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": "a1502209", + "id": "219a53fb", "metadata": { "papermill": { - "duration": 0.004182, - "end_time": "2023-09-13T18:27:39.823236", + "duration": 0.004385, + "end_time": "2023-09-13T19:02:32.553797", "exception": false, - "start_time": "2023-09-13T18:27:39.819054", + "start_time": "2023-09-13T19:02:32.549412", "status": "completed" }, "tags": [] @@ -25,13 +25,13 @@ { "attachments": {}, "cell_type": "markdown", - "id": "1466b539", + "id": "e73cb2f6", "metadata": { "papermill": { - "duration": 0.00276, - "end_time": "2023-09-13T18:27:39.828963", + "duration": 0.002807, + "end_time": "2023-09-13T19:02:32.559744", "exception": false, - "start_time": "2023-09-13T18:27:39.826203", + "start_time": "2023-09-13T19:02:32.556937", "status": "completed" }, "tags": [] @@ -43,19 +43,19 @@ { "cell_type": "code", "execution_count": 1, - "id": "edf9aaaa", + "id": "1d1252f7", "metadata": { "execution": { - "iopub.execute_input": "2023-09-13T18:27:39.832942Z", - "iopub.status.busy": "2023-09-13T18:27:39.832690Z", - "iopub.status.idle": "2023-09-13T18:27:40.704477Z", - "shell.execute_reply": "2023-09-13T18:27:40.703626Z" + "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" }, "papermill": { - "duration": 0.87598, - "end_time": "2023-09-13T18:27:40.706362", + "duration": 0.87593, + "end_time": "2023-09-13T19:02:33.437575", "exception": false, - "start_time": "2023-09-13T18:27:39.830382", + "start_time": "2023-09-13T19:02:32.561645", "status": "completed" }, "tags": [] @@ -83,19 +83,19 @@ { "cell_type": "code", "execution_count": 2, - "id": "46b17765", + "id": "b994a9a1", "metadata": { "execution": { - "iopub.execute_input": "2023-09-13T18:27:40.713791Z", - "iopub.status.busy": "2023-09-13T18:27:40.713529Z", - "iopub.status.idle": "2023-09-13T18:27:42.826782Z", - "shell.execute_reply": "2023-09-13T18:27:42.825983Z" + "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" }, "papermill": { - "duration": 2.118966, - "end_time": "2023-09-13T18:27:42.828557", + "duration": 2.117639, + "end_time": "2023-09-13T19:02:35.558459", "exception": false, - "start_time": "2023-09-13T18:27:40.709591", + "start_time": "2023-09-13T19:02:33.440820", "status": "completed" }, "tags": [] @@ -118,19 +118,19 @@ { "cell_type": "code", "execution_count": 3, - "id": "c5495674", + "id": "d509963e", "metadata": { "execution": { - "iopub.execute_input": "2023-09-13T18:27:42.836016Z", - "iopub.status.busy": "2023-09-13T18:27:42.835775Z", - "iopub.status.idle": "2023-09-13T18:27:42.844569Z", - "shell.execute_reply": "2023-09-13T18:27:42.843935Z" + "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" }, "papermill": { - "duration": 0.014523, - "end_time": "2023-09-13T18:27:42.846327", + "duration": 0.01433, + "end_time": "2023-09-13T19:02:35.576116", "exception": false, - "start_time": "2023-09-13T18:27:42.831804", + "start_time": "2023-09-13T19:02:35.561786", "status": "completed" }, "tags": [] @@ -197,19 +197,19 @@ { "cell_type": "code", "execution_count": 4, - "id": "22c06446", + "id": "1d025793", "metadata": { "execution": { - "iopub.execute_input": "2023-09-13T18:27:42.853755Z", - "iopub.status.busy": "2023-09-13T18:27:42.853516Z", - "iopub.status.idle": "2023-09-13T18:27:43.580730Z", - "shell.execute_reply": "2023-09-13T18:27:43.579953Z" + "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" }, "papermill": { - "duration": 0.732974, - "end_time": "2023-09-13T18:27:43.582534", + "duration": 0.71891, + "end_time": "2023-09-13T19:02:36.298255", "exception": false, - "start_time": "2023-09-13T18:27:42.849560", + "start_time": "2023-09-13T19:02:35.579345", "status": "completed" }, "tags": [] @@ -219,8 +219,8 @@ "name": "stdout", "output_type": "stream", "text": [ - "--2023-09-13 18:27:42-- 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, 13.33.33.102, 13.33.33.110, ...\r\n", + "--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", + "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 18:27:43 ERROR 404: Not Found.\r\n", + "2023-09-13 19:02:35 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 18:27 .\r\n", - "drwxr-xr-x 20 root root 24 Sep 13 18:27 ..\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" ] } ], @@ -255,13 +255,13 @@ }, { "cell_type": "markdown", - "id": "735a073e", + "id": "3d413898", "metadata": { "papermill": { - "duration": 0.003348, - "end_time": "2023-09-13T18:27:43.589546", + "duration": 0.00337, + "end_time": "2023-09-13T19:02:36.305351", "exception": false, - "start_time": "2023-09-13T18:27:43.586198", + "start_time": "2023-09-13T19:02:36.301981", "status": "completed" }, "tags": [] @@ -275,19 +275,19 @@ { "cell_type": "code", "execution_count": 5, - "id": "03f60711", + "id": "4b593663", "metadata": { "execution": { - "iopub.execute_input": "2023-09-13T18:27:43.596501Z", - "iopub.status.busy": "2023-09-13T18:27:43.596238Z", - "iopub.status.idle": "2023-09-13T18:28:06.781577Z", - "shell.execute_reply": "2023-09-13T18:28:06.781015Z" + "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" }, "papermill": { - "duration": 23.226562, - "end_time": "2023-09-13T18:28:06.819572", + "duration": 23.516383, + "end_time": "2023-09-13T19:02:59.825166", "exception": false, - "start_time": "2023-09-13T18:27:43.593010", + "start_time": "2023-09-13T19:02:36.308783", "status": "completed" }, "tags": [] @@ -304,574 +304,574 @@ "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 - 20 max words, 100 samples - at ../dataset/gen-word-20-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 JSONL file with - 25 max words, 100 samples - at ../dataset/gen-word-25-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated a single JSONL file with 750 samples (10 token repeat) - 35 max words - at ../dataset/shuffle-word-35-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 a single JSONL file with 1311 samples (10 token repeat) - 20 max words - at ../dataset/shuffle-word-20-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 - 45 max words, 100 samples - at ../dataset/gen-word-45-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 - 80 max words, 100 samples - at ../dataset/gen-word-80-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 a single JSONL file with 409 samples (10 token repeat) - 65 max words - at ../dataset/shuffle-word-65-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 JSONL file with - 40 max words, 100 samples - at ../dataset/gen-word-40-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 - 25 max words, 100 samples - at ../dataset/gen-word-25-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 a single JSONL file with 878 samples (10 token repeat) - 30 max words - at ../dataset/shuffle-word-30-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 JSONL file with - 100 max words, 100 samples - at ../dataset/gen-word-100-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 653 samples (10 token repeat) - 40 max words - at ../dataset/shuffle-word-40-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 - 10 max words, 100 samples - at ../dataset/gen-word-10-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 - 85 max words, 100 samples - at ../dataset/gen-word-85-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 a single JSONL file with 1053 samples (10 token repeat) - 25 max words - at ../dataset/shuffle-word-25-count.jsonl\n" + "Generated a single JSONL file with 445 samples (10 token repeat) - 60 max words - at ../dataset/shuffle-word-60-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 - 55 max words, 100 samples - at ../dataset/gen-word-55-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 JSONL file with - 80 max words, 100 samples - at ../dataset/gen-word-80-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated a single JSONL file with 369 samples (10 token repeat) - 70 max words - at ../dataset/shuffle-word-70-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 - 55 max words, 100 samples - at ../dataset/gen-word-55-count.jsonl\n" + "Generated a single JSONL file with 655 samples (10 token repeat) - 40 max words - at ../dataset/shuffle-word-40-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated a single JSONL file with 526 samples (10 token repeat) - 50 max words - at ../dataset/shuffle-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 272 samples (20 token repeat) - 200 max words - at ../dataset/shuffle-word-200-count.jsonl\n" + "Generated a single JSONL file with 522 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 100 samples (20 token repeat) - 600 max words - at ../dataset/shuffle-word-600-count.jsonl\n" + "Generated a single JSONL file with 2623 samples (10 token repeat) - 10 max words - at ../dataset/shuffle-word-10-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 20 max words, 100 samples - at ../dataset/gen-word-20-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 JSONL file with - 70 max words, 100 samples - at ../dataset/gen-word-70-count.jsonl\n" + "Generated a single JSONL file with 873 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 - 95 max words, 100 samples - at ../dataset/gen-word-95-count.jsonl\n" + "Generated a single JSONL file with 333 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 356 samples (10 token repeat) - 75 max words - at ../dataset/shuffle-word-75-count.jsonl\n" + "Generated a single JSONL file with 410 samples (10 token repeat) - 65 max words - at ../dataset/shuffle-word-65-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 a single JSONL file with 305 samples (10 token repeat) - 90 max words - at ../dataset/shuffle-word-90-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 65 max words, 100 samples - at ../dataset/gen-word-65-count.jsonl\n" + "Generated a single JSONL file with 1065 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 - 90 max words, 100 samples - at ../dataset/gen-word-90-count.jsonl\n" + "Generated a single JSONL file with 590 samples (10 token repeat) - 45 max words - at ../dataset/shuffle-word-45-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated 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 1306 samples (10 token repeat) - 20 max words - at ../dataset/shuffle-word-20-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 75 max words, 100 samples - at ../dataset/gen-word-75-count.jsonl\n" + "Generated a single JSONL file with 267 samples (10 token repeat) - 100 max words - at ../dataset/shuffle-word-100-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 a single JSONL file with 757 samples (10 token repeat) - 35 max words - at ../dataset/shuffle-word-35-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated a single JSONL file with 269 samples (10 token repeat) - 100 max words - at ../dataset/shuffle-word-100-count.jsonl\n" + "Generated a single JSONL file with 271 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 327 samples (10 token repeat) - 80 max words - at ../dataset/shuffle-word-80-count.jsonl\n" + "Generated a single JSONL file with 309 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 2619 samples (10 token repeat) - 10 max words - at ../dataset/shuffle-word-10-count.jsonl\n" + "Generated a single JSONL file with 278 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 279 samples (10 token repeat) - 95 max words - at ../dataset/shuffle-word-95-count.jsonl\n" + "Generated a single JSONL file with 142 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 313 samples (10 token repeat) - 85 max words - at ../dataset/shuffle-word-85-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 538 samples (20 token repeat) - 100 max words - at ../dataset/shuffle-word-100-count.jsonl\n" + "Generated a single JSONL file with 350 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 482 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) - 6300 max words - at ../dataset/shuffle-word-6300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated a single JSONL file with 581 samples (10 token repeat) - 45 max words - at ../dataset/shuffle-word-45-count.jsonl\n" + "Generated a single JSONL file with 377 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 - 50 max words, 100 samples - at ../dataset/gen-word-50-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) - 4800 max words - at ../dataset/shuffle-word-4800-count.jsonl\n" + "Generated a single JSONL file with 184 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 49 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) - 7600 max words - at ../dataset/shuffle-word-7600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated a single JSONL file with 185 samples (20 token repeat) - 300 max words - at ../dataset/shuffle-word-300-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 65 samples (20 token repeat) - 900 max words - at ../dataset/shuffle-word-900-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 5585 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) - 7500 max words - at ../dataset/shuffle-word-7500-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 1780 samples (10 token repeat) - 15 max words - at ../dataset/shuffle-word-15-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated a single JSONL file with 60 samples (20 token repeat) - 1100 max words - at ../dataset/shuffle-word-1100-count.jsonl\n" + "Generated a single JSONL file with 487 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) - 4500 max words - at ../dataset/shuffle-word-4500-count.jsonl\n" + "Generated a single JSONL file with 113 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 82 samples (20 token repeat) - 700 max words - at ../dataset/shuffle-word-700-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 440 samples (10 token repeat) - 60 max words - at ../dataset/shuffle-word-60-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 37 samples (20 token repeat) - 2500 max words - at ../dataset/shuffle-word-2500-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 1791 samples (10 token repeat) - 15 max words - at ../dataset/shuffle-word-15-count.jsonl\n" + "Generated a single JSONL file with 64 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 20 samples (20 token repeat) - 3800 max words - at ../dataset/shuffle-word-3800-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 20 samples (20 token repeat) - 3400 max words - at ../dataset/shuffle-word-3400-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 40 samples (20 token repeat) - 2300 max words - at ../dataset/shuffle-word-2300-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 32 samples (20 token repeat) - 2600 max words - at ../dataset/shuffle-word-2600-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) - 3900 max words - at ../dataset/shuffle-word-3900-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 20 samples (20 token repeat) - 4100 max words - at ../dataset/shuffle-word-4100-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 40 samples (20 token repeat) - 2100 max words - at ../dataset/shuffle-word-2100-count.jsonl\n" + "Generated a single JSONL file with 34 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) - 4200 max words - at ../dataset/shuffle-word-4200-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 298 samples (10 token repeat) - 90 max words - at ../dataset/shuffle-word-90-count.jsonl\n" + "Generated a single JSONL file with 21 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) - 3700 max words - at ../dataset/shuffle-word-3700-count.jsonl\n" + "Generated a single JSONL file with 30 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 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) - 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) - 5700 max words - at ../dataset/shuffle-word-5700-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 20 samples (20 token repeat) - 4000 max words - at ../dataset/shuffle-word-4000-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 20 samples (20 token repeat) - 6700 max words - at ../dataset/shuffle-word-6700-count.jsonl\n" + "Generated a single JSONL file with 534 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 60 samples (20 token repeat) - 1200 max words - at ../dataset/shuffle-word-1200-count.jsonl\n" + "Generated a single JSONL file with 22 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 117 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) - 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) - 6300 max words - at ../dataset/shuffle-word-6300-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 40 samples (20 token repeat) - 2000 max words - at ../dataset/shuffle-word-2000-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 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) - 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) - 6400 max words - at ../dataset/shuffle-word-6400-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) - 2900 max words - at ../dataset/shuffle-word-2900-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) - 6500 max words - at ../dataset/shuffle-word-6500-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 20 samples (20 token repeat) - 5300 max words - at ../dataset/shuffle-word-5300-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) - 5900 max words - at ../dataset/shuffle-word-5900-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) - 7000 max words - at ../dataset/shuffle-word-7000-count.jsonl\n" + "Generated a single JSONL file with 81 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 41 samples (20 token repeat) - 1400 max words - at ../dataset/shuffle-word-1400-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 20 samples (20 token repeat) - 7100 max words - at ../dataset/shuffle-word-7100-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) - 5200 max words - at ../dataset/shuffle-word-5200-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) - 7200 