diff --git "a/experiment/rwkv-x-exp/v5-memory/v5-L96-D1024-E1e-1-ctx4k-part4.ipynb" "b/experiment/rwkv-x-exp/v5-memory/v5-L96-D1024-E1e-1-ctx4k-part4.ipynb"
--- "a/experiment/rwkv-x-exp/v5-memory/v5-L96-D1024-E1e-1-ctx4k-part4.ipynb"
+++ "b/experiment/rwkv-x-exp/v5-memory/v5-L96-D1024-E1e-1-ctx4k-part4.ipynb"
@@ -3,13 +3,13 @@
   {
    "attachments": {},
    "cell_type": "markdown",
-   "id": "d2fa5a0c",
+   "id": "61a25afb",
    "metadata": {
     "papermill": {
-     "duration": 0.002706,
-     "end_time": "2023-09-01T13:53:29.614438",
+     "duration": 0.0025,
+     "end_time": "2023-09-01T14:29:53.361768",
      "exception": false,
-     "start_time": "2023-09-01T13:53:29.611732",
+     "start_time": "2023-09-01T14:29:53.359268",
      "status": "completed"
     },
     "tags": []
@@ -28,13 +28,13 @@
   {
    "attachments": {},
    "cell_type": "markdown",
-   "id": "d1743e66",
+   "id": "faebc84d",
    "metadata": {
     "papermill": {
-     "duration": 0.001587,
-     "end_time": "2023-09-01T13:53:29.618012",
+     "duration": 0.001611,
+     "end_time": "2023-09-01T14:29:53.365367",
      "exception": false,
-     "start_time": "2023-09-01T13:53:29.616425",
+     "start_time": "2023-09-01T14:29:53.363756",
      "status": "completed"
     },
     "tags": []
@@ -46,19 +46,19 @@
   {
    "cell_type": "code",
    "execution_count": 1,
-   "id": "68c7f316",
+   "id": "1a35f622",
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2023-09-01T13:53:29.622767Z",
-     "iopub.status.busy": "2023-09-01T13:53:29.622230Z",
-     "iopub.status.idle": "2023-09-01T13:53:30.334524Z",
-     "shell.execute_reply": "2023-09-01T13:53:30.333763Z"
+     "iopub.execute_input": "2023-09-01T14:29:53.369695Z",
+     "iopub.status.busy": "2023-09-01T14:29:53.369518Z",
+     "iopub.status.idle": "2023-09-01T14:29:54.099056Z",
+     "shell.execute_reply": "2023-09-01T14:29:54.098006Z"
     },
     "papermill": {
-     "duration": 0.716371,
-     "end_time": "2023-09-01T13:53:30.336141",
+     "duration": 0.733769,
+     "end_time": "2023-09-01T14:29:54.100913",
      "exception": false,
-     "start_time": "2023-09-01T13:53:29.619770",
+     "start_time": "2023-09-01T14:29:53.367144",
      "status": "completed"
     },
     "tags": []
@@ -74,19 +74,19 @@
   {
    "cell_type": "code",
    "execution_count": 2,
-   "id": "2e1d43a7",
+   "id": "4c1c27c2",
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2023-09-01T13:53:30.341499Z",
-     "iopub.status.busy": "2023-09-01T13:53:30.340733Z",
-     "iopub.status.idle": "2023-09-01T13:53:33.246194Z",
-     "shell.execute_reply": "2023-09-01T13:53:33.245609Z"
+     "iopub.execute_input": "2023-09-01T14:29:54.105696Z",
+     "iopub.status.busy": "2023-09-01T14:29:54.105496Z",
+     "iopub.status.idle": "2023-09-01T14:29:56.998968Z",
+     "shell.execute_reply": "2023-09-01T14:29:56.998026Z"
     },
     "papermill": {
-     "duration": 2.909393,
-     "end_time": "2023-09-01T13:53:33.247544",
+     "duration": 2.897843,
+     "end_time": "2023-09-01T14:29:57.000715",
      "exception": false,
-     "start_time": "2023-09-01T13:53:30.338151",
+     "start_time": "2023-09-01T14:29:54.102872",
      "status": "completed"
     },
     "tags": []
@@ -118,19 +118,19 @@
   {
    "cell_type": "code",
    "execution_count": 3,
-   "id": "83f5425d",
+   "id": "2a370570",
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2023-09-01T13:53:33.252815Z",
-     "iopub.status.busy": "2023-09-01T13:53:33.252627Z",
-     "iopub.status.idle": "2023-09-01T13:53:33.259073Z",
-     "shell.execute_reply": "2023-09-01T13:53:33.258537Z"
+     "iopub.execute_input": "2023-09-01T14:29:57.005910Z",
+     "iopub.status.busy": "2023-09-01T14:29:57.005718Z",
+     "iopub.status.idle": "2023-09-01T14:29:57.012155Z",
+     "shell.execute_reply": "2023-09-01T14:29:57.011618Z"
     },
     "papermill": {
-     "duration": 0.010424,
-     "end_time": "2023-09-01T13:53:33.260232",
+     "duration": 0.010415,
+     "end_time": "2023-09-01T14:29:57.013297",
      "exception": false,
-     "start_time": "2023-09-01T13:53:33.249808",
+     "start_time": "2023-09-01T14:29:57.002882",
      "status": "completed"
     },
     "tags": []
@@ -193,19 +193,19 @@
   {
    "cell_type": "code",
    "execution_count": 4,
-   "id": "bf354550",
+   "id": "d92e9387",
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2023-09-01T13:53:33.265011Z",
-     "iopub.status.busy": "2023-09-01T13:53:33.264853Z",
-     "iopub.status.idle": "2023-09-01T13:54:48.438087Z",
-     "shell.execute_reply": "2023-09-01T13:54:48.437420Z"
+     "iopub.execute_input": "2023-09-01T14:29:57.019137Z",
+     "iopub.status.busy": "2023-09-01T14:29:57.018963Z",
+     "iopub.status.idle": "2023-09-01T14:30:45.517596Z",
+     "shell.execute_reply": "2023-09-01T14:30:45.516964Z"
     },
     "papermill": {
-     "duration": 75.177229,
-     "end_time": "2023-09-01T13:54:48.439498",
+     "duration": 48.503927,
+     "end_time": "2023-09-01T14:30:45.519409",
      "exception": false,
-     "start_time": "2023-09-01T13:53:33.262269",
+     "start_time": "2023-09-01T14:29:57.015482",
      "status": "completed"
     },
     "tags": []
@@ -215,16 +215,15 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "--2023-09-01 13:53:33--  https://huggingface.co/rwkv-x-dev/rwkv-x-playground/resolve/main/experiment/rwkv-x-exp/v5-memory/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/v5-L96-D1024-E0_1-mem-ctx-2k.pth\r\n",
-      "Resolving huggingface.co (huggingface.co)... 18.165.122.30, 18.165.122.11, 18.165.122.120, ...\r\n",
-      "Connecting to huggingface.co (huggingface.co)|18.165.122.30|:443... "
+      "--2023-09-01 14:29:57--  https://huggingface.co/rwkv-x-dev/rwkv-x-playground/resolve/main/experiment/rwkv-x-exp/v5-memory/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/v5-L96-D1024-E0_1-mem-ctx-2k.pth\r\n",
+      "Resolving huggingface.co (huggingface.co)... 18.165.122.11, 18.165.122.120, 18.165.122.101, ...\r\n",
+      "Connecting to huggingface.co (huggingface.co)|18.165.122.11|:443... connected.\r\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "connected.\r\n",
       "HTTP request sent, awaiting response... "
      ]
     },
@@ -233,8 +232,8 @@
      "output_type": "stream",
      "text": [
       "302 Found\r\n",
-      "Location: https://cdn-lfs.huggingface.co/repos/2e/f7/2ef78555202aa92abdbdf476ce3d0fd5a8b15f7245edf0b80d4d30572355f30d/8ce9e4f8e10ab705b4705845936ac1ff97e2d060a5d29f1d209a510c59435b3c?response-content-disposition=attachment%3B+filename*%3DUTF-8%27%27v5-L96-D1024-E0_1-mem-ctx-2k.pth%3B+filename%3D%22v5-L96-D1024-E0_1-mem-ctx-2k.pth%22%3B&Expires=1693835613&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTY5MzgzNTYxM319LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy5odWdnaW5nZmFjZS5jby9yZXBvcy8yZS9mNy8yZWY3ODU1NTIwMmFhOTJhYmRiZGY0NzZjZTNkMGZkNWE4YjE1ZjcyNDVlZGYwYjgwZDRkMzA1NzIzNTVmMzBkLzhjZTllNGY4ZTEwYWI3MDViNDcwNTg0NTkzNmFjMWZmOTdlMmQwNjBhNWQyOWYxZDIwOWE1MTBjNTk0MzViM2M%7EcmVzcG9uc2UtY29udGVudC1kaXNwb3NpdGlvbj0qIn1dfQ__&Signature=y1iEXXhkyzbeMhU8fhdyvpqJ2Psd0LlEMfE6DKBP8kCeZTnF%7EVrB8I2ax-4Yt3LMLwPIYfUqBWY-mHzTABBfUyD7kXaM3YeKd-KePcd-oxS1O706bLh5YqO9KO3my9r7lJqrdevHpQvgoF5MGaTkT265oXvIgSXHuPp1mP%7Ejg7S-GrJGNsgoDcEjKEmNaCvTalz%7EGpetmIx3g1AgWxFFXpOWlZ%7EC8eurmlyG3RaRzIMyJJUuaN0JhbthqoYSfsbKwd2cCyq43qa-Njj3RtqtB5nbVaSgmV0yoExxngWzEBegKD5Uu2io3uWMDWKaZUV4Pi%7E%7EHavgMuUWAgieAu7ROw__&Key-Pair-Id=KVTP0A1DKRTAX [following]\r\n",
-      "--2023-09-01 13:53:33--  https://cdn-lfs.huggingface.co/repos/2e/f7/2ef78555202aa92abdbdf476ce3d0fd5a8b15f7245edf0b80d4d30572355f30d/8ce9e4f8e10ab705b4705845936ac1ff97e2d060a5d29f1d209a510c59435b3c?response-content-disposition=attachment%3B+filename*%3DUTF-8%27%27v5-L96-D1024-E0_1-mem-ctx-2k.pth%3B+filename%3D%22v5-L96-D1024-E0_1-mem-ctx-2k.pth%22%3B&Expires=1693835613&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTY5MzgzNTYxM319LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy5odWdnaW5nZmFjZS5jby9yZXBvcy8yZS9mNy8yZWY3ODU1NTIwMmFhOTJhYmRiZGY0NzZjZTNkMGZkNWE4YjE1ZjcyNDVlZGYwYjgwZDRkMzA1NzIzNTVmMzBkLzhjZTllNGY4ZTEwYWI3MDViNDcwNTg0NTkzNmFjMWZmOTdlMmQwNjBhNWQyOWYxZDIwOWE1MTBjNTk0MzViM2M%7EcmVzcG9uc2UtY29udGVudC1kaXNwb3NpdGlvbj0qIn1dfQ__&Signature=y1iEXXhkyzbeMhU8fhdyvpqJ2Psd0LlEMfE6DKBP8kCeZTnF%7EVrB8I2ax-4Yt3LMLwPIYfUqBWY-mHzTABBfUyD7kXaM3YeKd-KePcd-oxS1O706bLh5YqO9KO3my9r7lJqrdevHpQvgoF5MGaTkT265oXvIgSXHuPp1mP%7Ejg7S-GrJGNsgoDcEjKEmNaCvTalz%7EGpetmIx3g1AgWxFFXpOWlZ%7EC8eurmlyG3RaRzIMyJJUuaN0JhbthqoYSfsbKwd2cCyq43qa-Njj3RtqtB5nbVaSgmV0yoExxngWzEBegKD5Uu2io3uWMDWKaZUV4Pi%7E%7EHavgMuUWAgieAu7ROw__&Key-Pair-Id=KVTP0A1DKRTAX\r\n",
+      "Location: https://cdn-lfs.huggingface.co/repos/2e/f7/2ef78555202aa92abdbdf476ce3d0fd5a8b15f7245edf0b80d4d30572355f30d/8ce9e4f8e10ab705b4705845936ac1ff97e2d060a5d29f1d209a510c59435b3c?response-content-disposition=attachment%3B+filename*%3DUTF-8%27%27v5-L96-D1024-E0_1-mem-ctx-2k.pth%3B+filename%3D%22v5-L96-D1024-E0_1-mem-ctx-2k.pth%22%3B&Expires=1693837797&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTY5MzgzNzc5N319LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy5odWdnaW5nZmFjZS5jby9yZXBvcy8yZS9mNy8yZWY3ODU1NTIwMmFhOTJhYmRiZGY0NzZjZTNkMGZkNWE4YjE1ZjcyNDVlZGYwYjgwZDRkMzA1NzIzNTVmMzBkLzhjZTllNGY4ZTEwYWI3MDViNDcwNTg0NTkzNmFjMWZmOTdlMmQwNjBhNWQyOWYxZDIwOWE1MTBjNTk0MzViM2M%7EcmVzcG9uc2UtY29udGVudC1kaXNwb3NpdGlvbj0qIn1dfQ__&Signature=Oj3cBs20M1l5xhL-lcvqDUDPZuZTfgBbqIzqFpODlirkCJW-mMDRtGQ0Q9a7cB7ARNrzzd9Yk5I%7ETlLT%7E8zakkO6YaRYVem9GpWWSnfSlfbAvhgK5eXNdhAYPdXYxFVN%7E9wVpYRos6vAvDbIteUio2i2%7E4uC%7EuYYBdjReu6eNcjawkte9N-cEbaABvbAUsChE2wDh8lZebMqPNq7Jdtg9asXY7hZBBaCtih1XtaMshRhqwRpU64CyM%7E2mk6dy4Or8HfZrP05l4vXZ4H0ME9ylwE8aOlsvsHtSt8FdcrhvndbOYc2NmkJRiAkzEZPUVWHqZ6uS91EDtJWDK%7Exo5wYbA__&Key-Pair-Id=KVTP0A1DKRTAX [following]\r\n",
+      "--2023-09-01 14:29:57--  https://cdn-lfs.huggingface.co/repos/2e/f7/2ef78555202aa92abdbdf476ce3d0fd5a8b15f7245edf0b80d4d30572355f30d/8ce9e4f8e10ab705b4705845936ac1ff97e2d060a5d29f1d209a510c59435b3c?response-content-disposition=attachment%3B+filename*%3DUTF-8%27%27v5-L96-D1024-E0_1-mem-ctx-2k.pth%3B+filename%3D%22v5-L96-D1024-E0_1-mem-ctx-2k.pth%22%3B&Expires=1693837797&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTY5MzgzNzc5N319LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy5odWdnaW5nZmFjZS5jby9yZXBvcy8yZS9mNy8yZWY3ODU1NTIwMmFhOTJhYmRiZGY0NzZjZTNkMGZkNWE4YjE1ZjcyNDVlZGYwYjgwZDRkMzA1NzIzNTVmMzBkLzhjZTllNGY4ZTEwYWI3MDViNDcwNTg0NTkzNmFjMWZmOTdlMmQwNjBhNWQyOWYxZDIwOWE1MTBjNTk0MzViM2M%7EcmVzcG9uc2UtY29udGVudC1kaXNwb3NpdGlvbj0qIn1dfQ__&Signature=Oj3cBs20M1l5xhL-lcvqDUDPZuZTfgBbqIzqFpODlirkCJW-mMDRtGQ0Q9a7cB7ARNrzzd9Yk5I%7ETlLT%7E8zakkO6YaRYVem9GpWWSnfSlfbAvhgK5eXNdhAYPdXYxFVN%7E9wVpYRos6vAvDbIteUio2i2%7E4uC%7EuYYBdjReu6eNcjawkte9N-cEbaABvbAUsChE2wDh8lZebMqPNq7Jdtg9asXY7hZBBaCtih1XtaMshRhqwRpU64CyM%7E2mk6dy4Or8HfZrP05l4vXZ4H0ME9ylwE8aOlsvsHtSt8FdcrhvndbOYc2NmkJRiAkzEZPUVWHqZ6uS91EDtJWDK%7Exo5wYbA__&Key-Pair-Id=KVTP0A1DKRTAX\r\n",
       "Resolving cdn-lfs.huggingface.co (cdn-lfs.huggingface.co)... "
      ]
     },
@@ -242,8 +241,14 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "108.157.214.46, 108.157.214.7, 108.157.214.82, ...\r\n",
-      "Connecting to cdn-lfs.huggingface.co (cdn-lfs.huggingface.co)|108.157.214.46|:443... connected.\r\n",
+      "108.157.214.7, 108.157.214.82, 108.157.214.31, ...\r\n",
+      "Connecting to cdn-lfs.huggingface.co (cdn-lfs.huggingface.co)|108.157.214.7|:443... connected.\r\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
       "HTTP request sent, awaiting response... "
      ]
     },
@@ -264,7 +269,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "         v5-L96-D10   0%[                    ] 126.27K   456KB/s               "
+      "         v5-L96-D10   0%[                    ]   3.99M  19.6MB/s               "
      ]
     },
     {
@@ -272,7 +277,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "        v5-L96-D102   0%[                    ]   1.09M  2.30MB/s               "
+      "        v5-L96-D102   0%[                    ]  10.66M  25.4MB/s               "
      ]
     },
     {
@@ -280,7 +285,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "       v5-L96-D1024   0%[                    ]   3.76M  5.56MB/s               "
+      "       v5-L96-D1024   0%[                    ]  21.19M  33.8MB/s               "
      ]
     },
     {
@@ -288,7 +293,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "      v5-L96-D1024-   0%[                    ]  11.06M  12.3MB/s               "
+      "      v5-L96-D1024-   1%[                    ]  31.80M  38.4MB/s               "
      ]
     },
     {
@@ -296,7 +301,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "     v5-L96-D1024-E   0%[                    ]  17.01M  15.5MB/s               "
+      "     v5-L96-D1024-E   1%[                    ]  42.83M  41.7MB/s               "
      ]
     },
     {
@@ -304,7 +309,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "    v5-L96-D1024-E0   0%[                    ]  24.81M  19.1MB/s               "
+      "    v5-L96-D1024-E0   1%[                    ]  52.52M  42.8MB/s               "
      ]
     },
     {
@@ -312,7 +317,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "   v5-L96-D1024-E0_   1%[                    ]  34.27M  22.4MB/s               "
+      "   v5-L96-D1024-E0_   2%[                    ]  62.17M  43.5MB/s               "
      ]
     },
     {
@@ -320,7 +325,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "  v5-L96-D1024-E0_1   1%[                    ]  44.70M  25.5MB/s               "
+      "  v5-L96-D1024-E0_1   2%[                    ]  72.74M  44.7MB/s               "
      ]
     },
     {
@@ -328,7 +333,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      " v5-L96-D1024-E0_1-   1%[                    ]  52.32M  26.4MB/s               "
+      " v5-L96-D1024-E0_1-   3%[                    ]  88.50M  48.4MB/s               "
      ]
     },
     {
@@ -336,7 +341,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "v5-L96-D1024-E0_1-m   2%[                    ]  62.43M  28.6MB/s               "
+      "v5-L96-D1024-E0_1-m   3%[                    ]  99.19M  48.7MB/s               "
      ]
     },
     {
@@ -344,7 +349,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "5-L96-D1024-E0_1-me   2%[                    ]  70.80M  29.7MB/s               "
+      "5-L96-D1024-E0_1-me   4%[                    ] 111.10M  49.4MB/s               "
      ]
     },
     {
@@ -352,7 +357,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "-L96-D1024-E0_1-mem   2%[                    ]  78.79M  29.6MB/s               "
+      "-L96-D1024-E0_1-mem   4%[                    ] 124.07M  50.2MB/s               "
      ]
     },
     {
@@ -360,7 +365,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "L96-D1024-E0_1-mem-   3%[                    ]  90.25M  31.5MB/s               "
+      "L96-D1024-E0_1-mem-   5%[>                   ] 136.08M  50.8MB/s               "
      ]
     },
     {
@@ -368,7 +373,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "96-D1024-E0_1-mem-c   3%[                    ]  98.28M  32.1MB/s    eta 81s    "
+      "96-D1024-E0_1-mem-c   5%[>                   ] 146.83M  51.0MB/s               "
      ]
     },
     {
@@ -376,7 +381,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "6-D1024-E0_1-mem-ct   3%[                    ] 106.09M  32.4MB/s    eta 81s    "
+      "6-D1024-E0_1-mem-ct   5%[>                   ] 161.35M  52.4MB/s    eta 48s    "
      ]
     },
     {
@@ -384,7 +389,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "-D1024-E0_1-mem-ctx   4%[                    ] 114.38M  34.7MB/s    eta 81s    "
+      "-D1024-E0_1-mem-ctx   6%[>                   ] 173.13M  54.4MB/s    eta 48s    "
      ]
     },
     {
@@ -392,7 +397,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "D1024-E0_1-mem-ctx-   4%[                    ] 123.90M  37.0MB/s    eta 81s    "
+      "D1024-E0_1-mem-ctx-   6%[>                   ] 181.08M  54.6MB/s    eta 48s    "
      ]
     },
     {
@@ -400,7 +405,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "1024-E0_1-mem-ctx-2   4%[                    ] 132.07M  39.0MB/s    eta 81s    "
+      "1024-E0_1-mem-ctx-2   7%[>                   ] 194.72M  56.3MB/s    eta 48s    "
      ]
     },
     {
@@ -408,7 +413,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "024-E0_1-mem-ctx-2k   5%[>                   ] 140.23M  40.2MB/s    eta 75s    "
+      "024-E0_1-mem-ctx-2k   7%[>                   ] 208.39M  56.7MB/s    eta 48s    "
      ]
     },
     {
@@ -416,7 +421,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "24-E0_1-mem-ctx-2k.   5%[>                   ] 147.93M  40.7MB/s    eta 75s    "
+      "24-E0_1-mem-ctx-2k.   8%[>                   ] 223.11M  57.9MB/s    eta 46s    "
      ]
     },
     {
@@ -424,7 +429,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "4-E0_1-mem-ctx-2k.p   5%[>                   ] 155.70M  40.0MB/s    eta 75s    "
+      "4-E0_1-mem-ctx-2k.p   8%[>                   ] 233.50M  58.4MB/s    eta 46s    "
      ]
     },
     {
@@ -432,7 +437,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "-E0_1-mem-ctx-2k.pt   5%[>                   ] 160.21M  38.6MB/s    eta 75s    "
+      "-E0_1-mem-ctx-2k.pt   9%[>                   ] 245.26M  58.7MB/s    eta 46s    "
      ]
     },
     {
@@ -440,7 +445,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "E0_1-mem-ctx-2k.pth   6%[>                   ] 170.81M  39.2MB/s    eta 75s    "
+      "E0_1-mem-ctx-2k.pth   9%[>                   ] 257.88M  59.2MB/s    eta 46s    "
      ]
     },
     {
@@ -448,7 +453,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "0_1-mem-ctx-2k.pth    6%[>                   ] 176.98M  38.8MB/s    eta 74s    "
+      "0_1-mem-ctx-2k.pth   10%[=>                  ] 270.60M  57.8MB/s    eta 46s    "
      ]
     },
     {
@@ -456,7 +461,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "_1-mem-ctx-2k.pth     6%[>                   ] 186.16M  39.7MB/s    eta 74s    "
+      "_1-mem-ctx-2k.pth    10%[=>                  ] 283.37M  58.1MB/s    eta 44s    "
      ]
     },
     {
@@ -464,7 +469,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "1-mem-ctx-2k.pth      7%[>                   ] 195.69M  40.1MB/s    eta 74s    "
+      "1-mem-ctx-2k.pth     10%[=>                  ] 295.02M  58.0MB/s    eta 44s    "
      ]
     },
     {
@@ -472,7 +477,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "-mem-ctx-2k.pth       7%[>                   ] 202.26M  39.5MB/s    eta 74s    "
+      "-mem-ctx-2k.pth      11%[=>                  ] 306.49M  58.0MB/s    eta 44s    "
      ]
     },
     {
@@ -480,7 +485,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "mem-ctx-2k.pth        7%[>                   ] 210.82M  38.8MB/s    eta 74s    "
+      "mem-ctx-2k.pth       11%[=>                  ] 320.15M  59.1MB/s    eta 44s    "
      ]
     },
     {
@@ -488,7 +493,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "em-ctx-2k.pth         8%[>                   ] 219.09M  39.1MB/s    eta 70s    "
+      "em-ctx-2k.pth        12%[=>                  ] 332.47M  58.9MB/s    eta 44s    "
      ]
     },
     {
@@ -496,7 +501,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "m-ctx-2k.pth          8%[>                   ] 227.65M  38.6MB/s    eta 70s    "
+      "m-ctx-2k.pth         12%[=>                  ] 348.19M  60.9MB/s    eta 42s    "
      ]
     },
     {
@@ -504,7 +509,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "-ctx-2k.pth           8%[>                   ] 236.63M  38.6MB/s    eta 70s    "
+      "-ctx-2k.pth          13%[=>                  ] 361.80M  61.1MB/s    eta 42s    "
      ]
     },
     {
@@ -512,7 +517,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "ctx-2k.pth            9%[>                   ] 244.56M  38.6MB/s    eta 70s    "
+      "ctx-2k.pth           13%[=>                  ] 374.68M  61.3MB/s    eta 42s    "
      ]
     },
     {
@@ -520,7 +525,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "tx-2k.pth             9%[>                   ] 252.80M  38.4MB/s    eta 70s    "
+      "tx-2k.pth            14%[=>                  ] 385.51M  61.4MB/s    eta 42s    "
      ]
     },
     {
@@ -528,7 +533,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "x-2k.pth              9%[>                   ] 260.78M  38.7MB/s    eta 68s    "
+      "x-2k.pth             14%[=>                  ] 397.08M  60.3MB/s    eta 42s    "
      ]
     },
     {
@@ -536,7 +541,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "-2k.pth               9%[>                   ] 268.82M  38.6MB/s    eta 68s    "
+      "-2k.pth              15%[==>                 ] 408.65M  59.6MB/s    eta 41s    "
      ]
     },
     {
@@ -544,7 +549,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "2k.pth               10%[=>                  ] 279.51M  39.1MB/s    eta 68s    "
+      "2k.pth               15%[==>                 ] 419.96M  59.2MB/s    eta 41s    "
      ]
     },
     {
@@ -552,7 +557,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "k.pth                10%[=>                  ] 287.58M  39.6MB/s    eta 68s    "
+      "k.pth                16%[==>                 ] 433.00M  58.9MB/s    eta 41s    "
      ]
     },
     {
@@ -560,7 +565,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      ".pth                 10%[=>                  ] 296.22M  40.1MB/s    eta 68s    "
+      ".pth                 16%[==>                 ] 445.07M  58.7MB/s    eta 41s    "
      ]
     },
     {
@@ -568,7 +573,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "pth                  11%[=>                  ] 305.86M  40.9MB/s    eta 65s    "
+      "pth                  17%[==>                 ] 458.75M  59.3MB/s    eta 41s    "
      ]
     },
     {
@@ -576,7 +581,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "th                   11%[=>                  ] 312.43M  40.5MB/s    eta 65s    "
+      "th                   17%[==>                 ] 470.07M  58.5MB/s    eta 40s    "
      ]
     },
     {
@@ -584,7 +589,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "h                    11%[=>                  ] 319.91M  39.6MB/s    eta 65s    "
+      "h                    17%[==>                 ] 483.07M  59.4MB/s    eta 40s    "
      ]
     },
     {
@@ -592,7 +597,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "                     12%[=>                  ] 327.55M  39.3MB/s    eta 65s    "
+      "                     18%[==>                 ] 496.15M  60.1MB/s    eta 40s    "
      ]
     },
     {
@@ -600,7 +605,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "                  v  12%[=>                  ] 334.98M  39.4MB/s    eta 65s    "
+      "                  v  18%[==>                 ] 508.07M  59.9MB/s    eta 40s    "
      ]
     },
     {
@@ -608,7 +613,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "                 v5  12%[=>                  ] 342.82M  39.2MB/s    eta 65s    "
+      "                 v5  19%[==>                 ] 519.06M  59.0MB/s    eta 40s    "
      ]
     },
     {
@@ -616,7 +621,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "                v5-  13%[=>                  ] 353.23M  40.1MB/s    eta 65s    "
+      "                v5-  19%[==>                 ] 530.18M  57.3MB/s    eta 38s    "
      ]
     },
     {
@@ -624,7 +629,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "               v5-L  13%[=>                  ] 358.48M  38.9MB/s    eta 65s    "
+      "               v5-L  20%[===>                ] 541.83M  56.1MB/s    eta 38s    "
      ]
     },
     {
@@ -632,7 +637,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "              v5-L9  13%[=>                  ] 368.75M  38.8MB/s    eta 65s    "
+      "              v5-L9  20%[===>                ] 554.81M  56.6MB/s    eta 38s    "
      ]
     },
     {
@@ -640,7 +645,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "             v5-L96  13%[=>                  ] 377.00M  39.5MB/s    eta 65s    "
+      "             v5-L96  20%[===>                ] 563.83M  56.3MB/s    eta 38s    "
      ]
     },
     {
@@ -648,7 +653,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "            v5-L96-  14%[=>                  ] 385.15M  39.1MB/s    eta 62s    "
+      "            v5-L96-  21%[===>                ] 574.13M  55.3MB/s    eta 38s    "
      ]
     },
     {
@@ -656,7 +661,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "           v5-L96-D  14%[=>                  ] 393.70M  39.7MB/s    eta 62s    "
+      "           v5-L96-D  21%[===>                ] 581.91M  54.7MB/s    eta 38s    "
      ]
     },
     {
@@ -664,7 +669,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "          v5-L96-D1  14%[=>                  ] 401.40M  39.1MB/s    eta 62s    "
+      "          v5-L96-D1  21%[===>                ] 582.27M  51.7MB/s    eta 38s    "
      ]
     },
     {
@@ -672,7 +677,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "         v5-L96-D10  15%[==>                 ] 409.40M  38.6MB/s    eta 62s    "
+      "         v5-L96-D10  21%[===>                ] 590.72M  50.5MB/s    eta 38s    "
      ]
     },
     {
@@ -680,7 +685,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "        v5-L96-D102  15%[==>                 ] 419.24M  39.2MB/s    eta 62s    "
+      "        v5-L96-D102  22%[===>                ] 599.21M  49.3MB/s    eta 38s    "
      ]
     },
     {
@@ -688,7 +693,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "       v5-L96-D1024  15%[==>                 ] 426.04M  38.4MB/s    eta 61s    "
+      "       v5-L96-D1024  22%[===>                ] 612.27M  49.1MB/s    eta 38s    "
      ]
     },
     {
@@ -696,7 +701,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "      v5-L96-D1024-  16%[==>                 ] 434.41M  39.2MB/s    eta 61s    "
+      "      v5-L96-D1024-  23%[===>                ] 623.85M  49.8MB/s    eta 38s    "
      ]
     },
     {
@@ -704,7 +709,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "     v5-L96-D1024-E  16%[==>                 ] 442.45M  39.0MB/s    eta 61s    "
+      "     v5-L96-D1024-E  23%[===>                ] 637.04M  50.0MB/s    eta 38s    "
      ]
     },
     {
@@ -712,7 +717,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "    v5-L96-D1024-E0  16%[==>                 ] 451.24M  39.4MB/s    eta 61s    "
+      "    v5-L96-D1024-E0  24%[===>                ] 649.94M  51.1MB/s    eta 38s    "
      ]
     },
     {
@@ -720,7 +725,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "   v5-L96-D1024-E0_  17%[==>                 ] 459.62M  40.3MB/s    eta 61s    "
+      "   v5-L96-D1024-E0_  24%[===>                ] 659.05M  49.4MB/s    eta 38s    "
      ]
     },
     {
@@ -728,7 +733,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "  v5-L96-D1024-E0_1  17%[==>                 ] 466.82M  40.1MB/s    eta 60s    "
+      "  v5-L96-D1024-E0_1  24%[===>                ] 671.48M  50.4MB/s    eta 38s    "
      ]
     },
     {
@@ -736,7 +741,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      " v5-L96-D1024-E0_1-  17%[==>                 ] 475.33M  40.3MB/s    eta 60s    "
+      " v5-L96-D1024-E0_1-  25%[====>               ] 682.12M  49.7MB/s    eta 37s    "
      ]
     },
     {
@@ -744,7 +749,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "v5-L96-D1024-E0_1-m  17%[==>                 ] 482.72M  40.2MB/s    eta 60s    "
+      "v5-L96-D1024-E0_1-m  25%[====>               ] 694.30M  50.5MB/s    eta 37s    "
      ]
     },
     {
@@ -752,7 +757,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "5-L96-D1024-E0_1-me  18%[==>                 ] 491.76M  40.0MB/s    eta 60s    "
+      "5-L96-D1024-E0_1-me  26%[====>               ] 706.79M  50.5MB/s    eta 37s    "
      ]
     },
     {
@@ -760,7 +765,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "-L96-D1024-E0_1-mem  18%[==>                 ] 500.03M  39.9MB/s    eta 60s    "
+      "-L96-D1024-E0_1-mem  26%[====>               ] 718.11M  50.9MB/s    eta 37s    "
      ]
     },
     {
@@ -768,7 +773,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "L96-D1024-E0_1-mem-  18%[==>                 ] 508.20M  39.6MB/s    eta 58s    "
+      "L96-D1024-E0_1-mem-  27%[====>               ] 729.46M  51.7MB/s    eta 37s    "
      ]
     },
     {
@@ -776,7 +781,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "96-D1024-E0_1-mem-c  19%[==>                 ] 513.22M  38.6MB/s    eta 58s    "
+      "96-D1024-E0_1-mem-c  27%[====>               ] 740.72M  51.8MB/s    eta 35s    "
      ]
     },
     {
@@ -784,7 +789,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "6-D1024-E0_1-mem-ct  19%[==>                 ] 523.46M  38.8MB/s    eta 58s    "
+      "6-D1024-E0_1-mem-ct  27%[====>               ] 754.58M  56.8MB/s    eta 35s    "
      ]
     },
     {
@@ -792,7 +797,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "-D1024-E0_1-mem-ctx  19%[==>                 ] 530.92M  38.8MB/s    eta 58s    "
+      "-D1024-E0_1-mem-ctx  28%[====>               ] 770.62M  59.2MB/s    eta 35s    "
      ]
     },
     {
@@ -800,7 +805,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "D1024-E0_1-mem-ctx-  20%[===>                ] 539.69M  38.8MB/s    eta 58s    "
+      "D1024-E0_1-mem-ctx-  29%[====>               ] 784.93M  60.5MB/s    eta 35s    "
      ]
     },
     {
@@ -808,7 +813,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "1024-E0_1-mem-ctx-2  20%[===>                ] 549.73M  39.1MB/s    eta 57s    "
+      "1024-E0_1-mem-ctx-2  29%[====>               ] 796.29M  60.8MB/s    eta 35s    "
      ]
     },
     {
@@ -816,7 +821,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "024-E0_1-mem-ctx-2k  20%[===>                ] 557.96M  39.4MB/s    eta 57s    "
+      "024-E0_1-mem-ctx-2k  29%[====>               ] 805.85M  59.8MB/s    eta 34s    "
      ]
     },
     {
@@ -824,7 +829,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "24-E0_1-mem-ctx-2k.  21%[===>                ] 565.96M  39.3MB/s    eta 57s    "
+      "24-E0_1-mem-ctx-2k.  30%[=====>              ] 814.11M  58.2MB/s    eta 34s    "
      ]
     },
     {
@@ -832,7 +837,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "4-E0_1-mem-ctx-2k.p  21%[===>                ] 572.79M  39.0MB/s    eta 57s    "
+      "4-E0_1-mem-ctx-2k.p  30%[=====>              ] 822.72M  57.0MB/s    eta 34s    "
      ]
     },
     {
@@ -840,7 +845,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "-E0_1-mem-ctx-2k.pt  21%[===>                ] 580.84M  38.6MB/s    eta 57s    "
+      "-E0_1-mem-ctx-2k.pt  30%[=====>              ] 831.16M  56.0MB/s    eta 34s    "
      ]
     },
     {
@@ -848,7 +853,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "E0_1-mem-ctx-2k.pth  21%[===>                ] 588.87M  38.6MB/s    eta 56s    "
+      "E0_1-mem-ctx-2k.pth  31%[=====>              ] 842.53M  56.4MB/s    eta 34s    "
      ]
     },
     {
@@ -856,7 +861,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "0_1-mem-ctx-2k.pth   22%[===>                ] 599.18M  38.9MB/s    eta 56s    "
+      "0_1-mem-ctx-2k.pth   31%[=====>              ] 858.40M  58.5MB/s    eta 33s    "
      ]
     },
     {
@@ -864,7 +869,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "_1-mem-ctx-2k.pth    22%[===>                ] 607.39M  38.6MB/s    eta 56s    "
+      "_1-mem-ctx-2k.pth    32%[=====>              ] 872.58M  59.2MB/s    eta 33s    "
      ]
     },
     {
@@ -872,7 +877,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "1-mem-ctx-2k.pth     22%[===>                ] 613.70M  38.8MB/s    eta 56s    "
+      "1-mem-ctx-2k.pth     32%[=====>              ] 883.75M  58.7MB/s    eta 33s    "
      ]
     },
     {
@@ -880,7 +885,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "-mem-ctx-2k.pth      23%[===>                ] 622.86M  38.9MB/s    eta 56s    "
+      "-mem-ctx-2k.pth      33%[=====>              ] 899.60M  60.0MB/s    eta 33s    "
      ]
     },
     {
@@ -888,7 +893,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "mem-ctx-2k.pth       23%[===>                ] 632.65M  39.7MB/s    eta 54s    "
+      "mem-ctx-2k.pth       33%[=====>              ] 915.75M  61.6MB/s    eta 33s    "
      ]
     },
     {
@@ -896,7 +901,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "em-ctx-2k.pth        23%[===>                ] 640.77M  39.6MB/s    eta 54s    "
+      "em-ctx-2k.pth        34%[=====>              ] 931.13M  62.9MB/s    eta 31s    "
      ]
     },
     {
@@ -904,7 +909,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "m-ctx-2k.pth         24%[===>                ] 648.71M  39.6MB/s    eta 54s    "
+      "m-ctx-2k.pth         34%[=====>              ] 943.01M  62.9MB/s    eta 31s    "
      ]
     },
     {
@@ -912,7 +917,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "-ctx-2k.pth          24%[===>                ] 657.99M  40.0MB/s    eta 54s    "
+      "-ctx-2k.pth          35%[======>             ] 953.42M  61.9MB/s    eta 31s    "
      ]
     },
     {
@@ -920,7 +925,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "ctx-2k.pth           24%[===>                ] 665.37M  40.3MB/s    eta 54s    "
+      "ctx-2k.pth           35%[======>             ] 964.43M  60.3MB/s    eta 31s    "
      ]
     },
     {
@@ -928,7 +933,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "tx-2k.pth            25%[====>               ] 675.18M  40.3MB/s    eta 53s    "
+      "tx-2k.pth            36%[======>             ] 977.07M  58.9MB/s    eta 31s    "
      ]
     },
     {
@@ -936,7 +941,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "x-2k.pth             25%[====>               ] 683.32M  40.0MB/s    eta 53s    "
+      "x-2k.pth             36%[======>             ] 988.36M  59.6MB/s    eta 30s    "
      ]
     },
     {
@@ -944,7 +949,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "-2k.pth              25%[====>               ] 686.64M  38.2MB/s    eta 53s    "
+      "-2k.pth              37%[======>             ] 999.69M  60.2MB/s    eta 30s    "
      ]
     },
     {
@@ -952,7 +957,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "2k.pth               25%[====>               ] 693.79M  38.2MB/s    eta 53s    "
+      "2k.pth               37%[======>             ]   1011M  60.9MB/s    eta 30s    "
      ]
     },
     {
@@ -960,7 +965,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "k.pth                25%[====>               ] 700.24M  37.5MB/s    eta 53s    "
+      "k.pth                37%[======>             ]   1023M  61.5MB/s    eta 30s    "
      ]
     },
     {
@@ -968,7 +973,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      ".pth                 26%[====>               ] 709.16M  37.4MB/s    eta 53s    "
+      ".pth                 38%[======>             ]   1.01G  63.0MB/s    eta 30s    "
      ]
     },
     {
@@ -976,7 +981,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "pth                  26%[====>               ] 716.36M  37.1MB/s    eta 53s    "
+      "pth                  38%[======>             ]   1.02G  62.0MB/s    eta 29s    "
