diff --git "a/experiment/rwkv-x-exp/v5-r3-memory/L6-D2048-E1e-1-ctx4k/stage3.ipynb" "b/experiment/rwkv-x-exp/v5-r3-memory/L6-D2048-E1e-1-ctx4k/stage3.ipynb" --- "a/experiment/rwkv-x-exp/v5-r3-memory/L6-D2048-E1e-1-ctx4k/stage3.ipynb" +++ "b/experiment/rwkv-x-exp/v5-r3-memory/L6-D2048-E1e-1-ctx4k/stage3.ipynb" @@ -3,13 +3,13 @@ { "attachments": {}, "cell_type": "markdown", - "id": "2d294c56", + "id": "e6bf5eac", "metadata": { "papermill": { - "duration": 0.005601, - "end_time": "2023-09-14T00:22:48.660046", + "duration": 0.005682, + "end_time": "2023-09-14T02:37:04.293470", "exception": false, - "start_time": "2023-09-14T00:22:48.654445", + "start_time": "2023-09-14T02:37:04.287788", "status": "completed" }, "tags": [] @@ -25,13 +25,13 @@ { "attachments": {}, "cell_type": "markdown", - "id": "d8e1b078", + "id": "f59fa274", "metadata": { "papermill": { - "duration": 0.003053, - "end_time": "2023-09-14T00:22:48.666813", + "duration": 0.003026, + "end_time": "2023-09-14T02:37:04.300149", "exception": false, - "start_time": "2023-09-14T00:22:48.663760", + "start_time": "2023-09-14T02:37:04.297123", "status": "completed" }, "tags": [] @@ -43,19 +43,19 @@ { "cell_type": "code", "execution_count": 1, - "id": "25b2c35a", + "id": "b9505f51", "metadata": { "execution": { - "iopub.execute_input": "2023-09-14T00:22:48.675167Z", - "iopub.status.busy": "2023-09-14T00:22:48.674642Z", - "iopub.status.idle": "2023-09-14T00:22:49.678806Z", - "shell.execute_reply": "2023-09-14T00:22:49.677875Z" + "iopub.execute_input": "2023-09-14T02:37:04.308476Z", + "iopub.status.busy": "2023-09-14T02:37:04.307936Z", + "iopub.status.idle": "2023-09-14T02:37:05.309488Z", + "shell.execute_reply": "2023-09-14T02:37:05.308127Z" }, "papermill": { - "duration": 1.011151, - "end_time": "2023-09-14T00:22:49.681331", + "duration": 1.008439, + "end_time": "2023-09-14T02:37:05.311918", "exception": false, - "start_time": "2023-09-14T00:22:48.670180", + "start_time": "2023-09-14T02:37:04.303479", "status": "completed" }, "tags": [] @@ -83,19 +83,19 @@ { "cell_type": "code", "execution_count": 2, - "id": "10fc7c1c", + "id": "8d16737a", "metadata": { "execution": { - "iopub.execute_input": "2023-09-14T00:22:49.690536Z", - "iopub.status.busy": "2023-09-14T00:22:49.689989Z", - "iopub.status.idle": "2023-09-14T00:22:53.079072Z", - "shell.execute_reply": "2023-09-14T00:22:53.078184Z" + "iopub.execute_input": "2023-09-14T02:37:05.320892Z", + "iopub.status.busy": "2023-09-14T02:37:05.319751Z", + "iopub.status.idle": "2023-09-14T02:37:08.625564Z", + "shell.execute_reply": "2023-09-14T02:37:08.624420Z" }, "papermill": { - "duration": 3.39647, - "end_time": "2023-09-14T00:22:53.081568", + "duration": 3.312981, + "end_time": "2023-09-14T02:37:08.627991", "exception": false, - "start_time": "2023-09-14T00:22:49.685098", + "start_time": "2023-09-14T02:37:05.315010", "status": "completed" }, "tags": [] @@ -118,19 +118,19 @@ { "cell_type": "code", "execution_count": 3, - "id": "7983d767", + "id": "157915c9", "metadata": { "execution": { - "iopub.execute_input": "2023-09-14T00:22:53.090665Z", - "iopub.status.busy": "2023-09-14T00:22:53.090326Z", - "iopub.status.idle": "2023-09-14T00:22:53.098892Z", - "shell.execute_reply": "2023-09-14T00:22:53.098217Z" + "iopub.execute_input": "2023-09-14T02:37:08.636451Z", + "iopub.status.busy": "2023-09-14T02:37:08.635808Z", + "iopub.status.idle": "2023-09-14T02:37:08.646285Z", + "shell.execute_reply": "2023-09-14T02:37:08.644957Z" }, "papermill": { - "duration": 0.015364, - "end_time": "2023-09-14T00:22:53.100628", + "duration": 0.017165, + "end_time": "2023-09-14T02:37:08.648279", "exception": false, - "start_time": "2023-09-14T00:22:53.085264", + "start_time": "2023-09-14T02:37:08.631114", "status": "completed" }, "tags": [] @@ -197,19 +197,19 @@ { "cell_type": "code", "execution_count": 4, - "id": "dd9d3898", + "id": "ed6bf7ff", "metadata": { "execution": { - "iopub.execute_input": "2023-09-14T00:22:53.110224Z", - "iopub.status.busy": "2023-09-14T00:22:53.109711Z", - "iopub.status.idle": "2023-09-14T00:23:17.707948Z", - "shell.execute_reply": "2023-09-14T00:23:17.707026Z" + "iopub.execute_input": "2023-09-14T02:37:08.656415Z", + "iopub.status.busy": "2023-09-14T02:37:08.655852Z", + "iopub.status.idle": "2023-09-14T02:37:32.430048Z", + "shell.execute_reply": "2023-09-14T02:37:32.428850Z" }, "papermill": { - "duration": 24.605816, - "end_time": "2023-09-14T00:23:17.710192", + "duration": 23.781188, + "end_time": "2023-09-14T02:37:32.432519", "exception": false, - "start_time": "2023-09-14T00:22:53.104376", + "start_time": "2023-09-14T02:37:08.651331", "status": "completed" }, "tags": [] @@ -219,13 +219,20 @@ "name": "stdout", "output_type": "stream", "text": [ - "--2023-09-14 00:22:53-- https://huggingface.co/rwkv-x-dev/rwkv-x-playground/resolve/main/experiment/rwkv-x-exp/v5-r3-memory/L6-D2048-E1e-1-ctx4k/v5r3-L6-D2048-E0_1-mem-ctx-512.pth\r\n", - "Resolving huggingface.co (huggingface.co)... 18.154.227.69, 18.154.227.7, 18.154.227.67, ...\r\n", - "Connecting to huggingface.co (huggingface.co)|18.154.227.69|:443... connected.\r\n", + "--2023-09-14 02:37:08-- https://huggingface.co/rwkv-x-dev/rwkv-x-playground/resolve/main/experiment/rwkv-x-exp/v5-r3-memory/L6-D2048-E1e-1-ctx4k/v5r3-L6-D2048-E0_1-mem-ctx-512.pth\r\n", + "Resolving huggingface.co (huggingface.co)... 18.154.227.67, 18.154.227.69, 18.154.227.87, ...\r\n", + "Connecting to huggingface.co (huggingface.co)|18.154.227.67|:443... connected.\r\n", "HTTP request sent, awaiting response... 302 Found\r\n", - "Location: https://cdn-lfs.huggingface.co/repos/2e/f7/2ef78555202aa92abdbdf476ce3d0fd5a8b15f7245edf0b80d4d30572355f30d/92bee66e66bfcba8c592c785b63cb88f4e4889d78d7cdc49c33bd53bf0e3c31f?response-content-disposition=attachment%3B+filename*%3DUTF-8%27%27v5r3-L6-D2048-E0_1-mem-ctx-512.pth%3B+filename%3D%22v5r3-L6-D2048-E0_1-mem-ctx-512.pth%22%3B&Expires=1694910173&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTY5NDkxMDE3M319LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy5odWdnaW5nZmFjZS5jby9yZXBvcy8yZS9mNy8yZWY3ODU1NTIwMmFhOTJhYmRiZGY0NzZjZTNkMGZkNWE4YjE1ZjcyNDVlZGYwYjgwZDRkMzA1NzIzNTVmMzBkLzkyYmVlNjZlNjZiZmNiYThjNTkyYzc4NWI2M2NiODhmNGU0ODg5ZDc4ZDdjZGM0OWMzM2JkNTNiZjBlM2MzMWY%7EcmVzcG9uc2UtY29udGVudC1kaXNwb3NpdGlvbj0qIn1dfQ__&Signature=GR1YnPvQoVKj9gwtKNiUTUL4%7E4P7pRpMbhWmjUzDMWgzkiYouaXIzAN9URl86Zv2bAbnLHd9g3j4Vzz0aNbRFg%7EEZMGj%7EkHKdT%7E6HjVQ-1d6uBBJHun8oQ%7ErvqtiKpAxNSj3DG9qRSuBcRi8aiqbirX1vu9VoUJ8bma73mERSKnLVCbNGe72BSAkZpgGmCMtJ1GfKjZ2qwEBm9ThwCf3dxQ9bf8Hlc54OUe5MnQTmEZ5xJVG6eUm191DjRXhRGlAWzLK2vb5QdaXbnQIR52e9dug1YN5h55zhHKIevguaq1DXuLqrqYOBrLiPpo3DE6UG0gXI88jQANFlenNQixV8A__&Key-Pair-Id=KVTP0A1DKRTAX [following]\r\n", - "--2023-09-14 00:22:53-- https://cdn-lfs.huggingface.co/repos/2e/f7/2ef78555202aa92abdbdf476ce3d0fd5a8b15f7245edf0b80d4d30572355f30d/92bee66e66bfcba8c592c785b63cb88f4e4889d78d7cdc49c33bd53bf0e3c31f?response-content-disposition=attachment%3B+filename*%3DUTF-8%27%27v5r3-L6-D2048-E0_1-mem-ctx-512.pth%3B+filename%3D%22v5r3-L6-D2048-E0_1-mem-ctx-512.pth%22%3B&Expires=1694910173&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTY5NDkxMDE3M319LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy5odWdnaW5nZmFjZS5jby9yZXBvcy8yZS9mNy8yZWY3ODU1NTIwMmFhOTJhYmRiZGY0NzZjZTNkMGZkNWE4YjE1ZjcyNDVlZGYwYjgwZDRkMzA1NzIzNTVmMzBkLzkyYmVlNjZlNjZiZmNiYThjNTkyYzc4NWI2M2NiODhmNGU0ODg5ZDc4ZDdjZGM0OWMzM2JkNTNiZjBlM2MzMWY%7EcmVzcG9uc2UtY29udGVudC1kaXNwb3NpdGlvbj0qIn1dfQ__&Signature=GR1YnPvQoVKj9gwtKNiUTUL4%7E4P7pRpMbhWmjUzDMWgzkiYouaXIzAN9URl86Zv2bAbnLHd9g3j4Vzz0aNbRFg%7EEZMGj%7EkHKdT%7E6HjVQ-1d6uBBJHun8oQ%7ErvqtiKpAxNSj3DG9qRSuBcRi8aiqbirX1vu9VoUJ8bma73mERSKnLVCbNGe72BSAkZpgGmCMtJ1GfKjZ2qwEBm9ThwCf3dxQ9bf8Hlc54OUe5MnQTmEZ5xJVG6eUm191DjRXhRGlAWzLK2vb5QdaXbnQIR52e9dug1YN5h55zhHKIevguaq1DXuLqrqYOBrLiPpo3DE6UG0gXI88jQANFlenNQixV8A__&Key-Pair-Id=KVTP0A1DKRTAX\r\n", - "Resolving cdn-lfs.huggingface.co (cdn-lfs.huggingface.co)... 108.138.64.49, 108.138.64.111, 108.138.64.36, ...\r\n", + "Location: https://cdn-lfs.huggingface.co/repos/2e/f7/2ef78555202aa92abdbdf476ce3d0fd5a8b15f7245edf0b80d4d30572355f30d/92bee66e66bfcba8c592c785b63cb88f4e4889d78d7cdc49c33bd53bf0e3c31f?response-content-disposition=attachment%3B+filename*%3DUTF-8%27%27v5r3-L6-D2048-E0_1-mem-ctx-512.pth%3B+filename%3D%22v5r3-L6-D2048-E0_1-mem-ctx-512.pth%22%3B&Expires=1694918228&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTY5NDkxODIyOH19LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy5odWdnaW5nZmFjZS5jby9yZXBvcy8yZS9mNy8yZWY3ODU1NTIwMmFhOTJhYmRiZGY0NzZjZTNkMGZkNWE4YjE1ZjcyNDVlZGYwYjgwZDRkMzA1NzIzNTVmMzBkLzkyYmVlNjZlNjZiZmNiYThjNTkyYzc4NWI2M2NiODhmNGU0ODg5ZDc4ZDdjZGM0OWMzM2JkNTNiZjBlM2MzMWY%7EcmVzcG9uc2UtY29udGVudC1kaXNwb3NpdGlvbj0qIn1dfQ__&Signature=cJAoUY5y0W5uDSWebon3c0434JSN%7EgNHU8QPvHA1bl1fW7kXK0ETDur-X-85BKCXlTHdhzjGRWoxRQGb33uDdG35IvOOksMyaVFYfnyj0JA66Bh9q%7E35mFanEks9Ja7QfTFOyrfWlndyFOT0M5Hzx-rJQ-nLDBne1LfEZEwxt7Uv2jsFCYkukWDP1f-OwfqwTb1q4Ys7knlGyj1ZQ4sq45v6cFcJAXU8R8GUhEd5j8vg9bnxtYKZvYqJuZcX8T1w%7EQJ5DJK0l9lYIY0JIiqZr4tCNkjD6PbTvnVA7E8TQys0Hjgf0o291i9ruANc6bwjWcGOpPeBo4QI24aWO9Fxlg__&Key-Pair-Id=KVTP0A1DKRTAX [following]\r\n", + "--2023-09-14 02:37:08-- https://cdn-lfs.huggingface.co/repos/2e/f7/2ef78555202aa92abdbdf476ce3d0fd5a8b15f7245edf0b80d4d30572355f30d/92bee66e66bfcba8c592c785b63cb88f4e4889d78d7cdc49c33bd53bf0e3c31f?response-content-disposition=attachment%3B+filename*%3DUTF-8%27%27v5r3-L6-D2048-E0_1-mem-ctx-512.pth%3B+filename%3D%22v5r3-L6-D2048-E0_1-mem-ctx-512.pth%22%3B&Expires=1694918228&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTY5NDkxODIyOH19LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy5odWdnaW5nZmFjZS5jby9yZXBvcy8yZS9mNy8yZWY3ODU1NTIwMmFhOTJhYmRiZGY0NzZjZTNkMGZkNWE4YjE1ZjcyNDVlZGYwYjgwZDRkMzA1NzIzNTVmMzBkLzkyYmVlNjZlNjZiZmNiYThjNTkyYzc4NWI2M2NiODhmNGU0ODg5ZDc4ZDdjZGM0OWMzM2JkNTNiZjBlM2MzMWY%7EcmVzcG9uc2UtY29udGVudC1kaXNwb3NpdGlvbj0qIn1dfQ__&Signature=cJAoUY5y0W5uDSWebon3c0434JSN%7EgNHU8QPvHA1bl1fW7kXK0ETDur-X-85BKCXlTHdhzjGRWoxRQGb33uDdG35IvOOksMyaVFYfnyj0JA66Bh9q%7E35mFanEks9Ja7QfTFOyrfWlndyFOT0M5Hzx-rJQ-nLDBne1LfEZEwxt7Uv2jsFCYkukWDP1f-OwfqwTb1q4Ys7knlGyj1ZQ4sq45v6cFcJAXU8R8GUhEd5j8vg9bnxtYKZvYqJuZcX8T1w%7EQJ5DJK0l9lYIY0JIiqZr4tCNkjD6PbTvnVA7E8TQys0Hjgf0o291i9ruANc6bwjWcGOpPeBo4QI24aWO9Fxlg__&Key-Pair-Id=KVTP0A1DKRTAX\r\n", + "Resolving cdn-lfs.huggingface.co (cdn-lfs.huggingface.co)... " + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "108.138.64.49, 108.138.64.121, 108.138.64.111, ...\r\n", "Connecting to cdn-lfs.huggingface.co (cdn-lfs.huggingface.co)|108.138.64.49|:443... connected.\r\n", "HTTP request sent, awaiting response... " ] @@ -247,7 +254,23 @@ "output_type": "stream", "text": [ "\r", - " v5r3-L6-D2 1%[ ] 14.74M 69.8MB/s " + " v5r3-L6-D2 1%[ ] 14.74M 63.3MB/s " + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r", + " v5r3-L6-D20 2%[ ] 24.19M 47.2MB/s " + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r", + " v5r3-L6-D204 3%[ ] 30.52M 38.2MB/s " ] }, { @@ -255,7 +278,7 @@ "output_type": "stream", "text": [ "\r", - " v5r3-L6-D20 2%[ ] 24.19M 48.8MB/s " + " v5r3-L6-D2048 4%[ ] 45.26M 42.8MB/s " ] }, { @@ -263,7 +286,7 @@ "output_type": "stream", "text": [ "\r", - " v5r3-L6-D204 3%[ ] 30.52M 40.7MB/s " + " v5r3-L6-D2048- 5%[> ] 54.89M 43.6MB/s " ] }, { @@ -271,7 +294,7 @@ "output_type": "stream", "text": [ "\r", - " v5r3-L6-D2048 3%[ ] 32.58M 28.7MB/s " + " v5r3-L6-D2048-E 6%[> ] 61.03M 41.1MB/s " ] }, { @@ -279,7 +302,7 @@ "output_type": "stream", "text": [ "\r", - " v5r3-L6-D2048- 3%[ ] 36.82M 27.2MB/s " + " v5r3-L6-D2048-E0 7%[> ] 75.78M 43.5MB/s " ] }, { @@ -287,7 +310,7 @@ "output_type": "stream", "text": [ "\r", - " v5r3-L6-D2048-E 4%[ ] 45.26M 28.3MB/s " + " v5r3-L6-D2048-E0_ 8%[> ] 87.34M 44.9MB/s " ] }, { @@ -295,7 +318,7 @@ "output_type": "stream", "text": [ "\r", - " v5r3-L6-D2048-E0 5%[> ] 60.52M 31.9MB/s " + " v5r3-L6-D2048-E0_1 9%[> ] 91.55M 41.4MB/s " ] }, { @@ -303,7 +326,7 @@ "output_type": "stream", "text": [ "\r", - " v5r3-L6-D2048-E0_ 7%[> ] 74.59M 35.5MB/s " + "v5r3-L6-D2048-E0_1- 10%[=> ] 106.29M 43.3MB/s " ] }, { @@ -311,7 +334,7 @@ "output_type": "stream", "text": [ "\r", - " v5r3-L6-D2048-E0_1 7%[> ] 76.29M 30.8MB/s " + "5r3-L6-D2048-E0_1-m 11%[=> ] 114.75M 43.2MB/s " ] }, { @@ -319,7 +342,7 @@ "output_type": "stream", "text": [ "\r", - "v5r3-L6-D2048-E0_1- 8%[> ] 82.60M 29.0MB/s " + "r3-L6-D2048-E0_1-me 11%[=> ] 121.56M 42.5MB/s " ] }, { @@ -327,7 +350,7 @@ "output_type": "stream", "text": [ "\r", - "5r3-L6-D2048-E0_1-m 8%[> ] 91.03M 28.2MB/s eta 33s " + "3-L6-D2048-E0_1-mem 12%[=> ] 122.07M 39.8MB/s eta 22s " ] }, { @@ -335,7 +358,7 @@ "output_type": "stream", "text": [ "\r", - "r3-L6-D2048-E0_1-me 9%[> ] 99.38M 29.0MB/s eta 33s " + "-L6-D2048-E0_1-mem- 13%[=> ] 137.33M 42.0MB/s eta 22s " ] }, { @@ -343,7 +366,7 @@ "output_type": "stream", "text": [ "\r", - "3-L6-D2048-E0_1-mem 10%[=> ] 106.81M 29.0MB/s eta 33s " + "L6-D2048-E0_1-mem-c 14%[=> ] 152.07M 43.6MB/s eta 22s " ] }, { @@ -351,7 +374,7 @@ "output_type": "stream", "text": [ "\r", - "-L6-D2048-E0_1-mem- 12%[=> ] 122.07M 30.6MB/s eta 33s " + "6-D2048-E0_1-mem-ct 15%[==> ] 152.59M 41.2MB/s eta 22s " ] }, { @@ -359,7 +382,7 @@ "output_type": "stream", "text": [ "\r", - "L6-D2048-E0_1-mem-c 13%[=> ] 137.33M 32.3MB/s eta 27s " + "-D2048-E0_1-mem-ctx 16%[==> ] 167.33M 41.1MB/s eta 21s " ] }, { @@ -367,7 +390,7 @@ "output_type": "stream", "text": [ "\r", - "6-D2048-E0_1-mem-ct 15%[==> ] 152.59M 33.3MB/s eta 27s " + "D2048-E0_1-mem-ctx- 16%[==> ] 167.85M 37.9MB/s eta 21s " ] }, { @@ -375,7 +398,7 @@ "output_type": "stream", "text": [ "\r", - "-D2048-E0_1-mem-ctx 16%[==> ] 167.85M 32.6MB/s eta 27s " + "2048-E0_1-mem-ctx-5 17%[==> ] 181.27M 39.7MB/s eta 21s " ] }, { @@ -383,7 +406,7 @@ "output_type": "stream", "text": [ "\r", - "D2048-E0_1-mem-ctx- 18%[==> ] 183.10M 34.6MB/s eta 27s " + "048-E0_1-mem-ctx-51 18%[==> ] 183.10M 37.2MB/s eta 21s " ] }, { @@ -391,7 +414,7 @@ "output_type": "stream", "text": [ "\r", - "2048-E0_1-mem-ctx-5 19%[==> ] 197.85M 38.9MB/s eta 22s " + "48-E0_1-mem-ctx-512 19%[==> ] 198.36M 38.0MB/s eta 21s " ] }, { @@ -399,7 +422,7 @@ "output_type": "stream", "text": [ "\r", - "048-E0_1-mem-ctx-51 20%[===> ] 213.11M 40.6MB/s eta 22s " + "8-E0_1-mem-ctx-512. 