max words - at ../dataset/shuffle-word-7200-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" ] }, { @@ -885,203 +885,203 @@ "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) - 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) - 4700 max words - at ../dataset/shuffle-word-4700-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 40 samples (20 token repeat) - 1800 max words - at ../dataset/shuffle-word-1800-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 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) - 3900 max words - at ../dataset/shuffle-word-3900-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 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) - 3600 max words - at ../dataset/shuffle-word-3600-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 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) - 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) - 4300 max words - at ../dataset/shuffle-word-4300-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 60 samples (20 token repeat) - 1000 max words - at ../dataset/shuffle-word-1000-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) - 5600 max words - at ../dataset/shuffle-word-5600-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 20 samples (20 token repeat) - 7500 max words - at ../dataset/shuffle-word-7500-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 40 samples (20 token repeat) - 2400 max words - at ../dataset/shuffle-word-2400-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 23 samples (20 token repeat) - 2700 max words - at ../dataset/shuffle-word-2700-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 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) - 3400 max words - at ../dataset/shuffle-word-3400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 2800 max words - at ../dataset/shuffle-word-2800-count.jsonl\n" + "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 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) - 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 54 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 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) - 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) - 3300 max words - at ../dataset/shuffle-word-3300-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 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) - 6500 max words - at ../dataset/shuffle-word-6500-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 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) - 3100 max words - at ../dataset/shuffle-word-3100-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 20 samples (20 token repeat) - 5100 max words - at ../dataset/shuffle-word-5100-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 140 samples (20 token repeat) - 400 max words - at ../dataset/shuffle-word-400-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 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) - 4400 max words - at ../dataset/shuffle-word-4400-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 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) - 6600 max words - at ../dataset/shuffle-word-6600-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) - 6000 max words - at ../dataset/shuffle-word-6000-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) - 7600 max words - at ../dataset/shuffle-word-7600-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" ] }, { @@ -1095,49 +1095,49 @@ "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) - 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) - 8000 max words - at ../dataset/shuffle-word-8000-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) - 6100 max words - at ../dataset/shuffle-word-6100-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) - 4600 max words - at ../dataset/shuffle-word-4600-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) - 6900 max words - at ../dataset/shuffle-word-6900-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) - 5400 max words - at ../dataset/shuffle-word-5400-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 20 samples (20 token repeat) - 5800 max words - at ../dataset/shuffle-word-5800-count.jsonl\n" + "Generated a single JSONL file with 5566 samples (10 token repeat) - 5 max words - at ../dataset/shuffle-word-5-count.jsonl\n" ] }, { @@ -1165,77 +1165,77 @@ "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 - 400 max words, 2000 samples - at ../dataset/gen-word-400-count.jsonl\n" ] }, { "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 - 2000 max words, 2000 samples - at ../dataset/gen-word-2000-count.jsonl\n" + "Generated JSONL file with - 600 max words, 2000 samples - at ../dataset/gen-word-600-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 - 500 max words, 2000 samples - at ../dataset/gen-word-500-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 - 700 max words, 2000 samples - at ../dataset/gen-word-700-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 - 900 max words, 2000 samples - at ../dataset/gen-word-900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 700 max words, 2000 samples - at ../dataset/gen-word-700-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 - 900 max words, 2000 samples - at ../dataset/gen-word-900-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 - 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 - 1800 max words, 2000 samples - at ../dataset/gen-word-1800-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 - 1500 max words, 2000 samples - at ../dataset/gen-word-1500-count.jsonl\n" ] }, { @@ -1249,329 +1249,329 @@ "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 1700 max words, 2000 samples - at ../dataset/gen-word-1700-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 - 1500 max words, 2000 samples - at ../dataset/gen-word-1500-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 - 1600 max words, 2000 samples - at ../dataset/gen-word-1600-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 - 3300 max words, 2000 samples - at ../dataset/gen-word-3300-count.jsonl\n" + "Generated JSONL file with - 1700 max words, 2000 samples - at ../dataset/gen-word-1700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 2400 max words, 2000 samples - at ../dataset/gen-word-2400-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 - 3000 max words, 2000 samples - at ../dataset/gen-word-3000-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 - 1900 max words, 2000 samples - at ../dataset/gen-word-1900-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 - 2900 max words, 2000 samples - at ../dataset/gen-word-2900-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 - 3300 max words, 2000 samples - at ../dataset/gen-word-3300-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 - 2700 max words, 2000 samples - at ../dataset/gen-word-2700-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 - 2400 max words, 2000 samples - at ../dataset/gen-word-2400-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 - 3100 max words, 2000 samples - at ../dataset/gen-word-3100-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 - 2600 max words, 2000 samples - at ../dataset/gen-word-2600-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 - 3000 max words, 2000 samples - at ../dataset/gen-word-3000-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 - 2900 max words, 2000 samples - at ../dataset/gen-word-2900-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 - 3700 max words, 2000 samples - at ../dataset/gen-word-3700-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 - 2500 max words, 2000 samples - at ../dataset/gen-word-2500-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 - 2800 max words, 2000 samples - at ../dataset/gen-word-2800-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 - 3200 max words, 2000 samples - at ../dataset/gen-word-3200-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 - 3400 max words, 2000 samples - at ../dataset/gen-word-3400-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 - 3600 max words, 2000 samples - at ../dataset/gen-word-3600-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 - 4000 max words, 2000 samples - at ../dataset/gen-word-4000-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 - 3200 max words, 2000 samples - at ../dataset/gen-word-3200-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 - 3900 max words, 2000 samples - at ../dataset/gen-word-3900-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 - 4100 max words, 2000 samples - at ../dataset/gen-word-4100-count.jsonl\n" + "Generated JSONL file with - 5300 max words, 2000 samples - at ../dataset/gen-word-5300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 3800 max words, 2000 samples - at ../dataset/gen-word-3800-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 - 5200 max words, 2000 samples - at ../dataset/gen-word-5200-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 - 5000 max words, 2000 samples - at ../dataset/gen-word-5000-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 - 4200 max words, 2000 samples - at ../dataset/gen-word-4200-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 - 4500 max words, 2000 samples - at ../dataset/gen-word-4500-count.jsonl\n" + "Generated JSONL file with - 3500 max words, 2000 samples - at ../dataset/gen-word-3500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 4900 max words, 2000 samples - at ../dataset/gen-word-4900-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 - 5300 max words, 2000 samples - at ../dataset/gen-word-5300-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 - 4600 max words, 2000 samples - at ../dataset/gen-word-4600-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 - 4300 max words, 2000 samples - at ../dataset/gen-word-4300-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 - 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 - 4800 max words, 2000 samples - at ../dataset/gen-word-4800-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 - 5100 max words, 2000 samples - at ../dataset/gen-word-5100-count.jsonl\n" + "Generated JSONL file with - 4800 max words, 2000 samples - at ../dataset/gen-word-4800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 6300 max words, 2000 samples - at ../dataset/gen-word-6300-count.jsonl\n" + "Generated JSONL file with - 3900 max words, 2000 samples - at ../dataset/gen-word-3900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 5700 max words, 2000 samples - at ../dataset/gen-word-5700-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 - 5500 max words, 2000 samples - at ../dataset/gen-word-5500-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 - 5400 max words, 2000 samples - at ../dataset/gen-word-5400-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 - 6100 max words, 2000 samples - at ../dataset/gen-word-6100-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 - 5600 max words, 2000 samples - at ../dataset/gen-word-5600-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 - 6500 max words, 2000 samples - at ../dataset/gen-word-6500-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 - 6200 max words, 2000 samples - at ../dataset/gen-word-6200-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 - 7000 max words, 2000 samples - at ../dataset/gen-word-7000-count.jsonl\n" + "Generated JSONL file with - 5600 max words, 2000 samples - at ../dataset/gen-word-5600-count.jsonl\n" ] }, { @@ -1585,119 +1585,119 @@ "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 - 6300 max words, 2000 samples - at ../dataset/gen-word-6300-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 - 5700 max words, 2000 samples - at ../dataset/gen-word-5700-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 - 6200 max words, 2000 samples - at ../dataset/gen-word-6200-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 - 5900 max words, 2000 samples - at ../dataset/gen-word-5900-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 - 6700 max words, 2000 samples - at ../dataset/gen-word-6700-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 - 7300 max words, 2000 samples - at ../dataset/gen-word-7300-count.jsonl\n" + "Generated JSONL file with - 7100 max words, 2000 samples - at ../dataset/gen-word-7100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 6800 max words, 2000 samples - at ../dataset/gen-word-6800-count.jsonl\n" + "Generated JSONL file with - 8000 max words, 2000 samples - at ../dataset/gen-word-8000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 7100 max words, 2000 samples - at ../dataset/gen-word-7100-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 - 7200 max words, 2000 samples - at ../dataset/gen-word-7200-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 - 7800 max words, 2000 samples - at ../dataset/gen-word-7800-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 - 8000 max words, 2000 samples - at ../dataset/gen-word-8000-count.jsonl\n" + "Generated JSONL file with - 6400 max words, 2000 samples - at ../dataset/gen-word-6400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 7900 max words, 2000 samples - at ../dataset/gen-word-7900-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 - 7700 max words, 2000 samples - at ../dataset/gen-word-7700-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 - 7600 max words, 2000 samples - at ../dataset/gen-word-7600-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 - 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 - 7400 max words, 2000 samples - at ../dataset/gen-word-7400-count.jsonl\n" + "Generated JSONL file with - 7900 max words, 2000 samples - at ../dataset/gen-word-7900-count.jsonl\n" ] }, { @@ -1711,1393 +1711,1393 @@ "name": "stdout", "output_type": "stream", "text": [ - "total 2.5G\n" + "total 2.4G\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 20K Sep 13 18:27 gen-word-10-count.jsonl\n" + "-rw-r--r-- 1 root root 21K Sep 13 19:02 gen-word-10-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 2.1M Sep 13 18:27 gen-word-100-count.jsonl\n" + "-rw-r--r-- 1 root root 2.1M Sep 13 19:02 gen-word-100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 20M Sep 13 18:27 gen-word-1000-count.jsonl\n" + "-rw-r--r-- 1 root root 20M Sep 13 19:02 gen-word-1000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 22M Sep 13 18:27 gen-word-1100-count.jsonl\n" + "-rw-r--r-- 1 root root 22M Sep 13 19:02 gen-word-1100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 23M Sep 13 18:27 gen-word-1200-count.jsonl\n" + "-rw-r--r-- 1 root root 23M Sep 13 19:02 gen-word-1200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 25M Sep 13 18:27 gen-word-1300-count.jsonl\n" + "-rw-r--r-- 1 root root 25M Sep 13 19:02 gen-word-1300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 27M Sep 13 18:27 gen-word-1400-count.jsonl\n" + "-rw-r--r-- 1 root root 27M Sep 13 19:02 gen-word-1400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 25K Sep 13 18:27 gen-word-15-count.jsonl\n" + "-rw-r--r-- 1 root root 25K Sep 13 19:02 gen-word-15-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 29M Sep 13 18:27 gen-word-1500-count.jsonl\n" + "-rw-r--r-- 1 root root 29M Sep 13 19:02 gen-word-1500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 31M Sep 13 18:27 gen-word-1600-count.jsonl\n" + "-rw-r--r-- 1 root root 31M Sep 13 19:02 gen-word-1600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 33M Sep 13 18:27 gen-word-1700-count.jsonl\n" + "-rw-r--r-- 1 root root 33M Sep 13 19:02 gen-word-1700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 35M Sep 13 18:27 gen-word-1800-count.jsonl\n" + "-rw-r--r-- 1 root root 35M Sep 13 19:02 gen-word-1800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 37M Sep 13 18:27 gen-word-1900-count.jsonl\n" + "-rw-r--r-- 1 root root 37M Sep 13 19:02 gen-word-1900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 31K Sep 13 18:27 gen-word-20-count.jsonl\n" + "-rw-r--r-- 1 root root 30K Sep 13 19:02 gen-word-20-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 4.0M Sep 13 18:27 gen-word-200-count.jsonl\n" + "-rw-r--r-- 1 root root 4.0M Sep 13 19:02 gen-word-200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 39M Sep 13 18:27 gen-word-2000-count.jsonl\n" + "-rw-r--r-- 1 root root 39M Sep 13 19:02 gen-word-2000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 41M Sep 13 18:27 gen-word-2100-count.jsonl\n" + "-rw-r--r-- 1 root root 41M Sep 13 19:02 gen-word-2100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 42M Sep 13 18:27 gen-word-2200-count.jsonl\n" + "-rw-r--r-- 1 root root 42M Sep 13 19:02 gen-word-2200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 44M Sep 13 18:27 gen-word-2300-count.jsonl\n" + "-rw-r--r-- 1 root root 44M Sep 13 19:02 gen-word-2300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 46M Sep 13 18:27 gen-word-2400-count.jsonl\n" + "-rw-r--r-- 1 root root 46M Sep 13 19:02 gen-word-2400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 34K Sep 13 18:27 gen-word-25-count.jsonl\n" + "-rw-r--r-- 1 root root 35K Sep 13 19:02 gen-word-25-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 48M Sep 13 18:27 gen-word-2500-count.jsonl\n" + "-rw-r--r-- 1 root root 48M Sep 13 19:02 gen-word-2500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 50M Sep 13 18:27 gen-word-2600-count.jsonl\n" + "-rw-r--r-- 1 root root 50M Sep 13 19:02 gen-word-2600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 52M Sep 13 18:27 gen-word-2700-count.jsonl\n" + "-rw-r--r-- 1 root root 52M Sep 13 19:02 gen-word-2700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 54M Sep 13 18:27 gen-word-2800-count.jsonl\n" + "-rw-r--r-- 1 root root 54M Sep 13 19:02 gen-word-2800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 56M Sep 13 18:27 