      ]
     },
     {
@@ -984,7 +989,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "th                   26%[====>               ] 722.48M  36.3MB/s    eta 53s    "
+      "th                   39%[======>             ]   1.03G  61.4MB/s    eta 29s    "
      ]
     },
     {
@@ -992,7 +997,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "h                    27%[====>               ] 730.81M  36.8MB/s    eta 53s    "
+      "h                    39%[======>             ]   1.04G  61.5MB/s    eta 29s    "
      ]
     },
     {
@@ -1000,7 +1005,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "                     27%[====>               ] 737.76M  36.0MB/s    eta 53s    "
+      "                     40%[=======>            ]   1.05G  59.9MB/s    eta 29s    "
      ]
     },
     {
@@ -1008,7 +1013,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "                  v  27%[====>               ] 744.84M  36.0MB/s    eta 52s    "
+      "                  v  40%[=======>            ]   1.07G  58.4MB/s    eta 29s    "
      ]
     },
     {
@@ -1016,7 +1021,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "                 v5  27%[====>               ] 752.23M  35.6MB/s    eta 52s    "
+      "                 v5  41%[=======>            ]   1.08G  57.1MB/s    eta 28s    "
      ]
     },
     {
@@ -1024,7 +1029,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "                v5-  28%[====>               ] 759.08M  35.2MB/s    eta 52s    "
+      "                v5-  41%[=======>            ]   1.09G  56.0MB/s    eta 28s    "
      ]
     },
     {
@@ -1032,7 +1037,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "               v5-L  28%[====>               ] 767.24M  34.8MB/s    eta 52s    "
+      "               v5-L  41%[=======>            ]   1.10G  56.5MB/s    eta 28s    "
      ]
     },
     {
@@ -1040,7 +1045,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "              v5-L9  28%[====>               ] 772.00M  33.6MB/s    eta 52s    "
+      "              v5-L9  42%[=======>            ]   1.12G  56.5MB/s    eta 28s    "
      ]
     },
     {
@@ -1048,7 +1053,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "             v5-L96  28%[====>               ] 781.08M  33.9MB/s    eta 51s    "
+      "             v5-L96  42%[=======>            ]   1.13G  56.4MB/s    eta 28s    "
      ]
     },
     {
@@ -1056,7 +1061,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "            v5-L96-  29%[====>               ] 787.42M  33.8MB/s    eta 51s    "
+      "            v5-L96-  43%[=======>            ]   1.14G  57.3MB/s    eta 27s    "
      ]
     },
     {
@@ -1064,7 +1069,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "           v5-L96-D  29%[====>               ] 788.97M  32.1MB/s    eta 51s    "
+      "           v5-L96-D  43%[=======>            ]   1.14G  53.9MB/s    eta 27s    "
      ]
     },
     {
@@ -1072,7 +1077,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "          v5-L96-D1  29%[====>               ] 802.56M  35.5MB/s    eta 51s    "
+      "          v5-L96-D1  43%[=======>            ]   1.14G  51.1MB/s    eta 27s    "
      ]
     },
     {
@@ -1080,7 +1085,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "         v5-L96-D10  30%[=====>              ] 811.01M  35.4MB/s    eta 51s    "
+      "         v5-L96-D10  43%[=======>            ]   1.16G  50.7MB/s    eta 27s    "
      ]
     },
     {
@@ -1088,7 +1093,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "        v5-L96-D102  30%[=====>              ] 818.01M  35.6MB/s    eta 50s    "
+      "        v5-L96-D102  44%[=======>            ]   1.17G  51.4MB/s    eta 27s    "
      ]
     },
     {
@@ -1096,7 +1101,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "       v5-L96-D1024  30%[=====>              ] 825.19M  35.7MB/s    eta 50s    "
+      "       v5-L96-D1024  44%[=======>            ]   1.18G  52.0MB/s    eta 27s    "
      ]
     },
     {
@@ -1104,7 +1109,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "      v5-L96-D1024-  30%[=====>              ] 832.72M  35.3MB/s    eta 50s    "
+      "      v5-L96-D1024-  45%[========>           ]   1.19G  51.7MB/s    eta 27s    "
      ]
     },
     {
@@ -1112,7 +1117,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "     v5-L96-D1024-E  31%[=====>              ] 841.56M  36.4MB/s    eta 50s    "
+      "     v5-L96-D1024-E  45%[========>           ]   1.21G  51.1MB/s    eta 27s    "
      ]
     },
     {
@@ -1120,7 +1125,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "    v5-L96-D1024-E0  31%[=====>              ] 848.42M  36.0MB/s    eta 50s    "
+      "    v5-L96-D1024-E0  46%[========>           ]   1.22G  50.7MB/s    eta 27s    "
      ]
     },
     {
@@ -1128,7 +1133,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "   v5-L96-D1024-E0_  31%[=====>              ] 856.23M  36.4MB/s    eta 49s    "
+      "   v5-L96-D1024-E0_  46%[========>           ]   1.23G  51.7MB/s    eta 27s    "
      ]
     },
     {
@@ -1136,7 +1141,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "  v5-L96-D1024-E0_1  32%[=====>              ] 864.24M  36.5MB/s    eta 49s    "
+      "  v5-L96-D1024-E0_1  47%[========>           ]   1.24G  51.3MB/s    eta 26s    "
      ]
     },
     {
@@ -1144,7 +1149,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      " v5-L96-D1024-E0_1-  32%[=====>              ] 871.73M  36.2MB/s    eta 49s    "
+      " v5-L96-D1024-E0_1-  47%[========>           ]   1.25G  51.7MB/s    eta 26s    "
      ]
     },
     {
@@ -1152,7 +1157,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "v5-L96-D1024-E0_1-m  32%[=====>              ] 881.64M  37.3MB/s    eta 49s    "
+      "v5-L96-D1024-E0_1-m  48%[========>           ]   1.27G  51.4MB/s    eta 26s    "
      ]
     },
     {
@@ -1160,7 +1165,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "5-L96-D1024-E0_1-me  32%[=====>              ] 889.09M  37.1MB/s    eta 49s    "
+      "5-L96-D1024-E0_1-me  48%[========>           ]   1.28G  51.5MB/s    eta 26s    "
      ]
     },
     {
@@ -1168,7 +1173,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "-L96-D1024-E0_1-mem  33%[=====>              ] 896.74M  38.0MB/s    eta 48s    "
+      "-L96-D1024-E0_1-mem  48%[========>           ]   1.29G  51.3MB/s    eta 26s    "
      ]
     },
     {
@@ -1176,7 +1181,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "L96-D1024-E0_1-mem-  33%[=====>              ] 904.99M  37.6MB/s    eta 48s    "
+      "L96-D1024-E0_1-mem-  49%[========>           ]   1.30G  50.2MB/s    eta 25s    "
      ]
     },
     {
@@ -1184,7 +1189,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "96-D1024-E0_1-mem-c  33%[=====>              ] 912.07M  39.1MB/s    eta 48s    "
+      "96-D1024-E0_1-mem-c  49%[========>           ]   1.31G  50.4MB/s    eta 25s    "
      ]
     },
     {
@@ -1192,7 +1197,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "6-D1024-E0_1-mem-ct  34%[=====>              ] 919.46M  39.0MB/s    eta 48s    "
+      "6-D1024-E0_1-mem-ct  50%[=========>          ]   1.32G  56.5MB/s    eta 25s    "
      ]
     },
     {
@@ -1200,7 +1205,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "-D1024-E0_1-mem-ctx  34%[=====>              ] 928.87M  38.3MB/s    eta 48s    "
+      "-D1024-E0_1-mem-ctx  50%[=========>          ]   1.33G  57.7MB/s    eta 25s    "
      ]
     },
     {
@@ -1208,7 +1213,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "D1024-E0_1-mem-ctx-  34%[=====>              ] 937.16M  38.3MB/s    eta 47s    "
+      "D1024-E0_1-mem-ctx-  51%[=========>          ]   1.34G  57.0MB/s    eta 25s    "
      ]
     },
     {
@@ -1216,7 +1221,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "1024-E0_1-mem-ctx-2  35%[======>             ] 944.47M  38.1MB/s    eta 47s    "
+      "1024-E0_1-mem-ctx-2  51%[=========>          ]   1.36G  56.9MB/s    eta 23s    "
      ]
     },
     {
@@ -1224,7 +1229,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "024-E0_1-mem-ctx-2k  35%[======>             ] 953.45M  38.4MB/s    eta 47s    "
+      "024-E0_1-mem-ctx-2k  52%[=========>          ]   1.37G  57.4MB/s    eta 23s    "
      ]
     },
     {
@@ -1232,7 +1237,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "24-E0_1-mem-ctx-2k.  35%[======>             ] 961.39M  38.7MB/s    eta 47s    "
+      "24-E0_1-mem-ctx-2k.  52%[=========>          ]   1.38G  57.0MB/s    eta 23s    "
      ]
     },
     {
@@ -1240,7 +1245,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "4-E0_1-mem-ctx-2k.p  35%[======>             ] 968.32M  38.8MB/s    eta 47s    "
+      "4-E0_1-mem-ctx-2k.p  52%[=========>          ]   1.39G  58.1MB/s    eta 23s    "
      ]
     },
     {
@@ -1248,7 +1253,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "-E0_1-mem-ctx-2k.pt  36%[======>             ] 976.28M  38.2MB/s    eta 46s    "
+      "-E0_1-mem-ctx-2k.pt  53%[=========>          ]   1.40G  57.5MB/s    eta 23s    "
      ]
     },
     {
@@ -1256,7 +1261,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "E0_1-mem-ctx-2k.pth  36%[======>             ] 984.45M  38.6MB/s    eta 46s    "
+      "E0_1-mem-ctx-2k.pth  53%[=========>          ]   1.41G  57.9MB/s    eta 22s    "
      ]
     },
     {
@@ -1264,7 +1269,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "0_1-mem-ctx-2k.pth   36%[======>             ] 992.91M  38.5MB/s    eta 46s    "
+      "0_1-mem-ctx-2k.pth   54%[=========>          ]   1.43G  57.1MB/s    eta 22s    "
      ]
     },
     {
@@ -1272,7 +1277,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "_1-mem-ctx-2k.pth    37%[======>             ]   1000M  39.0MB/s    eta 46s    "
+      "_1-mem-ctx-2k.pth    54%[=========>          ]   1.44G  57.4MB/s    eta 22s    "
      ]
     },
     {
@@ -1280,7 +1285,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "1-mem-ctx-2k.pth     37%[======>             ]   1008M  38.3MB/s    eta 46s    "
+      "1-mem-ctx-2k.pth     55%[==========>         ]   1.45G  57.3MB/s    eta 22s    "
      ]
     },
     {
@@ -1288,7 +1293,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "-mem-ctx-2k.pth      37%[======>             ]   1016M  38.2MB/s    eta 45s    "
+      "-mem-ctx-2k.pth      55%[==========>         ]   1.46G  57.1MB/s    eta 22s    "
      ]
     },
     {
@@ -1296,7 +1301,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "mem-ctx-2k.pth       37%[======>             ]   1023M  37.7MB/s    eta 45s    "
+      "mem-ctx-2k.pth       55%[==========>         ]   1.47G  57.2MB/s    eta 21s    "
      ]
     },
     {
@@ -1304,7 +1309,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "em-ctx-2k.pth        38%[======>             ]   1.01G  39.0MB/s    eta 45s    "
+      "em-ctx-2k.pth        56%[==========>         ]   1.49G  57.8MB/s    eta 21s    "
      ]
     },
     {
@@ -1312,7 +1317,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "m-ctx-2k.pth         38%[======>             ]   1.01G  38.5MB/s    eta 45s    "
+      "m-ctx-2k.pth         56%[==========>         ]   1.49G  57.4MB/s    eta 21s    "
      ]
     },
     {
@@ -1320,7 +1325,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "-ctx-2k.pth          38%[======>             ]   1.02G  38.3MB/s    eta 45s    "
+      "-ctx-2k.pth          57%[==========>         ]   1.51G  58.3MB/s    eta 21s    "
      ]
     },
     {
@@ -1328,7 +1333,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "ctx-2k.pth           39%[======>             ]   1.03G  38.5MB/s    eta 44s    "
+      "ctx-2k.pth           57%[==========>         ]   1.52G  57.8MB/s    eta 21s    "
      ]
     },
     {
@@ -1336,7 +1341,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "tx-2k.pth            39%[======>             ]   1.04G  38.3MB/s    eta 44s    "
+      "tx-2k.pth            58%[==========>         ]   1.53G  58.0MB/s    eta 20s    "
      ]
     },
     {
@@ -1344,7 +1349,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "x-2k.pth             39%[======>             ]   1.05G  38.9MB/s    eta 44s    "
+      "x-2k.pth             58%[==========>         ]   1.54G  57.7MB/s    eta 20s    "
      ]
     },
     {
@@ -1352,7 +1357,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "-2k.pth              40%[=======>            ]   1.06G  39.1MB/s    eta 44s    "
+      "-2k.pth              58%[==========>         ]   1.55G  57.0MB/s    eta 20s    "
      ]
     },
     {
@@ -1360,7 +1365,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "2k.pth               40%[=======>            ]   1.06G  38.6MB/s    eta 44s    "
+      "2k.pth               59%[==========>         ]   1.56G  57.2MB/s    eta 20s    "
      ]
     },
     {
@@ -1368,7 +1373,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "k.pth                40%[=======>            ]   1.07G  39.5MB/s    eta 42s    "
+      "k.pth                59%[==========>         ]   1.57G  56.7MB/s    eta 20s    "
      ]
     },
     {
@@ -1376,7 +1381,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      ".pth                 41%[=======>            ]   1.08G  38.8MB/s    eta 42s    "
+      ".pth                 60%[===========>        ]   1.58G  57.0MB/s    eta 19s    "
      ]
     },
     {
@@ -1384,7 +1389,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "pth                  41%[=======>            ]   1.09G  39.4MB/s    eta 42s    "
+      "pth                  60%[===========>        ]   1.59G  56.7MB/s    eta 19s    "
      ]
     },
     {
@@ -1392,7 +1397,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "th                   41%[=======>            ]   1.10G  39.6MB/s    eta 42s    "
+      "th                   61%[===========>        ]   1.61G  56.7MB/s    eta 19s    "
      ]
     },
     {
@@ -1400,7 +1405,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "h                    41%[=======>            ]   1.10G  39.1MB/s    eta 42s    "
+      "h                    61%[===========>        ]   1.62G  56.9MB/s    eta 19s    "
      ]
     },
     {
@@ -1408,7 +1413,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "                     42%[=======>            ]   1.11G  39.2MB/s    eta 41s    "
+      "                     61%[===========>        ]   1.63G  57.4MB/s    eta 19s    "
      ]
     },
     {
@@ -1416,7 +1421,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "                  v  42%[=======>            ]   1.12G  39.4MB/s    eta 41s    "
+      "                  v  62%[===========>        ]   1.64G  59.1MB/s    eta 18s    "
      ]
     },
     {
@@ -1424,7 +1429,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "                 v5  42%[=======>            ]   1.13G  39.8MB/s    eta 41s    "
+      "                 v5  63%[===========>        ]   1.66G  59.4MB/s    eta 18s    "
      ]
     },
     {
@@ -1432,7 +1437,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "                v5-  43%[=======>            ]   1.13G  39.4MB/s    eta 41s    "
+      "                v5-  63%[===========>        ]   1.67G  58.5MB/s    eta 18s    "
      ]
     },
     {
@@ -1440,7 +1445,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "               v5-L  43%[=======>            ]   1.14G  39.1MB/s    eta 41s    "
+      "               v5-L  63%[===========>        ]   1.68G  59.1MB/s    eta 18s    "
      ]
     },
     {
@@ -1448,7 +1453,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "              v5-L9  43%[=======>            ]   1.15G  39.3MB/s    eta 40s    "
+      "              v5-L9  64%[===========>        ]   1.70G  58.3MB/s    eta 18s    "
      ]
     },
     {
@@ -1456,7 +1461,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "             v5-L96  43%[=======>            ]   1.15G  36.9MB/s    eta 40s    "
+      "             v5-L96  64%[===========>        ]   1.71G  58.7MB/s    eta 17s    "
      ]
     },
     {
@@ -1464,7 +1469,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "            v5-L96-  43%[=======>            ]   1.16G  36.3MB/s    eta 40s    "
+      "            v5-L96-  65%[============>       ]   1.72G  58.3MB/s    eta 17s    "
      ]
     },
     {
@@ -1472,7 +1477,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "           v5-L96-D  44%[=======>            ]   1.17G  37.2MB/s    eta 40s    "
+      "           v5-L96-D  65%[============>       ]   1.72G  54.7MB/s    eta 17s    "
      ]
     },
     {
@@ -1480,7 +1485,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "          v5-L96-D1  44%[=======>            ]   1.17G  36.6MB/s    eta 40s    "
+      "          v5-L96-D1  65%[============>       ]   1.73G  56.3MB/s    eta 17s    "
      ]
     },
     {
@@ -1488,7 +1493,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "         v5-L96-D10  44%[=======>            ]   1.18G  36.3MB/s    eta 40s    "
+      "         v5-L96-D10  66%[============>       ]   1.75G  57.2MB/s    eta 17s    "
      ]
     },
     {
@@ -1496,7 +1501,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "        v5-L96-D102  45%[========>           ]   1.19G  35.5MB/s    eta 40s    "
+      "        v5-L96-D102  66%[============>       ]   1.76G  56.8MB/s    eta 16s    "
      ]
     },
     {
@@ -1504,7 +1509,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "       v5-L96-D1024  45%[========>           ]   1.20G  35.4MB/s    eta 40s    "
+      "       v5-L96-D1024  67%[============>       ]   1.77G  57.7MB/s    eta 16s    "
      ]
     },
     {
@@ -1512,7 +1517,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "      v5-L96-D1024-  45%[========>           ]   1.20G  34.5MB/s    eta 40s    "
+      "      v5-L96-D1024-  68%[============>       ]   1.79G  59.6MB/s    eta 16s    "
      ]
     },
     {
@@ -1520,7 +1525,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "     v5-L96-D1024-E  45%[========>           ]   1.21G  34.7MB/s    eta 40s    "
+      "     v5-L96-D1024-E  68%[============>       ]   1.80G  59.6MB/s    eta 16s    "
      ]
     },
     {
@@ -1528,7 +1533,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "    v5-L96-D1024-E0  46%[========>           ]   1.22G  33.8MB/s    eta 39s    "
+      "    v5-L96-D1024-E0  68%[============>       ]   1.81G  59.5MB/s    eta 16s    "
      ]
     },
     {
@@ -1536,7 +1541,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "   v5-L96-D1024-E0_  46%[========>           ]   1.22G  33.7MB/s    eta 39s    "
+      "   v5-L96-D1024-E0_  69%[============>       ]   1.83G  58.3MB/s    eta 15s    "
      ]
     },
     {
@@ -1544,7 +1549,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "  v5-L96-D1024-E0_1  46%[========>           ]   1.23G  33.1MB/s    eta 39s    "
+      "  v5-L96-D1024-E0_1  69%[============>       ]   1.84G  58.1MB/s    eta 15s    "
      ]
     },
     {
@@ -1552,7 +1557,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      " v5-L96-D1024-E0_1-  46%[========>           ]   1.24G  33.1MB/s    eta 39s    "
+      " v5-L96-D1024-E0_1-  70%[=============>      ]   1.85G  56.8MB/s    eta 15s    "
      ]
     },
     {
@@ -1560,7 +1565,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "v5-L96-D1024-E0_1-m  47%[========>           ]   1.24G  32.8MB/s    eta 39s    "
+      "v5-L96-D1024-E0_1-m  70%[=============>      ]   1.86G  57.6MB/s    eta 15s    "
      ]
     },
     {
@@ -1568,7 +1573,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "5-L96-D1024-E0_1-me  47%[========>           ]   1.25G  33.1MB/s    eta 38s    "
+      "5-L96-D1024-E0_1-me  71%[=============>      ]   1.87G  56.7MB/s    eta 15s    "
      ]
     },
     {
@@ -1576,7 +1581,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "-L96-D1024-E0_1-mem  47%[========>           ]   1.26G  32.7MB/s    eta 38s    "
+      "-L96-D1024-E0_1-mem  71%[=============>      ]   1.88G  57.1MB/s    eta 14s    "
      ]
     },
     {
@@ -1584,7 +1589,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "L96-D1024-E0_1-mem-  48%[========>           ]   1.26G  34.1MB/s    eta 38s    "
+      "L96-D1024-E0_1-mem-  72%[=============>      ]   1.90G  60.1MB/s    eta 14s    "
      ]
     },
     {
@@ -1592,7 +1597,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "96-D1024-E0_1-mem-c  48%[========>           ]   1.27G  34.4MB/s    eta 38s    "
+      "96-D1024-E0_1-mem-c  72%[=============>      ]   1.91G  62.7MB/s    eta 14s    "
      ]
     },
     {
@@ -1600,7 +1605,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "6-D1024-E0_1-mem-ct  48%[========>           ]   1.28G  33.3MB/s    eta 38s    "
+      "6-D1024-E0_1-mem-ct  73%[=============>      ]   1.92G  61.7MB/s    eta 14s    "
      ]
     },
     {
@@ -1608,7 +1613,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "-D1024-E0_1-mem-ctx  48%[========>           ]   1.28G  33.4MB/s    eta 37s    "
+      "-D1024-E0_1-mem-ctx  73%[=============>      ]   1.93G  61.8MB/s    eta 14s    "
      ]
     },
     {
@@ -1616,7 +1621,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "D1024-E0_1-mem-ctx-  49%[========>           ]   1.29G  33.8MB/s    eta 37s    "
+      "D1024-E0_1-mem-ctx-  74%[=============>      ]   1.95G  62.7MB/s    eta 12s    "
      ]
     },
     {
@@ -1624,7 +1629,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "1024-E0_1-mem-ctx-2  49%[========>           ]   1.30G  34.3MB/s    eta 37s    "
+      "1024-E0_1-mem-ctx-2  74%[=============>      ]   1.96G  60.8MB/s    eta 12s    "
      ]
     },
     {
@@ -1632,7 +1637,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "024-E0_1-mem-ctx-2k  49%[========>           ]   1.31G  34.6MB/s    eta 37s    "
+      "024-E0_1-mem-ctx-2k  75%[==============>     ]   1.97G  60.6MB/s    eta 12s    "
      ]
     },
     {
@@ -1640,7 +1645,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "24-E0_1-mem-ctx-2k.  49%[========>           ]   1.31G  34.6MB/s    eta 37s    "
+      "24-E0_1-mem-ctx-2k.  75%[==============>     ]   1.99G  61.3MB/s    eta 12s    "
      ]
     },
     {
@@ -1648,7 +1653,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "4-E0_1-mem-ctx-2k.p  50%[=========>          ]   1.32G  35.0MB/s    eta 36s    "
+      "4-E0_1-mem-ctx-2k.p  76%[==============>     ]   2.00G  61.2MB/s    eta 12s    "
      ]
     },
     {
@@ -1656,7 +1661,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "-E0_1-mem-ctx-2k.pt  50%[=========>          ]   1.33G  34.9MB/s    eta 36s    "
+      "-E0_1-mem-ctx-2k.pt  76%[==============>     ]   2.01G  60.7MB/s    eta 11s    "
      ]
     },
     {
@@ -1664,7 +1669,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "E0_1-mem-ctx-2k.pth  50%[=========>          ]   1.34G  35.4MB/s    eta 36s    "
+      "E0_1-mem-ctx-2k.pth  76%[==============>     ]   2.02G  61.1MB/s    eta 11s    "
      ]
     },
     {
@@ -1672,7 +1677,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "0_1-mem-ctx-2k.pth   51%[=========>          ]   1.34G  35.3MB/s    eta 36s    "
+      "0_1-mem-ctx-2k.pth   77%[==============>     ]   2.04G  61.1MB/s    eta 11s    "
      ]
     },
     {
@@ -1680,7 +1685,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "_1-mem-ctx-2k.pth    51%[=========>          ]   1.35G  36.1MB/s    eta 36s    "
+      "_1-mem-ctx-2k.pth    77%[==============>     ]   2.05G  61.6MB/s    eta 11s    "
      ]
     },
     {
@@ -1688,7 +1693,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "1-mem-ctx-2k.pth     51%[=========>          ]   1.36G  35.6MB/s    eta 35s    "
+      "1-mem-ctx-2k.pth     78%[==============>     ]   2.06G  62.4MB/s    eta 11s    "
      ]
     },
     {
@@ -1696,7 +1701,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "-mem-ctx-2k.pth      51%[=========>          ]   1.37G  36.2MB/s    eta 35s    "
+      "-mem-ctx-2k.pth      78%[==============>     ]   2.07G  61.2MB/s    eta 10s    "
      ]
     },
     {
@@ -1704,7 +1709,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "mem-ctx-2k.pth       52%[=========>          ]   1.37G  36.5MB/s    eta 35s    "
+      "mem-ctx-2k.pth       79%[==============>     ]   2.08G  60.8MB/s    eta 10s    "
      ]
     },
     {
@@ -1712,7 +1717,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "em-ctx-2k.pth        52%[=========>          ]   1.38G  37.1MB/s    eta 35s    "
+      "em-ctx-2k.pth        79%[==============>     ]   2.09G  60.1MB/s    eta 10s    "
      ]
     },
     {
@@ -1720,7 +1725,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "m-ctx-2k.pth         52%[=========>          ]   1.39G  37.0MB/s    eta 35s    "
+      "m-ctx-2k.pth         79%[==============>     ]   2.10G  58.8MB/s    eta 10s    "
      ]
     },
     {
@@ -1728,7 +1733,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "-ctx-2k.pth          53%[=========>          ]   1.40G  36.9MB/s    eta 34s    "
+      "-ctx-2k.pth          80%[===============>    ]   2.11G  58.7MB/s    eta 10s    "
      ]
     },
     {
@@ -1736,7 +1741,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "ctx-2k.pth           53%[=========>          ]   1.41G  37.9MB/s    eta 34s    "
+      "ctx-2k.pth           80%[===============>    ]   2.13G  60.2MB/s    eta 9s     "
      ]
     },
     {
@@ -1744,7 +1749,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "tx-2k.pth            53%[=========>          ]   1.41G  37.4MB/s    eta 34s    "
+      "tx-2k.pth            81%[===============>    ]   2.14G  59.0MB/s    eta 9s     "
      ]
     },
     {
@@ -1752,7 +1757,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "x-2k.pth             53%[=========>          ]   1.42G  37.1MB/s    eta 34s    "
+      "x-2k.pth             81%[===============>    ]   2.15G  58.9MB/s    eta 9s     "
      ]
     },
     {
@@ -1760,7 +1765,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "-2k.pth              54%[=========>          ]   1.43G  37.3MB/s    eta 34s    "
+      "-2k.pth              82%[===============>    ]   2.16G  57.5MB/s    eta 9s     "
      ]
     },
     {
@@ -1768,7 +1773,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "2k.pth               54%[=========>          ]   1.44G  38.0MB/s    eta 33s    "
+      "2k.pth               82%[===============>    ]   2.17G  56.7MB/s    eta 9s     "
      ]
     },
     {
@@ -1776,7 +1781,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "k.pth                54%[=========>          ]   1.44G  37.3MB/s    eta 33s    "
+      "k.pth                82%[===============>    ]   2.18G  56.1MB/s    eta 8s     "
      ]
     },
     {
@@ -1784,7 +1789,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      ".pth                 55%[==========>         ]   1.45G  37.7MB/s    eta 33s    "
+      ".pth                 83%[===============>    ]   2.19G  53.8MB/s    eta 8s     "
      ]
     },
     {
@@ -1792,7 +1797,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "pth                  55%[==========>         ]   1.46G  37.6MB/s    eta 33s    "
+      "pth                  83%[===============>    ]   2.20G  52.8MB/s    eta 8s     "
      ]
     },
     {
@@ -1800,7 +1805,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "th                   55%[==========>         ]   1.47G  37.6MB/s    eta 33s    "
+      "th                   84%[===============>    ]   2.21G  53.2MB/s    eta 8s     "
      ]
     },
     {
@@ -1808,7 +1813,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "h                    55%[==========>         ]   1.47G  37.2MB/s    eta 32s    "
+      "h                    84%[===============>    ]   2.22G  53.8MB/s    eta 8s     "
      ]
     },
     {
@@ -1816,7 +1821,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "                     56%[==========>         ]   1.48G  37.9MB/s    eta 32s    "
+      "                     84%[===============>    ]   2.24G  54.7MB/s    eta 7s     "
      ]
     },
     {
@@ -1824,7 +1829,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "                  v  56%[==========>         ]   1.49G  38.5MB/s    eta 32s    "
+      "                  v  85%[================>   ]   2.25G  55.1MB/s    eta 7s     "
      ]
     },
     {
@@ -1832,7 +1837,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "                 v5  56%[==========>         ]   1.50G  37.9MB/s    eta 32s    "
+      "                 v5  85%[================>   ]   2.26G  55.7MB/s    eta 7s     "
      ]
     },
     {
@@ -1840,7 +1845,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "                v5-  57%[==========>         ]   1.50G  38.2MB/s    eta 32s    "
+      "                v5-  86%[================>   ]   2.27G  54.5MB/s    eta 7s     "
      ]
     },
     {
@@ -1848,7 +1853,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "               v5-L  57%[==========>         ]   1.51G  36.2MB/s    eta 31s    "
+      "               v5-L  86%[================>   ]   2.28G  54.1MB/s    eta 7s     "
      ]
     },
     {
@@ -1856,7 +1861,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "              v5-L9  57%[==========>         ]   1.51G  35.4MB/s    eta 31s    "
+      "              v5-L9  87%[================>   ]   2.29G  53.7MB/s    eta 6s     "
      ]
     },
     {
@@ -1864,7 +1869,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "             v5-L96  57%[==========>         ]   1.52G  36.5MB/s    eta 31s    "
+      "             v5-L96  87%[================>   ]   2.29G  50.5MB/s    eta 6s     "
      ]
     },
     {
@@ -1872,7 +1877,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "            v5-L96-  58%[==========>         ]   1.54G  37.9MB/s    eta 31s    "
+      "            v5-L96-  87%[================>   ]   2.31G  51.3MB/s    eta 6s     "
      ]
     },
     {
@@ -1880,7 +1885,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "           v5-L96-D  58%[==========>         ]   1.54G  38.4MB/s    eta 31s    "
+      "           v5-L96-D  88%[================>   ]   2.32G  52.2MB/s    eta 6s     "
      ]
     },
     {
@@ -1888,7 +1893,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "          v5-L96-D1  58%[==========>         ]   1.55G  37.6MB/s    eta 30s    "
+      "          v5-L96-D1  88%[================>   ]   2.33G  52.8MB/s    eta 6s     "
      ]
     },
     {
@@ -1896,7 +1901,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "         v5-L96-D10  59%[==========>         ]   1.56G  38.0MB/s    eta 30s    "
+      "         v5-L96-D10  89%[================>   ]   2.35G  54.0MB/s    eta 5s     "
      ]
     },
     {
@@ -1904,7 +1909,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "        v5-L96-D102  59%[==========>         ]   1.57G  38.1MB/s    eta 30s    "
+      "        v5-L96-D102  89%[================>   ]   2.36G  55.3MB/s    eta 5s     "
      ]
     },
     {
@@ -1912,7 +1917,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "       v5-L96-D1024  59%[==========>         ]   1.57G  37.7MB/s    eta 30s    "
+      "       v5-L96-D1024  90%[=================>  ]   2.37G  56.6MB/s    eta 5s     "
      ]
     },
     {
@@ -1920,7 +1925,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "      v5-L96-D1024-  60%[===========>        ]   1.58G  37.6MB/s    eta 30s    "
+      "      v5-L96-D1024-  90%[=================>  ]   2.38G  56.9MB/s    eta 5s     "
      ]
     },
     {
@@ -1928,7 +1933,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "     v5-L96-D1024-E  60%[===========>        ]   1.59G  37.4MB/s    eta 29s    "
+      "     v5-L96-D1024-E  91%[=================>  ]   2.40G  56.8MB/s    eta 5s     "
      ]
     },
     {
@@ -1936,7 +1941,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "    v5-L96-D1024-E0  60%[===========>        ]   1.60G  38.3MB/s    eta 29s    "
+      "    v5-L96-D1024-E0  91%[=================>  ]   2.41G  56.3MB/s    eta 4s     "
      ]
     },
     {
@@ -1944,7 +1949,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "   v5-L96-D1024-E0_  61%[===========>        ]   1.61G  37.7MB/s    eta 29s    "
+      "   v5-L96-D1024-E0_  92%[=================>  ]   2.42G  56.2MB/s    eta 4s     "
      ]
     },
     {
@@ -1952,7 +1957,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "  v5-L96-D1024-E0_1  61%[===========>        ]   1.62G  37.8MB/s    eta 29s    "
+      "  v5-L96-D1024-E0_1  92%[=================>  ]   2.43G  56.9MB/s    eta 4s     "
      ]
     },
     {
@@ -1960,7 +1965,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      " v5-L96-D1024-E0_1-  61%[===========>        ]   1.62G  38.6MB/s    eta 29s    "
+      " v5-L96-D1024-E0_1-  92%[=================>  ]   2.45G  57.2MB/s    eta 4s     "
      ]
     },
     {
@@ -1968,7 +1973,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "v5-L96-D1024-E0_1-m  61%[===========>        ]   1.63G  39.0MB/s    eta 27s    "
+      "v5-L96-D1024-E0_1-m  93%[=================>  ]   2.46G  57.3MB/s    eta 4s     "
      ]
     },
     {
@@ -1976,7 +1981,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "5-L96-D1024-E0_1-me  62%[===========>        ]   1.64G  40.7MB/s    eta 27s    "
+      "5-L96-D1024-E0_1-me  93%[=================>  ]   2.47G  57.2MB/s    eta 3s     "
      ]
     },
     {
@@ -1984,7 +1989,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "-L96-D1024-E0_1-mem  62%[===========>        ]   1.65G  40.9MB/s    eta 27s    "
+      "-L96-D1024-E0_1-mem  94%[=================>  ]   2.48G  60.3MB/s    eta 3s     "
      ]
     },
     {
@@ -1992,7 +1997,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "L96-D1024-E0_1-mem-  62%[===========>        ]   1.65G  39.1MB/s    eta 27s    "
+      "L96-D1024-E0_1-mem-  94%[=================>  ]   2.49G  60.6MB/s    eta 3s     "
      ]
     },
     {
@@ -2000,7 +2005,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "96-D1024-E0_1-mem-c  63%[===========>        ]   1.66G  39.2MB/s    eta 27s    "
+      "96-D1024-E0_1-mem-c  95%[==================> ]   2.50G  59.5MB/s    eta 3s     "
      ]
     },
     {
@@ -2008,7 +2013,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "6-D1024-E0_1-mem-ct  63%[===========>        ]   1.67G  38.4MB/s    eta 26s    "
+      "6-D1024-E0_1-mem-ct  95%[==================> ]   2.51G  58.9MB/s    eta 3s     "
      ]
     },
     {
@@ -2016,7 +2021,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "-D1024-E0_1-mem-ctx  63%[===========>        ]   1.68G  39.3MB/s    eta 26s    "
+      "-D1024-E0_1-mem-ctx  95%[==================> ]   2.52G  58.6MB/s    eta 2s     "
      ]
     },
     {
@@ -2024,7 +2029,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "D1024-E0_1-mem-ctx-  64%[===========>        ]   1.69G  38.7MB/s    eta 26s    "
+      "D1024-E0_1-mem-ctx-  96%[==================> ]   2.54G  59.4MB/s    eta 2s     "
      ]
     },
     {
@@ -2032,7 +2037,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "1024-E0_1-mem-ctx-2  64%[===========>        ]   1.70G  39.3MB/s    eta 26s    "
+      "1024-E0_1-mem-ctx-2  96%[==================> ]   2.55G  59.0MB/s    eta 2s     "
      ]
     },
     {
@@ -2040,7 +2045,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "024-E0_1-mem-ctx-2k  64%[===========>        ]   1.70G  39.5MB/s    eta 26s    "