20%[===> ] 213.11M 40.5MB/s eta 21s " ] }, { @@ -407,7 +430,7 @@ "output_type": "stream", "text": [ "\r", - "48-E0_1-mem-ctx-512 22%[===> ] 228.36M 40.9MB/s eta 22s " + "-E0_1-mem-ctx-512.p 22%[===> ] 228.36M 41.5MB/s eta 21s " ] }, { @@ -415,7 +438,7 @@ "output_type": "stream", "text": [ "\r", - "8-E0_1-mem-ctx-512. 23%[===> ] 234.90M 41.6MB/s eta 22s " + "E0_1-mem-ctx-512.pt 23%[===> ] 243.09M 42.1MB/s eta 21s " ] }, { @@ -423,7 +446,7 @@ "output_type": "stream", "text": [ "\r", - "-E0_1-mem-ctx-512.p 25%[====> ] 257.58M 43.6MB/s eta 19s " + "0_1-mem-ctx-512.pth 24%[===> ] 254.13M 44.3MB/s eta 21s " ] }, { @@ -431,7 +454,7 @@ "output_type": "stream", "text": [ "\r", - "E0_1-mem-ctx-512.pt 25%[====> ] 259.40M 43.7MB/s eta 19s " + "_1-mem-ctx-512.pth 25%[====> ] 259.40M 41.5MB/s eta 18s " ] }, { @@ -439,7 +462,7 @@ "output_type": "stream", "text": [ "\r", - "0_1-mem-ctx-512.pth 27%[====> ] 274.66M 49.4MB/s eta 19s " + "1-mem-ctx-512.pth 27%[====> ] 274.66M 42.2MB/s eta 18s " ] }, { @@ -447,7 +470,7 @@ "output_type": "stream", "text": [ "\r", - "_1-mem-ctx-512.pth 28%[====> ] 289.40M 51.8MB/s eta 19s " + "-mem-ctx-512.pth 28%[====> ] 289.40M 44.8MB/s eta 18s " ] }, { @@ -455,7 +478,7 @@ "output_type": "stream", "text": [ "\r", - "1-mem-ctx-512.pth 29%[====> ] 304.66M 50.5MB/s eta 18s " + "mem-ctx-512.pth 29%[====> ] 298.47M 43.8MB/s eta 18s " ] }, { @@ -463,7 +486,7 @@ "output_type": "stream", "text": [ "\r", - "-mem-ctx-512.pth 30%[=====> ] 307.24M 48.0MB/s eta 18s " + "em-ctx-512.pth 30%[=====> ] 305.18M 42.3MB/s eta 17s " ] }, { @@ -471,7 +494,7 @@ "output_type": "stream", "text": [ "\r", - "mem-ctx-512.pth 30%[=====> ] 311.49M 44.8MB/s eta 18s " + "m-ctx-512.pth 30%[=====> ] 313.62M 39.8MB/s eta 17s " ] }, { @@ -479,7 +502,7 @@ "output_type": "stream", "text": [ "\r", - "em-ctx-512.pth 31%[=====> ] 320.43M 42.2MB/s eta 18s " + "-ctx-512.pth 32%[=====> ] 333.86M 42.5MB/s eta 17s " ] }, { @@ -487,7 +510,7 @@ "output_type": "stream", "text": [ "\r", - "m-ctx-512.pth 33%[=====> ] 335.69M 43.8MB/s eta 18s " + "ctx-512.pth 33%[=====> ] 341.22M 44.0MB/s eta 17s " ] }, { @@ -495,7 +518,7 @@ "output_type": "stream", "text": [ "\r", - "-ctx-512.pth 34%[=====> ] 350.95M 44.2MB/s eta 18s " + "tx-512.pth 34%[=====> ] 350.95M 45.4MB/s eta 16s " ] }, { @@ -503,7 +526,7 @@ "output_type": "stream", "text": [ "\r", - "ctx-512.pth 35%[======> ] 365.70M 42.5MB/s eta 18s " + "x-512.pth 35%[======> ] 365.70M 44.4MB/s eta 16s " ] }, { @@ -511,7 +534,7 @@ "output_type": "stream", "text": [ "\r", - "tx-512.pth 37%[======> ] 376.60M 41.9MB/s eta 18s " + "-512.pth 36%[======> ] 371.37M 45.7MB/s eta 16s " ] }, { @@ -519,7 +542,7 @@ "output_type": "stream", "text": [ "\r", - "x-512.pth 37%[======> ] 381.59M 40.3MB/s eta 17s " + "512.pth 37%[======> ] 381.47M 44.0MB/s eta 16s " ] }, { @@ -527,7 +550,7 @@ "output_type": "stream", "text": [ "\r", - "-512.pth 39%[======> ] 396.73M 39.3MB/s eta 17s " + "12.pth 39%[======> ] 396.73M 45.9MB/s eta 15s " ] }, { @@ -535,7 +558,7 @@ "output_type": "stream", "text": [ "\r", - "512.pth 40%[=======> ] 411.99M 41.6MB/s eta 17s " + "2.pth 41%[=======> ] 419.01M 47.8MB/s eta 15s " ] }, { @@ -543,7 +566,7 @@ "output_type": "stream", "text": [ "\r", - "12.pth 42%[=======> ] 427.25M 43.5MB/s eta 17s " + ".pth 42%[=======> ] 427.25M 47.9MB/s eta 15s " ] }, { @@ -551,7 +574,7 @@ "output_type": "stream", "text": [ "\r", - "2.pth 43%[=======> ] 442.51M 43.0MB/s eta 17s " + "pth 43%[=======> ] 442.51M 47.9MB/s eta 15s " ] }, { @@ -559,7 +582,7 @@ "output_type": "stream", "text": [ "\r", - ".pth 45%[========> ] 464.66M 44.5MB/s eta 13s " + "th 45%[========> ] 457.76M 46.8MB/s eta 15s " ] }, { @@ -567,7 +590,7 @@ "output_type": "stream", "text": [ "\r", - "pth 46%[========> ] 473.02M 45.6MB/s eta 13s " + "h 46%[========> ] 473.02M 47.8MB/s eta 12s " ] }, { @@ -575,7 +598,7 @@ "output_type": "stream", "text": [ "\r", - "th 47%[========> ] 486.45M 44.0MB/s eta 13s " + " 48%[========> ] 488.28M 47.6MB/s eta 12s " ] }, { @@ -583,7 +606,7 @@ "output_type": "stream", "text": [ "\r", - "h 49%[========> ] 502.11M 44.8MB/s eta 13s " + " v 49%[========> ] 507.63M 50.4MB/s eta 12s " ] }, { @@ -591,7 +614,7 @@ "output_type": "stream", "text": [ "\r", - " 50%[=========> ] 510.22M 43.7MB/s eta 12s " + " v5 50%[=========> ] 512.48M 51.1MB/s eta 12s " ] }, { @@ -599,7 +622,7 @@ "output_type": "stream", "text": [ "\r", - " v 51%[=========> ] 518.80M 45.3MB/s eta 12s " + " v5r 52%[=========> ] 532.75M 54.5MB/s eta 12s " ] }, { @@ -607,7 +630,7 @@ "output_type": "stream", "text": [ "\r", - " v5 52%[=========> ] 534.05M 47.9MB/s eta 12s " + " v5r3 52%[=========> ] 534.05M 51.4MB/s eta 11s " ] }, { @@ -615,7 +638,7 @@ "output_type": "stream", "text": [ "\r", - " v5r 53%[=========> ] 547.90M 48.5MB/s eta 12s " + " v5r3- 53%[=========> ] 547.49M 52.6MB/s eta 11s " ] }, { @@ -623,7 +646,7 @@ "output_type": "stream", "text": [ "\r", - " v5r3 54%[=========> ] 555.93M 46.9MB/s eta 11s " + " v5r3-L 54%[=========> ] 557.13M 52.7MB/s eta 11s " ] }, { @@ -631,7 +654,7 @@ "output_type": "stream", "text": [ "\r", - " v5r3- 55%[==========> ] 564.58M 48.0MB/s eta 11s " + " v5r3-L6 56%[==========> ] 569.63M 54.0MB/s eta 11s " ] }, { @@ -639,7 +662,7 @@ "output_type": "stream", "text": [ "\r", - " v5r3-L 56%[==========> ] 579.31M 49.2MB/s eta 11s " + " v5r3-L6- 56%[==========> ] 579.31M 55.5MB/s eta 11s " ] }, { @@ -647,7 +670,7 @@ "output_type": "stream", "text": [ "\r", - " v5r3-L6 57%[==========> ] 579.96M 48.3MB/s eta 11s " + " v5r3-L6-D 58%[==========> ] 594.57M 54.4MB/s eta 9s " ] }, { @@ -655,7 +678,7 @@ "output_type": "stream", "text": [ "\r", - " v5r3-L6- 58%[==========> ] 595.09M 48.7MB/s eta 10s " + " v5r3-L6-D2 59%[==========> ] 600.21M 54.9MB/s eta 9s " ] }, { @@ -663,7 +686,7 @@ "output_type": "stream", "text": [ "\r", - " v5r3-L6-D 60%[===========> ] 610.35M 47.1MB/s eta 10s " + " v5r3-L6-D20 59%[==========> ] 602.76M 51.4MB/s eta 9s " ] }, { @@ -671,7 +694,7 @@ "output_type": "stream", "text": [ "\r", - " v5r3-L6-D2 61%[===========> ] 625.09M 46.6MB/s eta 10s " + " v5r3-L6-D204 60%[===========> ] 610.35M 48.1MB/s eta 9s " ] }, { @@ -679,7 +702,7 @@ "output_type": "stream", "text": [ "\r", - " v5r3-L6-D20 62%[===========> ] 634.25M 45.3MB/s eta 10s " + " v5r3-L6-D2048 61%[===========> ] 625.09M 48.0MB/s eta 9s " ] }, { @@ -687,7 +710,7 @@ "output_type": "stream", "text": [ "\r", - " v5r3-L6-D204 63%[===========> ] 640.87M 40.9MB/s eta 9s " + " v5r3-L6-D2048- 62%[===========> ] 640.36M 48.3MB/s eta 8s " ] }, { @@ -695,7 +718,7 @@ "output_type": "stream", "text": [ "\r", - " v5r3-L6-D2048 64%[===========> ] 655.62M 43.0MB/s eta 9s " + " v5r3-L6-D2048-E 64%[===========> ] 655.62M 47.5MB/s eta 8s " ] }, { @@ -703,7 +726,7 @@ "output_type": "stream", "text": [ "\r", - " v5r3-L6-D2048- 65%[============> ] 666.06M 43.6MB/s eta 9s " + " v5r3-L6-D2048-E0 64%[===========> ] 656.25M 43.3MB/s eta 8s " ] }, { @@ -711,7 +734,7 @@ "output_type": "stream", "text": [ "\r", - " v5r3-L6-D2048-E 65%[============> ] 669.55M 41.3MB/s eta 9s " + " v5r3-L6-D2048-E0_ 65%[============> ] 669.55M 42.5MB/s eta 8s " ] }, { @@ -719,7 +742,7 @@ "output_type": "stream", "text": [ "\r", - " v5r3-L6-D2048-E0 66%[============> ] 671.38M 39.6MB/s eta 9s " + " v5r3-L6-D2048-E0_1 66%[============> ] 678.94M 43.2MB/s eta 8s " ] }, { @@ -727,7 +750,7 @@ "output_type": "stream", "text": [ "\r", - " v5r3-L6-D2048-E0_ 67%[============> ] 686.13M 40.3MB/s eta 8s " + "v5r3-L6-D2048-E0_1- 67%[============> ] 686.64M 42.0MB/s eta 7s " ] }, { @@ -735,7 +758,7 @@ "output_type": "stream", "text": [ "\r", - " v5r3-L6-D2048-E0_1 68%[============> ] 701.39M 41.0MB/s eta 8s " + "5r3-L6-D2048-E0_1-m 69%[============> ] 701.90M 42.1MB/s eta 7s " ] }, { @@ -743,7 +766,7 @@ "output_type": "stream", "text": [ "\r", - "v5r3-L6-D2048-E0_1- 69%[============> ] 701.90M 39.7MB/s eta 8s " + "r3-L6-D2048-E0_1-me 70%[=============> ] 716.64M 42.5MB/s eta 7s " ] }, { @@ -751,7 +774,7 @@ "output_type": "stream", "text": [ "\r", - "5r3-L6-D2048-E0_1-m 70%[=============> ] 717.16M 39.8MB/s eta 8s " + "3-L6-D2048-E0_1-mem 70%[=============> ] 717.16M 41.4MB/s eta 7s " ] }, { @@ -759,7 +782,7 @@ "output_type": "stream", "text": [ "\r", - "r3-L6-D2048-E0_1-me 72%[=============> ] 732.42M 39.2MB/s eta 7s " + "-L6-D2048-E0_1-mem- 71%[=============> ] 724.85M 39.7MB/s eta 7s " ] }, { @@ -767,7 +790,7 @@ "output_type": "stream", "text": [ "\r", - "3-L6-D2048-E0_1-mem 73%[=============> ] 747.69M 41.0MB/s eta 7s " + "L6-D2048-E0_1-mem-c 72%[=============> ] 732.42M 38.1MB/s eta 7s " ] }, { @@ -775,7 +798,7 @@ "output_type": "stream", "text": [ "\r", - "-L6-D2048-E0_1-mem- 75%[==============> ] 762.94M 42.2MB/s eta 7s " + "6-D2048-E0_1-mem-ct 73%[=============> ] 747.69M 38.4MB/s eta 7s " ] }, { @@ -783,7 +806,7 @@ "output_type": "stream", "text": [ "\r", - "L6-D2048-E0_1-mem-c 76%[==============> ] 777.68M 43.3MB/s eta 7s " + "-D2048-E0_1-mem-ctx 75%[==============> ] 762.94M 40.7MB/s eta 7s " ] }, { @@ -791,7 +814,7 @@ "output_type": "stream", "text": [ "\r", - "6-D2048-E0_1-mem-ct 76%[==============> ] 780.57M 40.6MB/s eta 7s " + "D2048-E0_1-mem-ctx- 76%[==============> ] 777.68M 43.3MB/s eta 7s " ] }, { @@ -799,7 +822,7 @@ "output_type": "stream", "text": [ "\r", - "-D2048-E0_1-mem-ctx 77%[==============> ] 792.94M 42.4MB/s eta 5s " + "2048-E0_1-mem-ctx-5 77%[==============> ] 792.94M 42.8MB/s eta 5s " ] }, { @@ -807,7 +830,7 @@ "output_type": "stream", "text": [ "\r", - "D2048-E0_1-mem-ctx- 78%[==============> ] 798.64M 41.9MB/s eta 5s " + "048-E0_1-mem-ctx-51 78%[==============> ] 793.46M 39.6MB/s eta 5s " ] }, { @@ -815,7 +838,7 @@ "output_type": "stream", "text": [ "\r", - "2048-E0_1-mem-ctx-5 79%[==============> ] 808.20M 42.8MB/s eta 5s " + "48-E0_1-mem-ctx-512 79%[==============> ] 808.20M 41.4MB/s eta 5s " ] }, { @@ -823,7 +846,7 @@ "output_type": "stream", "text": [ "\r", - "048-E0_1-mem-ctx-51 80%[===============> ] 823.46M 42.0MB/s eta 5s " + "8-E0_1-mem-ctx-512. 79%[==============> ] 812.25M 39.4MB/s eta 5s " ] }, { @@ -831,7 +854,7 @@ "output_type": "stream", "text": [ "\r", - "48-E0_1-mem-ctx-512 82%[===============> ] 838.71M 42.8MB/s eta 4s " + "-E0_1-mem-ctx-512.p 81%[===============> ] 823.97M 40.9MB/s eta 5s " ] }, { @@ -839,7 +862,7 @@ "output_type": "stream", "text": [ "\r", - "8-E0_1-mem-ctx-512. 82%[===============> ] 839.23M 42.0MB/s eta 4s " + "E0_1-mem-ctx-512.pt 82%[===============> ] 838.71M 42.4MB/s eta 4s " ] }, { @@ -847,7 +870,7 @@ "output_type": "stream", "text": [ "\r", - "-E0_1-mem-ctx-512.p 85%[================> ] 867.93M 45.9MB/s eta 4s " + "0_1-mem-ctx-512.pth 82%[===============> ] 839.35M 41.6MB/s eta 4s " ] }, { @@ -855,7 +878,7 @@ "output_type": "stream", "text": [ "\r", - "E0_1-mem-ctx-512.pt 87%[================> ] 885.01M 48.1MB/s eta 4s " + "_1-mem-ctx-512.pth 85%[================> ] 866.03M 44.5MB/s eta 4s " ] }, { @@ -863,7 +886,7 @@ "output_type": "stream", "text": [ "\r", - "0_1-mem-ctx-512.pth 87%[================> ] 893.44M 47.0MB/s eta 3s " + "1-mem-ctx-512.pth 85%[================> ] 869.75M 42.1MB/s eta 4s " ] }, { @@ -871,7 +894,7 @@ "output_type": "stream", "text": [ "\r", - "_1-mem-ctx-512.pth 88%[================> ] 899.75M 48.1MB/s eta 3s " + "-mem-ctx-512.pth 87%[================> ] 885.01M 42.8MB/s eta 4s " ] }, { @@ -879,7 +902,7 @@ "output_type": "stream", "text": [ "\r", - "1-mem-ctx-512.pth 89%[================> ] 906.74M 46.0MB/s eta 3s " + "mem-ctx-512.pth 87%[================> ] 893.44M 44.4MB/s eta 3s " ] }, { @@ -887,7 +910,7 @@ "output_type": "stream", "text": [ "\r", - "-mem-ctx-512.pth 90%[=================> ] 917.87M 48.3MB/s eta 3s " + "em-ctx-512.pth 88%[================> ] 900.27M 43.8MB/s eta 3s " ] }, { @@ -895,7 +918,7 @@ "output_type": "stream", "text": [ "\r", - "mem-ctx-512.pth 91%[=================> ] 930.78M 46.4MB/s eta 3s " + "m-ctx-512.pth 89%[================> ] 911.78M 42.6MB/s eta 3s " ] }, { @@ -903,7 +926,7 @@ "output_type": "stream", "text": [ "\r", - "em-ctx-512.pth 92%[=================> ] 944.21M 47.3MB/s eta 2s " + "-ctx-512.pth 90%[=================> ] 915.53M 41.5MB/s eta 3s " ] }, { @@ -911,7 +934,7 @@ "output_type": "stream", "text": [ "\r", - "m-ctx-512.pth 93%[=================> ] 955.92M 46.9MB/s eta 2s " + "ctx-512.pth 91%[=================> ] 930.78M 40.9MB/s eta 2s " ] }, { @@ -919,7 +942,7 @@ "output_type": "stream", "text": [ "\r", - "-ctx-512.pth 94%[=================> ] 961.30M 44.8MB/s eta 2s " + "tx-512.pth 92%[=================> ] 944.21M 41.4MB/s eta 2s " ] }, { @@ -927,7 +950,7 @@ "output_type": "stream", "text": [ "\r", - "ctx-512.pth 96%[==================> ] 976.55M 48.0MB/s eta 2s " + "x-512.pth 94%[=================> ] 956.92M 42.2MB/s eta 2s " ] }, { @@ -935,7 +958,7 @@ "output_type": "stream", "text": [ "\r", - "tx-512.pth 96%[==================> ] 986.36M 47.3MB/s eta 2s " + "-512.pth 94%[=================> ] 961.30M 42.7MB/s eta 2s " ] }, { @@ -943,7 +966,7 @@ "output_type": "stream", "text": [ "\r", - "x-512.pth 97%[==================> ] 993.01M 48.4MB/s eta 1s " + "512.pth 96%[==================> ] 980.99M 44.8MB/s eta 1s " ] }, { @@ -951,7 +974,7 @@ "output_type": "stream", "text": [ "\r", - "-512.pth 99%[==================> ] 1007M 44.3MB/s eta 1s " + "12.pth 97%[==================> ] 986.93M 42.2MB/s eta 1s " ] }, { @@ -959,9 +982,25 @@ "output_type": "stream", "text": [ "\r", - "v5r3-L6-D2048-E0_1- 100%[===================>] 1017M 45.5MB/s in 24s \r\n", + "2.pth 98%[==================> ] 1004M 44.5MB/s eta 1s " + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r", + ".pth 99%[==================> ] 1007M 42.6MB/s eta 1s " + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r", + "v5r3-L6-D2048-E0_1- 100%[===================>] 1017M 45.2MB/s in 23s \r\n", "\r\n", - "2023-09-14 00:23:17 (42.7 MB/s) - ‘v5r3-L6-D2048-E0_1-mem-ctx-512.pth’ saved [1066537217/1066537217]\r\n", + "2023-09-14 02:37:32 (44.1 MB/s) - ‘v5r3-L6-D2048-E0_1-mem-ctx-512.pth’ saved [1066537217/1066537217]\r\n", "\r\n" ] }, @@ -970,8 +1009,8 @@ "output_type": "stream", "text": [ "total 1018M\r\n", - "drwxr-xr-x 2 root root 4.0K Sep 14 00:22 .