gen-word-2900-count.jsonl\n" + "-rw-r--r-- 1 root root 56M Sep 13 19:02 gen-word-2900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 39K Sep 13 18:27 gen-word-30-count.jsonl\n" + "-rw-r--r-- 1 root root 40K Sep 13 19:02 gen-word-30-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 5.9M Sep 13 18:27 gen-word-300-count.jsonl\n" + "-rw-r--r-- 1 root root 5.9M Sep 13 19:02 gen-word-300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 58M Sep 13 18:27 gen-word-3000-count.jsonl\n" + "-rw-r--r-- 1 root root 58M Sep 13 19:02 gen-word-3000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 60M Sep 13 18:27 gen-word-3100-count.jsonl\n" + "-rw-r--r-- 1 root root 60M Sep 13 19:02 gen-word-3100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 61M Sep 13 18:27 gen-word-3200-count.jsonl\n" + "-rw-r--r-- 1 root root 62M Sep 13 19:02 gen-word-3200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 63M Sep 13 18:27 gen-word-3300-count.jsonl\n" + "-rw-r--r-- 1 root root 63M Sep 13 19:02 gen-word-3300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 65M Sep 13 18:27 gen-word-3400-count.jsonl\n" + "-rw-r--r-- 1 root root 65M Sep 13 19:02 gen-word-3400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 44K Sep 13 18:27 gen-word-35-count.jsonl\n" + "-rw-r--r-- 1 root root 44K Sep 13 19:02 gen-word-35-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 67M Sep 13 18:27 gen-word-3500-count.jsonl\n" + "-rw-r--r-- 1 root root 67M Sep 13 19:02 gen-word-3500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 69M Sep 13 18:27 gen-word-3600-count.jsonl\n" + "-rw-r--r-- 1 root root 69M Sep 13 19:02 gen-word-3600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 71M Sep 13 18:27 gen-word-3700-count.jsonl\n" + "-rw-r--r-- 1 root root 71M Sep 13 19:02 gen-word-3700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 73M Sep 13 18:28 gen-word-3800-count.jsonl\n" + "-rw-r--r-- 1 root root 73M Sep 13 19:02 gen-word-3800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 75M Sep 13 18:28 gen-word-3900-count.jsonl\n" + "-rw-r--r-- 1 root root 75M Sep 13 19:02 gen-word-3900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 49K Sep 13 18:27 gen-word-40-count.jsonl\n" + "-rw-r--r-- 1 root root 50K Sep 13 19:02 gen-word-40-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 7.8M Sep 13 18:27 gen-word-400-count.jsonl\n" + "-rw-r--r-- 1 root root 7.8M Sep 13 19:02 gen-word-400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 77M Sep 13 18:27 gen-word-4000-count.jsonl\n" + "-rw-r--r-- 1 root root 77M Sep 13 19:02 gen-word-4000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 78M Sep 13 18:28 gen-word-4100-count.jsonl\n" + "-rw-r--r-- 1 root root 79M Sep 13 19:02 gen-word-4100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 81M Sep 13 18:28 gen-word-4200-count.jsonl\n" + "-rw-r--r-- 1 root root 80M Sep 13 19:02 gen-word-4200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 82M Sep 13 18:28 gen-word-4300-count.jsonl\n" + "-rw-r--r-- 1 root root 82M Sep 13 19:02 gen-word-4300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 84M Sep 13 18:27 gen-word-4400-count.jsonl\n" + "-rw-r--r-- 1 root root 84M Sep 13 19:02 gen-word-4400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 54K Sep 13 18:27 gen-word-45-count.jsonl\n" + "-rw-r--r-- 1 root root 54K Sep 13 19:02 gen-word-45-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 86M Sep 13 18:28 gen-word-4500-count.jsonl\n" + "-rw-r--r-- 1 root root 86M Sep 13 19:02 gen-word-4500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 88M Sep 13 18:28 gen-word-4600-count.jsonl\n" + "-rw-r--r-- 1 root root 88M Sep 13 19:02 gen-word-4600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 90M Sep 13 18:28 gen-word-4700-count.jsonl\n" + "-rw-r--r-- 1 root root 90M Sep 13 19:02 gen-word-4700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 92M Sep 13 18:28 gen-word-4800-count.jsonl\n" + "-rw-r--r-- 1 root root 92M Sep 13 19:02 gen-word-4800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 94M Sep 13 18:28 gen-word-4900-count.jsonl\n" + "-rw-r--r-- 1 root root 94M Sep 13 19:02 gen-word-4900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 15K Sep 13 18:27 gen-word-5-count.jsonl\n" + "-rw-r--r-- 1 root root 15K Sep 13 19:02 gen-word-5-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 58K Sep 13 18:27 gen-word-50-count.jsonl\n" + "-rw-r--r-- 1 root root 58K Sep 13 19:02 gen-word-50-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 9.7M Sep 13 18:27 gen-word-500-count.jsonl\n" + "-rw-r--r-- 1 root root 9.8M Sep 13 19:02 gen-word-500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 96M Sep 13 18:28 gen-word-5000-count.jsonl\n" + "-rw-r--r-- 1 root root 96M Sep 13 19:02 gen-word-5000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 98M Sep 13 18:28 gen-word-5100-count.jsonl\n" + "-rw-r--r-- 1 root root 98M Sep 13 19:02 gen-word-5100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 99M Sep 13 18:28 gen-word-5200-count.jsonl\n" + "-rw-r--r-- 1 root root 99M Sep 13 19:02 gen-word-5200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 101M Sep 13 18:28 gen-word-5300-count.jsonl\n" + "-rw-r--r-- 1 root root 101M Sep 13 19:02 gen-word-5300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 103M Sep 13 18:28 gen-word-5400-count.jsonl\n" + "-rw-r--r-- 1 root root 103M Sep 13 19:02 gen-word-5400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 64K Sep 13 18:27 gen-word-55-count.jsonl\n" + "-rw-r--r-- 1 root root 64K Sep 13 19:02 gen-word-55-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 105M Sep 13 18:28 gen-word-5500-count.jsonl\n" + "-rw-r--r-- 1 root root 105M Sep 13 19:02 gen-word-5500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 107M Sep 13 18:28 gen-word-5600-count.jsonl\n" + "-rw-r--r-- 1 root root 107M Sep 13 19:02 gen-word-5600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 109M Sep 13 18:28 gen-word-5700-count.jsonl\n" + "-rw-r--r-- 1 root root 109M Sep 13 19:02 gen-word-5700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 111M Sep 13 18:28 gen-word-5800-count.jsonl\n" + "-rw-r--r-- 1 root root 111M Sep 13 19:02 gen-word-5800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 113M Sep 13 18:28 gen-word-5900-count.jsonl\n" + "-rw-r--r-- 1 root root 113M Sep 13 19:02 gen-word-5900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 69K Sep 13 18:27 gen-word-60-count.jsonl\n" + "-rw-r--r-- 1 root root 70K Sep 13 19:02 gen-word-60-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 12M Sep 13 18:27 gen-word-600-count.jsonl\n" + "-rw-r--r-- 1 root root 12M Sep 13 19:02 gen-word-600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 115M Sep 13 18:28 gen-word-6000-count.jsonl\n" + "-rw-r--r-- 1 root root 115M Sep 13 19:02 gen-word-6000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 117M Sep 13 18:28 gen-word-6100-count.jsonl\n" + "-rw-r--r-- 1 root root 117M Sep 13 19:02 gen-word-6100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 118M Sep 13 18:28 gen-word-6200-count.jsonl\n" + "-rw-r--r-- 1 root root 118M Sep 13 19:02 gen-word-6200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 120M Sep 13 18:28 gen-word-6300-count.jsonl\n" + "-rw-r--r-- 1 root root 120M Sep 13 19:02 gen-word-6300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 122M Sep 13 18:28 gen-word-6400-count.jsonl\n" + "-rw-r--r-- 1 root root 122M Sep 13 19:02 gen-word-6400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 74K Sep 13 18:27 gen-word-65-count.jsonl\n" + "-rw-r--r-- 1 root root 75K Sep 13 19:02 gen-word-65-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 124M Sep 13 18:28 gen-word-6500-count.jsonl\n" + "-rw-r--r-- 1 root root 124M Sep 13 19:02 gen-word-6500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 126M Sep 13 18:28 gen-word-6600-count.jsonl\n" + "-rw-r--r-- 1 root root 126M Sep 13 19:02 gen-word-6600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 128M Sep 13 18:28 gen-word-6700-count.jsonl\n" + "-rw-r--r-- 1 root root 128M Sep 13 19:02 gen-word-6700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 130M Sep 13 18:28 gen-word-6800-count.jsonl\n" + "-rw-r--r-- 1 root root 130M Sep 13 19:02 gen-word-6800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 132M Sep 13 18:28 gen-word-6900-count.jsonl\n" + "-rw-r--r-- 1 root root 132M Sep 13 19:02 gen-word-6900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 80K Sep 13 18:27 gen-word-70-count.jsonl\n" + "-rw-r--r-- 1 root root 79K Sep 13 19:02 gen-word-70-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 14M Sep 13 18:27 gen-word-700-count.jsonl\n" + "-rw-r--r-- 1 root root 14M Sep 13 19:02 gen-word-700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 134M Sep 13 18:28 gen-word-7000-count.jsonl\n" + "-rw-r--r-- 1 root root 134M Sep 13 19:02 gen-word-7000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 135M Sep 13 18:28 gen-word-7100-count.jsonl\n" + "-rw-r--r-- 