+      "024-E0_1-mem-ctx-2k  97%[==================> ]   2.56G  59.2MB/s    eta 2s     "
      ]
     },
     {
@@ -2048,7 +2053,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "24-E0_1-mem-ctx-2k.  64%[===========>        ]   1.71G  39.1MB/s    eta 25s    "
+      "24-E0_1-mem-ctx-2k.  97%[==================> ]   2.58G  59.4MB/s    eta 2s     "
      ]
     },
     {
@@ -2056,7 +2061,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "4-E0_1-mem-ctx-2k.p  65%[============>       ]   1.72G  39.1MB/s    eta 25s    "
+      "4-E0_1-mem-ctx-2k.p  98%[==================> ]   2.58G  58.0MB/s    eta 1s     "
      ]
     },
     {
@@ -2064,7 +2069,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "-E0_1-mem-ctx-2k.pt  65%[============>       ]   1.72G  39.2MB/s    eta 25s    "
+      "-E0_1-mem-ctx-2k.pt  98%[==================> ]   2.60G  58.1MB/s    eta 1s     "
      ]
     },
     {
@@ -2072,7 +2077,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "E0_1-mem-ctx-2k.pth  65%[============>       ]   1.73G  39.7MB/s    eta 25s    "
+      "E0_1-mem-ctx-2k.pth  99%[==================> ]   2.61G  57.4MB/s    eta 1s     "
      ]
     },
     {
@@ -2080,7 +2085,7 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "0_1-mem-ctx-2k.pth   66%[============>       ]   1.74G  39.6MB/s    eta 25s    "
+      "0_1-mem-ctx-2k.pth   99%[==================> ]   2.62G  58.0MB/s    eta 1s     "
      ]
     },
     {
@@ -2088,6910 +2093,6785 @@
      "output_type": "stream",
      "text": [
       "\r",
-      "_1-mem-ctx-2k.pth    66%[============>       ]   1.75G  39.3MB/s    eta 24s    "
+      "v5-L96-D1024-E0_1-m 100%[===================>]   2.63G  58.8MB/s    in 47s     \r\n",
+      "\r\n",
+      "2023-09-01 14:30:45 (56.8 MB/s) - ‘v5-L96-D1024-E0_1-mem-ctx-2k.pth’ saved [2825976699/2825976699]\r\n",
+      "\r\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "1-mem-ctx-2k.pth     66%[============>       ]   1.76G  39.4MB/s    eta 24s    "
+      "total 2.7G\r\n",
+      "drwxr-xr-x  2 root root   54 Sep  1 14:29 .\r\n",
+      "drwxr-xr-x 19 root root 4.0K Sep  1 14:29 ..\r\n",
+      "-rw-r--r--  1 root root 2.7G Sep  1 08:04 v5-L96-D1024-E0_1-mem-ctx-2k.pth\r\n"
      ]
+    }
+   ],
+   "source": [
+    "# Download the model directly (stop gap till HF sync issues is resolved)\n",
+    "# !cd \"{TRAINER_DIR}\" && cd \"../model/\" && \\\n",
+    "#     wget -nc \"https://huggingface.co/rwkv-x-dev/rwkv-x-playground/resolve/main/experiment/rwkv-x-exp/v5-memory/{FILENAME_PREFIX}-mem-ctx-2k.pth\"\n",
+    "!cd \"{TRAINER_DIR}\" && cd \"../model/\" && \\\n",
+    "    wget -nc \"https://huggingface.co/rwkv-x-dev/rwkv-x-playground/resolve/main/experiment/rwkv-x-exp/v5-memory/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/v5-L96-D1024-E0_1-mem-ctx-2k.pth\"\n",
+    "\n",
+    "!cd \"{TRAINER_DIR}\" && cd \"../model/\" && \\\n",
+    "    ls -alh ."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7c75b2d4",
+   "metadata": {
+    "papermill": {
+     "duration": 0.01273,
+     "end_time": "2023-09-01T14:30:45.548016",
+     "exception": false,
+     "start_time": "2023-09-01T14:30:45.535286",
+     "status": "completed"
+    },
+    "tags": []
+   },
+   "source": [
+    "## Tune 5 : Ramping up the ctx size (4096), memory training\n",
+    "\n",
+    "- Tune 5: Mid ctx size (4096), Scaling up!"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "910befc3",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2023-09-01T14:30:45.575326Z",
+     "iopub.status.busy": "2023-09-01T14:30:45.575138Z",
+     "iopub.status.idle": "2023-09-01T14:30:50.041525Z",
+     "shell.execute_reply": "2023-09-01T14:30:50.040567Z"
+    },
+    "papermill": {
+     "duration": 4.844384,
+     "end_time": "2023-09-01T14:30:50.405173",
+     "exception": false,
+     "start_time": "2023-09-01T14:30:45.560789",
+     "status": "completed"
     },
+    "tags": []
+   },
+   "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "-mem-ctx-2k.pth      67%[============>       ]   1.77G  39.3MB/s    eta 24s    "
+      "## Generating word reptition dataset ##\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "mem-ctx-2k.pth       67%[============>       ]   1.78G  39.8MB/s    eta 24s    "
+      "Generated JSONL file with - 2 max words, 100 samples - at ../dataset/word-2-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "em-ctx-2k.pth        67%[============>       ]   1.78G  39.7MB/s    eta 24s    "
+      "Generated JSONL file with - 20 max words, 100 samples - at ../dataset/gen-word-20-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "m-ctx-2k.pth         68%[============>       ]   1.79G  39.5MB/s    eta 23s    "
+      "Generated JSONL file with - 5 max words, 100 samples - at ../dataset/gen-word-5-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "-ctx-2k.pth          68%[============>       ]   1.80G  40.1MB/s    eta 23s    "
+      "Generated a single JSONL file with 108 samples (1 token repeat) - 25 max words - at ../dataset/shuffle-word-25-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "ctx-2k.pth           68%[============>       ]   1.81G  39.6MB/s    eta 23s    "
+      "Generated a single JSONL file with 85 samples (1 token repeat) - 30 max words - at ../dataset/shuffle-word-30-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "tx-2k.pth            69%[============>       ]   1.82G  40.1MB/s    eta 23s    "
+      "Generated a single JSONL file with 127 samples (1 token repeat) - 20 max words - at ../dataset/shuffle-word-20-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "x-2k.pth             69%[============>       ]   1.83G  40.0MB/s    eta 23s    "
+      "Generated a single JSONL file with 37 samples (1 token repeat) - 70 max words - at ../dataset/shuffle-word-70-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "-2k.pth              69%[============>       ]   1.83G  40.4MB/s    eta 22s    "
+      "Generated a single JSONL file with 66 samples (1 token repeat) - 40 max words - at ../dataset/shuffle-word-40-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "2k.pth               69%[============>       ]   1.84G  39.7MB/s    eta 22s    "
+      "Generated JSONL file with - 10 max words, 100 samples - at ../dataset/gen-word-10-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "k.pth                70%[=============>      ]   1.85G  40.9MB/s    eta 22s    "
+      "Generated a single JSONL file with 40 samples (1 token repeat) - 65 max words - at ../dataset/shuffle-word-65-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      ".pth                 70%[=============>      ]   1.86G  40.3MB/s    eta 22s    "
+      "Generated JSONL file with - 25 max words, 100 samples - at ../dataset/gen-word-25-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "pth                  70%[=============>      ]   1.87G  40.6MB/s    eta 22s    "
+      "Generated JSONL file with - 35 max words, 100 samples - at ../dataset/gen-word-35-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "th                   71%[=============>      ]   1.88G  40.7MB/s    eta 21s    "
+      "Generated a single JSONL file with 179 samples (1 token repeat) - 15 max words - at ../dataset/shuffle-word-15-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "h                    71%[=============>      ]   1.88G  41.0MB/s    eta 21s    "
+      "Generated JSONL file with - 45 max words, 100 samples - at ../dataset/gen-word-45-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "                     71%[=============>      ]   1.89G  40.3MB/s    eta 21s    "
+      "Generated a single JSONL file with 262 samples (1 token repeat) - 10 max words - at ../dataset/shuffle-word-10-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "                  v  72%[=============>      ]   1.90G  40.5MB/s    eta 21s    "
+      "Generated JSONL file with - 40 max words, 100 samples - at ../dataset/gen-word-40-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "                 v5  72%[=============>      ]   1.91G  41.0MB/s    eta 21s    "
+      "Generated JSONL file with - 50 max words, 100 samples - at ../dataset/gen-word-50-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "                v5-  72%[=============>      ]   1.91G  40.2MB/s    eta 20s    "
+      "Generated a single JSONL file with 21 samples (1 token repeat) - 105 max words - at ../dataset/shuffle-word-105-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "               v5-L  72%[=============>      ]   1.92G  39.4MB/s    eta 20s    "
+      "Generated JSONL file with - 65 max words, 100 samples - at ../dataset/gen-word-65-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "              v5-L9  73%[=============>      ]   1.93G  39.7MB/s    eta 20s    "
+      "Generated JSONL file with - 60 max words, 100 samples - at ../dataset/gen-word-60-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "             v5-L96  73%[=============>      ]   1.94G  39.5MB/s    eta 20s    "
+      "Generated JSONL file with - 70 max words, 100 samples - at ../dataset/gen-word-70-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "            v5-L96-  73%[=============>      ]   1.94G  39.5MB/s    eta 20s    "
+      "Generated JSONL file with - 55 max words, 100 samples - at ../dataset/gen-word-55-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "           v5-L96-D  74%[=============>      ]   1.95G  39.1MB/s    eta 18s    "
+      "Generated a single JSONL file with 58 samples (1 token repeat) - 45 max words - at ../dataset/shuffle-word-45-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "          v5-L96-D1  74%[=============>      ]   1.96G  38.9MB/s    eta 18s    "
+      "Generated a single JSONL file with 34 samples (1 token repeat) - 75 max words - at ../dataset/shuffle-word-75-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "         v5-L96-D10  74%[=============>      ]   1.97G  38.7MB/s    eta 18s    "
+      "Generated a single JSONL file with 20 samples (1 token repeat) - 110 max words - at ../dataset/shuffle-word-110-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "        v5-L96-D102  75%[==============>     ]   1.98G  38.9MB/s    eta 18s    "
+      "Generated a single JSONL file with 52 samples (1 token repeat) - 50 max words - at ../dataset/shuffle-word-50-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "       v5-L96-D1024  75%[==============>     ]   1.98G  38.7MB/s    eta 18s    "
+      "Generated JSONL file with - 30 max words, 100 samples - at ../dataset/gen-word-30-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "      v5-L96-D1024-  75%[==============>     ]   1.99G  38.6MB/s    eta 17s    "
+      "Generated a single JSONL file with 14 samples (1 token repeat) - 185 max words - at ../dataset/shuffle-word-185-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "     v5-L96-D1024-E  76%[==============>     ]   2.00G  38.7MB/s    eta 17s    "
+      "Generated JSONL file with - 120 max words, 100 samples - at ../dataset/gen-word-120-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "    v5-L96-D1024-E0  76%[==============>     ]   2.01G  39.1MB/s    eta 17s    "
+      "Generated a single JSONL file with 18 samples (1 token repeat) - 130 max words - at ../dataset/shuffle-word-130-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "   v5-L96-D1024-E0_  76%[==============>     ]   2.02G  38.9MB/s    eta 17s    "
+      "Generated a single JSONL file with 18 samples (1 token repeat) - 120 max words - at ../dataset/shuffle-word-120-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "  v5-L96-D1024-E0_1  76%[==============>     ]   2.03G  39.1MB/s    eta 17s    "
+      "Generated a single JSONL file with 15 samples (1 token repeat) - 155 max words - at ../dataset/shuffle-word-155-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      " v5-L96-D1024-E0_1-  77%[==============>     ]   2.03G  39.5MB/s    eta 16s    "
+      "Generated JSONL file with - 110 max words, 100 samples - at ../dataset/gen-word-110-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "v5-L96-D1024-E0_1-m  77%[==============>     ]   2.04G  39.4MB/s    eta 16s    "
+      "Generated a single JSONL file with 9 samples (1 token repeat) - 240 max words - at ../dataset/shuffle-word-240-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "5-L96-D1024-E0_1-me  77%[==============>     ]   2.05G  39.0MB/s    eta 16s    "
+      "Generated a single JSONL file with 47 samples (1 token repeat) - 55 max words - at ../dataset/shuffle-word-55-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "-L96-D1024-E0_1-mem  78%[==============>     ]   2.06G  39.4MB/s    eta 16s    "
+      "Generated JSONL file with - 15 max words, 100 samples - at ../dataset/gen-word-15-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "L96-D1024-E0_1-mem-  78%[==============>     ]   2.07G  39.4MB/s    eta 16s    "
+      "Generated JSONL file with - 95 max words, 100 samples - at ../dataset/gen-word-95-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "96-D1024-E0_1-mem-c  78%[==============>     ]   2.08G  39.8MB/s    eta 15s    "
+      "Generated a single JSONL file with 32 samples (1 token repeat) - 80 max words - at ../dataset/shuffle-word-80-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "6-D1024-E0_1-mem-ct  79%[==============>     ]   2.08G  40.1MB/s    eta 15s    "
+      "Generated a single JSONL file with 74 samples (1 token repeat) - 35 max words - at ../dataset/shuffle-word-35-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "-D1024-E0_1-mem-ctx  79%[==============>     ]   2.09G  40.1MB/s    eta 15s    "
+      "Generated a single JSONL file with 544 samples (1 token repeat) - 5 max words - at ../dataset/shuffle-word-5-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "D1024-E0_1-mem-ctx-  79%[==============>     ]   2.10G  39.6MB/s    eta 15s    "
+      "Generated a single JSONL file with 44 samples (1 token repeat) - 60 max words - at ../dataset/shuffle-word-60-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "1024-E0_1-mem-ctx-2  80%[===============>    ]   2.11G  39.6MB/s    eta 15s    "
+      "Generated JSONL file with - 100 max words, 100 samples - at ../dataset/gen-word-100-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "024-E0_1-mem-ctx-2k  80%[===============>    ]   2.12G  40.1MB/s    eta 14s    "
+      "Generated JSONL file with - 125 max words, 100 samples - at ../dataset/gen-word-125-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "24-E0_1-mem-ctx-2k.  80%[===============>    ]   2.12G  40.5MB/s    eta 14s    "
+      "Generated JSONL file with - 140 max words, 100 samples - at ../dataset/gen-word-140-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "4-E0_1-mem-ctx-2k.p  81%[===============>    ]   2.13G  40.3MB/s    eta 14s    "
+      "Generated JSONL file with - 135 max words, 100 samples - at ../dataset/gen-word-135-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "-E0_1-mem-ctx-2k.pt  81%[===============>    ]   2.14G  39.9MB/s    eta 14s    "
+      "Generated a single JSONL file with 10 samples (1 token repeat) - 230 max words - at ../dataset/shuffle-word-230-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "E0_1-mem-ctx-2k.pth  81%[===============>    ]   2.15G  39.9MB/s    eta 14s    "
+      "Generated JSONL file with - 105 max words, 100 samples - at ../dataset/gen-word-105-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "0_1-mem-ctx-2k.pth   81%[===============>    ]   2.16G  39.8MB/s    eta 13s    "
+      "Generated a single JSONL file with 27 samples (1 token repeat) - 100 max words - at ../dataset/shuffle-word-100-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "_1-mem-ctx-2k.pth    82%[===============>    ]   2.17G  40.9MB/s    eta 13s    "
+      "Generated a single JSONL file with 31 samples (1 token repeat) - 85 max words - at ../dataset/shuffle-word-85-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "1-mem-ctx-2k.pth     82%[===============>    ]   2.17G  40.7MB/s    eta 13s    "
+      "Generated JSONL file with - 130 max words, 100 samples - at ../dataset/gen-word-130-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "-mem-ctx-2k.pth      82%[===============>    ]   2.18G  40.7MB/s    eta 13s    "
+      "Generated JSONL file with - 85 max words, 100 samples - at ../dataset/gen-word-85-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "mem-ctx-2k.pth       83%[===============>    ]   2.19G  40.6MB/s    eta 13s    "
+      "Generated a single JSONL file with 8 samples (1 token repeat) - 295 max words - at ../dataset/shuffle-word-295-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "em-ctx-2k.pth        83%[===============>    ]   2.20G  40.4MB/s    eta 12s    "
+      "Generated JSONL file with - 75 max words, 100 samples - at ../dataset/gen-word-75-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "m-ctx-2k.pth         83%[===============>    ]   2.21G  40.3MB/s    eta 12s    "
+      "Generated a single JSONL file with 19 samples (1 token repeat) - 115 max words - at ../dataset/shuffle-word-115-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "-ctx-2k.pth          84%[===============>    ]   2.21G  40.1MB/s    eta 12s    "
+      "Generated a single JSONL file with 29 samples (1 token repeat) - 95 max words - at ../dataset/shuffle-word-95-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "ctx-2k.pth           84%[===============>    ]   2.22G  40.4MB/s    eta 12s    "
+      "Generated a single JSONL file with 31 samples (1 token repeat) - 90 max words - at ../dataset/shuffle-word-90-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "tx-2k.pth            84%[===============>    ]   2.23G  40.1MB/s    eta 12s    "
+      "Generated JSONL file with - 115 max words, 100 samples - at ../dataset/gen-word-115-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "x-2k.pth             85%[================>   ]   2.24G  39.9MB/s    eta 11s    "
+      "Generated JSONL file with - 145 max words, 100 samples - at ../dataset/gen-word-145-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "-2k.pth              85%[================>   ]   2.25G  40.4MB/s    eta 11s    "
+      "Generated a single JSONL file with 14 samples (1 token repeat) - 190 max words - at ../dataset/shuffle-word-190-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "2k.pth               85%[================>   ]   2.25G  40.2MB/s    eta 11s    "
+      "Generated JSONL file with - 180 max words, 100 samples - at ../dataset/gen-word-180-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "k.pth                86%[================>   ]   2.26G  40.1MB/s    eta 11s    "
+      "Generated a single JSONL file with 14 samples (1 token repeat) - 170 max words - at ../dataset/shuffle-word-170-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      ".pth                 86%[================>   ]   2.27G  40.1MB/s    eta 11s    "
+      "Generated a single JSONL file with 6 samples (1 token repeat) - 405 max words - at ../dataset/shuffle-word-405-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "pth                  86%[================>   ]   2.28G  39.6MB/s    eta 10s    "
+      "Generated a single JSONL file with 16 samples (1 token repeat) - 145 max words - at ../dataset/shuffle-word-145-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "th                   86%[================>   ]   2.29G  39.6MB/s    eta 10s    "
+      "Generated a single JSONL file with 7 samples (1 token repeat) - 335 max words - at ../dataset/shuffle-word-335-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "h                    87%[================>   ]   2.29G  39.4MB/s    eta 10s    "
+      "Generated a single JSONL file with 7 samples (1 token repeat) - 385 max words - at ../dataset/shuffle-word-385-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "                     87%[================>   ]   2.30G  37.8MB/s    eta 10s    "
+      "Generated a single JSONL file with 11 samples (1 token repeat) - 210 max words - at ../dataset/shuffle-word-210-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "                  v  87%[================>   ]   2.31G  38.2MB/s    eta 10s    "
+      "Generated a single JSONL file with 7 samples (1 token repeat) - 395 max words - at ../dataset/shuffle-word-395-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "                 v5  88%[================>   ]   2.32G  39.8MB/s    eta 8s     "
+      "Generated a single JSONL file with 9 samples (1 token repeat) - 260 max words - at ../dataset/shuffle-word-260-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "                v5-  88%[================>   ]   2.32G  38.5MB/s    eta 8s     "
+      "Generated JSONL file with - 220 max words, 100 samples - at ../dataset/gen-word-220-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "               v5-L  88%[================>   ]   2.33G  37.8MB/s    eta 8s     "
+      "Generated a single JSONL file with 10 samples (1 token repeat) - 225 max words - at ../dataset/shuffle-word-225-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "              v5-L9  88%[================>   ]   2.34G  37.5MB/s    eta 8s     "
+      "Generated a single JSONL file with 18 samples (1 token repeat) - 125 max words - at ../dataset/shuffle-word-125-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "             v5-L96  89%[================>   ]   2.34G  36.9MB/s    eta 8s     "
+      "Generated a single JSONL file with 7 samples (1 token repeat) - 400 max words - at ../dataset/shuffle-word-400-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "            v5-L96-  89%[================>   ]   2.35G  36.8MB/s    eta 8s     "
+      "Generated a single JSONL file with 14 samples (1 token repeat) - 165 max words - at ../dataset/shuffle-word-165-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "           v5-L96-D  89%[================>   ]   2.36G  35.4MB/s    eta 8s     "
+      "Generated JSONL file with - 300 max words, 100 samples - at ../dataset/gen-word-300-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "          v5-L96-D1  89%[================>   ]   2.36G  34.7MB/s    eta 8s     "
+      "Generated a single JSONL file with 7 samples (1 token repeat) - 345 max words - at ../dataset/shuffle-word-345-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "         v5-L96-D10  89%[================>   ]   2.37G  33.7MB/s    eta 8s     "
+      "Generated JSONL file with - 470 max words, 100 samples - at ../dataset/gen-word-470-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "        v5-L96-D102  90%[=================>  ]   2.37G  32.9MB/s    eta 8s     "
+      "Generated a single JSONL file with 10 samples (1 token repeat) - 275 max words - at ../dataset/shuffle-word-275-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "       v5-L96-D1024  90%[=================>  ]   2.38G  32.6MB/s    eta 7s     "
+      "Generated JSONL file with - 175 max words, 100 samples - at ../dataset/gen-word-175-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "      v5-L96-D1024-  90%[=================>  ]   2.38G  31.6MB/s    eta 7s     "
+      "Generated JSONL file with - 395 max words, 100 samples - at ../dataset/gen-word-395-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "     v5-L96-D1024-E  90%[=================>  ]   2.39G  30.6MB/s    eta 7s     "
+      "Generated a single JSONL file with 6 samples (1 token repeat) - 450 max words - at ../dataset/shuffle-word-450-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "    v5-L96-D1024-E0  90%[=================>  ]   2.39G  29.7MB/s    eta 7s     "
+      "Generated a single JSONL file with 14 samples (1 token repeat) - 175 max words - at ../dataset/shuffle-word-175-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "   v5-L96-D1024-E0_  91%[=================>  ]   2.40G  30.5MB/s    eta 7s     "
+      "Generated a single JSONL file with 14 samples (1 token repeat) - 180 max words - at ../dataset/shuffle-word-180-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "  v5-L96-D1024-E0_1  91%[=================>  ]   2.40G  28.9MB/s    eta 6s     "
+      "Generated JSONL file with - 235 max words, 100 samples - at ../dataset/gen-word-235-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      " v5-L96-D1024-E0_1-  91%[=================>  ]   2.41G  26.9MB/s    eta 6s     "
+      "Generated JSONL file with - 405 max words, 100 samples - at ../dataset/gen-word-405-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "v5-L96-D1024-E0_1-m  91%[=================>  ]   2.41G  27.1MB/s    eta 6s     "
+      "Generated JSONL file with - 295 max words, 100 samples - at ../dataset/gen-word-295-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "5-L96-D1024-E0_1-me  91%[=================>  ]   2.42G  26.1MB/s    eta 6s     "
+      "Generated JSONL file with - 90 max words, 100 samples - at ../dataset/gen-word-90-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "-L96-D1024-E0_1-mem  92%[=================>  ]   2.43G  26.7MB/s    eta 6s     "
+      "Generated JSONL file with - 200 max words, 100 samples - at ../dataset/gen-word-200-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "L96-D1024-E0_1-mem-  92%[=================>  ]   2.43G  26.8MB/s    eta 5s     "
+      "Generated JSONL file with - 170 max words, 100 samples - at ../dataset/gen-word-170-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "96-D1024-E0_1-mem-c  92%[=================>  ]   2.44G  26.3MB/s    eta 5s     "
+      "Generated a single JSONL file with 15 samples (1 token repeat) - 160 max words - at ../dataset/shuffle-word-160-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "6-D1024-E0_1-mem-ct  92%[=================>  ]   2.44G  26.5MB/s    eta 5s     "
+      "Generated JSONL file with - 435 max words, 100 samples - at ../dataset/gen-word-435-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "-D1024-E0_1-mem-ctx  93%[=================>  ]   2.45G  26.7MB/s    eta 5s     "
+      "Generated JSONL file with - 400 max words, 100 samples - at ../dataset/gen-word-400-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "D1024-E0_1-mem-ctx-  93%[=================>  ]   2.45G  26.8MB/s    eta 5s     "
+      "Generated JSONL file with - 275 max words, 100 samples - at ../dataset/gen-word-275-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "1024-E0_1-mem-ctx-2  93%[=================>  ]   2.46G  26.6MB/s    eta 5s     "
+      "Generated a single JSONL file with 10 samples (1 token repeat) - 220 max words - at ../dataset/shuffle-word-220-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "024-E0_1-mem-ctx-2k  93%[=================>  ]   2.47G  27.2MB/s    eta 5s     "
+      "Generated a single JSONL file with 6 samples (1 token repeat) - 440 max words - at ../dataset/shuffle-word-440-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "24-E0_1-mem-ctx-2k.  93%[=================>  ]   2.47G  27.4MB/s    eta 5s     "
+      "Generated a single JSONL file with 6 samples (1 token repeat) - 445 max words - at ../dataset/shuffle-word-445-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "4-E0_1-mem-ctx-2k.p  94%[=================>  ]   2.48G  27.2MB/s    eta 5s     "
+      "Generated a single JSONL file with 9 samples (1 token repeat) - 255 max words - at ../dataset/shuffle-word-255-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "-E0_1-mem-ctx-2k.pt  94%[=================>  ]   2.48G  27.6MB/s    eta 5s     "
+      "Generated JSONL file with - 80 max words, 100 samples - at ../dataset/gen-word-80-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "E0_1-mem-ctx-2k.pth  94%[=================>  ]   2.49G  28.1MB/s    eta 4s     "
+      "Generated a single JSONL file with 99 samples (20 token repeat) - 530 max words - at ../dataset/shuffle-word-530-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "0_1-mem-ctx-2k.pth   94%[=================>  ]   2.49G  28.1MB/s    eta 4s     "
+      "Generated JSONL file with - 485 max words, 100 samples - at ../dataset/gen-word-485-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "_1-mem-ctx-2k.pth    94%[=================>  ]   2.50G  28.3MB/s    eta 4s     "
+      "Generated JSONL file with - 355 max words, 100 samples - at ../dataset/gen-word-355-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "1-mem-ctx-2k.pth     95%[==================> ]   2.50G  28.1MB/s    eta 4s     "
+      "Generated a single JSONL file with 7 samples (1 token repeat) - 375 max words - at ../dataset/shuffle-word-375-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "-mem-ctx-2k.pth      95%[==================> ]   2.51G  29.0MB/s    eta 4s     "
+      "Generated a single JSONL file with 6 samples (1 token repeat) - 420 max words - at ../dataset/shuffle-word-420-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "mem-ctx-2k.pth       95%[==================> ]   2.52G  28.5MB/s    eta 3s     "
+      "Generated JSONL file with - 155 max words, 100 samples - at ../dataset/gen-word-155-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "em-ctx-2k.pth        95%[==================> ]   2.52G  28.5MB/s    eta 3s     "
+      "Generated JSONL file with - 245 max words, 100 samples - at ../dataset/gen-word-245-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "m-ctx-2k.pth         96%[==================> ]   2.53G  28.2MB/s    eta 3s     "
+      "Generated a single JSONL file with 10 samples (1 token repeat) - 265 max words - at ../dataset/shuffle-word-265-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "-ctx-2k.pth          96%[==================> ]   2.53G  28.3MB/s    eta 3s     "
+      "Generated JSONL file with - 315 max words, 100 samples - at ../dataset/gen-word-315-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "ctx-2k.pth           96%[==================> ]   2.54G  28.8MB/s    eta 3s     "
+      "Generated JSONL file with - 160 max words, 100 samples - at ../dataset/gen-word-160-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "tx-2k.pth            96%[==================> ]   2.55G  28.7MB/s    eta 2s     "
+      "Generated a single JSONL file with 6 samples (1 token repeat) - 435 max words - at ../dataset/shuffle-word-435-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "x-2k.pth             96%[==================> ]   2.55G  28.8MB/s    eta 2s     "
+      "Generated a single JSONL file with 5 samples (1 token repeat) - 475 max words - at ../dataset/shuffle-word-475-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "-2k.pth              97%[==================> ]   2.56G  28.5MB/s    eta 2s     "
+      "Generated a single JSONL file with 10 samples (1 token repeat) - 250 max words - at ../dataset/shuffle-word-250-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "2k.pth               97%[==================> ]   2.56G  28.8MB/s    eta 2s     "
+      "Generated a single JSONL file with 6 samples (1 token repeat) - 410 max words - at ../dataset/shuffle-word-410-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "k.pth                97%[==================> ]   2.57G  29.0MB/s    eta 2s     "
+      "Generated a single JSONL file with 6 samples (1 token repeat) - 470 max words - at ../dataset/shuffle-word-470-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      ".pth                 97%[==================> ]   2.58G  28.9MB/s    eta 2s     "
+      "Generated a single JSONL file with 7 samples (1 token repeat) - 380 max words - at ../dataset/shuffle-word-380-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "pth                  98%[==================> ]   2.58G  28.5MB/s    eta 2s     "
+      "Generated JSONL file with - 425 max words, 100 samples - at ../dataset/gen-word-425-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "th                   98%[==================> ]   2.59G  28.6MB/s    eta 2s     "
+      "Generated a single JSONL file with 7 samples (1 token repeat) - 330 max words - at ../dataset/shuffle-word-330-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "h                    98%[==================> ]   2.59G  27.3MB/s    eta 2s     "
+      "Generated JSONL file with - 225 max words, 100 samples - at ../dataset/gen-word-225-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "                     98%[==================> ]   2.60G  29.3MB/s    eta 2s     "
+      "Generated a single JSONL file with 13 samples (1 token repeat) - 200 max words - at ../dataset/shuffle-word-200-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "                  v  98%[==================> ]   2.61G  29.2MB/s    eta 1s     "
+      "Generated a single JSONL file with 99 samples (20 token repeat) - 565 max words - at ../dataset/shuffle-word-565-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "                 v5  99%[==================> ]   2.61G  29.4MB/s    eta 1s     "
+      "Generated JSONL file with - 430 max words, 100 samples - at ../dataset/gen-word-430-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "                v5-  99%[==================> ]   2.62G  29.1MB/s    eta 1s     "
+      "Generated a single JSONL file with 6 samples (1 token repeat) - 415 max words - at ../dataset/shuffle-word-415-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "               v5-L  99%[==================> ]   2.62G  28.9MB/s    eta 1s     "
+      "Generated a single JSONL file with 7 samples (1 token repeat) - 350 max words - at ../dataset/shuffle-word-350-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "              v5-L9  99%[==================> ]   2.63G  29.4MB/s    eta 1s     "
+      "Generated a single JSONL file with 81 samples (20 token repeat) - 615 max words - at ../dataset/shuffle-word-615-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\r",
-      "v5-L96-D1024-E0_1-m 100%[===================>]   2.63G  29.8MB/s    in 74s     \r\n",
-      "\r\n",
-      "2023-09-01 13:54:48 (36.5 MB/s) - ‘v5-L96-D1024-E0_1-mem-ctx-2k.pth’ saved [2825976699/2825976699]\r\n",
-      "\r\n"
+      "Generated a single JSONL file with 67 samples (20 token repeat) - 870 max words - at ../dataset/shuffle-word-870-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "total 2.7G\r\n",
-      "drwxr-xr-x  2 root root   54 Sep  1 13:53 .\r\n",
-      "drwxr-xr-x 19 root root 4.0K Sep  1 13:53 ..\r\n",
-      "-rw-r--r--  1 root root 2.7G Sep  1 08:04 v5-L96-D1024-E0_1-mem-ctx-2k.pth\r\n"
+      "Generated JSONL file with - 570 max words, 200 samples - at ../dataset/gen-word-570-count.jsonl\n"
      ]
-    }
-   ],
-   "source": [
-    "# Download the model directly (stop gap till HF sync issues is resolved)\n",
-    "# !cd \"{TRAINER_DIR}\" && cd \"../model/\" && \\\n",
-    "#     wget -nc \"https://huggingface.co/rwkv-x-dev/rwkv-x-playground/resolve/main/experiment/rwkv-x-exp/v5-memory/{FILENAME_PREFIX}-mem-ctx-2k.pth\"\n",
-    "!cd \"{TRAINER_DIR}\" && cd \"../model/\" && \\\n",
-    "    wget -nc \"https://huggingface.co/rwkv-x-dev/rwkv-x-playground/resolve/main/experiment/rwkv-x-exp/v5-memory/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/model/v5-L96-D1024-E0_1-mem-ctx-2k.pth\"\n",
-    "\n",
-    "!cd \"{TRAINER_DIR}\" && cd \"../model/\" && \\\n",