\r\n", - "drwxr-xr-x 20 root root 4.0K Sep 14 00:22 ..\r\n", + "drwxr-xr-x 2 root root 4.0K Sep 14 02:37 .\r\n", + "drwxr-xr-x 20 root root 4.0K Sep 14 02:37 ..\r\n", "-rw-r--r-- 1 root root 1018M Sep 13 20:28 v5r3-L6-D2048-E0_1-mem-ctx-512.pth\r\n" ] } @@ -987,13 +1026,13 @@ }, { "cell_type": "markdown", - "id": "c2d7023a", + "id": "5700b4b5", "metadata": { "papermill": { - "duration": 0.008067, - "end_time": "2023-09-14T00:23:17.726510", + "duration": 0.008064, + "end_time": "2023-09-14T02:37:32.449084", "exception": false, - "start_time": "2023-09-14T00:23:17.718443", + "start_time": "2023-09-14T02:37:32.441020", "status": "completed" }, "tags": [] @@ -1007,19 +1046,19 @@ { "cell_type": "code", "execution_count": 5, - "id": "f827262e", + "id": "d5f911bc", "metadata": { "execution": { - "iopub.execute_input": "2023-09-14T00:23:17.745636Z", - "iopub.status.busy": "2023-09-14T00:23:17.744822Z", - "iopub.status.idle": "2023-09-14T00:23:38.055622Z", - "shell.execute_reply": "2023-09-14T00:23:38.054557Z" + "iopub.execute_input": "2023-09-14T02:37:32.468291Z", + "iopub.status.busy": "2023-09-14T02:37:32.467681Z", + "iopub.status.idle": "2023-09-14T02:37:52.531727Z", + "shell.execute_reply": "2023-09-14T02:37:52.530635Z" }, "papermill": { - "duration": 20.338726, - "end_time": "2023-09-14T00:23:38.073537", + "duration": 20.125122, + "end_time": "2023-09-14T02:37:52.582572", "exception": false, - "start_time": "2023-09-14T00:23:17.734811", + "start_time": "2023-09-14T02:37:32.457450", "status": "completed" }, "tags": [] @@ -1043,49 +1082,49 @@ "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 50 max words, 100 samples - at ../dataset/gen-word-50-count.jsonl\n" + "Generated JSONL file with - 30 max words, 100 samples - at ../dataset/gen-word-30-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 - 35 max words, 100 samples - at ../dataset/gen-word-35-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 - 45 max words, 100 samples - at ../dataset/gen-word-45-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 - 20 max words, 100 samples - at ../dataset/gen-word-20-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 - 5 max words, 100 samples - at ../dataset/gen-word-5-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 90 max words, 100 samples - at ../dataset/gen-word-90-count.jsonl\n" + "Generated JSONL file with - 50 max words, 100 samples - at ../dataset/gen-word-50-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated a single JSONL file with 518 samples (10 token repeat) - 50 max words - at ../dataset/shuffle-word-50-count.jsonl\n" + "Generated JSONL file with - 10 max words, 100 samples - at ../dataset/gen-word-10-count.jsonl\n" ] }, { @@ -1099,133 +1138,133 @@ "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 25 max words, 100 samples - at ../dataset/gen-word-25-count.jsonl\n" + "Generated a single JSONL file with 374 samples (10 token repeat) - 70 max words - at ../dataset/shuffle-word-70-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 35 max words, 100 samples - at ../dataset/gen-word-35-count.jsonl\n" + "Generated a single JSONL file with 869 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 - 45 max words, 100 samples - at ../dataset/gen-word-45-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 749 samples (10 token repeat) - 35 max words - at ../dataset/shuffle-word-35-count.jsonl\n" + "Generated a single JSONL file with 528 samples (10 token repeat) - 50 max words - at ../dataset/shuffle-word-50-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 586 samples (10 token repeat) - 45 max words - at ../dataset/shuffle-word-45-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 85 max words, 100 samples - at ../dataset/gen-word-85-count.jsonl\n" + "Generated a single JSONL file with 1060 samples (10 token repeat) - 25 max words - at ../dataset/shuffle-word-25-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated a single JSONL file with 478 samples (10 token repeat) - 55 max words - at ../dataset/shuffle-word-55-count.jsonl\n" + "Generated a single JSONL file with 747 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 651 samples (10 token repeat) - 40 max words - at ../dataset/shuffle-word-40-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 20 samples (20 token repeat) - 5100 max words - at ../dataset/shuffle-word-5100-count.jsonl\n" + "Generated a single JSONL file with 1301 samples (10 token repeat) - 20 max words - at ../dataset/shuffle-word-20-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated a single JSONL file with 1057 samples (10 token repeat) - 25 max words - at ../dataset/shuffle-word-25-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 185 samples (20 token repeat) - 300 max words - at ../dataset/shuffle-word-300-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 - 100 max words, 100 samples - at ../dataset/gen-word-100-count.jsonl\n" + "Generated a single JSONL file with 650 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 20 samples (20 token repeat) - 4300 max words - at ../dataset/shuffle-word-4300-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 590 samples (10 token repeat) - 45 max words - at ../dataset/shuffle-word-45-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 308 samples (10 token repeat) - 85 max words - at ../dataset/shuffle-word-85-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 20 samples (20 token repeat) - 3100 max words - at ../dataset/shuffle-word-3100-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 1304 samples (10 token repeat) - 20 max words - at ../dataset/shuffle-word-20-count.jsonl\n" + "Generated a single JSONL file with 1794 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) - 1200 max words - at ../dataset/shuffle-word-1200-count.jsonl\n" + "Generated a single JSONL file with 529 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 531 samples (20 token repeat) - 100 max words - at ../dataset/shuffle-word-100-count.jsonl\n" + "Generated JSONL file with - 85 max words, 100 samples - at ../dataset/gen-word-85-count.jsonl\n" ] }, { @@ -1239,315 +1278,315 @@ "name": "stdout", "output_type": "stream", "text": [ - "Generated a single JSONL file with 882 samples (10 token repeat) - 30 max words - at ../dataset/shuffle-word-30-count.jsonl\n" + "Generated a single JSONL file with 328 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 20 samples (20 token repeat) - 6800 max words - at ../dataset/shuffle-word-6800-count.jsonl\n" + "Generated a single JSONL file with 352 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 40 samples (20 token repeat) - 2300 max words - at ../dataset/shuffle-word-2300-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 20 samples (20 token repeat) - 6500 max words - at ../dataset/shuffle-word-6500-count.jsonl\n" + "Generated a single JSONL file with 293 samples (10 token repeat) - 90 max words - at ../dataset/shuffle-word-90-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated a single JSONL file with 379 samples (10 token repeat) - 70 max words - at ../dataset/shuffle-word-70-count.jsonl\n" + "Generated a single JSONL file with 20 samples (20 token repeat) - 4400 max words - at ../dataset/shuffle-word-4400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 5900 max words - at ../dataset/shuffle-word-5900-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 414 samples (10 token repeat) - 65 max words - at ../dataset/shuffle-word-65-count.jsonl\n" + "Generated a single JSONL file with 26 samples (20 token repeat) - 2600 max words - at ../dataset/shuffle-word-2600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated a single JSONL file with 1791 samples (10 token repeat) - 15 max words - at ../dataset/shuffle-word-15-count.jsonl\n" + "Generated a single JSONL file with 20 samples (20 token repeat) - 3700 max words - at ../dataset/shuffle-word-3700-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 20 samples (20 token repeat) - 2800 max words - at ../dataset/shuffle-word-2800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 7900 max words - at ../dataset/shuffle-word-7900-count.jsonl\n" + "Generated a single JSONL file with 313 samples (10 token repeat) - 85 max words - at ../dataset/shuffle-word-85-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 80 max words, 100 samples - at ../dataset/gen-word-80-count.jsonl\n" + "Generated a single JSONL file with 264 samples (10 token repeat) - 100 max words - at ../dataset/shuffle-word-100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated a single JSONL file with 40 samples (20 token repeat) - 2400 max words - at ../dataset/shuffle-word-2400-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 354 samples (10 token repeat) - 75 max words - at ../dataset/shuffle-word-75-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 332 samples (10 token repeat) - 80 max words - at ../dataset/shuffle-word-80-count.jsonl\n" + "Generated JSONL file with - 80 max words, 100 samples - at ../dataset/gen-word-80-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 70 max words, 100 samples - at ../dataset/gen-word-70-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 JSONL file with - 75 max words, 100 samples - at ../dataset/gen-word-75-count.jsonl\n" + "Generated a single JSONL file with 39 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 304 samples (10 token repeat) - 90 max words - at ../dataset/shuffle-word-90-count.jsonl\n" + "Generated a single JSONL file with 439 samples (10 token repeat) - 60 max words - at ../dataset/shuffle-word-60-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated a single JSONL file with 40 samples (20 token repeat) - 2100 max words - at ../dataset/shuffle-word-2100-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 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 40 samples (20 token repeat) - 1400 max words - at ../dataset/shuffle-word-1400-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 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) - 3200 max words - at ../dataset/shuffle-word-3200-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 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 401 samples (10 token repeat) - 65 max words - at ../dataset/shuffle-word-65-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 5400 max words - at ../dataset/shuffle-word-5400-count.jsonl\n" + "Generated a single JSONL file with 20 samples (20 token repeat) - 3900 max words - at ../dataset/shuffle-word-3900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 5500 max words - at ../dataset/shuffle-word-5500-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) - 6400 max words - at ../dataset/shuffle-word-6400-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) - 4700 max words - at ../dataset/shuffle-word-4700-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 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) - 4300 max words - at ../dataset/shuffle-word-4300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated a single JSONL file with 269 samples (20 token repeat) - 200 max words - at ../dataset/shuffle-word-200-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 21 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) - 2200 max words - at ../dataset/shuffle-word-2200-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 280 samples (10 token repeat) - 95 max words - at ../dataset/shuffle-word-95-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 6100 max words - at ../dataset/shuffle-word-6100-count.jsonl\n" + "Generated a single JSONL file with 20 samples (20 token repeat) - 7700 max words - at ../dataset/shuffle-word-7700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 6000 max words - at ../dataset/shuffle-word-6000-count.jsonl\n" + "Generated a single JSONL file with 2607 samples (10 token repeat) - 10 max words - at ../dataset/shuffle-word-10-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated a single JSONL file with 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) - 3300 max words - at ../dataset/shuffle-word-3300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 6700 max words - at ../dataset/shuffle-word-6700-count.jsonl\n" + "Generated a single JSONL file with 20 samples (20 token repeat) - 