1 root root 135M Sep 13 19:02 gen-word-7100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 137M Sep 13 18:28 gen-word-7200-count.jsonl\n" + "-rw-r--r-- 1 root root 137M Sep 13 19:02 gen-word-7200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 139M Sep 13 18:28 gen-word-7300-count.jsonl\n" + "-rw-r--r-- 1 root root 139M Sep 13 19:02 gen-word-7300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 141M Sep 13 18:28 gen-word-7400-count.jsonl\n" + "-rw-r--r-- 1 root root 141M Sep 13 19:02 gen-word-7400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 81K Sep 13 18:27 gen-word-75-count.jsonl\n" + "-rw-r--r-- 1 root root 84K Sep 13 19:02 gen-word-75-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 143M Sep 13 18:28 gen-word-7500-count.jsonl\n" + "-rw-r--r-- 1 root root 143M Sep 13 19:02 gen-word-7500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 145M Sep 13 18:28 gen-word-7600-count.jsonl\n" + "-rw-r--r-- 1 root root 145M Sep 13 19:02 gen-word-7600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 147M Sep 13 18:28 gen-word-7700-count.jsonl\n" + "-rw-r--r-- 1 root root 147M Sep 13 19:02 gen-word-7700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 149M Sep 13 18:28 gen-word-7800-count.jsonl\n" + "-rw-r--r-- 1 root root 149M Sep 13 19:02 gen-word-7800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 151M Sep 13 18:28 gen-word-7900-count.jsonl\n" + "-rw-r--r-- 1 root root 151M Sep 13 19:02 gen-word-7900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 89K Sep 13 18:27 gen-word-80-count.jsonl\n" + "-rw-r--r-- 1 root root 87K Sep 13 19:02 gen-word-80-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 16M Sep 13 18:27 gen-word-800-count.jsonl\n" + "-rw-r--r-- 1 root root 16M Sep 13 19:02 gen-word-800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 153M Sep 13 18:28 gen-word-8000-count.jsonl\n" + "-rw-r--r-- 1 root root 153M Sep 13 19:02 gen-word-8000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 95K Sep 13 18:27 gen-word-85-count.jsonl\n" + "-rw-r--r-- 1 root root 94K Sep 13 19:02 gen-word-85-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 97K Sep 13 18:27 gen-word-90-count.jsonl\n" + "-rw-r--r-- 1 root root 101K Sep 13 19:02 gen-word-90-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 18M Sep 13 18:27 gen-word-900-count.jsonl\n" + "-rw-r--r-- 1 root root 18M Sep 13 19:02 gen-word-900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 103K Sep 13 18:27 gen-word-95-count.jsonl\n" + "-rw-r--r-- 1 root root 105K Sep 13 19:02 gen-word-95-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 506K Sep 13 18:27 shuffle-word-10-count.jsonl\n" + "-rw-r--r-- 1 root root 520K Sep 13 19:02 shuffle-word-10-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 565K Sep 13 18:27 shuffle-word-100-count.jsonl\n" + "-rw-r--r-- 1 root root 574K Sep 13 19:02 shuffle-word-100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 521K Sep 13 18:27 shuffle-word-1000-count.jsonl\n" + "-rw-r--r-- 1 root root 523K Sep 13 19:02 shuffle-word-1000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 521K Sep 13 18:27 shuffle-word-1100-count.jsonl\n" + "-rw-r--r-- 1 root root 523K Sep 13 19:02 shuffle-word-1100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 521K Sep 13 18:27 shuffle-word-1200-count.jsonl\n" + "-rw-r--r-- 1 root root 522K Sep 13 19:02 shuffle-word-1200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 523K Sep 13 18:27 shuffle-word-1300-count.jsonl\n" + "-rw-r--r-- 1 root root 526K Sep 13 19:02 shuffle-word-1300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 521K Sep 13 18:27 shuffle-word-1400-count.jsonl\n" + "-rw-r--r-- 1 root root 520K Sep 13 19:02 shuffle-word-1400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 429K Sep 13 18:27 shuffle-word-15-count.jsonl\n" + "-rw-r--r-- 1 root root 432K Sep 13 19:02 shuffle-word-15-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 520K Sep 13 18:27 shuffle-word-1500-count.jsonl\n" + "-rw-r--r-- 1 root root 523K Sep 13 19:02 shuffle-word-1500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 518K Sep 13 18:27 shuffle-word-1600-count.jsonl\n" + "-rw-r--r-- 1 root root 522K Sep 13 19:02 shuffle-word-1600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 520K Sep 13 18:27 shuffle-word-1700-count.jsonl\n" + "-rw-r--r-- 1 root root 520K Sep 13 19:02 shuffle-word-1700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 521K Sep 13 18:27 shuffle-word-1800-count.jsonl\n" + "-rw-r--r-- 1 root root 521K Sep 13 19:02 shuffle-word-1800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 519K Sep 13 18:27 shuffle-word-1900-count.jsonl\n" + "-rw-r--r-- 1 root root 522K Sep 13 19:02 shuffle-word-1900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 399K Sep 13 18:27 shuffle-word-20-count.jsonl\n" + "-rw-r--r-- 1 root root 378K Sep 13 19:02 shuffle-word-20-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 540K Sep 13 18:27 shuffle-word-200-count.jsonl\n" + "-rw-r--r-- 1 root root 541K Sep 13 19:02 shuffle-word-200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 522K Sep 13 18:27 shuffle-word-2000-count.jsonl\n" + "-rw-r--r-- 1 root root 520K Sep 13 19:02 shuffle-word-2000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 524K Sep 13 18:27 shuffle-word-2100-count.jsonl\n" + "-rw-r--r-- 1 root root 520K Sep 13 19:02 shuffle-word-2100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 520K Sep 13 18:27 shuffle-word-2200-count.jsonl\n" + "-rw-r--r-- 1 root root 522K Sep 13 19:02 shuffle-word-2200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 520K Sep 13 18:27 shuffle-word-2300-count.jsonl\n" + "-rw-r--r-- 1 root root 518K Sep 13 19:02 shuffle-word-2300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 520K Sep 13 18:27 shuffle-word-2400-count.jsonl\n" + "-rw-r--r-- 1 root root 520K Sep 13 19:02 shuffle-word-2400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 366K Sep 13 18:27 shuffle-word-25-count.jsonl\n" + "-rw-r--r-- 1 root root 356K Sep 13 19:02 shuffle-word-25-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 518K Sep 13 18:27 shuffle-word-2500-count.jsonl\n" + "-rw-r--r-- 1 root root 518K Sep 13 19:02 shuffle-word-2500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 517K Sep 13 18:27 shuffle-word-2600-count.jsonl\n" + "-rw-r--r-- 1 root root 515K Sep 13 19:02 shuffle-word-2600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 511K Sep 13 18:27 shuffle-word-2700-count.jsonl\n" + "-rw-r--r-- 1 root root 511K Sep 13 19:02 shuffle-word-2700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 508K Sep 13 18:27 shuffle-word-2800-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-2800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 18:27 shuffle-word-2900-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-2900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 350K Sep 13 18:27 shuffle-word-30-count.jsonl\n" + "-rw-r--r-- 1 root root 344K Sep 13 19:02 shuffle-word-30-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 534K Sep 13 18:27 shuffle-word-300-count.jsonl\n" + "-rw-r--r-- 1 root root 535K Sep 13 19:02 shuffle-word-300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 18:27 shuffle-word-3000-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-3000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 508K Sep 13 18:27 shuffle-word-3100-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-3100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 508K Sep 13 18:27 shuffle-word-3200-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-3200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 508K Sep 13 18:27 shuffle-word-3300-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-3300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 18:27 shuffle-word-3400-count.jsonl\n" + "-rw-r--r-- 1 root root 508K Sep 13 19:02 shuffle-word-3400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 326K Sep 13 18:27 shuffle-word-35-count.jsonl\n" + "-rw-r--r-- 1 root root 332K Sep 13 19:02 shuffle-word-35-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 18:27 shuffle-word-3500-count.jsonl\n" + "-rw-r--r-- 1 root root 508K Sep 13 19:02 shuffle-word-3500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 18:27 shuffle-word-3600-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-3600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 18:27 shuffle-word-3700-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-3700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 18:27 shuffle-word-3800-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-3800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 18:27 shuffle-word-3900-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-3900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 328K Sep 13 18:27 shuffle-word-40-count.jsonl\n" + "-rw-r--r-- 1 root root 311K Sep 13 19:02 