-    "    ls -alh ."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "9e803f14",
-   "metadata": {
-    "papermill": {
-     "duration": 0.018596,
-     "end_time": "2023-09-01T13:54:48.477825",
-     "exception": false,
-     "start_time": "2023-09-01T13:54:48.459229",
-     "status": "completed"
-    },
-    "tags": []
-   },
-   "source": [
-    "## Tune 5 : Ramping up the ctx size (4096), memory training\n",
-    "\n",
-    "- Tune 5: Mid ctx size (4096), Scaling up!"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "65983184",
-   "metadata": {
-    "execution": {
-     "iopub.execute_input": "2023-09-01T13:54:48.516375Z",
-     "iopub.status.busy": "2023-09-01T13:54:48.516156Z",
-     "iopub.status.idle": "2023-09-01T13:54:53.010023Z",
-     "shell.execute_reply": "2023-09-01T13:54:53.007633Z"
-    },
-    "papermill": {
-     "duration": 5.038863,
-     "end_time": "2023-09-01T13:54:53.535167",
-     "exception": false,
-     "start_time": "2023-09-01T13:54:48.496304",
-     "status": "completed"
     },
-    "tags": []
-   },
-   "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "## Generating word reptition dataset ##\n"
+      "Generated a single JSONL file with 65 samples (20 token repeat) - 865 max words - at ../dataset/shuffle-word-865-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 a single JSONL file with 6 samples (1 token repeat) - 430 max words - at ../dataset/shuffle-word-430-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 267 samples (1 token repeat) - 10 max words - at ../dataset/shuffle-word-10-count.jsonl\n"
+      "Generated JSONL file with - 455 max words, 100 samples - at ../dataset/gen-word-455-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 51 samples (1 token repeat) - 50 max words - at ../dataset/shuffle-word-50-count.jsonl\n"
+      "Generated a single JSONL file with 65 samples (20 token repeat) - 850 max words - at ../dataset/shuffle-word-850-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2 max words, 100 samples - at ../dataset/word-2-count.jsonl\n"
+      "Generated a single JSONL file with 79 samples (20 token repeat) - 795 max words - at ../dataset/shuffle-word-795-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 49 samples (1 token repeat) - 55 max words - at ../dataset/shuffle-word-55-count.jsonl\n"
+      "Generated a single JSONL file with 60 samples (20 token repeat) - 945 max words - at ../dataset/shuffle-word-945-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 15 max words, 100 samples - at ../dataset/gen-word-15-count.jsonl\n"
+      "Generated a single JSONL file with 60 samples (20 token repeat) - 1045 max words - at ../dataset/shuffle-word-1045-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 132 samples (1 token repeat) - 20 max words - at ../dataset/shuffle-word-20-count.jsonl\n"
+      "Generated JSONL file with - 615 max words, 200 samples - at ../dataset/gen-word-615-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 178 samples (1 token repeat) - 15 max words - at ../dataset/shuffle-word-15-count.jsonl\n"
+      "Generated a single JSONL file with 80 samples (20 token repeat) - 695 max words - at ../dataset/shuffle-word-695-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 - 450 max words, 100 samples - at ../dataset/gen-word-450-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 104 samples (1 token repeat) - 25 max words - at ../dataset/shuffle-word-25-count.jsonl\n"
+      "Generated a single JSONL file with 99 samples (20 token repeat) - 590 max words - at ../dataset/shuffle-word-590-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 a single JSONL file with 100 samples (20 token repeat) - 515 max words - at ../dataset/shuffle-word-515-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 25 max words, 100 samples - at ../dataset/gen-word-25-count.jsonl\n"
+      "Generated a single JSONL file with 6 samples (1 token repeat) - 425 max words - at ../dataset/shuffle-word-425-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 40 max words, 100 samples - at ../dataset/gen-word-40-count.jsonl\n"
+      "Generated JSONL file with - 650 max words, 200 samples - at ../dataset/gen-word-650-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 75 samples (1 token repeat) - 35 max words - at ../dataset/shuffle-word-35-count.jsonl\n"
+      "Generated JSONL file with - 575 max words, 200 samples - at ../dataset/gen-word-575-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 50 max words, 100 samples - at ../dataset/gen-word-50-count.jsonl\n"
+      "Generated a single JSONL file with 7 samples (1 token repeat) - 360 max words - at ../dataset/shuffle-word-360-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 55 max words, 100 samples - at ../dataset/gen-word-55-count.jsonl\n"
+      "Generated a single JSONL file with 49 samples (20 token repeat) - 1245 max words - at ../dataset/shuffle-word-1245-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 45 max words, 100 samples - at ../dataset/gen-word-45-count.jsonl\n"
+      "Generated a single JSONL file with 81 samples (20 token repeat) - 605 max words - at ../dataset/shuffle-word-605-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 85 samples (1 token repeat) - 30 max words - at ../dataset/shuffle-word-30-count.jsonl\n"
+      "Generated a single JSONL file with 7 samples (1 token repeat) - 310 max words - at ../dataset/shuffle-word-310-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 60 max words, 100 samples - at ../dataset/gen-word-60-count.jsonl\n"
+      "Generated JSONL file with - 185 max words, 100 samples - at ../dataset/gen-word-185-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 67 samples (1 token repeat) - 40 max words - at ../dataset/shuffle-word-40-count.jsonl\n"
+      "Generated JSONL file with - 365 max words, 100 samples - at ../dataset/gen-word-365-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 30 max words, 100 samples - at ../dataset/gen-word-30-count.jsonl\n"
+      "Generated JSONL file with - 770 max words, 200 samples - at ../dataset/gen-word-770-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 65 max words, 100 samples - at ../dataset/gen-word-65-count.jsonl\n"
+      "Generated JSONL file with - 325 max words, 100 samples - at ../dataset/gen-word-325-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 JSONL file with - 330 max words, 100 samples - at ../dataset/gen-word-330-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 557 samples (1 token repeat) - 5 max words - at ../dataset/shuffle-word-5-count.jsonl\n"
+      "Generated JSONL file with - 280 max words, 100 samples - at ../dataset/gen-word-280-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 40 samples (20 token repeat) - 1345 max words - at ../dataset/shuffle-word-1345-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 30 samples (1 token repeat) - 85 max words - at ../dataset/shuffle-word-85-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1370 max words - at ../dataset/shuffle-word-1370-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 29 samples (1 token repeat) - 90 max words - at ../dataset/shuffle-word-90-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1440 max words - at ../dataset/shuffle-word-1440-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 60 samples (20 token repeat) - 975 max words - at ../dataset/shuffle-word-975-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 38 samples (1 token repeat) - 70 max words - at ../dataset/shuffle-word-70-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1510 max words - at ../dataset/shuffle-word-1510-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 40 samples (20 token repeat) - 1340 max words - at ../dataset/shuffle-word-1340-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 60 samples (1 token repeat) - 45 max words - at ../dataset/shuffle-word-45-count.jsonl\n"
+      "Generated a single JSONL file with 51 samples (20 token repeat) - 1290 max words - at ../dataset/shuffle-word-1290-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 19 samples (1 token repeat) - 115 max words - at ../dataset/shuffle-word-115-count.jsonl\n"
+      "Generated a single JSONL file with 41 samples (20 token repeat) - 1335 max words - at ../dataset/shuffle-word-1335-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 120 max words, 100 samples - at ../dataset/gen-word-120-count.jsonl\n"
+      "Generated JSONL file with - 495 max words, 100 samples - at ../dataset/gen-word-495-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 63 samples (20 token repeat) - 860 max words - at ../dataset/shuffle-word-860-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 26 samples (1 token repeat) - 100 max words - at ../dataset/shuffle-word-100-count.jsonl\n"
+      "Generated JSONL file with - 815 max words, 200 samples - at ../dataset/gen-word-815-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 115 max words, 100 samples - at ../dataset/gen-word-115-count.jsonl\n"
+      "Generated a single JSONL file with 60 samples (20 token repeat) - 1030 max words - at ../dataset/shuffle-word-1030-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 33 samples (1 token repeat) - 80 max words - at ../dataset/shuffle-word-80-count.jsonl\n"
+      "Generated a single JSONL file with 7 samples (1 token repeat) - 365 max words - at ../dataset/shuffle-word-365-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 17 samples (1 token repeat) - 135 max words - at ../dataset/shuffle-word-135-count.jsonl\n"
+      "Generated a single JSONL file with 80 samples (20 token repeat) - 675 max words - at ../dataset/shuffle-word-675-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 18 samples (1 token repeat) - 120 max words - at ../dataset/shuffle-word-120-count.jsonl\n"
+      "Generated a single JSONL file with 62 samples (20 token repeat) - 875 max words - at ../dataset/shuffle-word-875-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 10 samples (1 token repeat) - 225 max words - at ../dataset/shuffle-word-225-count.jsonl\n"
+      "Generated JSONL file with - 205 max words, 100 samples - at ../dataset/gen-word-205-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 14 samples (1 token repeat) - 175 max words - at ../dataset/shuffle-word-175-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1420 max words - at ../dataset/shuffle-word-1420-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 80 samples (20 token repeat) - 725 max words - at ../dataset/shuffle-word-725-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 9 samples (1 token repeat) - 260 max words - at ../dataset/shuffle-word-260-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1355 max words - at ../dataset/shuffle-word-1355-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 10 samples (1 token repeat) - 215 max words - at ../dataset/shuffle-word-215-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1475 max words - at ../dataset/shuffle-word-1475-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 14 samples (1 token repeat) - 180 max words - at ../dataset/shuffle-word-180-count.jsonl\n"
+      "Generated a single JSONL file with 43 samples (20 token repeat) - 1390 max words - at ../dataset/shuffle-word-1390-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 235 max words, 100 samples - at ../dataset/gen-word-235-count.jsonl\n"
+      "Generated a single JSONL file with 60 samples (20 token repeat) - 1155 max words - at ../dataset/shuffle-word-1155-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 10 samples (1 token repeat) - 240 max words - at ../dataset/shuffle-word-240-count.jsonl\n"
+      "Generated a single JSONL file with 60 samples (20 token repeat) - 1085 max words - at ../dataset/shuffle-word-1085-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 175 max words, 100 samples - at ../dataset/gen-word-175-count.jsonl\n"
+      "Generated JSONL file with - 360 max words, 100 samples - at ../dataset/gen-word-360-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 35 samples (1 token repeat) - 75 max words - at ../dataset/shuffle-word-75-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1650 max words - at ../dataset/shuffle-word-1650-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 18 samples (1 token repeat) - 125 max words - at ../dataset/shuffle-word-125-count.jsonl\n"
+      "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 - 225 max words, 100 samples - at ../dataset/gen-word-225-count.jsonl\n"
+      "Generated a single JSONL file with 64 samples (20 token repeat) - 890 max words - at ../dataset/shuffle-word-890-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 95 max words, 100 samples - at ../dataset/gen-word-95-count.jsonl\n"
+      "Generated a single JSONL file with 100 samples (20 token repeat) - 510 max words - at ../dataset/shuffle-word-510-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 125 max words, 100 samples - at ../dataset/gen-word-125-count.jsonl\n"
+      "Generated JSONL file with - 965 max words, 200 samples - at ../dataset/gen-word-965-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 21 samples (1 token repeat) - 105 max words - at ../dataset/shuffle-word-105-count.jsonl\n"
+      "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 26 samples (1 token repeat) - 95 max words - at ../dataset/shuffle-word-95-count.jsonl\n"
+      "Generated a single JSONL file with 100 samples (20 token repeat) - 520 max words - at ../dataset/shuffle-word-520-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 14 samples (1 token repeat) - 170 max words - at ../dataset/shuffle-word-170-count.jsonl\n"
+      "Generated JSONL file with - 955 max words, 200 samples - at ../dataset/gen-word-955-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 190 max words, 100 samples - at ../dataset/gen-word-190-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1590 max words - at ../dataset/shuffle-word-1590-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 10 samples (1 token repeat) - 210 max words - at ../dataset/shuffle-word-210-count.jsonl\n"
+      "Generated a single JSONL file with 60 samples (20 token repeat) - 1190 max words - at ../dataset/shuffle-word-1190-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 105 max words, 100 samples - at ../dataset/gen-word-105-count.jsonl\n"
+      "Generated a single JSONL file with 60 samples (20 token repeat) - 1175 max words - at ../dataset/shuffle-word-1175-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 370 max words, 100 samples - at ../dataset/gen-word-370-count.jsonl\n"
+      "Generated a single JSONL file with 79 samples (20 token repeat) - 760 max words - at ../dataset/shuffle-word-760-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 45 samples (1 token repeat) - 60 max words - at ../dataset/shuffle-word-60-count.jsonl\n"
+      "Generated a single JSONL file with 9 samples (1 token repeat) - 285 max words - at ../dataset/shuffle-word-285-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 14 samples (1 token repeat) - 165 max words - at ../dataset/shuffle-word-165-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1870 max words - at ../dataset/shuffle-word-1870-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 6 samples (1 token repeat) - 470 max words - at ../dataset/shuffle-word-470-count.jsonl\n"
+      "Generated a single JSONL file with 7 samples (1 token repeat) - 315 max words - at ../dataset/shuffle-word-315-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 10 samples (1 token repeat) - 230 max words - at ../dataset/shuffle-word-230-count.jsonl\n"
+      "Generated a single JSONL file with 60 samples (20 token repeat) - 1125 max words - at ../dataset/shuffle-word-1125-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 16 samples (1 token repeat) - 145 max words - at ../dataset/shuffle-word-145-count.jsonl\n"
+      "Generated JSONL file with - 620 max words, 200 samples - at ../dataset/gen-word-620-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (1 token repeat) - 65 max words - at ../dataset/shuffle-word-65-count.jsonl\n"
+      "Generated a single JSONL file with 60 samples (20 token repeat) - 1040 max words - at ../dataset/shuffle-word-1040-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 90 max words, 100 samples - at ../dataset/gen-word-90-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1835 max words - at ../dataset/shuffle-word-1835-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 270 max words, 100 samples - at ../dataset/gen-word-270-count.jsonl\n"
+      "Generated a single JSONL file with 53 samples (20 token repeat) - 1265 max words - at ../dataset/shuffle-word-1265-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 265 max words, 100 samples - at ../dataset/gen-word-265-count.jsonl\n"
+      "Generated JSONL file with - 465 max words, 100 samples - at ../dataset/gen-word-465-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 13 samples (1 token repeat) - 195 max words - at ../dataset/shuffle-word-195-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1595 max words - at ../dataset/shuffle-word-1595-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 160 max words, 100 samples - at ../dataset/gen-word-160-count.jsonl\n"
+      "Generated a single JSONL file with 60 samples (20 token repeat) - 920 max words - at ../dataset/shuffle-word-920-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 255 max words, 100 samples - at ../dataset/gen-word-255-count.jsonl\n"
+      "Generated JSONL file with - 1120 max words, 200 samples - at ../dataset/gen-word-1120-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 200 max words, 100 samples - at ../dataset/gen-word-200-count.jsonl\n"
+      "Generated a single JSONL file with 49 samples (20 token repeat) - 1295 max words - at ../dataset/shuffle-word-1295-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 99 samples (20 token repeat) - 585 max words - at ../dataset/shuffle-word-585-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1430 max words - at ../dataset/shuffle-word-1430-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 180 max words, 100 samples - at ../dataset/gen-word-180-count.jsonl\n"
+      "Generated a single JSONL file with 80 samples (20 token repeat) - 775 max words - at ../dataset/shuffle-word-775-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 195 max words, 100 samples - at ../dataset/gen-word-195-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1635 max words - at ../dataset/shuffle-word-1635-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 81 samples (20 token repeat) - 680 max words - at ../dataset/shuffle-word-680-count.jsonl\n"
+      "Generated JSONL file with - 255 max words, 100 samples - at ../dataset/gen-word-255-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 14 samples (1 token repeat) - 200 max words - at ../dataset/shuffle-word-200-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1520 max words - at ../dataset/shuffle-word-1520-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 210 max words, 100 samples - at ../dataset/gen-word-210-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1680 max words - at ../dataset/shuffle-word-1680-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 19 samples (1 token repeat) - 110 max words - at ../dataset/shuffle-word-110-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1665 max words - at ../dataset/shuffle-word-1665-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 185 max words, 100 samples - at ../dataset/gen-word-185-count.jsonl\n"
+      "Generated a single JSONL file with 7 samples (1 token repeat) - 305 max words - at ../dataset/shuffle-word-305-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 7 samples (1 token repeat) - 325 max words - at ../dataset/shuffle-word-325-count.jsonl\n"
+      "Generated JSONL file with - 195 max words, 100 samples - at ../dataset/gen-word-195-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 16 samples (1 token repeat) - 150 max words - at ../dataset/shuffle-word-150-count.jsonl\n"
+      "Generated a single JSONL file with 60 samples (20 token repeat) - 955 max words - at ../dataset/shuffle-word-955-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 355 max words, 100 samples - at ../dataset/gen-word-355-count.jsonl\n"
+      "Generated JSONL file with - 845 max words, 200 samples - at ../dataset/gen-word-845-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 135 max words, 100 samples - at ../dataset/gen-word-135-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1775 max words - at ../dataset/shuffle-word-1775-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 100 samples (20 token repeat) - 530 max words - at ../dataset/shuffle-word-530-count.jsonl\n"
+      "Generated a single JSONL file with 60 samples (20 token repeat) - 1070 max words - at ../dataset/shuffle-word-1070-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 140 max words, 100 samples - at ../dataset/gen-word-140-count.jsonl\n"
+      "Generated a single JSONL file with 83 samples (20 token repeat) - 640 max words - at ../dataset/shuffle-word-640-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 565 max words, 200 samples - at ../dataset/gen-word-565-count.jsonl\n"
+      "Generated JSONL file with - 940 max words, 200 samples - at ../dataset/gen-word-940-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 17 samples (1 token repeat) - 140 max words - at ../dataset/shuffle-word-140-count.jsonl\n"
+      "Generated a single JSONL file with 60 samples (20 token repeat) - 1025 max words - at ../dataset/shuffle-word-1025-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 80 samples (20 token repeat) - 630 max words - at ../dataset/shuffle-word-630-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1790 max words - at ../dataset/shuffle-word-1790-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 230 max words, 100 samples - at ../dataset/gen-word-230-count.jsonl\n"
+      "Generated JSONL file with - 500 max words, 100 samples - at ../dataset/gen-word-500-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 560 max words, 200 samples - at ../dataset/gen-word-560-count.jsonl\n"
+      "Generated a single JSONL file with 60 samples (20 token repeat) - 905 max words - at ../dataset/shuffle-word-905-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 100 samples (20 token repeat) - 565 max words - at ../dataset/shuffle-word-565-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1465 max words - at ../dataset/shuffle-word-1465-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 450 max words, 100 samples - at ../dataset/gen-word-450-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1660 max words - at ../dataset/shuffle-word-1660-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 65 samples (20 token repeat) - 815 max words - at ../dataset/shuffle-word-815-count.jsonl\n"
+      "Generated a single JSONL file with 62 samples (20 token repeat) - 805 max words - at ../dataset/shuffle-word-805-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 6 samples (1 token repeat) - 480 max words - at ../dataset/shuffle-word-480-count.jsonl\n"
+      "Generated a single JSONL file with 60 samples (20 token repeat) - 985 max words - at ../dataset/shuffle-word-985-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 9 samples (1 token repeat) - 300 max words - at ../dataset/shuffle-word-300-count.jsonl\n"
+      "Generated JSONL file with - 1105 max words, 200 samples - at ../dataset/gen-word-1105-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 60 samples (20 token repeat) - 910 max words - at ../dataset/shuffle-word-910-count.jsonl\n"
+      "Generated a single JSONL file with 49 samples (20 token repeat) - 1230 max words - at ../dataset/shuffle-word-1230-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 9 samples (1 token repeat) - 235 max words - at ../dataset/shuffle-word-235-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1350 max words - at ../dataset/shuffle-word-1350-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 41 samples (20 token repeat) - 1320 max words - at ../dataset/shuffle-word-1320-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1545 max words - at ../dataset/shuffle-word-1545-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 60 samples (20 token repeat) - 1095 max words - at ../dataset/shuffle-word-1095-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1585 max words - at ../dataset/shuffle-word-1585-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 60 samples (20 token repeat) - 920 max words - at ../dataset/shuffle-word-920-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1490 max words - at ../dataset/shuffle-word-1490-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 60 samples (20 token repeat) - 905 max words - at ../dataset/shuffle-word-905-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1535 max words - at ../dataset/shuffle-word-1535-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 61 samples (20 token repeat) - 845 max words - at ../dataset/shuffle-word-845-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1640 max words - at ../dataset/shuffle-word-1640-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 630 max words, 200 samples - at ../dataset/gen-word-630-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1805 max words - at ../dataset/shuffle-word-1805-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 595 max words, 200 samples - at ../dataset/gen-word-595-count.jsonl\n"
+      "Generated JSONL file with - 370 max words, 100 samples - at ../dataset/gen-word-370-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 400 max words, 100 samples - at ../dataset/gen-word-400-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1605 max words - at ../dataset/shuffle-word-1605-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 660 max words, 200 samples - at ../dataset/gen-word-660-count.jsonl\n"
+      "Generated a single JSONL file with 60 samples (20 token repeat) - 960 max words - at ../dataset/shuffle-word-960-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 62 samples (20 token repeat) - 865 max words - at ../dataset/shuffle-word-865-count.jsonl\n"
+      "Generated a single JSONL file with 78 samples (20 token repeat) - 780 max words - at ../dataset/shuffle-word-780-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 240 max words, 100 samples - at ../dataset/gen-word-240-count.jsonl\n"
+      "Generated a single JSONL file with 100 samples (20 token repeat) - 555 max words - at ../dataset/shuffle-word-555-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 15 samples (1 token repeat) - 155 max words - at ../dataset/shuffle-word-155-count.jsonl\n"
+      "Generated JSONL file with - 490 max words, 100 samples - at ../dataset/gen-word-490-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 80 samples (20 token repeat) - 640 max words - at ../dataset/shuffle-word-640-count.jsonl\n"
+      "Generated JSONL file with - 930 max words, 200 samples - at ../dataset/gen-word-930-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 6 samples (1 token repeat) - 420 max words - at ../dataset/shuffle-word-420-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1620 max words - at ../dataset/shuffle-word-1620-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 295 max words, 100 samples - at ../dataset/gen-word-295-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1410 max words - at ../dataset/shuffle-word-1410-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 60 samples (20 token repeat) - 1075 max words - at ../dataset/shuffle-word-1075-count.jsonl\n"
+      "Generated JSONL file with - 215 max words, 100 samples - at ../dataset/gen-word-215-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 60 samples (20 token repeat) - 925 max words - at ../dataset/shuffle-word-925-count.jsonl\n"
+      "Generated a single JSONL file with 60 samples (20 token repeat) - 1160 max words - at ../dataset/shuffle-word-1160-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 64 samples (20 token repeat) - 825 max words - at ../dataset/shuffle-word-825-count.jsonl\n"
+      "Generated JSONL file with - 230 max words, 100 samples - at ../dataset/gen-word-230-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 80 samples (20 token repeat) - 610 max words - at ../dataset/shuffle-word-610-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1615 max words - at ../dataset/shuffle-word-1615-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 17 samples (1 token repeat) - 130 max words - at ../dataset/shuffle-word-130-count.jsonl\n"
+      "Generated JSONL file with - 705 max words, 200 samples - at ../dataset/gen-word-705-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 60 samples (20 token repeat) - 1125 max words - at ../dataset/shuffle-word-1125-count.jsonl\n"
+      "Generated a single JSONL file with 51 samples (20 token repeat) - 1300 max words - at ../dataset/shuffle-word-1300-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 6 samples (1 token repeat) - 410 max words - at ../dataset/shuffle-word-410-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1825 max words - at ../dataset/shuffle-word-1825-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 7 samples (1 token repeat) - 380 max words - at ../dataset/shuffle-word-380-count.jsonl\n"
+      "Generated JSONL file with - 625 max words, 200 samples - at ../dataset/gen-word-625-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 55 samples (20 token repeat) - 1215 max words - at ../dataset/shuffle-word-1215-count.jsonl\n"
+      "Generated a single JSONL file with 52 samples (20 token repeat) - 1270 max words - at ../dataset/shuffle-word-1270-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 60 samples (20 token repeat) - 1160 max words - at ../dataset/shuffle-word-1160-count.jsonl\n"
+      "Generated a single JSONL file with 55 samples (20 token repeat) - 1210 max words - at ../dataset/shuffle-word-1210-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 63 samples (20 token repeat) - 895 max words - at ../dataset/shuffle-word-895-count.jsonl\n"
+      "Generated JSONL file with - 265 max words, 100 samples - at ../dataset/gen-word-265-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 80 samples (20 token repeat) - 750 max words - at ../dataset/shuffle-word-750-count.jsonl\n"
+      "Generated JSONL file with - 920 max words, 200 samples - at ../dataset/gen-word-920-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 7 samples (1 token repeat) - 350 max words - at ../dataset/shuffle-word-350-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1470 max words - at ../dataset/shuffle-word-1470-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 80 samples (20 token repeat) - 615 max words - at ../dataset/shuffle-word-615-count.jsonl\n"
+      "Generated a single JSONL file with 81 samples (20 token repeat) - 630 max words - at ../dataset/shuffle-word-630-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 62 samples (20 token repeat) - 885 max words - at ../dataset/shuffle-word-885-count.jsonl\n"
+      "Generated a single JSONL file with 50 samples (20 token repeat) - 1235 max words - at ../dataset/shuffle-word-1235-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 170 max words, 100 samples - at ../dataset/gen-word-170-count.jsonl\n"
+      "Generated JSONL file with - 665 max words, 200 samples - at ../dataset/gen-word-665-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 80 samples (20 token repeat) - 720 max words - at ../dataset/shuffle-word-720-count.jsonl\n"
+      "Generated a single JSONL file with 100 samples (20 token repeat) - 545 max words - at ../dataset/shuffle-word-545-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1565 max words - at ../dataset/shuffle-word-1565-count.jsonl\n"
+      "Generated a single JSONL file with 80 samples (20 token repeat) - 745 max words - at ../dataset/shuffle-word-745-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 7 samples (1 token repeat) - 390 max words - at ../dataset/shuffle-word-390-count.jsonl\n"
+      "Generated JSONL file with - 410 max words, 100 samples - at ../dataset/gen-word-410-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 80 samples (20 token repeat) - 690 max words - at ../dataset/shuffle-word-690-count.jsonl\n"
+      "Generated a single JSONL file with 100 samples (20 token repeat) - 595 max words - at ../dataset/shuffle-word-595-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 60 samples (20 token repeat) - 930 max words - at ../dataset/shuffle-word-930-count.jsonl\n"
+      "Generated a single JSONL file with 80 samples (20 token repeat) - 735 max words - at ../dataset/shuffle-word-735-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1350 max words - at ../dataset/shuffle-word-1350-count.jsonl\n"
+      "Generated a single JSONL file with 7 samples (1 token repeat) - 390 max words - at ../dataset/shuffle-word-390-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1420 max words - at ../dataset/shuffle-word-1420-count.jsonl\n"
+      "Generated a single JSONL file with 6 samples (1 token repeat) - 485 max words - at ../dataset/shuffle-word-485-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 10 samples (1 token repeat) - 220 max words - at ../dataset/shuffle-word-220-count.jsonl\n"
+      "Generated a single JSONL file with 6 samples (1 token repeat) - 455 max words - at ../dataset/shuffle-word-455-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 8 samples (1 token repeat) - 375 max words - at ../dataset/shuffle-word-375-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1950 max words - at ../dataset/shuffle-word-1950-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 60 samples (20 token repeat) - 985 max words - at ../dataset/shuffle-word-985-count.jsonl\n"
+      "Generated a single JSONL file with 60 samples (20 token repeat) - 1080 max words - at ../dataset/shuffle-word-1080-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 80 samples (20 token repeat) - 795 max words - at ../dataset/shuffle-word-795-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1375 max words - at ../dataset/shuffle-word-1375-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 80 samples (20 token repeat) - 645 max words - at ../dataset/shuffle-word-645-count.jsonl\n"
+      "Generated a single JSONL file with 41 samples (20 token repeat) - 1310 max words - at ../dataset/shuffle-word-1310-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 80 samples (20 token repeat) - 660 max words - at ../dataset/shuffle-word-660-count.jsonl\n"
+      "Generated JSONL file with - 440 max words, 100 samples - at ../dataset/gen-word-440-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 48 samples (20 token repeat) - 1220 max words - at ../dataset/shuffle-word-1220-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1840 max words - at ../dataset/shuffle-word-1840-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 81 samples (20 token repeat) - 695 max words - at ../dataset/shuffle-word-695-count.jsonl\n"