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) - 7400 max words - at ../dataset/shuffle-word-7400-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 31 samples (20 token repeat) - 2600 max words - at ../dataset/shuffle-word-2600-count.jsonl\n" + "Generated a single JSONL file with 40 samples (20 token repeat) - 1500 max words - at ../dataset/shuffle-word-1500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 3700 max words - at ../dataset/shuffle-word-3700-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) - 5600 max words - at ../dataset/shuffle-word-5600-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 2592 samples (10 token repeat) - 10 max words - at ../dataset/shuffle-word-10-count.jsonl\n" + "Generated a single JSONL file with 21 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 21 samples (20 token repeat) - 2800 max words - at ../dataset/shuffle-word-2800-count.jsonl\n" + "Generated a single JSONL file with 20 samples (20 token repeat) - 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) - 3500 max words - at ../dataset/shuffle-word-3500-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 283 samples (10 token repeat) - 95 max words - at ../dataset/shuffle-word-95-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 60 samples (20 token repeat) - 1000 max words - at ../dataset/shuffle-word-1000-count.jsonl\n" + "Generated a single JSONL file with 482 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) - 4600 max words - at ../dataset/shuffle-word-4600-count.jsonl\n" + "Generated a single JSONL file with 37 samples (20 token repeat) - 2500 max words - at ../dataset/shuffle-word-2500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 3400 max words - at ../dataset/shuffle-word-3400-count.jsonl\n" + "Generated a single JSONL file with 20 samples (20 token repeat) - 5200 max words - at ../dataset/shuffle-word-5200-count.jsonl\n" ] }, { @@ -1561,315 +1600,315 @@ "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 267 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 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) - 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) - 4500 max words - at ../dataset/shuffle-word-4500-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 60 samples (20 token repeat) - 1100 max words - at ../dataset/shuffle-word-1100-count.jsonl\n" + "Generated a single JSONL file with 60 samples (20 token repeat) - 1000 max words - at ../dataset/shuffle-word-1000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 7100 max words - at ../dataset/shuffle-word-7100-count.jsonl\n" + "Generated a single JSONL file with 20 samples (20 token repeat) - 8000 max words - at ../dataset/shuffle-word-8000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 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) - 3800 max words - at ../dataset/shuffle-word-3800-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 40 samples (20 token repeat) - 1900 max words - at ../dataset/shuffle-word-1900-count.jsonl\n" + "Generated a single JSONL file with 20 samples (20 token repeat) - 6300 max words - at ../dataset/shuffle-word-6300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated a single JSONL file with 5561 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) - 4900 max words - at ../dataset/shuffle-word-4900-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) - 3500 max words - at ../dataset/shuffle-word-3500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated a single JSONL file with 40 samples (20 token repeat) - 2200 max words - at ../dataset/shuffle-word-2200-count.jsonl\n" + "Generated a single JSONL file with 20 samples (20 token repeat) - 7100 max words - at ../dataset/shuffle-word-7100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 3300 max words - at ../dataset/shuffle-word-3300-count.jsonl\n" + "Generated a single JSONL file with 20 samples (20 token repeat) - 5800 max words - at ../dataset/shuffle-word-5800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 5700 max words - at ../dataset/shuffle-word-5700-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) - 5800 max words - at ../dataset/shuffle-word-5800-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) - 6200 max words - at ../dataset/shuffle-word-6200-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 82 samples (20 token repeat) - 700 max words - at ../dataset/shuffle-word-700-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) - 5000 max words - at ../dataset/shuffle-word-5000-count.jsonl\n" + "Generated a single JSONL file with 117 samples (20 token repeat) - 500 max words - at ../dataset/shuffle-word-500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated a single JSONL file with 438 samples (10 token repeat) - 60 max words - at ../dataset/shuffle-word-60-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) - 5300 max words - at ../dataset/shuffle-word-5300-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 35 samples (20 token repeat) - 2500 max words - at ../dataset/shuffle-word-2500-count.jsonl\n" + "Generated a single JSONL file with 20 samples (20 token repeat) - 7600 max words - at ../dataset/shuffle-word-7600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated a single JSONL file with 119 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) - 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) - 8000 max words - at ../dataset/shuffle-word-8000-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) - 4100 max words - at ../dataset/shuffle-word-4100-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 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) - 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) - 7600 max words - at ../dataset/shuffle-word-7600-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) - 4400 max words - at ../dataset/shuffle-word-4400-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) - 5200 max words - at ../dataset/shuffle-word-5200-count.jsonl\n" + "Generated a single JSONL file with 20 samples (20 token repeat) - 3400 max words - at ../dataset/shuffle-word-3400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated a single JSONL file with 40 samples (20 token repeat) - 1500 max words - at ../dataset/shuffle-word-1500-count.jsonl\n" + "Generated a single JSONL file with 48 samples (20 token repeat) - 1300 max words - at ../dataset/shuffle-word-1300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated 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) - 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) - 3000 max words - at ../dataset/shuffle-word-3000-count.jsonl\n" + "Generated a single JSONL file with 5563 samples (10 token repeat) - 5 max words - at ../dataset/shuffle-word-5-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated a single JSONL file with 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) - 6900 max words - at ../dataset/shuffle-word-6900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated a single JSONL file with 268 samples (10 token repeat) - 100 max words - at ../dataset/shuffle-word-100-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) - 6600 max words - at ../dataset/shuffle-word-6600-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 140 samples (20 token repeat) - 400 max words - at ../dataset/shuffle-word-400-count.jsonl\n" + "Generated a single JSONL file with 40 samples (20 token repeat) - 2300 max words - at ../dataset/shuffle-word-2300-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) - 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 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 80 samples (20 token repeat) - 800 max words - at ../dataset/shuffle-word-800-count.jsonl\n" + "Generated a single JSONL file with 20 samples (20 token repeat) - 7200 max words - at ../dataset/shuffle-word-7200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated a single JSONL file with 52 samples (20 token repeat) - 1300 max words - at ../dataset/shuffle-word-1300-count.jsonl\n" + "Generated a single JSONL file with 140 samples (20 token repeat) - 400 max words - at ../dataset/shuffle-word-400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 7300 max words - at ../dataset/shuffle-word-7300-count.jsonl\n" + "Generated a single JSONL file with 63 samples (20 token repeat) - 900 max words - at ../dataset/shuffle-word-900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated a single JSONL file with 62 samples (20 token repeat) - 900 max words - at ../dataset/shuffle-word-900-count.jsonl\n" + "Generated a single JSONL file with 40 samples (20 token repeat) - 1900 max words - at ../dataset/shuffle-word-1900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated a single JSONL file with 20 samples (20 token repeat) - 7700 max words - at ../dataset/shuffle-word-7700-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 21 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) - 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) - 7200 max words - at ../dataset/shuffle-word-7200-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) - 7800 max words - at ../dataset/shuffle-word-7800-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) - 3900 max words - at ../dataset/shuffle-word-3900-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" ] }, { @@ -1911,364 +1950,364 @@ "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 - 500 max words, 2000 samples - at ../dataset/gen-word-500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 500 max words, 2000 samples - at ../dataset/gen-word-500-count.jsonl\n" + "Generated JSONL file with - 1300 max words, 2000 samples - at ../dataset/gen-word-1300-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 - 600 max words, 2000 samples - at ../dataset/gen-word-600-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 - 1700 max words, 2000 samples - at ../dataset/gen-word-1700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 600 max words, 2000 samples - at ../dataset/gen-word-600-count.jsonl\n" + "Generated JSONL file with - 1000 max words, 2000 samples - at ../dataset/gen-word-1000-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 - 1600 max words, 2000 samples - at ../dataset/gen-word-1600-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 - 800 max words, 2000 samples - at ../dataset/gen-word-800-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 - 900 max words, 2000 samples - at ../dataset/gen-word-900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 1200 max words, 2000 samples - at ../dataset/gen-word-1200-count.jsonl\n" + "Generated JSONL file with - 1100 max words, 2000 samples - at ../dataset/gen-word-1100-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 - 1200 max words, 2000 samples - at ../dataset/gen-word-1200-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 - 2900 max words, 2000 samples - at ../dataset/gen-word-2900-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 - 1400 max words, 2000 samples - at ../dataset/gen-word-1400-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 - 1800 max words, 2000 samples - at ../dataset/gen-word-1800-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 - 1500 max words, 2000 samples - at ../dataset/gen-word-1500-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 - 3000 max words, 2000 samples - at ../dataset/gen-word-3000-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 - 2000 max words, 2000 samples - at ../dataset/gen-word-2000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 1700 max words, 2000 samples - at ../dataset/gen-word-1700-count.jsonl\n" + "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 - 2000 max words, 2000 samples - at ../dataset/gen-word-2000-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 - 1800 max words, 2000 samples - at ../dataset/gen-word-1800-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 - 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 - 2100 max words, 2000 samples - at ../dataset/gen-word-2100-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 - 3300 max words, 2000 samples - at ../dataset/gen-word-3300-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 - 5400 max words, 2000 samples - at ../dataset/gen-word-5400-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 - 2600 max words, 2000 samples - at ../dataset/gen-word-2600-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 - 2300 max words, 2000 samples - at ../dataset/gen-word-2300-count.jsonl\n" + "Generated JSONL file with - 2500 max words, 2000 samples - at ../dataset/gen-word-2500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 3200 max words, 2000 samples - at ../dataset/gen-word-3200-count.jsonl\n" + "Generated JSONL file with - 2400 max words, 2000 samples - at ../dataset/gen-word-2400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 4200 max words, 2000 samples - at ../dataset/gen-word-4200-count.jsonl\n" + "Generated JSONL file with - 3900 max words, 2000 samples - at ../dataset/gen-word-3900-count.jsonl\n" ] }, { "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 - 4700 max words, 2000 samples - at ../dataset/gen-word-4700-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 - 4800 max words, 2000 samples - at ../dataset/gen-word-4800-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 - 2700 max words, 2000 samples - at ../dataset/gen-word-2700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 3400 max words, 2000 samples - at ../dataset/gen-word-3400-count.jsonl\n" + "Generated JSONL