154Z", - "iopub.status.busy": "2023-09-13T19:03:17.354655Z", - "iopub.status.idle": "2023-09-13T19:03:19.753824Z", - "shell.execute_reply": "2023-09-13T19:03:19.753071Z" + "iopub.execute_input": "2023-09-13T21:44:04.583165Z", + "iopub.status.busy": "2023-09-13T21:44:04.582610Z", + "iopub.status.idle": "2023-09-13T21:44:06.987560Z", + "shell.execute_reply": "2023-09-13T21:44:06.986803Z" }, "papermill": { - "duration": 2.418382, - "end_time": "2023-09-13T19:03:19.755548", + "duration": 2.423633, + "end_time": "2023-09-13T21:44:06.989296", "exception": false, - "start_time": "2023-09-13T19:03:17.337166", + "start_time": "2023-09-13T21:44:04.565663", "status": "completed" }, "tags": [] @@ -3304,7 +3304,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "[2023-09-13 19:03:18,896] [INFO] [real_accelerator.py:133:get_accelerator] Setting ds_accelerator to cuda (auto detect)\r\n" + "[2023-09-13 21:44:06,121] [INFO] [real_accelerator.py:133:get_accelerator] Setting ds_accelerator to cuda (auto detect)\r\n" ] }, { @@ -3341,19 +3341,19 @@ { "cell_type": "code", "execution_count": 8, - "id": "9b9a3a59", + "id": "9f9af732", "metadata": { "execution": { - "iopub.execute_input": "2023-09-13T19:03:19.817289Z", - "iopub.status.busy": "2023-09-13T19:03:19.817027Z", - "iopub.status.idle": "2023-09-13T19:03:20.048868Z", - "shell.execute_reply": "2023-09-13T19:03:20.048169Z" + "iopub.execute_input": "2023-09-13T21:44:07.049788Z", + "iopub.status.busy": "2023-09-13T21:44:07.049295Z", + "iopub.status.idle": "2023-09-13T21:44:07.282197Z", + "shell.execute_reply": "2023-09-13T21:44:07.281400Z" }, "papermill": { - "duration": 0.251531, - "end_time": "2023-09-13T19:03:20.050541", + "duration": 0.252463, + "end_time": "2023-09-13T21:44:07.283862", "exception": false, - "start_time": "2023-09-13T19:03:19.799010", + "start_time": "2023-09-13T21:44:07.031399", "status": "completed" }, "tags": [] @@ -3375,19 +3375,19 @@ { "cell_type": "code", "execution_count": 9, - "id": "101c9366", + "id": "53b57a14", "metadata": { "execution": { - "iopub.execute_input": "2023-09-13T19:03:20.089853Z", - "iopub.status.busy": "2023-09-13T19:03:20.089597Z", - "iopub.status.idle": "2023-09-13T19:03:20.322371Z", - "shell.execute_reply": "2023-09-13T19:03:20.321517Z" + "iopub.execute_input": "2023-09-13T21:44:07.322800Z", + "iopub.status.busy": "2023-09-13T21:44:07.322265Z", + "iopub.status.idle": "2023-09-13T21:44:07.553994Z", + "shell.execute_reply": "2023-09-13T21:44:07.553234Z" }, "papermill": { - "duration": 0.251914, - "end_time": "2023-09-13T19:03:20.324282", + "duration": 0.251029, + "end_time": "2023-09-13T21:44:07.555639", "exception": false, - "start_time": "2023-09-13T19:03:20.072368", + "start_time": "2023-09-13T21:44:07.304610", "status": "completed" }, "tags": [] @@ -3426,14 +3426,14 @@ }, "papermill": { "default_parameters": {}, - "duration": 48.904767, - "end_time": "2023-09-13T19:03:20.462590", + "duration": 48.916499, + "end_time": "2023-09-13T21:44:07.691878", "environment_variables": {}, "exception": null, "input_path": "/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/notebook/experiment/rwkv-x-exp/v5-r3-memory/L6-D2560-E1e-1-ctx4k/stage3.ipynb", "output_path": "/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/rwkv-x-exp/v5-r3-memory/L6-D2560-E1e-1-ctx4k/stage3.ipynb", "parameters": {}, - "start_time": "2023-09-13T19:02:31.557823", + "start_time": "2023-09-13T21:43:18.775379", "version": "2.4.0" } },