+      "Generated JSONL file with - 1185 max words, 200 samples - at ../dataset/gen-word-1185-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1915 max words - at ../dataset/shuffle-word-1915-count.jsonl\n"
+      "Generated a single JSONL file with 7 samples (1 token repeat) - 370 max words - at ../dataset/shuffle-word-370-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 60 samples (20 token repeat) - 1020 max words - at ../dataset/shuffle-word-1020-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1915 max words - at ../dataset/shuffle-word-1915-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 99 samples (20 token repeat) - 520 max words - at ../dataset/shuffle-word-520-count.jsonl\n"
+      "Generated a single JSONL file with 16 samples (1 token repeat) - 135 max words - at ../dataset/shuffle-word-135-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 80 samples (20 token repeat) - 620 max words - at ../dataset/shuffle-word-620-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1675 max words - at ../dataset/shuffle-word-1675-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 685 max words, 200 samples - at ../dataset/gen-word-685-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2010 max words - at ../dataset/shuffle-word-2010-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 60 samples (20 token repeat) - 1010 max words - at ../dataset/shuffle-word-1010-count.jsonl\n"
+      "Generated JSONL file with - 895 max words, 200 samples - at ../dataset/gen-word-895-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 7 samples (1 token repeat) - 360 max words - at ../dataset/shuffle-word-360-count.jsonl\n"
+      "Generated a single JSONL file with 59 samples (20 token repeat) - 1170 max words - at ../dataset/shuffle-word-1170-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 80 samples (20 token repeat) - 665 max words - at ../dataset/shuffle-word-665-count.jsonl\n"
+      "Generated JSONL file with - 345 max words, 100 samples - at ../dataset/gen-word-345-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 215 max words, 100 samples - at ../dataset/gen-word-215-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2035 max words - at ../dataset/shuffle-word-2035-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 63 samples (20 token repeat) - 890 max words - at ../dataset/shuffle-word-890-count.jsonl\n"
+      "Generated JSONL file with - 1330 max words, 200 samples - at ../dataset/gen-word-1330-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1475 max words - at ../dataset/shuffle-word-1475-count.jsonl\n"
+      "Generated a single JSONL file with 60 samples (20 token repeat) - 1010 max words - at ../dataset/shuffle-word-1010-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 9 samples (1 token repeat) - 290 max words - at ../dataset/shuffle-word-290-count.jsonl\n"
+      "Generated JSONL file with - 480 max words, 100 samples - at ../dataset/gen-word-480-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 80 samples (20 token repeat) - 760 max words - at ../dataset/shuffle-word-760-count.jsonl\n"
+      "Generated JSONL file with - 585 max words, 200 samples - at ../dataset/gen-word-585-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 80 samples (20 token repeat) - 745 max words - at ../dataset/shuffle-word-745-count.jsonl\n"
+      "Generated a single JSONL file with 80 samples (20 token repeat) - 740 max words - at ../dataset/shuffle-word-740-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 79 samples (20 token repeat) - 715 max words - at ../dataset/shuffle-word-715-count.jsonl\n"
+      "Generated JSONL file with - 1460 max words, 200 samples - at ../dataset/gen-word-1460-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1705 max words - at ../dataset/shuffle-word-1705-count.jsonl\n"
+      "Generated JSONL file with - 190 max words, 100 samples - at ../dataset/gen-word-190-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 52 samples (20 token repeat) - 1225 max words - at ../dataset/shuffle-word-1225-count.jsonl\n"
+      "Generated a single JSONL file with 11 samples (1 token repeat) - 205 max words - at ../dataset/shuffle-word-205-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 80 samples (20 token repeat) - 765 max words - at ../dataset/shuffle-word-765-count.jsonl\n"
+      "Generated a single JSONL file with 6 samples (1 token repeat) - 465 max words - at ../dataset/shuffle-word-465-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 7 samples (1 token repeat) - 330 max words - at ../dataset/shuffle-word-330-count.jsonl\n"
+      "Generated a single JSONL file with 49 samples (20 token repeat) - 1275 max words - at ../dataset/shuffle-word-1275-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 6 samples (1 token repeat) - 435 max words - at ../dataset/shuffle-word-435-count.jsonl\n"
+      "Generated JSONL file with - 260 max words, 100 samples - at ../dataset/gen-word-260-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1825 max words - at ../dataset/shuffle-word-1825-count.jsonl\n"
+      "Generated a single JSONL file with 8 samples (1 token repeat) - 325 max words - at ../dataset/shuffle-word-325-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 62 samples (20 token repeat) - 840 max words - at ../dataset/shuffle-word-840-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1795 max words - at ../dataset/shuffle-word-1795-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 60 samples (20 token repeat) - 990 max words - at ../dataset/shuffle-word-990-count.jsonl\n"
+      "Generated JSONL file with - 1575 max words, 200 samples - at ../dataset/gen-word-1575-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 7 samples (1 token repeat) - 340 max words - at ../dataset/shuffle-word-340-count.jsonl\n"
+      "Generated a single JSONL file with 37 samples (20 token repeat) - 2430 max words - at ../dataset/shuffle-word-2430-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1710 max words - at ../dataset/shuffle-word-1710-count.jsonl\n"
+      "Generated JSONL file with - 240 max words, 100 samples - at ../dataset/gen-word-240-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 60 samples (20 token repeat) - 980 max words - at ../dataset/shuffle-word-980-count.jsonl\n"
+      "Generated a single JSONL file with 99 samples (20 token repeat) - 585 max words - at ../dataset/shuffle-word-585-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 78 samples (20 token repeat) - 800 max words - at ../dataset/shuffle-word-800-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1765 max words - at ../dataset/shuffle-word-1765-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 9 samples (1 token repeat) - 295 max words - at ../dataset/shuffle-word-295-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1865 max words - at ../dataset/shuffle-word-1865-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 60 samples (20 token repeat) - 965 max words - at ../dataset/shuffle-word-965-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1560 max words - at ../dataset/shuffle-word-1560-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 525 max words, 200 samples - at ../dataset/gen-word-525-count.jsonl\n"
+      "Generated JSONL file with - 740 max words, 200 samples - at ../dataset/gen-word-740-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 280 max words, 100 samples - at ../dataset/gen-word-280-count.jsonl\n"
+      "Generated a single JSONL file with 49 samples (20 token repeat) - 1250 max words - at ../dataset/shuffle-word-1250-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 7 samples (1 token repeat) - 315 max words - at ../dataset/shuffle-word-315-count.jsonl\n"
+      "Generated a single JSONL file with 100 samples (20 token repeat) - 550 max words - at ../dataset/shuffle-word-550-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 150 max words, 100 samples - at ../dataset/gen-word-150-count.jsonl\n"
+      "Generated JSONL file with - 1525 max words, 200 samples - at ../dataset/gen-word-1525-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 155 max words, 100 samples - at ../dataset/gen-word-155-count.jsonl\n"
+      "Generated a single JSONL file with 60 samples (20 token repeat) - 1035 max words - at ../dataset/shuffle-word-1035-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 9 samples (1 token repeat) - 255 max words - at ../dataset/shuffle-word-255-count.jsonl\n"
+      "Generated a single JSONL file with 79 samples (20 token repeat) - 790 max words - at ../dataset/shuffle-word-790-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 62 samples (20 token repeat) - 805 max words - at ../dataset/shuffle-word-805-count.jsonl\n"
+      "Generated JSONL file with - 970 max words, 200 samples - at ../dataset/gen-word-970-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 440 max words, 100 samples - at ../dataset/gen-word-440-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2050 max words - at ../dataset/shuffle-word-2050-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 330 max words, 100 samples - at ../dataset/gen-word-330-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2000 max words - at ../dataset/shuffle-word-2000-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 80 samples (20 token repeat) - 730 max words - at ../dataset/shuffle-word-730-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1920 max words - at ../dataset/shuffle-word-1920-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 62 samples (20 token repeat) - 875 max words - at ../dataset/shuffle-word-875-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2125 max words - at ../dataset/shuffle-word-2125-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 205 max words, 100 samples - at ../dataset/gen-word-205-count.jsonl\n"
+      "Generated JSONL file with - 915 max words, 200 samples - at ../dataset/gen-word-915-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 100 samples (20 token repeat) - 595 max words - at ../dataset/shuffle-word-595-count.jsonl\n"
+      "Generated JSONL file with - 520 max words, 200 samples - at ../dataset/gen-word-520-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1655 max words - at ../dataset/shuffle-word-1655-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1735 max words - at ../dataset/shuffle-word-1735-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 79 samples (20 token repeat) - 785 max words - at ../dataset/shuffle-word-785-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1405 max words - at ../dataset/shuffle-word-1405-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1855 max words - at ../dataset/shuffle-word-1855-count.jsonl\n"
+      "Generated a single JSONL file with 52 samples (20 token repeat) - 1255 max words - at ../dataset/shuffle-word-1255-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 390 max words, 100 samples - at ../dataset/gen-word-390-count.jsonl\n"
+      "Generated JSONL file with - 760 max words, 200 samples - at ../dataset/gen-word-760-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 80 samples (20 token repeat) - 710 max words - at ../dataset/shuffle-word-710-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2070 max words - at ../dataset/shuffle-word-2070-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 64 samples (20 token repeat) - 855 max words - at ../dataset/shuffle-word-855-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1815 max words - at ../dataset/shuffle-word-1815-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 600 max words, 200 samples - at ../dataset/gen-word-600-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1655 max words - at ../dataset/shuffle-word-1655-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1345 max words - at ../dataset/shuffle-word-1345-count.jsonl\n"
+      "Generated JSONL file with - 1000 max words, 200 samples - at ../dataset/gen-word-1000-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 60 samples (20 token repeat) - 945 max words - at ../dataset/shuffle-word-945-count.jsonl\n"
+      "Generated JSONL file with - 210 max words, 100 samples - at ../dataset/gen-word-210-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 80 samples (20 token repeat) - 670 max words - at ../dataset/shuffle-word-670-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2025 max words - at ../dataset/shuffle-word-2025-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 6 samples (1 token repeat) - 485 max words - at ../dataset/shuffle-word-485-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1975 max words - at ../dataset/shuffle-word-1975-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 38 samples (20 token repeat) - 2445 max words - at ../dataset/shuffle-word-2445-count.jsonl\n"
+      "Generated JSONL file with - 1850 max words, 200 samples - at ../dataset/gen-word-1850-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 81 samples (20 token repeat) - 675 max words - at ../dataset/shuffle-word-675-count.jsonl\n"
+      "Generated a single JSONL file with 6 samples (1 token repeat) - 480 max words - at ../dataset/shuffle-word-480-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1330 max words - at ../dataset/shuffle-word-1330-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1565 max words - at ../dataset/shuffle-word-1565-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1910 max words - at ../dataset/shuffle-word-1910-count.jsonl\n"
+      "Generated JSONL file with - 1840 max words, 200 samples - at ../dataset/gen-word-1840-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 5 samples (1 token repeat) - 490 max words - at ../dataset/shuffle-word-490-count.jsonl\n"
+      "Generated JSONL file with - 350 max words, 100 samples - at ../dataset/gen-word-350-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1620 max words - at ../dataset/shuffle-word-1620-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1985 max words - at ../dataset/shuffle-word-1985-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 80 samples (20 token repeat) - 655 max words - at ../dataset/shuffle-word-655-count.jsonl\n"
+      "Generated a single JSONL file with 60 samples (20 token repeat) - 1130 max words - at ../dataset/shuffle-word-1130-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 41 samples (20 token repeat) - 1470 max words - at ../dataset/shuffle-word-1470-count.jsonl\n"
+      "Generated JSONL file with - 540 max words, 200 samples - at ../dataset/gen-word-540-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 640 max words, 200 samples - at ../dataset/gen-word-640-count.jsonl\n"
+      "Generated a single JSONL file with 64 samples (20 token repeat) - 845 max words - at ../dataset/shuffle-word-845-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 60 samples (20 token repeat) - 915 max words - at ../dataset/shuffle-word-915-count.jsonl\n"
+      "Generated JSONL file with - 870 max words, 200 samples - at ../dataset/gen-word-870-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1560 max words - at ../dataset/shuffle-word-1560-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1575 max words - at ../dataset/shuffle-word-1575-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1610 max words - at ../dataset/shuffle-word-1610-count.jsonl\n"
+      "Generated a single JSONL file with 64 samples (20 token repeat) - 835 max words - at ../dataset/shuffle-word-835-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2300 max words - at ../dataset/shuffle-word-2300-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1580 max words - at ../dataset/shuffle-word-1580-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 80 samples (20 token repeat) - 725 max words - at ../dataset/shuffle-word-725-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3070 max words - at ../dataset/shuffle-word-3070-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 735 max words, 200 samples - at ../dataset/gen-word-735-count.jsonl\n"
+      "Generated JSONL file with - 445 max words, 100 samples - at ../dataset/gen-word-445-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1880 max words - at ../dataset/shuffle-word-1880-count.jsonl\n"
+      "Generated a single JSONL file with 60 samples (20 token repeat) - 1075 max words - at ../dataset/shuffle-word-1075-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 380 max words, 100 samples - at ../dataset/gen-word-380-count.jsonl\n"
+      "Generated JSONL file with - 1370 max words, 200 samples - at ../dataset/gen-word-1370-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 80 samples (20 token repeat) - 650 max words - at ../dataset/shuffle-word-650-count.jsonl\n"
+      "Generated a single JSONL file with 21 samples (20 token repeat) - 2745 max words - at ../dataset/shuffle-word-2745-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 485 max words, 100 samples - at ../dataset/gen-word-485-count.jsonl\n"
+      "Generated JSONL file with - 655 max words, 200 samples - at ../dataset/gen-word-655-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 695 max words, 200 samples - at ../dataset/gen-word-695-count.jsonl\n"
+      "Generated JSONL file with - 1170 max words, 200 samples - at ../dataset/gen-word-1170-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 63 samples (20 token repeat) - 880 max words - at ../dataset/shuffle-word-880-count.jsonl\n"
+      "Generated JSONL file with - 1320 max words, 200 samples - at ../dataset/gen-word-1320-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 61 samples (20 token repeat) - 810 max words - at ../dataset/shuffle-word-810-count.jsonl\n"
+      "Generated a single JSONL file with 10 samples (1 token repeat) - 270 max words - at ../dataset/shuffle-word-270-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 6 samples (1 token repeat) - 430 max words - at ../dataset/shuffle-word-430-count.jsonl\n"
+      "Generated a single JSONL file with 60 samples (20 token repeat) - 925 max words - at ../dataset/shuffle-word-925-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 535 max words, 200 samples - at ../dataset/gen-word-535-count.jsonl\n"
+      "Generated a single JSONL file with 60 samples (20 token repeat) - 910 max words - at ../dataset/shuffle-word-910-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 62 samples (20 token repeat) - 830 max words - at ../dataset/shuffle-word-830-count.jsonl\n"
+      "Generated JSONL file with - 1115 max words, 200 samples - at ../dataset/gen-word-1115-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 80 samples (20 token repeat) - 755 max words - at ../dataset/shuffle-word-755-count.jsonl\n"
+      "Generated JSONL file with - 1130 max words, 200 samples - at ../dataset/gen-word-1130-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1945 max words - at ../dataset/shuffle-word-1945-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1365 max words - at ../dataset/shuffle-word-1365-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1780 max words - at ../dataset/shuffle-word-1780-count.jsonl\n"
+      "Generated JSONL file with - 1345 max words, 200 samples - at ../dataset/gen-word-1345-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 245 max words, 100 samples - at ../dataset/gen-word-245-count.jsonl\n"
+      "Generated JSONL file with - 1150 max words, 200 samples - at ../dataset/gen-word-1150-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 60 samples (20 token repeat) - 995 max words - at ../dataset/shuffle-word-995-count.jsonl\n"
+      "Generated JSONL file with - 1290 max words, 200 samples - at ../dataset/gen-word-1290-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 80 samples (20 token repeat) - 790 max words - at ../dataset/shuffle-word-790-count.jsonl\n"
+      "Generated JSONL file with - 1035 max words, 200 samples - at ../dataset/gen-word-1035-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 305 max words, 100 samples - at ../dataset/gen-word-305-count.jsonl\n"
+      "Generated a single JSONL file with 9 samples (1 token repeat) - 290 max words - at ../dataset/shuffle-word-290-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 405 max words, 100 samples - at ../dataset/gen-word-405-count.jsonl\n"
+      "Generated JSONL file with - 1360 max words, 200 samples - at ../dataset/gen-word-1360-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 14 samples (1 token repeat) - 190 max words - at ../dataset/shuffle-word-190-count.jsonl\n"
+      "Generated JSONL file with - 1275 max words, 200 samples - at ../dataset/gen-word-1275-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 78 samples (20 token repeat) - 705 max words - at ../dataset/shuffle-word-705-count.jsonl\n"
+      "Generated a single JSONL file with 24 samples (20 token repeat) - 2635 max words - at ../dataset/shuffle-word-2635-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 60 samples (20 token repeat) - 1130 max words - at ../dataset/shuffle-word-1130-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1745 max words - at ../dataset/shuffle-word-1745-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2330 max words - at ../dataset/shuffle-word-2330-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1785 max words - at ../dataset/shuffle-word-1785-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 325 max words, 100 samples - at ../dataset/gen-word-325-count.jsonl\n"
+      "Generated a single JSONL file with 60 samples (20 token repeat) - 1060 max words - at ../dataset/shuffle-word-1060-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 36 samples (20 token repeat) - 2430 max words - at ../dataset/shuffle-word-2430-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 JSONL file with - 880 max words, 200 samples - at ../dataset/gen-word-880-count.jsonl\n"
+      "Generated JSONL file with - 1880 max words, 200 samples - at ../dataset/gen-word-1880-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 80 samples (20 token repeat) - 770 max words - at ../dataset/shuffle-word-770-count.jsonl\n"
+      "Generated a single JSONL file with 82 samples (20 token repeat) - 660 max words - at ../dataset/shuffle-word-660-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2270 max words - at ../dataset/shuffle-word-2270-count.jsonl\n"
+      "Generated a single JSONL file with 82 samples (20 token repeat) - 650 max words - at ../dataset/shuffle-word-650-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 2980 max words - at ../dataset/shuffle-word-2980-count.jsonl\n"
+      "Generated a single JSONL file with 37 samples (20 token repeat) - 2490 max words - at ../dataset/shuffle-word-2490-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 48 samples (20 token repeat) - 1230 max words - at ../dataset/shuffle-word-1230-count.jsonl\n"
+      "Generated JSONL file with - 990 max words, 200 samples - at ../dataset/gen-word-990-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 2880 max words - at ../dataset/shuffle-word-2880-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 38 samples (20 token repeat) - 2475 max words - at ../dataset/shuffle-word-2475-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 JSONL file with - 835 max words, 200 samples - at ../dataset/gen-word-835-count.jsonl\n"
+      "Generated JSONL file with - 1305 max words, 200 samples - at ../dataset/gen-word-1305-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1805 max words - at ../dataset/shuffle-word-1805-count.jsonl\n"
+      "Generated JSONL file with - 1145 max words, 200 samples - at ../dataset/gen-word-1145-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 11 samples (1 token repeat) - 205 max words - at ../dataset/shuffle-word-205-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1555 max words - at ../dataset/shuffle-word-1555-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 755 max words, 200 samples - at ../dataset/gen-word-755-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1990 max words - at ../dataset/shuffle-word-1990-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 6 samples (1 token repeat) - 465 max words - at ../dataset/shuffle-word-465-count.jsonl\n"
+      "Generated a single JSONL file with 80 samples (20 token repeat) - 720 max words - at ../dataset/shuffle-word-720-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 7 samples (1 token repeat) - 370 max words - at ../dataset/shuffle-word-370-count.jsonl\n"
+      "Generated JSONL file with - 1280 max words, 200 samples - at ../dataset/gen-word-1280-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 495 max words, 100 samples - at ../dataset/gen-word-495-count.jsonl\n"
+      "Generated JSONL file with - 1375 max words, 200 samples - at ../dataset/gen-word-1375-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 20 samples (20 token repeat) - 3100 max words - at ../dataset/shuffle-word-3100-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 865 max words, 200 samples - at ../dataset/gen-word-865-count.jsonl\n"
+      "Generated a single JSONL file with 99 samples (20 token repeat) - 505 max words - at ../dataset/shuffle-word-505-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1390 max words - at ../dataset/shuffle-word-1390-count.jsonl\n"
+      "Generated a single JSONL file with 81 samples (20 token repeat) - 635 max words - at ../dataset/shuffle-word-635-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 145 max words, 100 samples - at ../dataset/gen-word-145-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3065 max words - at ../dataset/shuffle-word-3065-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 165 max words, 100 samples - at ../dataset/gen-word-165-count.jsonl\n"
+      "Generated JSONL file with - 1380 max words, 200 samples - at ../dataset/gen-word-1380-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 49 samples (20 token repeat) - 1295 max words - at ../dataset/shuffle-word-1295-count.jsonl\n"
+      "Generated a single JSONL file with 60 samples (20 token repeat) - 1165 max words - at ../dataset/shuffle-word-1165-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 635 max words, 200 samples - at ../dataset/gen-word-635-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1940 max words - at ../dataset/shuffle-word-1940-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 100 samples (20 token repeat) - 510 max words - at ../dataset/shuffle-word-510-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2175 max words - at ../dataset/shuffle-word-2175-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 66 samples (20 token repeat) - 835 max words - at ../dataset/shuffle-word-835-count.jsonl\n"
+      "Generated JSONL file with - 670 max words, 200 samples - at ../dataset/gen-word-670-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1630 max words - at ../dataset/shuffle-word-1630-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2180 max words - at ../dataset/shuffle-word-2180-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1770 max words, 200 samples - at ../dataset/gen-word-1770-count.jsonl\n"
+      "Generated JSONL file with - 380 max words, 100 samples - at ../dataset/gen-word-380-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1360 max words - at ../dataset/shuffle-word-1360-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1895 max words - at ../dataset/shuffle-word-1895-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 99 samples (20 token repeat) - 590 max words - at ../dataset/shuffle-word-590-count.jsonl\n"
+      "Generated JSONL file with - 1175 max words, 200 samples - at ../dataset/gen-word-1175-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 83 samples (20 token repeat) - 685 max words - at ../dataset/shuffle-word-685-count.jsonl\n"
+      "Generated a single JSONL file with 61 samples (20 token repeat) - 840 max words - at ../dataset/shuffle-word-840-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 9 samples (1 token repeat) - 270 max words - at ../dataset/shuffle-word-270-count.jsonl\n"
+      "Generated a single JSONL file with 38 samples (20 token repeat) - 2410 max words - at ../dataset/shuffle-word-2410-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2375 max words - at ../dataset/shuffle-word-2375-count.jsonl\n"
+      "Generated JSONL file with - 1215 max words, 200 samples - at ../dataset/gen-word-1215-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 60 samples (20 token repeat) - 1175 max words - at ../dataset/shuffle-word-1175-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1890 max words - at ../dataset/shuffle-word-1890-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 6 samples (1 token repeat) - 500 max words - at ../dataset/shuffle-word-500-count.jsonl\n"
+      "Generated JSONL file with - 515 max words, 200 samples - at ../dataset/gen-word-515-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 520 max words, 200 samples - at ../dataset/gen-word-520-count.jsonl\n"
+      "Generated JSONL file with - 1465 max words, 200 samples - at ../dataset/gen-word-1465-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 7 samples (1 token repeat) - 305 max words - at ../dataset/shuffle-word-305-count.jsonl\n"
+      "Generated JSONL file with - 290 max words, 100 samples - at ../dataset/gen-word-290-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 60 samples (20 token repeat) - 955 max words - at ../dataset/shuffle-word-955-count.jsonl\n"
+      "Generated a single JSONL file with 60 samples (20 token repeat) - 1055 max words - at ../dataset/shuffle-word-1055-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1495 max words - at ../dataset/shuffle-word-1495-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 2965 max words - at ../dataset/shuffle-word-2965-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 645 max words, 200 samples - at ../dataset/gen-word-645-count.jsonl\n"
+      "Generated JSONL file with - 1025 max words, 200 samples - at ../dataset/gen-word-1025-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 2770 max words - at ../dataset/shuffle-word-2770-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2400 max words - at ../dataset/shuffle-word-2400-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 680 max words, 200 samples - at ../dataset/gen-word-680-count.jsonl\n"
+      "Generated a single JSONL file with 41 samples (20 token repeat) - 1395 max words - at ../dataset/shuffle-word-1395-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 9 samples (1 token repeat) - 285 max words - at ../dataset/shuffle-word-285-count.jsonl\n"
+      "Generated a single JSONL file with 62 samples (20 token repeat) - 825 max words - at ../dataset/shuffle-word-825-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 7 samples (1 token repeat) - 385 max words - at ../dataset/shuffle-word-385-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1830 max words - at ../dataset/shuffle-word-1830-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 670 max words, 200 samples - at ../dataset/gen-word-670-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 60 samples (20 token repeat) - 1100 max words - at ../dataset/shuffle-word-1100-count.jsonl\n"
+      "Generated a single JSONL file with 21 samples (20 token repeat) - 2755 max words - at ../dataset/shuffle-word-2755-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 2985 max words - at ../dataset/shuffle-word-2985-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 2885 max words - at ../dataset/shuffle-word-2885-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 765 max words, 200 samples - at ../dataset/gen-word-765-count.jsonl\n"
+      "Generated JSONL file with - 1045 max words, 200 samples - at ../dataset/gen-word-1045-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 60 samples (20 token repeat) - 1110 max words - at ../dataset/shuffle-word-1110-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2140 max words - at ../dataset/shuffle-word-2140-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 870 max words, 200 samples - at ../dataset/gen-word-870-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 40 samples (20 token repeat) - 1555 max words - at ../dataset/shuffle-word-1555-count.jsonl\n"
+      "Generated a single JSONL file with 100 samples (20 token repeat) - 540 max words - at ../dataset/shuffle-word-540-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 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) - 2815 max words - at ../dataset/shuffle-word-2815-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 30 samples (20 token repeat) - 2525 max words - at ../dataset/shuffle-word-2525-count.jsonl\n"
+      "Generated JSONL file with - 1255 max words, 200 samples - at ../dataset/gen-word-1255-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 51 samples (20 token repeat) - 1270 max words - at ../dataset/shuffle-word-1270-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3090 max words - at ../dataset/shuffle-word-3090-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 2640 max words - at ../dataset/shuffle-word-2640-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1695 max words - at ../dataset/shuffle-word-1695-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 2955 max words - at ../dataset/shuffle-word-2955-count.jsonl\n"
+      "Generated a single JSONL file with 50 samples (20 token repeat) - 1215 max words - at ../dataset/shuffle-word-1215-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 51 samples (20 token repeat) - 1250 max words - at ../dataset/shuffle-word-1250-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1360 max words - at ../dataset/shuffle-word-1360-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 2930 max words - at ../dataset/shuffle-word-2930-count.jsonl\n"
+      "Generated a single JSONL file with 21 samples (20 token repeat) - 2795 max words - at ../dataset/shuffle-word-2795-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 650 max words, 200 samples - at ../dataset/gen-word-650-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2120 max words - at ../dataset/shuffle-word-2120-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 580 max words, 200 samples - at ../dataset/gen-word-580-count.jsonl\n"
+      "Generated JSONL file with - 715 max words, 200 samples - at ../dataset/gen-word-715-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 665 max words, 200 samples - at ../dataset/gen-word-665-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3095 max words - at ../dataset/shuffle-word-3095-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1820 max words - at ../dataset/shuffle-word-1820-count.jsonl\n"
+      "Generated JSONL file with - 165 max words, 100 samples - at ../dataset/gen-word-165-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 63 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) - 1820 max words - at ../dataset/shuffle-word-1820-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2195 max words - at ../dataset/shuffle-word-2195-count.jsonl\n"