file with - 2800 max words, 2000 samples - at ../dataset/gen-word-2800-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 - 6800 max words, 2000 samples - at ../dataset/gen-word-6800-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 - 3200 max words, 2000 samples - at ../dataset/gen-word-3200-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 - 6600 max words, 2000 samples - at ../dataset/gen-word-6600-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 - 3100 max words, 2000 samples - at ../dataset/gen-word-3100-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 - 3400 max words, 2000 samples - at ../dataset/gen-word-3400-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 - 3300 max words, 2000 samples - at ../dataset/gen-word-3300-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 - 3700 max words, 2000 samples - at ../dataset/gen-word-3700-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 - 5000 max words, 2000 samples - at ../dataset/gen-word-5000-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 - 4000 max words, 2000 samples - at ../dataset/gen-word-4000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 3600 max words, 2000 samples - at ../dataset/gen-word-3600-count.jsonl\n" + "Generated JSONL file with - 5100 max words, 2000 samples - at ../dataset/gen-word-5100-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 - 3600 max words, 2000 samples - at ../dataset/gen-word-3600-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 - 7200 max words, 2000 samples - at ../dataset/gen-word-7200-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 - 4500 max words, 2000 samples - at ../dataset/gen-word-4500-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 - 4400 max words, 2000 samples - at ../dataset/gen-word-4400-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 - 4100 max words, 2000 samples - at ../dataset/gen-word-4100-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 - 3800 max words, 2000 samples - at ../dataset/gen-word-3800-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 - 6100 max words, 2000 samples - at ../dataset/gen-word-6100-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 - 6700 max words, 2000 samples - at ../dataset/gen-word-6700-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 - 4300 max words, 2000 samples - at ../dataset/gen-word-4300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 4300 max words, 2000 samples - at ../dataset/gen-word-4300-count.jsonl\n" + "Generated JSONL file with - 5600 max words, 2000 samples - at ../dataset/gen-word-5600-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 - 7500 max words, 2000 samples - at ../dataset/gen-word-7500-count.jsonl\n" ] }, { @@ -2282,154 +2321,154 @@ "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 - 7100 max words, 2000 samples - at ../dataset/gen-word-7100-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 - 6200 max words, 2000 samples - at ../dataset/gen-word-6200-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 - 5200 max words, 2000 samples - at ../dataset/gen-word-5200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 6700 max words, 2000 samples - at ../dataset/gen-word-6700-count.jsonl\n" + "Generated JSONL file with - 5700 max words, 2000 samples - at ../dataset/gen-word-5700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 6600 max words, 2000 samples - at ../dataset/gen-word-6600-count.jsonl\n" + "Generated JSONL file with - 5500 max words, 2000 samples - at ../dataset/gen-word-5500-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 - 4900 max words, 2000 samples - at ../dataset/gen-word-4900-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 - 5400 max words, 2000 samples - at ../dataset/gen-word-5400-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 - 6000 max words, 2000 samples - at ../dataset/gen-word-6000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 6100 max words, 2000 samples - at ../dataset/gen-word-6100-count.jsonl\n" + "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 - 7100 max words, 2000 samples - at ../dataset/gen-word-7100-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 - 5700 max words, 2000 samples - at ../dataset/gen-word-5700-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 - 6500 max words, 2000 samples - at ../dataset/gen-word-6500-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 - 5600 max words, 2000 samples - at ../dataset/gen-word-5600-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 - 5800 max words, 2000 samples - at ../dataset/gen-word-5800-count.jsonl\n" + "Generated JSONL file with - 7000 max words, 2000 samples - at ../dataset/gen-word-7000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 6300 max words, 2000 samples - at ../dataset/gen-word-6300-count.jsonl\n" + "Generated JSONL file with - 6400 max words, 2000 samples - at ../dataset/gen-word-6400-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 - 5800 max words, 2000 samples - at ../dataset/gen-word-5800-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 - 6300 max words, 2000 samples - at ../dataset/gen-word-6300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 7000 max words, 2000 samples - at ../dataset/gen-word-7000-count.jsonl\n" + "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 - 7900 max words, 2000 samples - at ../dataset/gen-word-7900-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 - 7200 max words, 2000 samples - at ../dataset/gen-word-7200-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 - 7800 max words, 2000 samples - at ../dataset/gen-word-7800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "Generated JSONL file with - 8000 max words, 2000 samples - at ../dataset/gen-word-8000-count.jsonl\n" + "Generated JSONL file with - 7900 max words, 2000 samples - at ../dataset/gen-word-7900-count.jsonl\n" ] }, { @@ -2450,1386 +2489,1386 @@ "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 20K Sep 14 00:23 gen-word-10-count.jsonl\n" + "-rw-r--r-- 1 root root 21K Sep 14 02:37 gen-word-10-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 2.1M Sep 14 00:23 gen-word-100-count.jsonl\n" + "-rw-r--r-- 1 root root 2.1M Sep 14 02:37 gen-word-100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 20M Sep 14 00:23 gen-word-1000-count.jsonl\n" + "-rw-r--r-- 1 root root 20M Sep 14 02:37 gen-word-1000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 22M Sep 14 00:23 gen-word-1100-count.jsonl\n" + "-rw-r--r-- 1 root root 22M Sep 14 02:37 gen-word-1100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 23M Sep 14 00:23 gen-word-1200-count.jsonl\n" + "-rw-r--r-- 1 root root 23M Sep 14 02:37 gen-word-1200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 25M Sep 14 00:23 gen-word-1300-count.jsonl\n" + "-rw-r--r-- 1 root root 25M Sep 14 02:37 gen-word-1300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 27M Sep 14 00:23 gen-word-1400-count.jsonl\n" + "-rw-r--r-- 1 root root 27M Sep 14 02:37 gen-word-1400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 24K Sep 14 00:23 gen-word-15-count.jsonl\n" + "-rw-r--r-- 1 root root 24K Sep 14 02:37 gen-word-15-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 29M Sep 14 00:23 gen-word-1500-count.jsonl\n" + "-rw-r--r-- 1 root root 29M Sep 14 02:37 gen-word-1500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 31M Sep 14 00:23 gen-word-1600-count.jsonl\n" + "-rw-r--r-- 1 root root 31M Sep 14 02:37 gen-word-1600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 33M Sep 14 00:23 gen-word-1700-count.jsonl\n" + "-rw-r--r-- 1 root root 33M Sep 14 02:37 gen-word-1700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 35M Sep 14 00:23 gen-word-1800-count.jsonl\n" + "-rw-r--r-- 1 root root 35M Sep 14 02:37 gen-word-1800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 37M Sep 14 00:23 gen-word-1900-count.jsonl\n" + "-rw-r--r-- 1 root root 37M Sep 14 02:37 gen-word-1900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 30K Sep 14 00:23 gen-word-20-count.jsonl\n" + "-rw-r--r-- 1 root root 30K Sep 14 02:37 gen-word-20-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 4.0M Sep 14 00:23 gen-word-200-count.jsonl\n" + "-rw-r--r-- 1 root root 4.0M Sep 14 02:37 gen-word-200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 39M Sep 14 00:23 gen-word-2000-count.jsonl\n" + "-rw-r--r-- 1 root root 39M Sep 14 02:37 gen-word-2000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 41M Sep 14 00:23 gen-word-2100-count.jsonl\n" + "-rw-r--r-- 1 root root 41M Sep 14 02:37 gen-word-2100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 42M Sep 14 00:23 gen-word-2200-count.jsonl\n" + "-rw-r--r-- 1 root root 42M Sep 14 02:37 gen-word-2200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 44M Sep 14 00:23 gen-word-2300-count.jsonl\n" + "-rw-r--r-- 1 root root 44M Sep 14 02:37 gen-word-2300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 46M Sep 14 00:23 gen-word-2400-count.jsonl\n" + "-rw-r--r-- 1 root root 46M Sep 14 02:37 gen-word-2400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 35K Sep 14 00:23 gen-word-25-count.jsonl\n" + "-rw-r--r-- 1 root root 35K Sep 14 02:37 gen-word-25-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 48M Sep 14 00:23 gen-word-2500-count.jsonl\n" + "-rw-r--r-- 1 root root 48M Sep 14 02:37 gen-word-2500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 50M Sep 14 00:23 gen-word-2600-count.jsonl\n" + "-rw-r--r-- 1 root root 50M Sep 14 02:37 gen-word-2600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 52M Sep 14 00:23 gen-word-2700-count.jsonl\n" + "-rw-r--r-- 1 root root 52M Sep 14 02:37 gen-word-2700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 54M Sep 14 00:23 gen-word-2800-count.jsonl\n" + "-rw-r--r-- 1 root root 54M Sep 14 02:37 gen-word-2800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 56M Sep 14 00:23 gen-word-2900-count.jsonl\n" + "-rw-r--r-- 1 root root 56M Sep 14 02:37 gen-word-2900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 39K Sep 14 00:23 gen-word-30-count.jsonl\n" + "-rw-r--r-- 1 root root 39K Sep 14 02:37 gen-word-30-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 5.9M Sep 14 00:23 gen-word-300-count.jsonl\n" + "-rw-r--r-- 1 root root 5.9M Sep 14 02:37 gen-word-300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 58M Sep 14 00:23 gen-word-3000-count.jsonl\n" + "-rw-r--r-- 1 root root 58M Sep 14 02:37 gen-word-3000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 60M Sep 14 00:23 gen-word-3100-count.jsonl\n" + "-rw-r--r-- 1 root root 60M Sep 14 02:37 gen-word-3100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 61M Sep 14 00:23 gen-word-3200-count.jsonl\n" + "-rw-r--r-- 1 root root 61M Sep 14 02:37 gen-word-3200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 63M Sep 14 00:23 gen-word-3300-count.jsonl\n" + "-rw-r--r-- 1 root root 63M Sep 14 02:37 gen-word-3300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 65M Sep 14 00:23 gen-word-3400-count.jsonl\n" + "-rw-r--r-- 1 root root 65M Sep 14 02:37 gen-word-3400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 44K Sep 14 00:23 gen-word-35-count.jsonl\n" + "-rw-r--r-- 1 root root 45K Sep 14 02:37 gen-word-35-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 67M Sep 14 00:23 gen-word-3500-count.jsonl\n" + "-rw-r--r-- 1 root root 67M Sep 14 02:37 gen-word-3500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 69M Sep 14 00:23 gen-word-3600-count.jsonl\n" + "-rw-r--r-- 1 root root 69M Sep 14 02:37 gen-word-3600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 71M Sep 14 00:23 gen-word-3700-count.jsonl\n" + "-rw-r--r-- 1 root root 71M Sep 14 02:37 gen-word-3700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 73M Sep 14 00:23 gen-word-3800-count.jsonl\n" + "-rw-r--r-- 1 root root 73M Sep 14 02:37 gen-word-3800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 75M Sep 14 00:23 gen-word-3900-count.jsonl\n" + "-rw-r--r-- 1 root root 75M Sep 14 02:37 gen-word-3900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 48K Sep 14 00:23 gen-word-40-count.jsonl\n" + "-rw-r--r-- 1 root root 49K Sep 14 02:37 gen-word-40-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 7.8M Sep 14 00:23 gen-word-400-count.jsonl\n" + "-rw-r--r-- 1 root root 7.8M Sep 14 02:37 gen-word-400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 77M Sep 14 00:23 gen-word-4000-count.jsonl\n" + "-rw-r--r-- 1 root root 77M Sep 14 02:37 gen-word-4000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 79M Sep 14 00:23 gen-word-4100-count.jsonl\n" + "-rw-r--r-- 1 root root 79M Sep 14 02:37 gen-word-4100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 80M Sep 14 00:23 gen-word-4200-count.jsonl\n" + "-rw-r--r-- 1 root root 80M Sep 14 02:37 gen-word-4200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 82M Sep 14 00:23 gen-word-4300-count.jsonl\n" + "-rw-r--r-- 1 root root 82M Sep 14 02:37 gen-word-4300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 84M Sep 14 00:23 gen-word-4400-count.jsonl\n" + "-rw-r--r-- 1 root root 84M Sep 14 02:37 gen-word-4400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 54K Sep 14 00:23 gen-word-45-count.jsonl\n" + "-rw-r--r-- 1 root root 54K Sep 14 02:37 gen-word-45-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 86M Sep 14 00:23 gen-word-4500-count.jsonl\n" + "-rw-r--r-- 1 root root 86M Sep 14 02:37 gen-word-4500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 88M Sep 14 00:23 gen-word-4600-count.jsonl\n" + "-rw-r--r-- 1 root root 88M Sep 14 02:37 