shuffle-word-40-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 529K Sep 13 18:27 shuffle-word-400-count.jsonl\n" + "-rw-r--r-- 1 root root 529K Sep 13 19:02 shuffle-word-400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 18:27 shuffle-word-4000-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-4000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 18:27 shuffle-word-4100-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-4100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 18:27 shuffle-word-4200-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-4200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 18:27 shuffle-word-4300-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-4300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 18:27 shuffle-word-4400-count.jsonl\n" + "-rw-r--r-- 1 root root 508K Sep 13 19:02 shuffle-word-4400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 312K Sep 13 18:27 shuffle-word-45-count.jsonl\n" + "-rw-r--r-- 1 root root 305K Sep 13 19:02 shuffle-word-45-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 18:27 shuffle-word-4500-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-4500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 18:27 shuffle-word-4600-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-4600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 18:27 shuffle-word-4700-count.jsonl\n" + "-rw-r--r-- 1 root root 508K Sep 13 19:02 shuffle-word-4700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 18:27 shuffle-word-4800-count.jsonl\n" + "-rw-r--r-- 1 root root 508K Sep 13 19:02 shuffle-word-4800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 18:27 shuffle-word-4900-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-4900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 827K Sep 13 18:27 shuffle-word-5-count.jsonl\n" + "-rw-r--r-- 1 root root 809K Sep 13 19:02 shuffle-word-5-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 304K Sep 13 18:27 shuffle-word-50-count.jsonl\n" + "-rw-r--r-- 1 root root 313K Sep 13 19:02 shuffle-word-50-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 523K Sep 13 18:27 shuffle-word-500-count.jsonl\n" + "-rw-r--r-- 1 root root 526K Sep 13 19:02 shuffle-word-500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 18:27 shuffle-word-5000-count.jsonl\n" + "-rw-r--r-- 1 root root 508K Sep 13 19:02 shuffle-word-5000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 18:27 shuffle-word-5100-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-5100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 18:27 shuffle-word-5200-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-5200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 508K Sep 13 18:27 shuffle-word-5300-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-5300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 18:27 shuffle-word-5400-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-5400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 299K Sep 13 18:27 shuffle-word-55-count.jsonl\n" + "-rw-r--r-- 1 root root 306K Sep 13 19:02 shuffle-word-55-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 18:27 shuffle-word-5500-count.jsonl\n" + "-rw-r--r-- 1 root root 508K Sep 13 19:02 shuffle-word-5500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 18:27 shuffle-word-5600-count.jsonl\n" + "-rw-r--r-- 1 root root 508K Sep 13 19:02 shuffle-word-5600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 18:27 shuffle-word-5700-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-5700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 18:27 shuffle-word-5800-count.jsonl\n" + "-rw-r--r-- 1 root root 508K Sep 13 19:02 shuffle-word-5800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 18:27 shuffle-word-5900-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-5900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 296K Sep 13 18:27 shuffle-word-60-count.jsonl\n" + "-rw-r--r-- 1 root root 299K Sep 13 19:02 shuffle-word-60-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 528K Sep 13 18:27 shuffle-word-600-count.jsonl\n" + "-rw-r--r-- 1 root root 527K Sep 13 19:02 shuffle-word-600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 18:27 shuffle-word-6000-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-6000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 18:27 shuffle-word-6100-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-6100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 18:27 shuffle-word-6200-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-6200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 18:27 shuffle-word-6300-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-6300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 18:27 shuffle-word-6400-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-6400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 294K Sep 13 18:27 shuffle-word-65-count.jsonl\n" + "-rw-r--r-- 1 root root 296K Sep 13 19:02 shuffle-word-65-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 508K Sep 13 18:27 shuffle-word-6500-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-6500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 508K Sep 13 18:27 shuffle-word-6600-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-6600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 18:27 shuffle-word-6700-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-6700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 18:27 shuffle-word-6800-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-6800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 508K Sep 13 18:27 shuffle-word-6900-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-6900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 297K Sep 13 18:27 shuffle-word-70-count.jsonl\n" + "-rw-r--r-- 1 root root 290K Sep 13 19:02 shuffle-word-70-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 521K Sep 13 18:27 shuffle-word-700-count.jsonl\n" + "-rw-r--r-- 1 root root 523K Sep 13 19:02 shuffle-word-700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 18:27 shuffle-word-7000-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-7000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 18:27 shuffle-word-7100-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-7100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 18:27 shuffle-word-7200-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-7200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 18:27 shuffle-word-7300-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-7300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 18:27 shuffle-word-7400-count.jsonl\n" + "-rw-r--r-- 1 root root 508K Sep 13 19:02 shuffle-word-7400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 294K Sep 13 18:27 shuffle-word-75-count.jsonl\n" + "-rw-r--r-- 1 root root 290K Sep 13 19:02 shuffle-word-75-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 508K Sep 13 18:27 shuffle-word-7500-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-7500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 508K Sep 13 18:27 shuffle-word-7600-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-7600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 18:27 shuffle-word-7700-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-7700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 18:27 shuffle-word-7800-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-7800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 18:27 shuffle-word-7900-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-7900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 290K Sep 13 18:27 shuffle-word-80-count.jsonl\n" + "-rw-r--r-- 1 root root 291K Sep 13 19:02 shuffle-word-80-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 524K Sep 13 18:27 shuffle-word-800-count.jsonl\n" + "-rw-r--r-- 1 root root 527K Sep 13 19:02 shuffle-word-800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 13 18:27 shuffle-word-8000-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 13 19:02 shuffle-word-8000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 286K Sep 13 18:27 shuffle-word-85-count.jsonl\n" + "-rw-r--r-- 1 root root 289K Sep 13 19:02 shuffle-word-85-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 286K Sep 13 18:27 shuffle-word-90-count.jsonl\n" + "-rw-r--r-- 1 root root 287K Sep 13 19:02 shuffle-word-90-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 522K Sep 13 18:27 shuffle-word-900-count.jsonl\n" + "-rw-r--r-- 1 root root 522K Sep 13 19:02 shuffle-word-900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 284K Sep 13 18:27 shuffle-word-95-count.jsonl\n" + "-rw-r--r-- 1 root root 282K Sep 13 19:02 shuffle-word-95-count.jsonl\n" ] } ], @@ -3146,19 +3146,19 @@ { "cell_type": "code", "execution_count": 