+      "Generated a single JSONL file with 81 samples (20 token repeat) - 625 max words - at ../dataset/shuffle-word-625-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 725 max words, 200 samples - at ../dataset/gen-word-725-count.jsonl\n"
+      "Generated JSONL file with - 830 max words, 200 samples - at ../dataset/gen-word-830-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 60 samples (20 token repeat) - 1105 max words - at ../dataset/shuffle-word-1105-count.jsonl\n"
+      "Generated a single JSONL file with 60 samples (20 token repeat) - 1120 max words - at ../dataset/shuffle-word-1120-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 60 samples (20 token repeat) - 1065 max words - at ../dataset/shuffle-word-1065-count.jsonl\n"
+      "Generated JSONL file with - 730 max words, 200 samples - at ../dataset/gen-word-730-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 720 max words, 200 samples - at ../dataset/gen-word-720-count.jsonl\n"
+      "Generated JSONL file with - 420 max words, 100 samples - at ../dataset/gen-word-420-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 395 max words, 100 samples - at ../dataset/gen-word-395-count.jsonl\n"
+      "Generated JSONL file with - 1755 max words, 200 samples - at ../dataset/gen-word-1755-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 785 max words, 200 samples - at ../dataset/gen-word-785-count.jsonl\n"
+      "Generated a single JSONL file with 7 samples (1 token repeat) - 355 max words - at ../dataset/shuffle-word-355-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 5 samples (1 token repeat) - 415 max words - at ../dataset/shuffle-word-415-count.jsonl\n"
+      "Generated a single JSONL file with 27 samples (20 token repeat) - 2575 max words - at ../dataset/shuffle-word-2575-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1660 max words - at ../dataset/shuffle-word-1660-count.jsonl\n"
+      "Generated JSONL file with - 1355 max words, 200 samples - at ../dataset/gen-word-1355-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 100 samples (20 token repeat) - 515 max words - at ../dataset/shuffle-word-515-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 2970 max words - at ../dataset/shuffle-word-2970-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 5 samples (1 token repeat) - 405 max words - at ../dataset/shuffle-word-405-count.jsonl\n"
+      "Generated JSONL file with - 1325 max words, 200 samples - at ../dataset/gen-word-1325-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 60 samples (20 token repeat) - 950 max words - at ../dataset/shuffle-word-950-count.jsonl\n"
+      "Generated a single JSONL file with 10 samples (1 token repeat) - 215 max words - at ../dataset/shuffle-word-215-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 60 samples (20 token repeat) - 935 max words - at ../dataset/shuffle-word-935-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1690 max words - at ../dataset/shuffle-word-1690-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 7 samples (1 token repeat) - 355 max words - at ../dataset/shuffle-word-355-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1885 max words - at ../dataset/shuffle-word-1885-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2290 max words - at ../dataset/shuffle-word-2290-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1720 max words - at ../dataset/shuffle-word-1720-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 655 max words, 200 samples - at ../dataset/gen-word-655-count.jsonl\n"
+      "Generated JSONL file with - 1085 max words, 200 samples - at ../dataset/gen-word-1085-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 885 max words, 200 samples - at ../dataset/gen-word-885-count.jsonl\n"
+      "Generated JSONL file with - 270 max words, 100 samples - at ../dataset/gen-word-270-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 6 samples (1 token repeat) - 455 max words - at ../dataset/shuffle-word-455-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1845 max words - at ../dataset/shuffle-word-1845-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 480 max words, 100 samples - at ../dataset/gen-word-480-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 2995 max words - at ../dataset/shuffle-word-2995-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) - 1965 max words - at ../dataset/shuffle-word-1965-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2335 max words - at ../dataset/shuffle-word-2335-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1740 max words - at ../dataset/shuffle-word-1740-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 2905 max words - at ../dataset/shuffle-word-2905-count.jsonl\n"
+      "Generated a single JSONL file with 60 samples (20 token repeat) - 1150 max words - at ../dataset/shuffle-word-1150-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2205 max words - at ../dataset/shuffle-word-2205-count.jsonl\n"
+      "Generated JSONL file with - 580 max words, 200 samples - at ../dataset/gen-word-580-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 60 samples (20 token repeat) - 1180 max words - at ../dataset/shuffle-word-1180-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 80 samples (20 token repeat) - 740 max words - at ../dataset/shuffle-word-740-count.jsonl\n"
+      "Generated JSONL file with - 1775 max words, 200 samples - at ../dataset/gen-word-1775-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 845 max words, 200 samples - at ../dataset/gen-word-845-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3030 max words - at ../dataset/shuffle-word-3030-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 99 samples (20 token repeat) - 560 max words - at ../dataset/shuffle-word-560-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1455 max words - at ../dataset/shuffle-word-1455-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 345 max words, 100 samples - at ../dataset/gen-word-345-count.jsonl\n"
+      "Generated a single JSONL file with 37 samples (20 token repeat) - 2465 max words - at ../dataset/shuffle-word-2465-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 99 samples (20 token repeat) - 545 max words - at ../dataset/shuffle-word-545-count.jsonl\n"
+      "Generated JSONL file with - 415 max words, 100 samples - at ../dataset/gen-word-415-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 555 max words, 200 samples - at ../dataset/gen-word-555-count.jsonl\n"
+      "Generated a single JSONL file with 60 samples (20 token repeat) - 970 max words - at ../dataset/shuffle-word-970-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1675 max words - at ../dataset/shuffle-word-1675-count.jsonl\n"
+      "Generated a single JSONL file with 51 samples (20 token repeat) - 1280 max words - at ../dataset/shuffle-word-1280-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 350 max words, 100 samples - at ../dataset/gen-word-350-count.jsonl\n"
+      "Generated a single JSONL file with 80 samples (20 token repeat) - 750 max words - at ../dataset/shuffle-word-750-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 540 max words, 200 samples - at ../dataset/gen-word-540-count.jsonl\n"
+      "Generated a single JSONL file with 36 samples (20 token repeat) - 2495 max words - at ../dataset/shuffle-word-2495-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 700 max words, 200 samples - at ../dataset/gen-word-700-count.jsonl\n"
+      "Generated a single JSONL file with 60 samples (20 token repeat) - 1110 max words - at ../dataset/shuffle-word-1110-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 7 samples (1 token repeat) - 365 max words - at ../dataset/shuffle-word-365-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1480 max words - at ../dataset/shuffle-word-1480-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 385 max words, 100 samples - at ../dataset/gen-word-385-count.jsonl\n"
+      "Generated a single JSONL file with 79 samples (20 token repeat) - 765 max words - at ../dataset/shuffle-word-765-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 985 max words, 200 samples - at ../dataset/gen-word-985-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3680 max words - at ../dataset/shuffle-word-3680-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1520 max words - at ../dataset/shuffle-word-1520-count.jsonl\n"
+      "Generated JSONL file with - 1100 max words, 200 samples - at ../dataset/gen-word-1100-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 22 samples (20 token repeat) - 2690 max words - at ../dataset/shuffle-word-2690-count.jsonl\n"
+      "Generated JSONL file with - 700 max words, 200 samples - at ../dataset/gen-word-700-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2105 max words - at ../dataset/shuffle-word-2105-count.jsonl\n"
+      "Generated JSONL file with - 1680 max words, 200 samples - at ../dataset/gen-word-1680-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2185 max words - at ../dataset/shuffle-word-2185-count.jsonl\n"
+      "Generated a single JSONL file with 82 samples (20 token repeat) - 645 max words - at ../dataset/shuffle-word-645-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3055 max words - at ../dataset/shuffle-word-3055-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1325 max words - at ../dataset/shuffle-word-1325-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 30 samples (20 token repeat) - 2560 max words - at ../dataset/shuffle-word-2560-count.jsonl\n"
+      "Generated a single JSONL file with 6 samples (1 token repeat) - 495 max words - at ../dataset/shuffle-word-495-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2325 max words - at ../dataset/shuffle-word-2325-count.jsonl\n"
+      "Generated JSONL file with - 505 max words, 200 samples - at ../dataset/gen-word-505-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 790 max words, 200 samples - at ../dataset/gen-word-790-count.jsonl\n"
+      "Generated JSONL file with - 1670 max words, 200 samples - at ../dataset/gen-word-1670-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 37 samples (20 token repeat) - 2420 max words - at ../dataset/shuffle-word-2420-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1725 max words - at ../dataset/shuffle-word-1725-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2155 max words - at ../dataset/shuffle-word-2155-count.jsonl\n"
+      "Generated a single JSONL file with 100 samples (20 token repeat) - 560 max words - at ../dataset/shuffle-word-560-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1005 max words, 200 samples - at ../dataset/gen-word-1005-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1515 max words - at ../dataset/shuffle-word-1515-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 945 max words, 200 samples - at ../dataset/gen-word-945-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3280 max words - at ../dataset/shuffle-word-3280-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 435 max words, 100 samples - at ../dataset/gen-word-435-count.jsonl\n"
+      "Generated a single JSONL file with 29 samples (20 token repeat) - 2515 max words - at ../dataset/shuffle-word-2515-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1535 max words - at ../dataset/shuffle-word-1535-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1435 max words - at ../dataset/shuffle-word-1435-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 900 max words, 200 samples - at ../dataset/gen-word-900-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2135 max words - at ../dataset/shuffle-word-2135-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 31 samples (20 token repeat) - 2505 max words - at ../dataset/shuffle-word-2505-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1320 max words - at ../dataset/shuffle-word-1320-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 970 max words, 200 samples - at ../dataset/gen-word-970-count.jsonl\n"
+      "Generated JSONL file with - 860 max words, 200 samples - at ../dataset/gen-word-860-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1635 max words - at ../dataset/shuffle-word-1635-count.jsonl\n"
+      "Generated a single JSONL file with 60 samples (20 token repeat) - 1135 max words - at ../dataset/shuffle-word-1135-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 690 max words, 200 samples - at ../dataset/gen-word-690-count.jsonl\n"
+      "Generated JSONL file with - 1415 max words, 200 samples - at ../dataset/gen-word-1415-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1055 max words, 200 samples - at ../dataset/gen-word-1055-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2265 max words - at ../dataset/shuffle-word-2265-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 2705 max words - at ../dataset/shuffle-word-2705-count.jsonl\n"
+      "Generated a single JSONL file with 23 samples (20 token repeat) - 2790 max words - at ../dataset/shuffle-word-2790-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1810 max words - at ../dataset/shuffle-word-1810-count.jsonl\n"
+      "Generated a single JSONL file with 7 samples (1 token repeat) - 340 max words - at ../dataset/shuffle-word-340-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1700 max words, 200 samples - at ../dataset/gen-word-1700-count.jsonl\n"
+      "Generated JSONL file with - 560 max words, 200 samples - at ../dataset/gen-word-560-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 24 samples (20 token repeat) - 2670 max words - at ../dataset/shuffle-word-2670-count.jsonl\n"
+      "Generated a single JSONL file with 80 samples (20 token repeat) - 680 max words - at ../dataset/shuffle-word-680-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 850 max words, 200 samples - at ../dataset/gen-word-850-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1810 max words - at ../dataset/shuffle-word-1810-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 920 max words, 200 samples - at ../dataset/gen-word-920-count.jsonl\n"
+      "Generated a single JSONL file with 80 samples (20 token repeat) - 730 max words - at ../dataset/shuffle-word-730-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 14 samples (1 token repeat) - 185 max words - at ../dataset/shuffle-word-185-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 2735 max words - at ../dataset/shuffle-word-2735-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 675 max words, 200 samples - at ../dataset/gen-word-675-count.jsonl\n"
+      "Generated JSONL file with - 805 max words, 200 samples - at ../dataset/gen-word-805-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1740 max words, 200 samples - at ../dataset/gen-word-1740-count.jsonl\n"
+      "Generated JSONL file with - 1055 max words, 200 samples - at ../dataset/gen-word-1055-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 23 samples (20 token repeat) - 2620 max words - at ../dataset/shuffle-word-2620-count.jsonl\n"
+      "Generated JSONL file with - 1825 max words, 200 samples - at ../dataset/gen-word-1825-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 705 max words, 200 samples - at ../dataset/gen-word-705-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1530 max words - at ../dataset/shuffle-word-1530-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 2945 max words - at ../dataset/shuffle-word-2945-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 2865 max words - at ../dataset/shuffle-word-2865-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1255 max words, 200 samples - at ../dataset/gen-word-1255-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1710 max words - at ../dataset/shuffle-word-1710-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1965 max words - at ../dataset/shuffle-word-1965-count.jsonl\n"
+      "Generated a single JSONL file with 60 samples (20 token repeat) - 930 max words - at ../dataset/shuffle-word-930-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 340 max words, 100 samples - at ../dataset/gen-word-340-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1935 max words - at ../dataset/shuffle-word-1935-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 730 max words, 200 samples - at ../dataset/gen-word-730-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 2975 max words - at ../dataset/shuffle-word-2975-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 26 samples (20 token repeat) - 2610 max words - at ../dataset/shuffle-word-2610-count.jsonl\n"
+      "Generated a single JSONL file with 62 samples (20 token repeat) - 820 max words - at ../dataset/shuffle-word-820-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 290 max words, 100 samples - at ../dataset/gen-word-290-count.jsonl\n"
+      "Generated JSONL file with - 985 max words, 200 samples - at ../dataset/gen-word-985-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 2725 max words - at ../dataset/shuffle-word-2725-count.jsonl\n"
+      "Generated JSONL file with - 720 max words, 200 samples - at ../dataset/gen-word-720-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2255 max words - at ../dataset/shuffle-word-2255-count.jsonl\n"
+      "Generated a single JSONL file with 60 samples (20 token repeat) - 940 max words - at ../dataset/shuffle-word-940-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 81 samples (20 token repeat) - 635 max words - at ../dataset/shuffle-word-635-count.jsonl\n"
+      "Generated JSONL file with - 310 max words, 100 samples - at ../dataset/gen-word-310-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 59 samples (20 token repeat) - 1190 max words - at ../dataset/shuffle-word-1190-count.jsonl\n"
+      "Generated JSONL file with - 1480 max words, 200 samples - at ../dataset/gen-word-1480-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 10 samples (1 token repeat) - 245 max words - at ../dataset/shuffle-word-245-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3110 max words - at ../dataset/shuffle-word-3110-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 610 max words, 200 samples - at ../dataset/gen-word-610-count.jsonl\n"
+      "Generated a single JSONL file with 22 samples (20 token repeat) - 2700 max words - at ../dataset/shuffle-word-2700-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 24 samples (20 token repeat) - 2700 max words - at ../dataset/shuffle-word-2700-count.jsonl\n"
+      "Generated JSONL file with - 600 max words, 200 samples - at ../dataset/gen-word-600-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 21 samples (20 token repeat) - 2740 max words - at ../dataset/shuffle-word-2740-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 2985 max words - at ../dataset/shuffle-word-2985-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 29 samples (20 token repeat) - 2570 max words - at ../dataset/shuffle-word-2570-count.jsonl\n"
+      "Generated JSONL file with - 1240 max words, 200 samples - at ../dataset/gen-word-1240-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 575 max words, 200 samples - at ../dataset/gen-word-575-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1850 max words - at ../dataset/shuffle-word-1850-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 100 samples (20 token repeat) - 550 max words - at ../dataset/shuffle-word-550-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3025 max words - at ../dataset/shuffle-word-3025-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 2750 max words - at ../dataset/shuffle-word-2750-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3355 max words - at ../dataset/shuffle-word-3355-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1555 max words, 200 samples - at ../dataset/gen-word-1555-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 2870 max words - at ../dataset/shuffle-word-2870-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 2800 max words - at ../dataset/shuffle-word-2800-count.jsonl\n"
+      "Generated JSONL file with - 680 max words, 200 samples - at ../dataset/gen-word-680-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 780 max words, 200 samples - at ../dataset/gen-word-780-count.jsonl\n"
+      "Generated JSONL file with - 820 max words, 200 samples - at ../dataset/gen-word-820-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1215 max words, 200 samples - at ../dataset/gen-word-1215-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1550 max words - at ../dataset/shuffle-word-1550-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1990 max words - at ../dataset/shuffle-word-1990-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3395 max words - at ../dataset/shuffle-word-3395-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 59 samples (20 token repeat) - 1155 max words - at ../dataset/shuffle-word-1155-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3995 max words - at ../dataset/shuffle-word-3995-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3250 max words - at ../dataset/shuffle-word-3250-count.jsonl\n"
+      "Generated JSONL file with - 1235 max words, 200 samples - at ../dataset/gen-word-1235-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 60 samples (20 token repeat) - 1120 max words - at ../dataset/shuffle-word-1120-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3495 max words - at ../dataset/shuffle-word-3495-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 740 max words, 200 samples - at ../dataset/gen-word-740-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1880 max words - at ../dataset/shuffle-word-1880-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2060 max words - at ../dataset/shuffle-word-2060-count.jsonl\n"
+      "Generated a single JSONL file with 10 samples (1 token repeat) - 235 max words - at ../dataset/shuffle-word-235-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 2890 max words - at ../dataset/shuffle-word-2890-count.jsonl\n"
+      "Generated JSONL file with - 550 max words, 200 samples - at ../dataset/gen-word-550-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 21 samples (20 token repeat) - 2685 max words - at ../dataset/shuffle-word-2685-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 38 samples (20 token repeat) - 2435 max words - at ../dataset/shuffle-word-2435-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3140 max words - at ../dataset/shuffle-word-3140-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2130 max words - at ../dataset/shuffle-word-2130-count.jsonl\n"
+      "Generated a single JSONL file with 31 samples (20 token repeat) - 2570 max words - at ../dataset/shuffle-word-2570-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3470 max words - at ../dataset/shuffle-word-3470-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3835 max words - at ../dataset/shuffle-word-3835-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3210 max words - at ../dataset/shuffle-word-3210-count.jsonl\n"
+      "Generated JSONL file with - 250 max words, 100 samples - at ../dataset/gen-word-250-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 875 max words, 200 samples - at ../dataset/gen-word-875-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1875 max words - at ../dataset/shuffle-word-1875-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 2970 max words - at ../dataset/shuffle-word-2970-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 40 samples (20 token repeat) - 1715 max words - at ../dataset/shuffle-word-1715-count.jsonl\n"
+      "Generated a single JSONL file with 60 samples (20 token repeat) - 1020 max words - at ../dataset/shuffle-word-1020-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 2845 max words - at ../dataset/shuffle-word-2845-count.jsonl\n"
+      "Generated JSONL file with - 1110 max words, 200 samples - at ../dataset/gen-word-1110-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 2910 max words - at ../dataset/shuffle-word-2910-count.jsonl\n"
+      "Generated JSONL file with - 375 max words, 100 samples - at ../dataset/gen-word-375-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 2960 max words - at ../dataset/shuffle-word-2960-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 2915 max words - at ../dataset/shuffle-word-2915-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1775 max words - at ../dataset/shuffle-word-1775-count.jsonl\n"
+      "Generated JSONL file with - 1805 max words, 200 samples - at ../dataset/gen-word-1805-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1250 max words, 200 samples - at ../dataset/gen-word-1250-count.jsonl\n"
+      "Generated JSONL file with - 1820 max words, 200 samples - at ../dataset/gen-word-1820-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 615 max words, 200 samples - at ../dataset/gen-word-615-count.jsonl\n"
+      "Generated JSONL file with - 1020 max words, 200 samples - at ../dataset/gen-word-1020-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 2885 max words - at ../dataset/shuffle-word-2885-count.jsonl\n"
+      "Generated a single JSONL file with 60 samples (20 token repeat) - 1065 max words - at ../dataset/shuffle-word-1065-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 62 samples (20 token repeat) - 820 max words - at ../dataset/shuffle-word-820-count.jsonl\n"
+      "Generated JSONL file with - 1450 max words, 200 samples - at ../dataset/gen-word-1450-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 830 max words, 200 samples - at ../dataset/gen-word-830-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 2720 max words - at ../dataset/shuffle-word-2720-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3265 max words - at ../dataset/shuffle-word-3265-count.jsonl\n"
+      "Generated JSONL file with - 1410 max words, 200 samples - at ../dataset/gen-word-1410-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1440 max words - at ../dataset/shuffle-word-1440-count.jsonl\n"
+      "Generated a single JSONL file with 80 samples (20 token repeat) - 800 max words - at ../dataset/shuffle-word-800-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 21 samples (20 token repeat) - 2780 max words - at ../dataset/shuffle-word-2780-count.jsonl\n"
+      "Generated a single JSONL file with 23 samples (20 token repeat) - 2730 max words - at ../dataset/shuffle-word-2730-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3430 max words - at ../dataset/shuffle-word-3430-count.jsonl\n"
+      "Generated JSONL file with - 1365 max words, 200 samples - at ../dataset/gen-word-1365-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 23 samples (20 token repeat) - 2730 max words - at ../dataset/shuffle-word-2730-count.jsonl\n"
+      "Generated JSONL file with - 1395 max words, 200 samples - at ../dataset/gen-word-1395-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1815 max words - at ../dataset/shuffle-word-1815-count.jsonl\n"
+      "Generated JSONL file with - 1810 max words, 200 samples - at ../dataset/gen-word-1810-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1815 max words, 200 samples - at ../dataset/gen-word-1815-count.jsonl\n"
+      "Generated a single JSONL file with 64 samples (20 token repeat) - 895 max words - at ../dataset/shuffle-word-895-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 2840 max words - at ../dataset/shuffle-word-2840-count.jsonl\n"
+      "Generated JSONL file with - 1580 max words, 200 samples - at ../dataset/gen-word-1580-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 31 samples (20 token repeat) - 2520 max words - at ../dataset/shuffle-word-2520-count.jsonl\n"
+      "Generated JSONL file with - 1165 max words, 200 samples - at ../dataset/gen-word-1165-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1515 max words - at ../dataset/shuffle-word-1515-count.jsonl\n"
+      "Generated JSONL file with - 555 max words, 200 samples - at ../dataset/gen-word-555-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1415 max words, 200 samples - at ../dataset/gen-word-1415-count.jsonl\n"
+      "Generated JSONL file with - 545 max words, 200 samples - at ../dataset/gen-word-545-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 6 samples (1 token repeat) - 450 max words - at ../dataset/shuffle-word-450-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1905 max words - at ../dataset/shuffle-word-1905-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 59 samples (20 token repeat) - 1145 max words - at ../dataset/shuffle-word-1145-count.jsonl\n"
+      "Generated JSONL file with - 1700 max words, 200 samples - at ../dataset/gen-word-1700-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2260 max words - at ../dataset/shuffle-word-2260-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2155 max words - at ../dataset/shuffle-word-2155-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 39 samples (20 token repeat) - 2320 max words - at ../dataset/shuffle-word-2320-count.jsonl\n"
+      "Generated JSONL file with - 1590 max words, 200 samples - at ../dataset/gen-word-1590-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 60 samples (20 token repeat) - 1070 max words - at ../dataset/shuffle-word-1070-count.jsonl\n"
+      "Generated JSONL file with - 1265 max words, 200 samples - at ../dataset/gen-word-1265-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 505 max words, 200 samples - at ../dataset/gen-word-505-count.jsonl\n"
+      "Generated JSONL file with - 510 max words, 200 samples - at ../dataset/gen-word-510-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 2715 max words - at ../dataset/shuffle-word-2715-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1780 max words - at ../dataset/shuffle-word-1780-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 79 samples (20 token repeat) - 775 max words - at ../dataset/shuffle-word-775-count.jsonl\n"
+      "Generated a single JSONL file with 6 samples (1 token repeat) - 500 max words - at ../dataset/shuffle-word-500-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 22 samples (20 token repeat) - 2630 max words - at ../dataset/shuffle-word-2630-count.jsonl\n"
+      "Generated JSONL file with - 1435 max words, 200 samples - at ../dataset/gen-word-1435-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1210 max words, 200 samples - at ../dataset/gen-word-1210-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2165 max words - at ../dataset/shuffle-word-2165-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 925 max words, 200 samples - at ../dataset/gen-word-925-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2115 max words - at ../dataset/shuffle-word-2115-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 39 samples (20 token repeat) - 2370 max words - at ../dataset/shuffle-word-2370-count.jsonl\n"
+      "Generated JSONL file with - 1910 max words, 200 samples - at ../dataset/gen-word-1910-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 545 max words, 200 samples - at ../dataset/gen-word-545-count.jsonl\n"
+      "Generated JSONL file with - 1800 max words, 200 samples - at ../dataset/gen-word-1800-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 35 samples (20 token repeat) - 2465 max words - at ../dataset/shuffle-word-2465-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1980 max words - at ../dataset/shuffle-word-1980-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 770 max words, 200 samples - at ../dataset/gen-word-770-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1705 max words - at ../dataset/shuffle-word-1705-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 420 max words, 100 samples - at ../dataset/gen-word-420-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1760 max words - at ../dataset/shuffle-word-1760-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1450 max words, 200 samples - at ../dataset/gen-word-1450-count.jsonl\n"
+      "Generated JSONL file with - 1505 max words, 200 samples - at ../dataset/gen-word-1505-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 515 max words, 200 samples - at ../dataset/gen-word-515-count.jsonl\n"
+      "Generated JSONL file with - 610 max words, 200 samples - at ../dataset/gen-word-610-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 JSONL file with - 1155 max words, 200 samples - at ../dataset/gen-word-1155-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 60 samples (20 token repeat) - 960 max words - at ../dataset/shuffle-word-960-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3610 max words - at ../dataset/shuffle-word-3610-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2210 max words - at ../dataset/shuffle-word-2210-count.jsonl\n"
+      "Generated a single JSONL file with 60 samples (20 token repeat) - 1090 max words - at ../dataset/shuffle-word-1090-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 2820 max words - at ../dataset/shuffle-word-2820-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 JSONL file with - 590 max words, 200 samples - at ../dataset/gen-word-590-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1630 max words - at ../dataset/shuffle-word-1630-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2160 max words - at ../dataset/shuffle-word-2160-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1450 max words - at ../dataset/shuffle-word-1450-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2215 max words - at ../dataset/shuffle-word-2215-count.jsonl\n"
+      "Generated JSONL file with - 765 max words, 200 samples - at ../dataset/gen-word-765-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 100 samples (20 token repeat) - 535 max words - at ../dataset/shuffle-word-535-count.jsonl\n"
+      "Generated a single JSONL file with 9 samples (1 token repeat) - 300 max words - at ../dataset/shuffle-word-300-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3115 max words - at ../dataset/shuffle-word-3115-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2020 max words - at ../dataset/shuffle-word-2020-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2240 max words - at ../dataset/shuffle-word-2240-count.jsonl\n"
+      "Generated a single JSONL file with 82 samples (20 token repeat) - 685 max words - at ../dataset/shuffle-word-685-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 37 samples (20 token repeat) - 2490 max words - at ../dataset/shuffle-word-2490-count.jsonl\n"
+      "Generated JSONL file with - 1600 max words, 200 samples - at ../dataset/gen-word-1600-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2050 max words - at ../dataset/shuffle-word-2050-count.jsonl\n"
+      "Generated a single JSONL file with 100 samples (20 token repeat) - 580 max words - at ../dataset/shuffle-word-580-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3685 max words - at ../dataset/shuffle-word-3685-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1750 max words - at ../dataset/shuffle-word-1750-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 59 samples (20 token repeat) - 1135 max words - at ../dataset/shuffle-word-1135-count.jsonl\n"