gen-word-4600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 90M Sep 14 00:23 gen-word-4700-count.jsonl\n" + "-rw-r--r-- 1 root root 90M Sep 14 02:37 gen-word-4700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 92M Sep 14 00:23 gen-word-4800-count.jsonl\n" + "-rw-r--r-- 1 root root 92M Sep 14 02:37 gen-word-4800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 94M Sep 14 00:23 gen-word-4900-count.jsonl\n" + "-rw-r--r-- 1 root root 94M Sep 14 02:37 gen-word-4900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 15K Sep 14 00:23 gen-word-5-count.jsonl\n" + "-rw-r--r-- 1 root root 15K Sep 14 02:37 gen-word-5-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 59K Sep 14 00:23 gen-word-50-count.jsonl\n" + "-rw-r--r-- 1 root root 57K Sep 14 02:37 gen-word-50-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 9.7M Sep 14 00:23 gen-word-500-count.jsonl\n" + "-rw-r--r-- 1 root root 9.7M Sep 14 02:37 gen-word-500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 96M Sep 14 00:23 gen-word-5000-count.jsonl\n" + "-rw-r--r-- 1 root root 96M Sep 14 02:37 gen-word-5000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 98M Sep 14 00:23 gen-word-5100-count.jsonl\n" + "-rw-r--r-- 1 root root 97M Sep 14 02:37 gen-word-5100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 99M Sep 14 00:23 gen-word-5200-count.jsonl\n" + "-rw-r--r-- 1 root root 99M Sep 14 02:37 gen-word-5200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 101M Sep 14 00:23 gen-word-5300-count.jsonl\n" + "-rw-r--r-- 1 root root 101M Sep 14 02:37 gen-word-5300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 103M Sep 14 00:23 gen-word-5400-count.jsonl\n" + "-rw-r--r-- 1 root root 103M Sep 14 02:37 gen-word-5400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 63K Sep 14 00:23 gen-word-55-count.jsonl\n" + "-rw-r--r-- 1 root root 62K Sep 14 02:37 gen-word-55-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 105M Sep 14 00:23 gen-word-5500-count.jsonl\n" + "-rw-r--r-- 1 root root 105M Sep 14 02:37 gen-word-5500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 107M Sep 14 00:23 gen-word-5600-count.jsonl\n" + "-rw-r--r-- 1 root root 107M Sep 14 02:37 gen-word-5600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 109M Sep 14 00:23 gen-word-5700-count.jsonl\n" + "-rw-r--r-- 1 root root 109M Sep 14 02:37 gen-word-5700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 111M Sep 14 00:23 gen-word-5800-count.jsonl\n" + "-rw-r--r-- 1 root root 111M Sep 14 02:37 gen-word-5800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 113M Sep 14 00:23 gen-word-5900-count.jsonl\n" + "-rw-r--r-- 1 root root 113M Sep 14 02:37 gen-word-5900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 70K Sep 14 00:23 gen-word-60-count.jsonl\n" + "-rw-r--r-- 1 root root 68K Sep 14 02:37 gen-word-60-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 12M Sep 14 00:23 gen-word-600-count.jsonl\n" + "-rw-r--r-- 1 root root 12M Sep 14 02:37 gen-word-600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 115M Sep 14 00:23 gen-word-6000-count.jsonl\n" + "-rw-r--r-- 1 root root 115M Sep 14 02:37 gen-word-6000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 117M Sep 14 00:23 gen-word-6100-count.jsonl\n" + "-rw-r--r-- 1 root root 117M Sep 14 02:37 gen-word-6100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 119M Sep 14 00:23 gen-word-6200-count.jsonl\n" + "-rw-r--r-- 1 root root 118M Sep 14 02:37 gen-word-6200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 121M Sep 14 00:23 gen-word-6300-count.jsonl\n" + "-rw-r--r-- 1 root root 120M Sep 14 02:37 gen-word-6300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 122M Sep 14 00:23 gen-word-6400-count.jsonl\n" + "-rw-r--r-- 1 root root 122M Sep 14 02:37 gen-word-6400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 72K Sep 14 00:23 gen-word-65-count.jsonl\n" + "-rw-r--r-- 1 root root 73K Sep 14 02:37 gen-word-65-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 124M Sep 14 00:23 gen-word-6500-count.jsonl\n" + "-rw-r--r-- 1 root root 124M Sep 14 02:37 gen-word-6500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 126M Sep 14 00:23 gen-word-6600-count.jsonl\n" + "-rw-r--r-- 1 root root 126M Sep 14 02:37 gen-word-6600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 128M Sep 14 00:23 gen-word-6700-count.jsonl\n" + "-rw-r--r-- 1 root root 128M Sep 14 02:37 gen-word-6700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 130M Sep 14 00:23 gen-word-6800-count.jsonl\n" + "-rw-r--r-- 1 root root 130M Sep 14 02:37 gen-word-6800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 132M Sep 14 00:23 gen-word-6900-count.jsonl\n" + "-rw-r--r-- 1 root root 132M Sep 14 02:37 gen-word-6900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 74K Sep 14 00:23 gen-word-70-count.jsonl\n" + "-rw-r--r-- 1 root root 79K Sep 14 02:37 gen-word-70-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 14M Sep 14 00:23 gen-word-700-count.jsonl\n" + "-rw-r--r-- 1 root root 14M Sep 14 02:37 gen-word-700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 134M Sep 14 00:23 gen-word-7000-count.jsonl\n" + "-rw-r--r-- 1 root root 134M Sep 14 02:37 gen-word-7000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 135M Sep 14 00:23 gen-word-7100-count.jsonl\n" + "-rw-r--r-- 1 root root 136M Sep 14 02:37 gen-word-7100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 138M Sep 14 00:23 gen-word-7200-count.jsonl\n" + "-rw-r--r-- 1 root root 137M Sep 14 02:37 gen-word-7200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 139M Sep 14 00:23 gen-word-7300-count.jsonl\n" + "-rw-r--r-- 1 root root 139M Sep 14 02:37 gen-word-7300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 141M Sep 14 00:23 gen-word-7400-count.jsonl\n" + "-rw-r--r-- 1 root root 141M Sep 14 02:37 gen-word-7400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 81K Sep 14 00:23 gen-word-75-count.jsonl\n" + "-rw-r--r-- 1 root root 83K Sep 14 02:37 gen-word-75-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 143M Sep 14 00:23 gen-word-7500-count.jsonl\n" + "-rw-r--r-- 1 root root 143M Sep 14 02:37 gen-word-7500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 145M Sep 14 00:23 gen-word-7600-count.jsonl\n" + "-rw-r--r-- 1 root root 145M Sep 14 02:37 gen-word-7600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 147M Sep 14 00:23 gen-word-7700-count.jsonl\n" + "-rw-r--r-- 1 root root 147M Sep 14 02:37 gen-word-7700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 149M Sep 14 00:23 gen-word-7800-count.jsonl\n" + "-rw-r--r-- 1 root root 149M Sep 14 02:37 gen-word-7800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 151M Sep 14 00:23 gen-word-7900-count.jsonl\n" + "-rw-r--r-- 1 root root 151M Sep 14 02:37 gen-word-7900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 88K Sep 14 00:23 gen-word-80-count.jsonl\n" + "-rw-r--r-- 1 root root 86K Sep 14 02:37 gen-word-80-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 16M Sep 14 00:23 gen-word-800-count.jsonl\n" + "-rw-r--r-- 1 root root 16M Sep 14 02:37 gen-word-800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 153M Sep 14 00:23 gen-word-8000-count.jsonl\n" + "-rw-r--r-- 1 root root 153M Sep 14 02:37 gen-word-8000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 90K Sep 14 00:23 gen-word-85-count.jsonl\n" + "-rw-r--r-- 1 root root 88K Sep 14 02:37 gen-word-85-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 95K Sep 14 00:23 gen-word-90-count.jsonl\n" + "-rw-r--r-- 1 root root 101K Sep 14 02:37 gen-word-90-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 18M Sep 14 00:23 gen-word-900-count.jsonl\n" + "-rw-r--r-- 1 root root 18M Sep 14 02:37 gen-word-900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 101K Sep 14 00:23 gen-word-95-count.jsonl\n" + "-rw-r--r-- 1 root root 101K Sep 14 02:37 gen-word-95-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 507K Sep 14 00:23 shuffle-word-10-count.jsonl\n" + "-rw-r--r-- 1 root root 500K Sep 14 02:37 shuffle-word-10-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 288K Sep 14 00:23 shuffle-word-100-count.jsonl\n" + "-rw-r--r-- 1 root root 281K Sep 14 02:37 shuffle-word-100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 524K Sep 14 00:23 shuffle-word-1000-count.jsonl\n" + "-rw-r--r-- 1 root root 525K Sep 14 02:37 shuffle-word-1000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 521K Sep 14 00:23 shuffle-word-1100-count.jsonl\n" + "-rw-r--r-- 1 root root 520K Sep 14 02:37 shuffle-word-1100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 521K Sep 14 00:23 shuffle-word-1200-count.jsonl\n" + "-rw-r--r-- 1 root root 522K Sep 14 02:37 shuffle-word-1200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 525K Sep 14 00:23 shuffle-word-1300-count.jsonl\n" + "-rw-r--r-- 1 root root 524K Sep 14 02:37 shuffle-word-1300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 522K Sep 14 00:23 shuffle-word-1400-count.jsonl\n" + "-rw-r--r-- 1 root root 520K Sep 14 02:37 shuffle-word-1400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 433K Sep 14 00:23 shuffle-word-15-count.jsonl\n" + "-rw-r--r-- 1 root root 432K Sep 14 02:37 shuffle-word-15-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 521K Sep 14 00:23 shuffle-word-1500-count.jsonl\n" + "-rw-r--r-- 1 root root 522K Sep 14 02:37 shuffle-word-1500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 518K Sep 14 00:23 shuffle-word-1600-count.jsonl\n" + "-rw-r--r-- 1 root root 521K Sep 14 02:37 shuffle-word-1600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 522K Sep 14 00:23 shuffle-word-1700-count.jsonl\n" + "-rw-r--r-- 1 root root 519K Sep 14 02:37 shuffle-word-1700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 521K Sep 14 00:23 shuffle-word-1800-count.jsonl\n" + "-rw-r--r-- 1 root root 520K Sep 14 02:37 shuffle-word-1800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 522K Sep 14 00:23 shuffle-word-1900-count.jsonl\n" + "-rw-r--r-- 1 root root 519K Sep 14 02:37 shuffle-word-1900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 386K Sep 14 00:23 shuffle-word-20-count.jsonl\n" + "-rw-r--r-- 1 root root 393K Sep 14 02:37 shuffle-word-20-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 540K Sep 14 00:23 shuffle-word-200-count.jsonl\n" + "-rw-r--r-- 1 root root 540K Sep 14 02:37 shuffle-word-200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 518K Sep 14 00:23 shuffle-word-2000-count.jsonl\n" + "-rw-r--r-- 1 root root 520K Sep 14 02:37 shuffle-word-2000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 522K Sep 14 00:23 shuffle-word-2100-count.jsonl\n" + "-rw-r--r-- 1 root root 519K Sep 14 02:37 shuffle-word-2100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 519K Sep 14 00:23 shuffle-word-2200-count.jsonl\n" + "-rw-r--r-- 1 root root 520K Sep 14 02:37 shuffle-word-2200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 519K Sep 14 00:23 shuffle-word-2300-count.jsonl\n" + "-rw-r--r-- 1 root root 521K Sep 14 02:37 shuffle-word-2300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 520K Sep 14 00:23 shuffle-word-2400-count.jsonl\n" + "-rw-r--r-- 1 root root 517K Sep 14 02:37 shuffle-word-2400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 363K Sep 14 00:23 shuffle-word-25-count.jsonl\n" + "-rw-r--r-- 1 root root 357K Sep 14 02:37 shuffle-word-25-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 519K Sep 14 00:23 shuffle-word-2500-count.jsonl\n" + "-rw-r--r-- 1 root root 519K Sep 14 02:37 shuffle-word-2500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 516K Sep 14 00:23 shuffle-word-2600-count.jsonl\n" + "-rw-r--r-- 1 root root 512K Sep 14 02:37 shuffle-word-2600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 14 00:23 shuffle-word-2700-count.jsonl\n" + "-rw-r--r-- 1 root root 510K Sep 14 02:37 shuffle-word-2700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 510K Sep 14 00:23 shuffle-word-2800-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 14 02:37 shuffle-word-2800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 510K Sep 14 00:23 shuffle-word-2900-count.jsonl\n" + "-rw-r--r-- 1 root root 508K Sep 14 02:37 shuffle-word-2900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 336K Sep 14 00:23 shuffle-word-30-count.jsonl\n" + "-rw-r--r-- 1 root root 334K Sep 14 02:37 shuffle-word-30-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 535K Sep 14 00:23 shuffle-word-300-count.jsonl\n" + "-rw-r--r-- 1 root root 534K Sep 14 02:37 shuffle-word-300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 14 00:23 shuffle-word-3000-count.jsonl\n" + "-rw-r--r-- 1 root root 508K Sep 14 02:37 shuffle-word-3000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 14 00:23 shuffle-word-3100-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 14 02:37 shuffle-word-3100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 508K Sep 14 00:23 shuffle-word-3200-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 14 02:37 shuffle-word-3200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 14 00:23 shuffle-word-3300-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 14 02:37 shuffle-word-3300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 14 00:23 shuffle-word-3400-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 14 02:37 shuffle-word-3400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 331K Sep 14 00:23 shuffle-word-35-count.jsonl\n" + "-rw-r--r-- 1 root root 322K Sep 14 02:37 shuffle-word-35-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 14 00:23 shuffle-word-3500-count.jsonl\n" + "-rw-r--r-- 1 root root 508K Sep 14 