6, - "id": "29a05b80", + "id": "4da0b8bc", "metadata": { "execution": { - "iopub.execute_input": "2023-09-13T18:28:06.855712Z", - "iopub.status.busy": "2023-09-13T18:28:06.855353Z", - "iopub.status.idle": "2023-09-13T18:28:25.531402Z", - "shell.execute_reply": "2023-09-13T18:28:25.530601Z" + "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" }, "papermill": { - "duration": 18.696984, - "end_time": "2023-09-13T18:28:25.533284", + "duration": 17.474014, + "end_time": "2023-09-13T19:03:17.316238", "exception": false, - "start_time": "2023-09-13T18:28:06.836300", + "start_time": "2023-09-13T19:02:59.842224", "status": "completed" }, "tags": [] @@ -3168,7 +3168,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "[2023-09-13 18:28:09,853] [INFO] [real_accelerator.py:133:get_accelerator] Setting ds_accelerator to cuda (auto detect)\r\n" + "[2023-09-13 19:03:02,731] [INFO] [real_accelerator.py:133:get_accelerator] Setting ds_accelerator to cuda (auto detect)\r\n" ] }, { @@ -3182,7 +3182,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "/usr/local/lib/python3.10/dist-packages/lightning/pytorch/cli.py:484: UserWarning: LightningCLI's args parameter is intended to run from within Python like if it were from the command line. To prevent mistakes it is not recommended to provide both args and command line arguments, got: sys.argv[1:]=['fit', '-c', '/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/notebook/experiment/rwkv-x-exp/v5-r3-memory/config-mem-template.yaml', '--trainer.logger.init_args.name=v5r3-L12-D2560-E0.1 - Mem-Tune ctx-8k (train-ctx=4k, deepspeed_stage_1)', '--trainer.strategy=deepspeed_stage_1', '--trainer.devices=auto', '--trainer.callbacks.init_args.dirpath=../checkpoint/v5r3-L12-D2560-E0_1-mem-ctx-8k/', '--model.lr_init=4e-4', '--model.lr_final=2e-4', '--data.max_token_size=8192', '--data.sort_by_length=True', '--model.ctx_len=4096', '--model.bptt_learning_range=2', '--model.load_model=../model/v5r3-L12-D2560-E0_1-mem-ctx-8k.pth'], args=['fit', '-c', '/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/notebook/experiment/rwkv-x-exp/v5-r3-memory/config-mem-template.yaml', '--trainer.logger.init_args.name=v5r3-L12-D2560-E0.1 - Mem-Tune ctx-8k (train-ctx=4k, deepspeed_stage_1)', '--trainer.strategy=deepspeed_stage_1', '--trainer.devices=auto', '--trainer.callbacks.init_args.dirpath=../checkpoint/v5r3-L12-D2560-E0_1-mem-ctx-8k/', '--model.lr_init=4e-4', '--model.lr_final=2e-4', '--data.max_token_size=8192', '--data.sort_by_length=True', '--model.ctx_len=4096', '--model.bptt_learning_range=2', '--model.load_model=../model/v5r3-L12-D2560-E0_1-mem-ctx-8k.pth'].\r\n", + "/usr/local/lib/python3.10/dist-packages/lightning/pytorch/cli.py:484: UserWarning: LightningCLI's args parameter is intended to run from within Python like if it were from the command line. To prevent mistakes it is not recommended to provide both args and command line arguments, got: sys.argv[1:]=['fit', '-c', '/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/notebook/experiment/rwkv-x-exp/v5-r3-memory/config-mem-template.yaml', '--trainer.logger.init_args.name=v5r3-L12-D2560-E0.1 - Mem-Tune ctx-8k (train-ctx=4k, deepspeed_stage_1)', '--trainer.strategy=deepspeed_stage_1', '--trainer.devices=auto', '--trainer.callbacks.init_args.dirpath=../checkpoint/v5r3-L12-D2560-E0_1-mem-ctx-8k/', '--model.lr_init=4e-4', '--model.lr_final=2e-4', '--data.max_token_size=8192', '--data.sort_by_length=True', '--model.ctx_len=4096', '--model.bptt_learning_range=2', '--model.load_model=../model/v5r3-L12-D2560-E0_1-mem-ctx-512.pth'], args=['fit', '-c', '/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/notebook/experiment/rwkv-x-exp/v5-r3-memory/config-mem-template.yaml', '--trainer.logger.init_args.name=v5r3-L12-D2560-E0.1 - Mem-Tune ctx-8k (train-ctx=4k, deepspeed_stage_1)', '--trainer.strategy=deepspeed_stage_1', '--trainer.devices=auto', '--trainer.callbacks.init_args.dirpath=../checkpoint/v5r3-L12-D2560-E0_1-mem-ctx-8k/', '--model.lr_init=4e-4', '--model.lr_final=2e-4', '--data.max_token_size=8192', '--data.sort_by_length=True', '--model.ctx_len=4096', '--model.bptt_learning_range=2', '--model.load_model=../model/v5r3-L12-D2560-E0_1-mem-ctx-512.pth'].\r\n", " rank_zero_warn(\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 2484677956\r\n", + "/usr/local/lib/python3.10/dist-packages/lightning/fabric/utilities/seed.py:39: UserWarning: No seed found, seed set to 1648783608\r\n", " rank_zero_warn(f\"No seed found, seed set to {seed}\")\r\n", - "Global seed set to 2484677956\r\n" + "Global seed set to 1648783608\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_182812-zxyexb8q\u001b[0m\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 \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/zxyexb8q\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" ] }, { @@ -3239,7 +3239,13 @@ " parent[key] = group.group_class(**value)\r\n", " File \"/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/RWKV-v5/src/model.py\", line 565, in __init__\r\n", " raise ValueError(f\"load_model file '{load_model}' does not exist\")\r\n", - "ValueError: load_model file '../model/v5r3-L12-D2560-E0_1-mem-ctx-8k.pth' does not exist\r\n", + "ValueError: load_model file '../model/v5r3-L12-D2560-E0_1-mem-ctx-512.pth' does not exist\r\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ "\u001b[34m\u001b[1mwandb\u001b[0m: Waiting for W&B process to finish... \u001b[31m(failed 1).\u001b[0m Press Control-C to abort syncing.\r\n" ] }, @@ -3247,10 +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/zxyexb8q\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/v48\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/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: 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_182812-zxyexb8q/logs\u001b[0m\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" ] } ], @@ -3270,25 +3276,25 @@ " --data.sort_by_length=True \\\n", " --model.ctx_len=4096 \\\n", " --model.bptt_learning_range=2 \\\n", - " --model.load_model=\"../model/{FILENAME_PREFIX}-mem-ctx-8k.pth\"" + " --model.load_model=\"../model/{FILENAME_PREFIX}-mem-ctx-512.pth\"" ] }, { "cell_type": "code", "execution_count": 7, - "id": "04cb7a35", + "id": "dcf71a84", "metadata": { "execution": { - "iopub.execute_input": "2023-09-13T18:28:25.571088Z", - "iopub.status.busy": "2023-09-13T18:28:25.570819Z", - "iopub.status.idle": "2023-09-13T18:28:27.980941Z", - "shell.execute_reply": "2023-09-13T18:28:27.980189Z" + "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" }, "papermill": { - "duration": 2.429307, - "end_time": "2023-09-13T18:28:27.982768", + "duration": 2.418382, + "end_time": "2023-09-13T19:03:19.755548", "exception": false, - "start_time": "2023-09-13T18:28:25.553461", + "start_time": "2023-09-13T19:03:17.337166", "status": "completed" }, "tags": [] @@ -3298,7 +3304,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "[2023-09-13 18:28:27,119] [INFO] [real_accelerator.py:133:get_accelerator] Setting ds_accelerator to cuda (auto detect)\r\n" + "[2023-09-13 19:03:18,896] [INFO] [real_accelerator.py:133:get_accelerator] Setting ds_accelerator to cuda (auto detect)\r\n" ] }, { @@ -3335,19 +3341,19 @@ { "cell_type": "code", "execution_count": 8, - "id": "3fb0f972", + "id": "9b9a3a59", "metadata": { "execution": { - "iopub.execute_input": "2023-09-13T18:28:28.043862Z", - "iopub.status.busy": "2023-09-13T18:28:28.043677Z", - "iopub.status.idle": "2023-09-13T18:28:28.275304Z", - "shell.execute_reply": "2023-09-13T18:28:28.274550Z" + "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" }, "papermill": { - "duration": 0.25089, - "end_time": "2023-09-13T18:28:28.277145", + "duration": 0.251531, + "end_time": "2023-09-13T19:03:20.050541", "exception": false, - "start_time": "2023-09-13T18:28:28.026255", + "start_time": "2023-09-13T19:03:19.799010", "status": "completed" }, "tags": [] @@ -3369,19 +3375,19 @@ { "cell_type": "code", "execution_count": 9, - "id": "7fb71aeb", + "id": "101c9366", "metadata": { "execution": { - "iopub.execute_input": "2023-09-13T18:28:28.314387Z", - "iopub.status.busy": "2023-09-13T18:28:28.314238Z", - "iopub.status.idle": "2023-09-13T18:28:28.542753Z", - "shell.execute_reply": "2023-09-13T18:28:28.542009Z" + "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" }, "papermill": { - "duration": 0.247293, - "end_time": "2023-09-13T18:28:28.544469", + "duration": 0.251914, + "end_time": "2023-09-13T19:03:20.324282", "exception": false, - "start_time": "2023-09-13T18:28:28.297176", + "start_time": "2023-09-13T19:03:20.072368", "status": "completed" }, "tags": [] @@ -3420,14 +3426,14 @@ }, "papermill": { "default_parameters": {}, - "duration": 49.763404, - "end_time": "2023-09-13T18:28:28.680735", + "duration": 48.904767, + "end_time": "2023-09-13T19:03:20.462590", "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": "2023-09-13T18:27:38.917331", + "start_time": "2023-09-13T19:02:31.557823", "version": "2.4.0" } },