+      "Generated JSONL file with - 1180 max words, 200 samples - at ../dataset/gen-word-1180-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 2950 max words - at ../dataset/shuffle-word-2950-count.jsonl\n"
+      "Generated a single JSONL file with 41 samples (20 token repeat) - 1315 max words - at ../dataset/shuffle-word-1315-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2180 max words - at ../dataset/shuffle-word-2180-count.jsonl\n"
+      "Generated JSONL file with - 1565 max words, 200 samples - at ../dataset/gen-word-1565-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 24 samples (20 token repeat) - 2615 max words - at ../dataset/shuffle-word-2615-count.jsonl\n"
+      "Generated JSONL file with - 565 max words, 200 samples - at ../dataset/gen-word-565-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 990 max words, 200 samples - at ../dataset/gen-word-990-count.jsonl\n"
+      "Generated JSONL file with - 335 max words, 100 samples - at ../dataset/gen-word-335-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2360 max words - at ../dataset/shuffle-word-2360-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 62 samples (20 token repeat) - 860 max words - at ../dataset/shuffle-word-860-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3905 max words - at ../dataset/shuffle-word-3905-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 815 max words, 200 samples - at ../dataset/gen-word-815-count.jsonl\n"
+      "Generated a single JSONL file with 33 samples (20 token repeat) - 2530 max words - at ../dataset/shuffle-word-2530-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3970 max words - at ../dataset/shuffle-word-3970-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 60 samples (20 token repeat) - 1140 max words - at ../dataset/shuffle-word-1140-count.jsonl\n"
+      "Generated JSONL file with - 2045 max words, 200 samples - at ../dataset/gen-word-2045-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 960 max words, 200 samples - at ../dataset/gen-word-960-count.jsonl\n"
+      "Generated a single JSONL file with 100 samples (20 token repeat) - 570 max words - at ../dataset/shuffle-word-570-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 28 samples (20 token repeat) - 2655 max words - at ../dataset/shuffle-word-2655-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1770 max words - at ../dataset/shuffle-word-1770-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1975 max words - at ../dataset/shuffle-word-1975-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1755 max words - at ../dataset/shuffle-word-1755-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2080 max words - at ../dataset/shuffle-word-2080-count.jsonl\n"
+      "Generated JSONL file with - 1390 max words, 200 samples - at ../dataset/gen-word-1390-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 52 samples (20 token repeat) - 1240 max words - at ../dataset/shuffle-word-1240-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1730 max words - at ../dataset/shuffle-word-1730-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1570 max words - at ../dataset/shuffle-word-1570-count.jsonl\n"
+      "Generated a single JSONL file with 60 samples (20 token repeat) - 1145 max words - at ../dataset/shuffle-word-1145-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 60 samples (20 token repeat) - 1060 max words - at ../dataset/shuffle-word-1060-count.jsonl\n"
+      "Generated JSONL file with - 905 max words, 200 samples - at ../dataset/gen-word-905-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2065 max words - at ../dataset/shuffle-word-2065-count.jsonl\n"
+      "Generated a single JSONL file with 81 samples (20 token repeat) - 670 max words - at ../dataset/shuffle-word-670-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 950 max words, 200 samples - at ../dataset/gen-word-950-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3985 max words - at ../dataset/shuffle-word-3985-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2030 max words - at ../dataset/shuffle-word-2030-count.jsonl\n"
+      "Generated a single JSONL file with 51 samples (20 token repeat) - 1285 max words - at ../dataset/shuffle-word-1285-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 220 max words, 100 samples - at ../dataset/gen-word-220-count.jsonl\n"
+      "Generated a single JSONL file with 100 samples (20 token repeat) - 575 max words - at ../dataset/shuffle-word-575-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3845 max words - at ../dataset/shuffle-word-3845-count.jsonl\n"
+      "Generated JSONL file with - 775 max words, 200 samples - at ../dataset/gen-word-775-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2190 max words - at ../dataset/shuffle-word-2190-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2160 max words - at ../dataset/shuffle-word-2160-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 60 samples (20 token repeat) - 1150 max words - at ../dataset/shuffle-word-1150-count.jsonl\n"
+      "Generated JSONL file with - 1295 max words, 200 samples - at ../dataset/gen-word-1295-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 60 samples (20 token repeat) - 1035 max words - at ../dataset/shuffle-word-1035-count.jsonl\n"
+      "Generated JSONL file with - 320 max words, 100 samples - at ../dataset/gen-word-320-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 7 samples (1 token repeat) - 400 max words - at ../dataset/shuffle-word-400-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2340 max words - at ../dataset/shuffle-word-2340-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1180 max words, 200 samples - at ../dataset/gen-word-1180-count.jsonl\n"
+      "Generated JSONL file with - 1010 max words, 200 samples - at ../dataset/gen-word-1010-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 60 samples (20 token repeat) - 1090 max words - at ../dataset/shuffle-word-1090-count.jsonl\n"
+      "Generated JSONL file with - 1315 max words, 200 samples - at ../dataset/gen-word-1315-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1955 max words, 200 samples - at ../dataset/gen-word-1955-count.jsonl\n"
+      "Generated a single JSONL file with 100 samples (20 token repeat) - 525 max words - at ../dataset/shuffle-word-525-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 80 samples (20 token repeat) - 605 max words - at ../dataset/shuffle-word-605-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3750 max words - at ../dataset/shuffle-word-3750-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1130 max words, 200 samples - at ../dataset/gen-word-1130-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 60 samples (20 token repeat) - 1180 max words - at ../dataset/shuffle-word-1180-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 40 samples (20 token repeat) - 2275 max words - at ../dataset/shuffle-word-2275-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1425 max words - at ../dataset/shuffle-word-1425-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2075 max words - at ../dataset/shuffle-word-2075-count.jsonl\n"
+      "Generated JSONL file with - 1830 max words, 200 samples - at ../dataset/gen-word-1830-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 58 samples (20 token repeat) - 1115 max words - at ../dataset/shuffle-word-1115-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3885 max words - at ../dataset/shuffle-word-3885-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 930 max words, 200 samples - at ../dataset/gen-word-930-count.jsonl\n"
+      "Generated JSONL file with - 785 max words, 200 samples - at ../dataset/gen-word-785-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1430 max words, 200 samples - at ../dataset/gen-word-1430-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1925 max words - at ../dataset/shuffle-word-1925-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1090 max words, 200 samples - at ../dataset/gen-word-1090-count.jsonl\n"
+      "Generated JSONL file with - 735 max words, 200 samples - at ../dataset/gen-word-735-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2390 max words - at ../dataset/shuffle-word-2390-count.jsonl\n"
+      "Generated JSONL file with - 790 max words, 200 samples - at ../dataset/gen-word-790-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 470 max words, 100 samples - at ../dataset/gen-word-470-count.jsonl\n"
+      "Generated JSONL file with - 1665 max words, 200 samples - at ../dataset/gen-word-1665-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1000 max words, 200 samples - at ../dataset/gen-word-1000-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1855 max words - at ../dataset/shuffle-word-1855-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3620 max words - at ../dataset/shuffle-word-3620-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1670 max words - at ../dataset/shuffle-word-1670-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2670 max words, 200 samples - at ../dataset/gen-word-2670-count.jsonl\n"
+      "Generated JSONL file with - 630 max words, 200 samples - at ../dataset/gen-word-630-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 510 max words, 200 samples - at ../dataset/gen-word-510-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3585 max words - at ../dataset/shuffle-word-3585-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1095 max words, 200 samples - at ../dataset/gen-word-1095-count.jsonl\n"
+      "Generated JSONL file with - 460 max words, 100 samples - at ../dataset/gen-word-460-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2015 max words - at ../dataset/shuffle-word-2015-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3765 max words - at ../dataset/shuffle-word-3765-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3355 max words - at ../dataset/shuffle-word-3355-count.jsonl\n"
+      "Generated a single JSONL file with 29 samples (20 token repeat) - 2545 max words - at ../dataset/shuffle-word-2545-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1590 max words - at ../dataset/shuffle-word-1590-count.jsonl\n"
+      "Generated a single JSONL file with 60 samples (20 token repeat) - 1005 max words - at ../dataset/shuffle-word-1005-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2345 max words - at ../dataset/shuffle-word-2345-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3195 max words - at ../dataset/shuffle-word-3195-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 80 samples (20 token repeat) - 700 max words - at ../dataset/shuffle-word-700-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2360 max words - at ../dataset/shuffle-word-2360-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1705 max words, 200 samples - at ../dataset/gen-word-1705-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1540 max words - at ../dataset/shuffle-word-1540-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2135 max words - at ../dataset/shuffle-word-2135-count.jsonl\n"
+      "Generated JSONL file with - 945 max words, 200 samples - at ../dataset/gen-word-945-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3895 max words - at ../dataset/shuffle-word-3895-count.jsonl\n"
+      "Generated JSONL file with - 1855 max words, 200 samples - at ../dataset/gen-word-1855-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3285 max words - at ../dataset/shuffle-word-3285-count.jsonl\n"
+      "Generated JSONL file with - 1495 max words, 200 samples - at ../dataset/gen-word-1495-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3890 max words - at ../dataset/shuffle-word-3890-count.jsonl\n"
+      "Generated JSONL file with - 1080 max words, 200 samples - at ../dataset/gen-word-1080-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 810 max words, 200 samples - at ../dataset/gen-word-810-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3210 max words - at ../dataset/shuffle-word-3210-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 2920 max words - at ../dataset/shuffle-word-2920-count.jsonl\n"
+      "Generated JSONL file with - 525 max words, 200 samples - at ../dataset/gen-word-525-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 415 max words, 100 samples - at ../dataset/gen-word-415-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3860 max words - at ../dataset/shuffle-word-3860-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3325 max words - at ../dataset/shuffle-word-3325-count.jsonl\n"
+      "Generated JSONL file with - 1075 max words, 200 samples - at ../dataset/gen-word-1075-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1325 max words - at ../dataset/shuffle-word-1325-count.jsonl\n"
+      "Generated JSONL file with - 1690 max words, 200 samples - at ../dataset/gen-word-1690-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1765 max words - at ../dataset/shuffle-word-1765-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3085 max words - at ../dataset/shuffle-word-3085-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 2755 max words - at ../dataset/shuffle-word-2755-count.jsonl\n"
+      "Generated JSONL file with - 780 max words, 200 samples - at ../dataset/gen-word-780-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 6 samples (1 token repeat) - 460 max words - at ../dataset/shuffle-word-460-count.jsonl\n"
+      "Generated a single JSONL file with 10 samples (1 token repeat) - 245 max words - at ../dataset/shuffle-word-245-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1145 max words, 200 samples - at ../dataset/gen-word-1145-count.jsonl\n"
+      "Generated JSONL file with - 1725 max words, 200 samples - at ../dataset/gen-word-1725-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 24 samples (20 token repeat) - 2625 max words - at ../dataset/shuffle-word-2625-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1955 max words - at ../dataset/shuffle-word-1955-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 940 max words, 200 samples - at ../dataset/gen-word-940-count.jsonl\n"
+      "Generated JSONL file with - 1335 max words, 200 samples - at ../dataset/gen-word-1335-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3190 max words - at ../dataset/shuffle-word-3190-count.jsonl\n"
+      "Generated JSONL file with - 1735 max words, 200 samples - at ../dataset/gen-word-1735-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1460 max words - at ../dataset/shuffle-word-1460-count.jsonl\n"
+      "Generated JSONL file with - 725 max words, 200 samples - at ../dataset/gen-word-725-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1790 max words - at ../dataset/shuffle-word-1790-count.jsonl\n"
+      "Generated JSONL file with - 835 max words, 200 samples - at ../dataset/gen-word-835-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1655 max words, 200 samples - at ../dataset/gen-word-1655-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3120 max words - at ../dataset/shuffle-word-3120-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1060 max words, 200 samples - at ../dataset/gen-word-1060-count.jsonl\n"
+      "Generated JSONL file with - 1470 max words, 200 samples - at ../dataset/gen-word-1470-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3005 max words - at ../dataset/shuffle-word-3005-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3485 max words - at ../dataset/shuffle-word-3485-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 52 samples (20 token repeat) - 1235 max words - at ../dataset/shuffle-word-1235-count.jsonl\n"
+      "Generated JSONL file with - 590 max words, 200 samples - at ../dataset/gen-word-590-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 490 max words, 100 samples - at ../dataset/gen-word-490-count.jsonl\n"
+      "Generated JSONL file with - 1400 max words, 200 samples - at ../dataset/gen-word-1400-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 22 samples (20 token repeat) - 2645 max words - at ../dataset/shuffle-word-2645-count.jsonl\n"
+      "Generated JSONL file with - 150 max words, 100 samples - at ../dataset/gen-word-150-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 36 samples (20 token repeat) - 2405 max words - at ../dataset/shuffle-word-2405-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3955 max words - at ../dataset/shuffle-word-3955-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3565 max words - at ../dataset/shuffle-word-3565-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 2990 max words - at ../dataset/shuffle-word-2990-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2065 max words, 200 samples - at ../dataset/gen-word-2065-count.jsonl\n"
+      "Generated JSONL file with - 595 max words, 200 samples - at ../dataset/gen-word-595-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1720 max words - at ../dataset/shuffle-word-1720-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3935 max words - at ../dataset/shuffle-word-3935-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 29 samples (20 token repeat) - 2530 max words - at ../dataset/shuffle-word-2530-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1960 max words - at ../dataset/shuffle-word-1960-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3760 max words - at ../dataset/shuffle-word-3760-count.jsonl\n"
+      "Generated a single JSONL file with 37 samples (20 token repeat) - 2450 max words - at ../dataset/shuffle-word-2450-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 315 max words, 100 samples - at ../dataset/gen-word-315-count.jsonl\n"
+      "Generated a single JSONL file with 9 samples (1 token repeat) - 280 max words - at ../dataset/shuffle-word-280-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1335 max words, 200 samples - at ../dataset/gen-word-1335-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1505 max words - at ../dataset/shuffle-word-1505-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1900 max words, 200 samples - at ../dataset/gen-word-1900-count.jsonl\n"
+      "Generated JSONL file with - 1405 max words, 200 samples - at ../dataset/gen-word-1405-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2355 max words - at ../dataset/shuffle-word-2355-count.jsonl\n"
+      "Generated JSONL file with - 3050 max words, 200 samples - at ../dataset/gen-word-3050-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 750 max words, 200 samples - at ../dataset/gen-word-750-count.jsonl\n"
+      "Generated a single JSONL file with 64 samples (20 token repeat) - 815 max words - at ../dataset/shuffle-word-815-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 250 max words, 100 samples - at ../dataset/gen-word-250-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1525 max words - at ../dataset/shuffle-word-1525-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2095 max words, 200 samples - at ../dataset/gen-word-2095-count.jsonl\n"
+      "Generated a single JSONL file with 39 samples (20 token repeat) - 2315 max words - at ../dataset/shuffle-word-2315-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 710 max words, 200 samples - at ../dataset/gen-word-710-count.jsonl\n"
+      "Generated a single JSONL file with 38 samples (20 token repeat) - 2480 max words - at ../dataset/shuffle-word-2480-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 2810 max words - at ../dataset/shuffle-word-2810-count.jsonl\n"
+      "Generated a single JSONL file with 39 samples (20 token repeat) - 2440 max words - at ../dataset/shuffle-word-2440-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2250 max words, 200 samples - at ../dataset/gen-word-2250-count.jsonl\n"
+      "Generated JSONL file with - 900 max words, 200 samples - at ../dataset/gen-word-900-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3595 max words - at ../dataset/shuffle-word-3595-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2280 max words - at ../dataset/shuffle-word-2280-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1855 max words, 200 samples - at ../dataset/gen-word-1855-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2130 max words - at ../dataset/shuffle-word-2130-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 715 max words, 200 samples - at ../dataset/gen-word-715-count.jsonl\n"
+      "Generated JSONL file with - 1620 max words, 200 samples - at ../dataset/gen-word-1620-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3830 max words - at ../dataset/shuffle-word-3830-count.jsonl\n"
+      "Generated a single JSONL file with 81 samples (20 token repeat) - 665 max words - at ../dataset/shuffle-word-665-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 805 max words, 200 samples - at ../dataset/gen-word-805-count.jsonl\n"
+      "Generated JSONL file with - 935 max words, 200 samples - at ../dataset/gen-word-935-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2350 max words - at ../dataset/shuffle-word-2350-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3150 max words - at ../dataset/shuffle-word-3150-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3120 max words - at ../dataset/shuffle-word-3120-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 JSONL file with - 1035 max words, 200 samples - at ../dataset/gen-word-1035-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2290 max words - at ../dataset/shuffle-word-2290-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1070 max words, 200 samples - at ../dataset/gen-word-1070-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1610 max words - at ../dataset/shuffle-word-1610-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 2805 max words - at ../dataset/shuffle-word-2805-count.jsonl\n"
+      "Generated JSONL file with - 305 max words, 100 samples - at ../dataset/gen-word-305-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 53 samples (20 token repeat) - 1275 max words - at ../dataset/shuffle-word-1275-count.jsonl\n"
+      "Generated JSONL file with - 475 max words, 100 samples - at ../dataset/gen-word-475-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1365 max words, 200 samples - at ../dataset/gen-word-1365-count.jsonl\n"
+      "Generated a single JSONL file with 80 samples (20 token repeat) - 755 max words - at ../dataset/shuffle-word-755-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 775 max words, 200 samples - at ../dataset/gen-word-775-count.jsonl\n"
+      "Generated JSONL file with - 1545 max words, 200 samples - at ../dataset/gen-word-1545-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1010 max words, 200 samples - at ../dataset/gen-word-1010-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2220 max words - at ../dataset/shuffle-word-2220-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3330 max words - at ../dataset/shuffle-word-3330-count.jsonl\n"
+      "Generated JSONL file with - 755 max words, 200 samples - at ../dataset/gen-word-755-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1830 max words, 200 samples - at ../dataset/gen-word-1830-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 2705 max words - at ../dataset/shuffle-word-2705-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 7 samples (1 token repeat) - 310 max words - at ../dataset/shuffle-word-310-count.jsonl\n"
+      "Generated JSONL file with - 675 max words, 200 samples - at ../dataset/gen-word-675-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1385 max words - at ../dataset/shuffle-word-1385-count.jsonl\n"
+      "Generated JSONL file with - 810 max words, 200 samples - at ../dataset/gen-word-810-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2245 max words - at ../dataset/shuffle-word-2245-count.jsonl\n"
+      "Generated JSONL file with - 1785 max words, 200 samples - at ../dataset/gen-word-1785-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1105 max words, 200 samples - at ../dataset/gen-word-1105-count.jsonl\n"
+      "Generated JSONL file with - 285 max words, 100 samples - at ../dataset/gen-word-285-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 110 max words, 100 samples - at ../dataset/gen-word-110-count.jsonl\n"
+      "Generated a single JSONL file with 60 samples (20 token repeat) - 950 max words - at ../dataset/shuffle-word-950-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1985 max words, 200 samples - at ../dataset/gen-word-1985-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3870 max words - at ../dataset/shuffle-word-3870-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 63 samples (20 token repeat) - 870 max words - at ../dataset/shuffle-word-870-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2330 max words - at ../dataset/shuffle-word-2330-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3090 max words - at ../dataset/shuffle-word-3090-count.jsonl\n"
+      "Generated JSONL file with - 1030 max words, 200 samples - at ../dataset/gen-word-1030-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1895 max words, 200 samples - at ../dataset/gen-word-1895-count.jsonl\n"
+      "Generated JSONL file with - 1935 max words, 200 samples - at ../dataset/gen-word-1935-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3155 max words - at ../dataset/shuffle-word-3155-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 2835 max words - at ../dataset/shuffle-word-2835-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1290 max words, 200 samples - at ../dataset/gen-word-1290-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3915 max words - at ../dataset/shuffle-word-3915-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2070 max words - at ../dataset/shuffle-word-2070-count.jsonl\n"
+      "Generated a single JSONL file with 60 samples (20 token repeat) - 1185 max words - at ../dataset/shuffle-word-1185-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2185 max words, 200 samples - at ../dataset/gen-word-2185-count.jsonl\n"
+      "Generated a single JSONL file with 60 samples (20 token repeat) - 915 max words - at ../dataset/shuffle-word-915-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 2975 max words - at ../dataset/shuffle-word-2975-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2150 max words - at ../dataset/shuffle-word-2150-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3215 max words - at ../dataset/shuffle-word-3215-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 2770 max words - at ../dataset/shuffle-word-2770-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 2830 max words - at ../dataset/shuffle-word-2830-count.jsonl\n"
+      "Generated JSONL file with - 1445 max words, 200 samples - at ../dataset/gen-word-1445-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 745 max words, 200 samples - at ../dataset/gen-word-745-count.jsonl\n"
+      "Generated JSONL file with - 1970 max words, 200 samples - at ../dataset/gen-word-1970-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3665 max words - at ../dataset/shuffle-word-3665-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3165 max words - at ../dataset/shuffle-word-3165-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 2835 max words - at ../dataset/shuffle-word-2835-count.jsonl\n"
+      "Generated JSONL file with - 1420 max words, 200 samples - at ../dataset/gen-word-1420-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 2925 max words - at ../dataset/shuffle-word-2925-count.jsonl\n"
+      "Generated JSONL file with - 1540 max words, 200 samples - at ../dataset/gen-word-1540-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3065 max words - at ../dataset/shuffle-word-3065-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 2825 max words - at ../dataset/shuffle-word-2825-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 895 max words, 200 samples - at ../dataset/gen-word-895-count.jsonl\n"
+      "Generated JSONL file with - 1530 max words, 200 samples - at ../dataset/gen-word-1530-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3835 max words - at ../dataset/shuffle-word-3835-count.jsonl\n"
+      "Generated a single JSONL file with 29 samples (20 token repeat) - 2565 max words - at ../dataset/shuffle-word-2565-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 60 samples (20 token repeat) - 1015 max words - at ../dataset/shuffle-word-1015-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2270 max words - at ../dataset/shuffle-word-2270-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1635 max words, 200 samples - at ../dataset/gen-word-1635-count.jsonl\n"
+      "Generated JSONL file with - 850 max words, 200 samples - at ../dataset/gen-word-850-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3180 max words - at ../dataset/shuffle-word-3180-count.jsonl\n"
+      "Generated a single JSONL file with 99 samples (20 token repeat) - 535 max words - at ../dataset/shuffle-word-535-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 15 samples (1 token repeat) - 160 max words - at ../dataset/shuffle-word-160-count.jsonl\n"
+      "Generated a single JSONL file with 60 samples (20 token repeat) - 990 max words - at ../dataset/shuffle-word-990-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3045 max words - at ../dataset/shuffle-word-3045-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1305 max words - at ../dataset/shuffle-word-1305-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 38 samples (20 token repeat) - 2435 max words - at ../dataset/shuffle-word-2435-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3070 max words - at ../dataset/shuffle-word-3070-count.jsonl\n"
+      "Generated a single JSONL file with 33 samples (20 token repeat) - 2580 max words - at ../dataset/shuffle-word-2580-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2265 max words - at ../dataset/shuffle-word-2265-count.jsonl\n"
+      "Generated a single JSONL file with 30 samples (20 token repeat) - 2525 max words - at ../dataset/shuffle-word-2525-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 795 max words, 200 samples - at ../dataset/gen-word-795-count.jsonl\n"
+      "Generated JSONL file with - 390 max words, 100 samples - at ../dataset/gen-word-390-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1550 max words, 200 samples - at ../dataset/gen-word-1550-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2005 max words - at ../dataset/shuffle-word-2005-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 9 samples (1 token repeat) - 280 max words - at ../dataset/shuffle-word-280-count.jsonl\n"
+      "Generated JSONL file with - 750 max words, 200 samples - at ../dataset/gen-word-750-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 7 samples (1 token repeat) - 395 max words - at ../dataset/shuffle-word-395-count.jsonl\n"
+      "Generated a single JSONL file with 6 samples (1 token repeat) - 490 max words - at ../dataset/shuffle-word-490-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3270 max words - at ../dataset/shuffle-word-3270-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3205 max words - at ../dataset/shuffle-word-3205-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3060 max words - at ../dataset/shuffle-word-3060-count.jsonl\n"
+      "Generated JSONL file with - 340 max words, 100 samples - at ../dataset/gen-word-340-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1800 max words, 200 samples - at ../dataset/gen-word-1800-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2260 max words - at ../dataset/shuffle-word-2260-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1205 max words, 200 samples - at ../dataset/gen-word-1205-count.jsonl\n"
+      "Generated JSONL file with - 2795 max words, 200 samples - at ../dataset/gen-word-2795-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1020 max words, 200 samples - at ../dataset/gen-word-1020-count.jsonl\n"
+      "Generated a single JSONL file with 22 samples (20 token repeat) - 2780 max words - at ../dataset/shuffle-word-2780-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3125 max words - at ../dataset/shuffle-word-3125-count.jsonl\n"
+      "Generated a single JSONL file with 60 samples (20 token repeat) - 965 max words - at ../dataset/shuffle-word-965-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 28 samples (20 token repeat) - 2565 max words - at ../dataset/shuffle-word-2565-count.jsonl\n"
+      "Generated JSONL file with - 1780 max words, 200 samples - at ../dataset/gen-word-1780-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3940 max words - at ../dataset/shuffle-word-3940-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2040 max words - at ../dataset/shuffle-word-2040-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3765 max words - at ../dataset/shuffle-word-3765-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1645 max words - at ../dataset/shuffle-word-1645-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3085 max words - at ../dataset/shuffle-word-3085-count.jsonl\n"
+      "Generated JSONL file with - 535 max words, 200 samples - at ../dataset/gen-word-535-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1195 max words, 200 samples - at ../dataset/gen-word-1195-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2215 max words - at ../dataset/shuffle-word-2215-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1840 max words - at ../dataset/shuffle-word-1840-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1930 max words - at ../dataset/shuffle-word-1930-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 2785 max words - at ../dataset/shuffle-word-2785-count.jsonl\n"
+      "Generated JSONL file with - 1550 max words, 200 samples - at ../dataset/gen-word-1550-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3720 max words - at ../dataset/shuffle-word-3720-count.jsonl\n"
+      "Generated a single JSONL file with 24 samples (20 token repeat) - 2690 max words - at ../dataset/shuffle-word-2690-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1580 max words - at ../dataset/shuffle-word-1580-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2285 max words - at ../dataset/shuffle-word-2285-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1755 max words - at ../dataset/shuffle-word-1755-count.jsonl\n"
+      "Generated a single JSONL file with 29 samples (20 token repeat) - 2520 max words - at ../dataset/shuffle-word-2520-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1455 max words, 200 samples - at ../dataset/gen-word-1455-count.jsonl\n"
+      "Generated a single JSONL file with 80 samples (20 token repeat) - 655 max words - at ../dataset/shuffle-word-655-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 21 samples (20 token repeat) - 2650 max words - at ../dataset/shuffle-word-2650-count.jsonl\n"
+      "Generated JSONL file with - 2100 max words, 200 samples - at ../dataset/gen-word-2100-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2145 max words - at ../dataset/shuffle-word-2145-count.jsonl\n"