02:37 shuffle-word-3500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 14 00:23 shuffle-word-3600-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 14 02:37 shuffle-word-3600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 508K Sep 14 00:23 shuffle-word-3700-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 14 02:37 shuffle-word-3700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 14 00:23 shuffle-word-3800-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 14 02:37 shuffle-word-3800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 14 00:23 shuffle-word-3900-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 14 02:37 shuffle-word-3900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 321K Sep 14 00:23 shuffle-word-40-count.jsonl\n" + "-rw-r--r-- 1 root root 314K Sep 14 02:37 shuffle-word-40-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 529K Sep 14 00:23 shuffle-word-400-count.jsonl\n" + "-rw-r--r-- 1 root root 527K Sep 14 02:37 shuffle-word-400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 14 00:23 shuffle-word-4000-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 14 02:37 shuffle-word-4000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 508K Sep 14 00:23 shuffle-word-4100-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 14 02:37 shuffle-word-4100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 14 00:23 shuffle-word-4200-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 14 02:37 shuffle-word-4200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 14 00:23 shuffle-word-4300-count.jsonl\n" + "-rw-r--r-- 1 root root 508K Sep 14 02:37 shuffle-word-4300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 14 00:23 shuffle-word-4400-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 14 02:37 shuffle-word-4400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 311K Sep 14 00:23 shuffle-word-45-count.jsonl\n" + "-rw-r--r-- 1 root root 317K Sep 14 02:37 shuffle-word-45-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 14 00:23 shuffle-word-4500-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 14 02:37 shuffle-word-4500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 14 00:23 shuffle-word-4600-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 14 02:37 shuffle-word-4600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 14 00:23 shuffle-word-4700-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 14 02:37 shuffle-word-4700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 14 00:23 shuffle-word-4800-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 14 02:37 shuffle-word-4800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 14 00:23 shuffle-word-4900-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 14 02:37 shuffle-word-4900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 813K Sep 14 00:23 shuffle-word-5-count.jsonl\n" + "-rw-r--r-- 1 root root 822K Sep 14 02:37 shuffle-word-5-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 308K Sep 14 00:23 shuffle-word-50-count.jsonl\n" + "-rw-r--r-- 1 root root 311K Sep 14 02:37 shuffle-word-50-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 529K Sep 14 00:23 shuffle-word-500-count.jsonl\n" + "-rw-r--r-- 1 root root 526K Sep 14 02:37 shuffle-word-500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 14 00:23 shuffle-word-5000-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 14 02:37 shuffle-word-5000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 14 00:23 shuffle-word-5100-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 14 02:37 shuffle-word-5100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 14 00:23 shuffle-word-5200-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 14 02:37 shuffle-word-5200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 14 00:23 shuffle-word-5300-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 14 02:37 shuffle-word-5300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 14 00:23 shuffle-word-5400-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 14 02:37 shuffle-word-5400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 309K Sep 14 00:23 shuffle-word-55-count.jsonl\n" + "-rw-r--r-- 1 root root 301K Sep 14 02:37 shuffle-word-55-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 14 00:23 shuffle-word-5500-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 14 02:37 shuffle-word-5500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 14 00:23 shuffle-word-5600-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 14 02:37 shuffle-word-5600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 14 00:23 shuffle-word-5700-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 14 02:37 shuffle-word-5700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 14 00:23 shuffle-word-5800-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 14 02:37 shuffle-word-5800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 14 00:23 shuffle-word-5900-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 14 02:37 shuffle-word-5900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 300K Sep 14 00:23 shuffle-word-60-count.jsonl\n" + "-rw-r--r-- 1 root root 300K Sep 14 02:37 shuffle-word-60-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 527K Sep 14 00:23 shuffle-word-600-count.jsonl\n" + "-rw-r--r-- 1 root root 527K Sep 14 02:37 shuffle-word-600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 14 00:23 shuffle-word-6000-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 14 02:37 shuffle-word-6000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 508K Sep 14 00:23 shuffle-word-6100-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 14 02:37 shuffle-word-6100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 14 00:23 shuffle-word-6200-count.jsonl\n" + "-rw-r--r-- 1 root root 508K Sep 14 02:37 shuffle-word-6200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 14 00:23 shuffle-word-6300-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 14 02:37 shuffle-word-6300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 14 00:23 shuffle-word-6400-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 14 02:37 shuffle-word-6400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 300K Sep 14 00:23 shuffle-word-65-count.jsonl\n" + "-rw-r--r-- 1 root root 297K Sep 14 02:37 shuffle-word-65-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 14 00:23 shuffle-word-6500-count.jsonl\n" + "-rw-r--r-- 1 root root 508K Sep 14 02:37 shuffle-word-6500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 508K Sep 14 00:23 shuffle-word-6600-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 14 02:37 shuffle-word-6600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 14 00:23 shuffle-word-6700-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 14 02:37 shuffle-word-6700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 508K Sep 14 00:23 shuffle-word-6800-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 14 02:37 shuffle-word-6800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 508K Sep 14 00:23 shuffle-word-6900-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 14 02:37 shuffle-word-6900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 295K Sep 14 00:23 shuffle-word-70-count.jsonl\n" + "-rw-r--r-- 1 root root 297K Sep 14 02:37 shuffle-word-70-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 527K Sep 14 00:23 shuffle-word-700-count.jsonl\n" + "-rw-r--r-- 1 root root 530K Sep 14 02:37 shuffle-word-700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 14 00:23 shuffle-word-7000-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 14 02:37 shuffle-word-7000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 14 00:23 shuffle-word-7100-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 14 02:37 shuffle-word-7100-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 14 00:23 shuffle-word-7200-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 14 02:37 shuffle-word-7200-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 14 00:23 shuffle-word-7300-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 14 02:37 shuffle-word-7300-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 14 00:23 shuffle-word-7400-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 14 02:37 shuffle-word-7400-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 288K Sep 14 00:23 shuffle-word-75-count.jsonl\n" + "-rw-r--r-- 1 root root 284K Sep 14 02:37 shuffle-word-75-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 14 00:23 shuffle-word-7500-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 14 02:37 shuffle-word-7500-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 14 00:23 shuffle-word-7600-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 14 02:37 shuffle-word-7600-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 14 00:23 shuffle-word-7700-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 14 02:37 shuffle-word-7700-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 14 00:23 shuffle-word-7800-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 14 02:37 shuffle-word-7800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 14 00:23 shuffle-word-7900-count.jsonl\n" + "-rw-r--r-- 1 root root 508K Sep 14 02:37 shuffle-word-7900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 290K Sep 14 00:23 shuffle-word-80-count.jsonl\n" + "-rw-r--r-- 1 root root 291K Sep 14 02:37 shuffle-word-80-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 523K Sep 14 00:23 shuffle-word-800-count.jsonl\n" + "-rw-r--r-- 1 root root 526K Sep 14 02:37 shuffle-word-800-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 509K Sep 14 00:23 shuffle-word-8000-count.jsonl\n" + "-rw-r--r-- 1 root root 509K Sep 14 02:37 shuffle-word-8000-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 284K Sep 14 00:23 shuffle-word-85-count.jsonl\n" + "-rw-r--r-- 1 root root 283K Sep 14 02:37 shuffle-word-85-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 290K Sep 14 00:23 shuffle-word-90-count.jsonl\n" + "-rw-r--r-- 1 root root 281K Sep 14 02:37 shuffle-word-90-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 525K Sep 14 00:23 shuffle-word-900-count.jsonl\n" + "-rw-r--r-- 1 root root 524K Sep 14 02:37 shuffle-word-900-count.jsonl\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "-rw-r--r-- 1 root root 288K Sep 14 00:23 shuffle-word-95-count.jsonl\n" + "-rw-r--r-- 1 root root 286K Sep 14 02:37 shuffle-word-95-count.jsonl\n" ] } ], @@ -3878,19 +3917,19 @@ { "cell_type": "code", "execution_count": 6, - "id": "dc750aad", + "id": "af9b83d3", "metadata": { "execution": { - "iopub.execute_input": "2023-09-14T00:23:38.144140Z", - "iopub.status.busy": "2023-09-14T00:23:38.143744Z", - "iopub.status.idle": "2023-09-14T00:24:09.381956Z", - "shell.execute_reply": "2023-09-14T00:24:09.380782Z" + "iopub.execute_input": "2023-09-14T02:37:52.652229Z", + "iopub.status.busy": "2023-09-14T02:37:52.651608Z", + "iopub.status.idle": "2023-09-14T02:38:21.558685Z", + "shell.execute_reply": "2023-09-14T02:38:21.557835Z" }, "papermill": { - "duration": 31.277099, - "end_time": "2023-09-14T00:24:09.384289", + "duration": 28.945501, + "end_time": "2023-09-14T02:38:21.561935", "exception": false, - "start_time": "2023-09-14T00:23:38.107190", + "start_time": "2023-09-14T02:37:52.616434", "status": "completed" }, "tags": [] @@ -3900,7 +3939,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "[2023-09-14 00:23:43,047] [INFO] [real_accelerator.py:133:get_accelerator] Setting ds_accelerator to cuda (auto detect)\r\n" + "[2023-09-14 02:37:56,909] [INFO] [real_accelerator.py:133:get_accelerator] Setting ds_accelerator to cuda (auto detect)\r\n" ] }, { @@ -3922,9 +3961,9 @@ "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 2409510691\r\n", + "/usr/local/lib/python3.10/dist-packages/lightning/fabric/utilities/seed.py:39: UserWarning: No seed found, seed set to 1547623296\r\n", " rank_zero_warn(f\"No seed found, seed set to {seed}\")\r\n", - "Global seed set to 2409510691\r\n" + "Global seed set to 1547623296\r\n" ] }, { @@ -3939,11 +3978,11 @@ "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-20230914_002346-rjj8azcb\u001b[0m\r\n", + "\u001b[34m\u001b[1mwandb\u001b[0m: Run data is saved locally in \u001b[35m\u001b[1m./wandb/run-20230914_023759-9o2jwwvs\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-L6-D2048-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/rjj8azcb\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/9o2jwwvs\u001b[0m\r\n" ] }, { @@ -3979,10 +4018,17 @@ "text": [ "\r", "Resolving data files: 0%| | 0/198 [00:00: JSON parse error: The document is empty.\r\n", + "Failed to read file '/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/notebook/experiment/rwkv-x-exp/dataset/gen-word-100-count.jsonl' with error : JSON parse error: Missing a comma or '}' after an object member. in row 27\r\n", + "\r", + "Generating train split: 100 examples [00:01, 58.74 examples/s]" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ "\r", - "Generating train split: 100 examples [00:01, 59.81 examples/s]" + "Generating train split: 4119 examples [00:01, 3148.90 examples/s]" ] }, { @@ -4011,7 +4065,7 @@ "output_type": "stream", "text": [ "\r", - "Generating train split: 4192 examples [00:01, 3264.19 examples/s]" + "Generating train split: 9991 examples [00:01, 8377.41 examples/s]" ] }, { @@ -4019,7 +4073,7 @@ "output_type": "stream", "text": [ "\r", - "Generating train split: 7274 examples [00:01, 5941.16 examples/s]" + "Generating train split: 16136 examples [00:02, 14631.65 examples/s]" ] }, { @@ -4027,7 +4081,7 @@ "output_type": "stream", "text": [ "\r", - "Generating train split: 12298 examples [00:02, 11319.63 examples/s]" + "Generating train split: 21292 examples [00:02, 19123.98 examples/s]" ] }, { @@ -4035,7 +4089,7 @@ "output_type": "stream", "text": [ "\r", - "Generating train split: 16646 examples [00:02, 15857.43 examples/s]" + "Generating train split: 42124 examples [00:02, 48567.56 examples/s]" ] }, { @@ -4043,7 +4097,7 @@ "output_type": "stream", "text": [ "\r", - "Generating train split: 24754 examples [00:02, 25730.84 examples/s]" + "Generating train split: 50633 examples [00:02, 48135.15 examples/s]" ] }, { @@ -4051,7 +4105,7 @@ "output_type": "stream", "text": [ "\r", - "Generating train split: 29784 examples [00:02, 29814.87 examples/s]" + "Generating train split: 59623 examples [00:02, 55584.20 examples/s]" ] }, { @@ -4059,7 +4113,7 @@ "output_type": "stream", "text": [ "\r", - "Generating train split: 51040 examples [00:02, 67851.73 examples/s]" + "Generating train split: 67337 examples [00:02, 53321.94 examples/s]" ] }, { @@ -4067,7 +4121,7 @@ "output_type": "stream", "text": [ "\r", - "Generating train split: 60766 examples [00:02, 69517.43 examples/s]" + "Generating train split: 74360 examples [00:02, 50060.00 examples/s]" ] }, { @@ -4075,7 +4129,7 @@ "output_type": "stream", "text": [ "\r", - "Generating train split: 69699 examples [00:02, 61870.64 examples/s]" + "Generating train split: 80571 examples [00:03, 46642.17 examples/s]" ] }, { @@ -4083,7 +4137,7 @@ "output_type": "stream", "text": [ "\r", - "Generating train split: 77449 examples [00:02, 55006.72 examples/s]" + "Generating train split: 85925 examples [00:03, 46695.96 examples/s]" ] }, { @@ -4091,7 +4145,7 @@ "output_type": "stream", "text": [ "\r", - "Generating train split: 84355 examples [00:03, 52194.78 examples/s]" + "Generating train split: 91087 examples [00:03, 42287.60 examples/s]" ] }, { @@ -4099,7 +4153,7 @@ "output_type": "stream", "text": [ "\r", - "Generating train split: 90582 examples [00:03, 52818.03 examples/s]" + "Generating train split: 95851 examples [00:03, 41277.70 examples/s]" ] }, { @@ -4107,7 +4161,7 @@ "output_type": "stream", "text": [ "\r", - "Generating train split: 96557 examples [00:03, 49398.87 examples/s]" + "Generating train split: 100328 examples [00:03, 41903.98 examples/s]" ] }, { @@ -4115,7 +4169,7 @@ "output_type": "stream", "text": [ "\r", - "Generating train split: 101972 examples [00:03, 44994.14 examples/s]" + "Generating train split: 105109 examples [00:03, 43330.01 examples/s]" ] }, { @@ -4123,7 +4177,7 @@ "output_type": "stream", "text": [ "\r", - "Generating train split: 106761 examples [00:03, 42524.57 examples/s]" + "Generating train split: 109873 examples [00:03, 38887.49 examples/s]" ] }, { @@ -4131,7 +4185,7 @@ "output_type": "stream", "text": [ "\r", - "Generating train split: 111314 examples [00:03, 40451.50 examples/s]" + "Generating train split: 114106 examples [00:03, 38800.38 examples/s]" ] }, { @@ -4139,7 +4193,7 @@ "output_type": "stream", "text": [ "\r", - "Generating train split: 115495 examples [00:03, 38042.11 examples/s]" + "Generating train split: 118536 examples [00:04, 40082.20 examples/s]" ] }, { @@ -4147,7 +4201,7 @@ "output_type": "stream", "text": [ "\r", - "Generating train split: 121217 examples [00:04, 42265.52 examples/s]" + "Generating train split: 122694 examples [00:04, 38268.69 examples/s]" ] }, { @@ -4155,7 +4209,7 @@ "output_type": "stream", "text": [ "\r", - "Generating train split: 125781 examples [00:04, 38604.07 examples/s]" + "Generating train split: 127281 examples [00:04, 38358.03 examples/s]" ] }, { @@ -4163,7 +4217,7 @@ "output_type": "stream", "text": [ "\r", - "Generating train split: 131059 examples [00:04, 41930.09 examples/s]" + "Generating train split: 131204 examples [00:04, 37584.81 examples/s]" ] }, { @@ -4171,7 +4225,7 @@ "output_type": "stream", "text": [ "\r", - "Generating train split: 135527 examples [00:04, 37367.60 examples/s]" + "Generating train split: 135020 examples [00:04, 32997.15 examples/s]" ] }, { @@ -4179,7 +4233,7 @@ "output_type": "stream", "text": [ "\r", - "Generating train split: 140337 examples [00:04, 39261.42 examples/s]" + "Generating train split: 139737 examples [00:04, 35623.56 examples/s]" ] }, { @@ -4187,7 +4241,7 @@ "output_type": "stream", "text": [ "\r", - "Generating train split: 144530 examples [00:04, 38141.40 examples/s]" + "Generating train split: 143828 examples [00:04, 36646.73 examples/s]" ] }, { @@ -4195,7 +4249,7 @@ "output_type": "stream", "text": [ "\r", - "Generating train split: 148531 examples [00:04, 35123.00 examples/s]" + "Generating train split: 147603 examples [00:04, 34959.40 examples/s]" ] }, { @@ -4203,7 +4257,7 @@ "output_type": "stream", "text": [ "\r", - "Generating train split: 152149 examples [00:04, 32635.68 examples/s]" + "Generating train split: 151330 examples [00:05, 28703.38 examples/s]" ] }, { @@ -4211,7 +4265,7 @@ "output_type": "stream", "text": [ "\r", - "Generating train split: 155588 examples [00:05, 28239.31 examples/s]" + "Generating train split: 154519 examples [00:05, 26946.66 examples/s]" ] }, { @@ -4219,7 +4273,7 @@ "output_type": "stream", "text": [ "\r", - "Generating train split: 158703 examples [00:05, 25877.65 examples/s]" + "Generating train split: 157445 examples [00:05, 25877.83 examples/s]" ] }, { @@ -4227,7 +4281,7 @@ "output_type": "stream", "text": [ "\r", - "Generating train split: 161402 examples [00:05, 25746.47 examples/s]" + "Generating train split: 160186 examples [00:05, 24367.50 examples/s]" ] }, { @@ -4235,7 +4289,7 @@ "output_type": "stream", "text": [ "\r", - "Generating train split: 164146 examples [00:05, 23432.26 examples/s]" + "Generating train split: 162774 examples [00:05, 23524.07 examples/s]" ] }, { @@ -4243,7 +4297,7 @@ "output_type": "stream", "text": [ "\r", - "Generating train split: 166599 examples [00:05, 22161.96 examples/s]" + "Generating train split: 165326 examples [00:05, 21662.50 examples/s]" ] }, { @@ -4251,7 +4305,7 @@ "output_type": "stream", "text": [ "\r", - "Generating train split: 169044 examples [00:05, 18107.60 examples/s]" + "Generating train split: 167801 examples [00:05, 18798.65 examples/s]" ] }, { @@ -4259,7 +4313,7 @@ "output_type": "stream", "text": [ "\r", - "Generating train split: 171109 examples [00:06, 13602.32 examples/s]" + "Generating train split: 169818 examples [00:06, 17953.36 examples/s]" ] }, { @@ -4267,7 +4321,15 @@ "output_type": "stream", "text": [ "\r", - "Generating train split: 172012 examples [00:06, 26818.32 examples/s]\r\n" + "Generating train split: 171755 examples [00:06, 11617.64 examples/s]" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\r", + "Generating train split: 171974 examples [00:06, 26184.81 examples/s]\r\n" ] }, { @@ -4285,7 +4347,7 @@ " return _default_decoder.decode(s)\r\n", " File \"/usr/lib/python3.10/json/decoder.py\", line 340, in decode\r\n", " raise JSONDecodeError(\"Extra data\", s, end)\r\n", - "json.decoder.JSONDecodeError: Extra data: line 2 column 1 (char 909)\r\n", + "json.decoder.JSONDecodeError: Extra data: line 2 column 1 (char 1231)\r\n", "\r\n", "During handling of the above exception, another exception occurred:\r\n", "\r\n", @@ -4299,7 +4361,7 @@ " File \"pyarrow/_json.pyx\", line 258, in pyarrow._json.read_json\r\n", " File \"pyarrow/error.pxi\", line 144, in pyarrow.lib.pyarrow_internal_check_status\r\n", " File \"pyarrow/error.pxi\", line 100, in pyarrow.lib.check_status\r\n", - "pyarrow.lib.ArrowInvalid: JSON parse error: The document is empty.\r\n", + "pyarrow.lib.ArrowInvalid: JSON parse error: Missing a comma or '}' after an object member. in row 27\r\n", "\r\n", "The above exception was the direct cause of the following exception:\r\n", "\r\n", @@ -4356,46 +4418,45 @@ " [async_result.get(timeout=0.05) for async_result in async_results]\r\n", " File \"/usr/local/lib/python3.10/dist-packages/multiprocess/pool.py\", line 774, in get\r\n", " raise self._value\r\n", - "datasets.builder.DatasetGenerationError: An error occurred while generating the dataset\r\n", - "\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" + "datasets.builder.DatasetGenerationError: An error occurred while generating the dataset\r\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\u001b[34m\u001b[1mwandb\u001b[0m: - 0.005 MB of 0.005 MB uploaded (0.000 MB deduped)\r" + "\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" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\u001b[34m\u001b[1mwandb\u001b[0m: \\ 0.005 MB of 0.005 MB uploaded (0.000 MB deduped)\r" + "\u001b[34m\u001b[1mwandb\u001b[0m: - 0.005 MB of 0.005 MB uploaded (0.000 MB deduped)\r" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\u001b[34m\u001b[1mwandb\u001b[0m: | 0.005 MB of 0.005 MB uploaded (0.000 MB deduped)\r" + "\u001b[34m\u001b[1mwandb\u001b[0m: \\ 0.005 MB of 0.016 MB uploaded (0.000 MB deduped)\r" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\u001b[34m\u001b[1mwandb\u001b[0m: / 0.005 MB of 0.005 MB uploaded (0.000 MB deduped)\r" + "\u001b[34m\u001b[1mwandb\u001b[0m: | 0.005 MB of 0.016 MB uploaded (0.000 MB deduped)\r" ] }, { "name": "stdout", "output_type": "stream", "text": [ - "\u001b[34m\u001b[1mwandb\u001b[0m: 🚀 View run \u001b[33mv5r3-L6-D2048-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/rjj8azcb\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/v52\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-20230914_002346-rjj8azcb/logs\u001b[0m\r\n" + "\u001b[34m\u001b[1mwandb\u001b[0m: 🚀 View run \u001b[33mv5r3-L6-D2048-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/9o2jwwvs\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/v54\u001b[0m\r\n", + "\u001b[34m\u001b[1mwandb\u001b[0m: Synced 5 W&B file(s), 0 media file(s), 0 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-20230914_023759-9o2jwwvs/logs\u001b[0m\r\n" ] } ], @@ -4421,19 +4482,19 @@ { "cell_type": "code", "execution_count": 7, - "id": "7c6294af", + "id": "6db19b87", "metadata": { "execution": { - "iopub.execute_input": "2023-09-14T00:24:09.519443Z", - "iopub.status.busy": "2023-09-14T00:24:09.518429Z", - "iopub.status.idle": "2023-09-14T00:24:13.424492Z", - "shell.execute_reply": "2023-09-14T00:24:13.423305Z" + "iopub.execute_input": "2023-09-14T02:38:21.728358Z", + "iopub.status.busy": "2023-09-14T02:38:21.727768Z", + "iopub.status.idle": "2023-09-14T02:38:25.677206Z", + "shell.execute_reply": "2023-09-14T02:38:25.676074Z" }, "papermill": { - "duration": 3.942579, - "end_time": "2023-09-14T00:24:13.426912", + "duration": 3.986198, + "end_time": "2023-09-14T02:38:25.679730", "exception": false, - "start_time": "2023-09-14T00:24:09.484333", + "start_time": "2023-09-14T02:38:21.693532", "status": "completed" }, "tags": [] @@ -4443,7 +4504,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "[2023-09-14 00:24:11,902] [INFO] [real_accelerator.py:133:get_accelerator] Setting ds_accelerator to cuda (auto detect)\r\n" + "[2023-09-14 02:38:24,136] [INFO] [real_accelerator.py:133:get_accelerator] Setting ds_accelerator to cuda (auto detect)\r\n" ] }, { @@ -4480,19 +4541,19 @@ { "cell_type": "code", "execution_count": 8, - "id": "959cb71d", + "id": "ec391cb3", "metadata": { "execution": { - "iopub.execute_input": "2023-09-14T00:24:13.493646Z", - "iopub.status.busy": "2023-09-14T00:24:13.493200Z", - "iopub.status.idle": "2023-09-14T00:24:13.760260Z", - "shell.execute_reply": "2023-09-14T00:24:13.759053Z" + "iopub.execute_input": "2023-09-14T02:38:25.748202Z", + "iopub.status.busy": "2023-09-14T02:38:25.747247Z", + "iopub.status.idle": "2023-09-14T02:38:26.013713Z", + "shell.execute_reply": "2023-09-14T02:38:26.012573Z" }, "papermill": { - "duration": 0.303638, - "end_time": "2023-09-14T00:24:13.762669", + "duration": 0.303358, + "end_time": "2023-09-14T02:38:26.016073", "exception": false, - "start_time": "2023-09-14T00:24:13.459031", + "start_time": "2023-09-14T02:38:25.712715", "status": "completed" }, "tags": [] @@ -4514,19 +4575,19 @@ { "cell_type": "code", "execution_count": 9, - "id": "c39913f9", + "id": "2748101d", "metadata": { "execution": { - "iopub.execute_input": "2023-09-14T00:24:13.829059Z", - "iopub.status.busy": "2023-09-14T00:24:13.828546Z", - "iopub.status.idle": "2023-09-14T00:24:14.094937Z", - "shell.execute_reply": "2023-09-14T00:24:14.093719Z" + "iopub.execute_input": "2023-09-14T02:38:26.085118Z", + "iopub.status.busy": "2023-09-14T02:38:26.084169Z", + "iopub.status.idle": "2023-09-14T02:38:26.352535Z", + "shell.execute_reply": "2023-09-14T02:38:26.351341Z" }, "papermill": { - "duration": 0.302801, - "end_time": "2023-09-14T00:24:14.097341", + "duration": 0.305573, + "end_time": "2023-09-14T02:38:26.354898", "exception": false, - "start_time": "2023-09-14T00:24:13.794540", + "start_time": "2023-09-14T02:38:26.049325", "status": "completed" }, "tags": [] @@ -4565,14 +4626,14 @@ }, "papermill": { "default_parameters": {}, - "duration": 87.06318, - "end_time": "2023-09-14T00:24:14.449806", + "duration": 83.790874, + "end_time": "2023-09-14T02:38:26.808961", "environment_variables": {}, "exception": null, "input_path": "/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/notebook/experiment/rwkv-x-exp/v5-r3-memory/L6-D2048-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-D2048-E1e-1-ctx4k/stage3.ipynb", "parameters": {}, - "start_time": "2023-09-14T00:22:47.386626", + "start_time": "2023-09-14T02:37:03.018087", "version": "2.4.0" } },