+      "Generated JSONL file with - 635 max words, 200 samples - at ../dataset/gen-word-635-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 23 samples (20 token repeat) - 2680 max words - at ../dataset/shuffle-word-2680-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2255 max words - at ../dataset/shuffle-word-2255-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3315 max words - at ../dataset/shuffle-word-3315-count.jsonl\n"
+      "Generated a single JSONL file with 58 samples (20 token repeat) - 1105 max words - at ../dataset/shuffle-word-1105-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) - 3795 max words - at ../dataset/shuffle-word-3795-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 64 samples (20 token repeat) - 850 max words - at ../dataset/shuffle-word-850-count.jsonl\n"
+      "Generated a single JSONL file with 36 samples (20 token repeat) - 2475 max words - at ../dataset/shuffle-word-2475-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 21 samples (20 token repeat) - 2635 max words - at ../dataset/shuffle-word-2635-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3345 max words - at ../dataset/shuffle-word-3345-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3960 max words - at ../dataset/shuffle-word-3960-count.jsonl\n"
+      "Generated JSONL file with - 1630 max words, 200 samples - at ../dataset/gen-word-1630-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 6 samples (1 token repeat) - 445 max words - at ../dataset/shuffle-word-445-count.jsonl\n"
+      "Generated JSONL file with - 1795 max words, 200 samples - at ../dataset/gen-word-1795-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1850 max words - at ../dataset/shuffle-word-1850-count.jsonl\n"
+      "Generated a single JSONL file with 25 samples (20 token repeat) - 2670 max words - at ../dataset/shuffle-word-2670-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1630 max words, 200 samples - at ../dataset/gen-word-1630-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 2860 max words - at ../dataset/shuffle-word-2860-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 890 max words, 200 samples - at ../dataset/gen-word-890-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3520 max words - at ../dataset/shuffle-word-3520-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 2850 max words - at ../dataset/shuffle-word-2850-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3735 max words - at ../dataset/shuffle-word-3735-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1945 max words, 200 samples - at ../dataset/gen-word-1945-count.jsonl\n"
+      "Generated JSONL file with - 1230 max words, 200 samples - at ../dataset/gen-word-1230-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 825 max words, 200 samples - at ../dataset/gen-word-825-count.jsonl\n"
+      "Generated JSONL file with - 385 max words, 100 samples - at ../dataset/gen-word-385-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1540 max words - at ../dataset/shuffle-word-1540-count.jsonl\n"
+      "Generated a single JSONL file with 22 samples (20 token repeat) - 2620 max words - at ../dataset/shuffle-word-2620-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1310 max words - at ../dataset/shuffle-word-1310-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2375 max words - at ../dataset/shuffle-word-2375-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2040 max words, 200 samples - at ../dataset/gen-word-2040-count.jsonl\n"
+      "Generated JSONL file with - 3055 max words, 200 samples - at ../dataset/gen-word-3055-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1320 max words, 200 samples - at ../dataset/gen-word-1320-count.jsonl\n"
+      "Generated a single JSONL file with 15 samples (1 token repeat) - 150 max words - at ../dataset/shuffle-word-150-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1165 max words, 200 samples - at ../dataset/gen-word-1165-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2275 max words - at ../dataset/shuffle-word-2275-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1155 max words, 200 samples - at ../dataset/gen-word-1155-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 2805 max words - at ../dataset/shuffle-word-2805-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1770 max words - at ../dataset/shuffle-word-1770-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1945 max words - at ../dataset/shuffle-word-1945-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3985 max words - at ../dataset/shuffle-word-3985-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2345 max words - at ../dataset/shuffle-word-2345-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3005 max words, 200 samples - at ../dataset/gen-word-3005-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2235 max words - at ../dataset/shuffle-word-2235-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1425 max words - at ../dataset/shuffle-word-1425-count.jsonl\n"
+      "Generated a single JSONL file with 32 samples (20 token repeat) - 2560 max words - at ../dataset/shuffle-word-2560-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1520 max words, 200 samples - at ../dataset/gen-word-1520-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2055 max words - at ../dataset/shuffle-word-2055-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1495 max words, 200 samples - at ../dataset/gen-word-1495-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2355 max words - at ../dataset/shuffle-word-2355-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3345 max words - at ../dataset/shuffle-word-3345-count.jsonl\n"
+      "Generated a single JSONL file with 14 samples (1 token repeat) - 195 max words - at ../dataset/shuffle-word-195-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1160 max words, 200 samples - at ../dataset/gen-word-1160-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3480 max words - at ../dataset/shuffle-word-3480-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1940 max words - at ../dataset/shuffle-word-1940-count.jsonl\n"
+      "Generated a single JSONL file with 80 samples (20 token repeat) - 620 max words - at ../dataset/shuffle-word-620-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3205 max words - at ../dataset/shuffle-word-3205-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 2810 max words - at ../dataset/shuffle-word-2810-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2510 max words, 200 samples - at ../dataset/gen-word-2510-count.jsonl\n"
+      "Generated a single JSONL file with 60 samples (20 token repeat) - 980 max words - at ../dataset/shuffle-word-980-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1120 max words, 200 samples - at ../dataset/gen-word-1120-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3075 max words - at ../dataset/shuffle-word-3075-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1305 max words - at ../dataset/shuffle-word-1305-count.jsonl\n"
+      "Generated a single JSONL file with 32 samples (20 token repeat) - 2510 max words - at ../dataset/shuffle-word-2510-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1740 max words - at ../dataset/shuffle-word-1740-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 2750 max words - at ../dataset/shuffle-word-2750-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 21 samples (20 token repeat) - 2765 max words - at ../dataset/shuffle-word-2765-count.jsonl\n"
+      "Generated a single JSONL file with 36 samples (20 token repeat) - 2405 max words - at ../dataset/shuffle-word-2405-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1885 max words, 200 samples - at ../dataset/gen-word-1885-count.jsonl\n"
+      "Generated a single JSONL file with 7 samples (1 token repeat) - 320 max words - at ../dataset/shuffle-word-320-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 820 max words, 200 samples - at ../dataset/gen-word-820-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3445 max words - at ../dataset/shuffle-word-3445-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1240 max words, 200 samples - at ../dataset/gen-word-1240-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 2905 max words - at ../dataset/shuffle-word-2905-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 855 max words, 200 samples - at ../dataset/gen-word-855-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2305 max words - at ../dataset/shuffle-word-2305-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 10 samples (1 token repeat) - 250 max words - at ../dataset/shuffle-word-250-count.jsonl\n"
+      "Generated a single JSONL file with 26 samples (20 token repeat) - 2680 max words - at ../dataset/shuffle-word-2680-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 2940 max words - at ../dataset/shuffle-word-2940-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2210 max words - at ../dataset/shuffle-word-2210-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1995 max words - at ../dataset/shuffle-word-1995-count.jsonl\n"
+      "Generated a single JSONL file with 63 samples (20 token repeat) - 830 max words - at ../dataset/shuffle-word-830-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2055 max words - at ../dataset/shuffle-word-2055-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2095 max words - at ../dataset/shuffle-word-2095-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3915 max words - at ../dataset/shuffle-word-3915-count.jsonl\n"
+      "Generated JSONL file with - 1535 max words, 200 samples - at ../dataset/gen-word-1535-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 2870 max words - at ../dataset/shuffle-word-2870-count.jsonl\n"
+      "Generated JSONL file with - 1490 max words, 200 samples - at ../dataset/gen-word-1490-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 980 max words, 200 samples - at ../dataset/gen-word-980-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 22 samples (20 token repeat) - 2665 max words - at ../dataset/shuffle-word-2665-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2245 max words - at ../dataset/shuffle-word-2245-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 48 samples (20 token repeat) - 1300 max words - at ../dataset/shuffle-word-1300-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 2910 max words - at ../dataset/shuffle-word-2910-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 300 max words, 100 samples - at ../dataset/gen-word-300-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2110 max words - at ../dataset/shuffle-word-2110-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2010 max words - at ../dataset/shuffle-word-2010-count.jsonl\n"
+      "Generated JSONL file with - 1885 max words, 200 samples - at ../dataset/gen-word-1885-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1685 max words - at ../dataset/shuffle-word-1685-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1910 max words - at ../dataset/shuffle-word-1910-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 965 max words, 200 samples - at ../dataset/gen-word-965-count.jsonl\n"
+      "Generated JSONL file with - 2605 max words, 200 samples - at ../dataset/gen-word-2605-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1750 max words - at ../dataset/shuffle-word-1750-count.jsonl\n"
+      "Generated a single JSONL file with 33 samples (20 token repeat) - 2505 max words - at ../dataset/shuffle-word-2505-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1375 max words, 200 samples - at ../dataset/gen-word-1375-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3925 max words - at ../dataset/shuffle-word-3925-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2250 max words - at ../dataset/shuffle-word-2250-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3185 max words - at ../dataset/shuffle-word-3185-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3965 max words - at ../dataset/shuffle-word-3965-count.jsonl\n"
+      "Generated a single JSONL file with 80 samples (20 token repeat) - 705 max words - at ../dataset/shuffle-word-705-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 99 samples (20 token repeat) - 555 max words - at ../dataset/shuffle-word-555-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2030 max words - at ../dataset/shuffle-word-2030-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 79 samples (20 token repeat) - 780 max words - at ../dataset/shuffle-word-780-count.jsonl\n"
+      "Generated a single JSONL file with 36 samples (20 token repeat) - 2415 max words - at ../dataset/shuffle-word-2415-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 24 samples (20 token repeat) - 2660 max words - at ../dataset/shuffle-word-2660-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1860 max words - at ../dataset/shuffle-word-1860-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 21 samples (20 token repeat) - 2720 max words - at ../dataset/shuffle-word-2720-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3250 max words - at ../dataset/shuffle-word-3250-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1625 max words - at ../dataset/shuffle-word-1625-count.jsonl\n"
+      "Generated JSONL file with - 2980 max words, 200 samples - at ../dataset/gen-word-2980-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1860 max words - at ../dataset/shuffle-word-1860-count.jsonl\n"
+      "Generated a single JSONL file with 60 samples (20 token repeat) - 1050 max words - at ../dataset/shuffle-word-1050-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 475 max words, 100 samples - at ../dataset/gen-word-475-count.jsonl\n"
+      "Generated JSONL file with - 1425 max words, 200 samples - at ../dataset/gen-word-1425-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2085 max words - at ../dataset/shuffle-word-2085-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 39 samples (20 token repeat) - 2305 max words - at ../dataset/shuffle-word-2305-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2390 max words - at ../dataset/shuffle-word-2390-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3950 max words - at ../dataset/shuffle-word-3950-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1715 max words - at ../dataset/shuffle-word-1715-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1370 max words - at ../dataset/shuffle-word-1370-count.jsonl\n"
+      "Generated a single JSONL file with 39 samples (20 token repeat) - 2310 max words - at ../dataset/shuffle-word-2310-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 23 samples (20 token repeat) - 2685 max words - at ../dataset/shuffle-word-2685-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2040 max words - at ../dataset/shuffle-word-2040-count.jsonl\n"
+      "Generated a single JSONL file with 32 samples (20 token repeat) - 2555 max words - at ../dataset/shuffle-word-2555-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1940 max words, 200 samples - at ../dataset/gen-word-1940-count.jsonl\n"
+      "Generated a single JSONL file with 34 samples (20 token repeat) - 2455 max words - at ../dataset/shuffle-word-2455-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 60 samples (20 token repeat) - 1165 max words - at ../dataset/shuffle-word-1165-count.jsonl\n"
+      "Generated JSONL file with - 1160 max words, 200 samples - at ../dataset/gen-word-1160-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1200 max words, 200 samples - at ../dataset/gen-word-1200-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3565 max words - at ../dataset/shuffle-word-3565-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1735 max words - at ../dataset/shuffle-word-1735-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 2925 max words - at ../dataset/shuffle-word-2925-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 60 samples (20 token repeat) - 1030 max words - at ../dataset/shuffle-word-1030-count.jsonl\n"
+      "Generated a single JSONL file with 67 samples (20 token repeat) - 880 max words - at ../dataset/shuffle-word-880-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1660 max words, 200 samples - at ../dataset/gen-word-1660-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3725 max words - at ../dataset/shuffle-word-3725-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 915 max words, 200 samples - at ../dataset/gen-word-915-count.jsonl\n"
+      "Generated a single JSONL file with 6 samples (1 token repeat) - 460 max words - at ../dataset/shuffle-word-460-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1485 max words - at ../dataset/shuffle-word-1485-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2380 max words - at ../dataset/shuffle-word-2380-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3195 max words - at ../dataset/shuffle-word-3195-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3105 max words - at ../dataset/shuffle-word-3105-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1875 max words - at ../dataset/shuffle-word-1875-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3690 max words - at ../dataset/shuffle-word-3690-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 550 max words, 200 samples - at ../dataset/gen-word-550-count.jsonl\n"
+      "Generated JSONL file with - 2060 max words, 200 samples - at ../dataset/gen-word-2060-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 54 samples (20 token repeat) - 1255 max words - at ../dataset/shuffle-word-1255-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3240 max words - at ../dataset/shuffle-word-3240-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1605 max words - at ../dataset/shuffle-word-1605-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3410 max words - at ../dataset/shuffle-word-3410-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1185 max words, 200 samples - at ../dataset/gen-word-1185-count.jsonl\n"
+      "Generated a single JSONL file with 80 samples (20 token repeat) - 770 max words - at ../dataset/shuffle-word-770-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 41 samples (20 token repeat) - 1365 max words - at ../dataset/shuffle-word-1365-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 2950 max words - at ../dataset/shuffle-word-2950-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3135 max words - at ../dataset/shuffle-word-3135-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3040 max words - at ../dataset/shuffle-word-3040-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2810 max words, 200 samples - at ../dataset/gen-word-2810-count.jsonl\n"
+      "Generated JSONL file with - 1090 max words, 200 samples - at ../dataset/gen-word-1090-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1405 max words - at ../dataset/shuffle-word-1405-count.jsonl\n"
+      "Generated a single JSONL file with 30 samples (20 token repeat) - 2590 max words - at ../dataset/shuffle-word-2590-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1015 max words, 200 samples - at ../dataset/gen-word-1015-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3125 max words - at ../dataset/shuffle-word-3125-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1115 max words, 200 samples - at ../dataset/gen-word-1115-count.jsonl\n"
+      "Generated JSONL file with - 1595 max words, 200 samples - at ../dataset/gen-word-1595-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 27 samples (20 token repeat) - 2515 max words - at ../dataset/shuffle-word-2515-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3375 max words - at ../dataset/shuffle-word-3375-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1835 max words - at ../dataset/shuffle-word-1835-count.jsonl\n"
+      "Generated JSONL file with - 1710 max words, 200 samples - at ../dataset/gen-word-1710-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 7 samples (1 token repeat) - 320 max words - at ../dataset/shuffle-word-320-count.jsonl\n"
+      "Generated JSONL file with - 840 max words, 200 samples - at ../dataset/gen-word-840-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3335 max words - at ../dataset/shuffle-word-3335-count.jsonl\n"
+      "Generated a single JSONL file with 24 samples (20 token repeat) - 2650 max words - at ../dataset/shuffle-word-2650-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 2865 max words - at ../dataset/shuffle-word-2865-count.jsonl\n"
+      "Generated a single JSONL file with 22 samples (20 token repeat) - 2630 max words - at ../dataset/shuffle-word-2630-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 30 samples (20 token repeat) - 2540 max words - at ../dataset/shuffle-word-2540-count.jsonl\n"
+      "Generated a single JSONL file with 27 samples (20 token repeat) - 2645 max words - at ../dataset/shuffle-word-2645-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 910 max words, 200 samples - at ../dataset/gen-word-910-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 2945 max words - at ../dataset/shuffle-word-2945-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1455 max words - at ../dataset/shuffle-word-1455-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1995 max words - at ../dataset/shuffle-word-1995-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1695 max words - at ../dataset/shuffle-word-1695-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3635 max words - at ../dataset/shuffle-word-3635-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 625 max words, 200 samples - at ../dataset/gen-word-625-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 2960 max words - at ../dataset/shuffle-word-2960-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3795 max words - at ../dataset/shuffle-word-3795-count.jsonl\n"
+      "Generated JSONL file with - 2775 max words, 200 samples - at ../dataset/gen-word-2775-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 60 samples (20 token repeat) - 1005 max words - at ../dataset/shuffle-word-1005-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3850 max words - at ../dataset/shuffle-word-3850-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1450 max words - at ../dataset/shuffle-word-1450-count.jsonl\n"
+      "Generated a single JSONL file with 81 samples (20 token repeat) - 690 max words - at ../dataset/shuffle-word-690-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1545 max words - at ../dataset/shuffle-word-1545-count.jsonl\n"
+      "Generated JSONL file with - 1975 max words, 200 samples - at ../dataset/gen-word-1975-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1285 max words, 200 samples - at ../dataset/gen-word-1285-count.jsonl\n"
+      "Generated a single JSONL file with 24 samples (20 token repeat) - 2640 max words - at ../dataset/shuffle-word-2640-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3230 max words - at ../dataset/shuffle-word-3230-count.jsonl\n"
+      "Generated JSONL file with - 1625 max words, 200 samples - at ../dataset/gen-word-1625-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1695 max words, 200 samples - at ../dataset/gen-word-1695-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 40 samples (20 token repeat) - 2000 max words - at ../dataset/shuffle-word-2000-count.jsonl\n"
+      "Generated a single JSONL file with 16 samples (1 token repeat) - 140 max words - at ../dataset/shuffle-word-140-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2620 max words, 200 samples - at ../dataset/gen-word-2620-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2195 max words - at ../dataset/shuffle-word-2195-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3855 max words - at ../dataset/shuffle-word-3855-count.jsonl\n"
+      "Generated a single JSONL file with 60 samples (20 token repeat) - 935 max words - at ../dataset/shuffle-word-935-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2460 max words, 200 samples - at ../dataset/gen-word-2460-count.jsonl\n"
+      "Generated a single JSONL file with 21 samples (20 token repeat) - 2740 max words - at ../dataset/shuffle-word-2740-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2505 max words, 200 samples - at ../dataset/gen-word-2505-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3255 max words - at ../dataset/shuffle-word-3255-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 2915 max words - at ../dataset/shuffle-word-2915-count.jsonl\n"
+      "Generated a single JSONL file with 23 samples (20 token repeat) - 2695 max words - at ../dataset/shuffle-word-2695-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3515 max words - at ../dataset/shuffle-word-3515-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2065 max words - at ../dataset/shuffle-word-2065-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 60 samples (20 token repeat) - 975 max words - at ../dataset/shuffle-word-975-count.jsonl\n"
+      "Generated a single JSONL file with 29 samples (20 token repeat) - 2600 max words - at ../dataset/shuffle-word-2600-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1235 max words, 200 samples - at ../dataset/gen-word-1235-count.jsonl\n"
+      "Generated a single JSONL file with 23 samples (20 token repeat) - 2605 max words - at ../dataset/shuffle-word-2605-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1475 max words, 200 samples - at ../dataset/gen-word-1475-count.jsonl\n"
+      "Generated a single JSONL file with 39 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 40 samples (20 token repeat) - 1895 max words - at ../dataset/shuffle-word-1895-count.jsonl\n"
+      "Generated JSONL file with - 1750 max words, 200 samples - at ../dataset/gen-word-1750-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 100 samples (20 token repeat) - 540 max words - at ../dataset/shuffle-word-540-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3160 max words - at ../dataset/shuffle-word-3160-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 27 samples (20 token repeat) - 2675 max words - at ../dataset/shuffle-word-2675-count.jsonl\n"
+      "Generated JSONL file with - 645 max words, 200 samples - at ../dataset/gen-word-645-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1300 max words, 200 samples - at ../dataset/gen-word-1300-count.jsonl\n"
+      "Generated JSONL file with - 1875 max words, 200 samples - at ../dataset/gen-word-1875-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 2895 max words - at ../dataset/shuffle-word-2895-count.jsonl\n"
+      "Generated a single JSONL file with 29 samples (20 token repeat) - 2585 max words - at ../dataset/shuffle-word-2585-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 100 samples (20 token repeat) - 525 max words - at ../dataset/shuffle-word-525-count.jsonl\n"
+      "Generated a single JSONL file with 39 samples (20 token repeat) - 2325 max words - at ../dataset/shuffle-word-2325-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3165 max words - at ../dataset/shuffle-word-3165-count.jsonl\n"
+      "Generated JSONL file with - 1210 max words, 200 samples - at ../dataset/gen-word-1210-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1440 max words, 200 samples - at ../dataset/gen-word-1440-count.jsonl\n"
+      "Generated a single JSONL file with 26 samples (20 token repeat) - 2550 max words - at ../dataset/shuffle-word-2550-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1580 max words, 200 samples - at ../dataset/gen-word-1580-count.jsonl\n"
+      "Generated a single JSONL file with 39 samples (20 token repeat) - 2335 max words - at ../dataset/shuffle-word-2335-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 60 samples (20 token repeat) - 1055 max words - at ../dataset/shuffle-word-1055-count.jsonl\n"
+      "Generated a single JSONL file with 81 samples (20 token repeat) - 610 max words - at ../dataset/shuffle-word-610-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1550 max words - at ../dataset/shuffle-word-1550-count.jsonl\n"
+      "Generated JSONL file with - 1960 max words, 200 samples - at ../dataset/gen-word-1960-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2005 max words, 200 samples - at ../dataset/gen-word-2005-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2250 max words - at ../dataset/shuffle-word-2250-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2285 max words - at ../dataset/shuffle-word-2285-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2105 max words - at ../dataset/shuffle-word-2105-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1640 max words, 200 samples - at ../dataset/gen-word-1640-count.jsonl\n"
+      "Generated a single JSONL file with 28 samples (20 token repeat) - 2535 max words - at ../dataset/shuffle-word-2535-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2025 max words - at ../dataset/shuffle-word-2025-count.jsonl\n"
+      "Generated JSONL file with - 1430 max words, 200 samples - at ../dataset/gen-word-1430-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3675 max words - at ../dataset/shuffle-word-3675-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3455 max words - at ../dataset/shuffle-word-3455-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1190 max words, 200 samples - at ../dataset/gen-word-1190-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2185 max words - at ../dataset/shuffle-word-2185-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1390 max words, 200 samples - at ../dataset/gen-word-1390-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3020 max words - at ../dataset/shuffle-word-3020-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1325 max words, 200 samples - at ../dataset/gen-word-1325-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2090 max words - at ../dataset/shuffle-word-2090-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 60 samples (20 token repeat) - 1185 max words - at ../dataset/shuffle-word-1185-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2190 max words - at ../dataset/shuffle-word-2190-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1730 max words - at ../dataset/shuffle-word-1730-count.jsonl\n"
+      "Generated a single JSONL file with 21 samples (20 token repeat) - 2725 max words - at ../dataset/shuffle-word-2725-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3980 max words - at ../dataset/shuffle-word-3980-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 2955 max words - at ../dataset/shuffle-word-2955-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1505 max words - at ../dataset/shuffle-word-1505-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 2940 max words - at ../dataset/shuffle-word-2940-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1425 max words, 200 samples - at ../dataset/gen-word-1425-count.jsonl\n"
+      "Generated a single JSONL file with 24 samples (20 token repeat) - 2610 max words - at ../dataset/shuffle-word-2610-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 60 samples (20 token repeat) - 1025 max words - at ../dataset/shuffle-word-1025-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2365 max words - at ../dataset/shuffle-word-2365-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1275 max words, 200 samples - at ../dataset/gen-word-1275-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 2935 max words - at ../dataset/shuffle-word-2935-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1870 max words - at ../dataset/shuffle-word-1870-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3175 max words - at ../dataset/shuffle-word-3175-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 21 samples (20 token repeat) - 2760 max words - at ../dataset/shuffle-word-2760-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 2840 max words - at ../dataset/shuffle-word-2840-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 2965 max words - at ../dataset/shuffle-word-2965-count.jsonl\n"
+      "Generated JSONL file with - 1300 max words, 200 samples - at ../dataset/gen-word-1300-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2920 max words, 200 samples - at ../dataset/gen-word-2920-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3260 max words - at ../dataset/shuffle-word-3260-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2290 max words, 200 samples - at ../dataset/gen-word-2290-count.jsonl\n"
+      "Generated JSONL file with - 745 max words, 200 samples - at ../dataset/gen-word-745-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3955 max words - at ../dataset/shuffle-word-3955-count.jsonl\n"
+      "Generated JSONL file with - 1890 max words, 200 samples - at ../dataset/gen-word-1890-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2220 max words - at ../dataset/shuffle-word-2220-count.jsonl\n"
+      "Generated JSONL file with - 1605 max words, 200 samples - at ../dataset/gen-word-1605-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1265 max words, 200 samples - at ../dataset/gen-word-1265-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2395 max words - at ../dataset/shuffle-word-2395-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1650 max words, 200 samples - at ../dataset/gen-word-1650-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 2880 max words - at ../dataset/shuffle-word-2880-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1930 max words - at ../dataset/shuffle-word-1930-count.jsonl\n"
+      "Generated a single JSONL file with 24 samples (20 token repeat) - 2665 max words - at ../dataset/shuffle-word-2665-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3450 max words - at ../dataset/shuffle-word-3450-count.jsonl\n"
+      "Generated JSONL file with - 1790 max words, 200 samples - at ../dataset/gen-word-1790-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 32 samples (20 token repeat) - 2600 max words - at ../dataset/shuffle-word-2600-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 2785 max words - at ../dataset/shuffle-word-2785-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1040 max words, 200 samples - at ../dataset/gen-word-1040-count.jsonl\n"
+      "Generated JSONL file with - 1350 max words, 200 samples - at ../dataset/gen-word-1350-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2895 max words, 200 samples - at ../dataset/gen-word-2895-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 2875 max words - at ../dataset/shuffle-word-2875-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1045 max words, 200 samples - at ../dataset/gen-word-1045-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3895 max words - at ../dataset/shuffle-word-3895-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 410 max words, 100 samples - at ../dataset/gen-word-410-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2045 max words - at ../dataset/shuffle-word-2045-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3935 max words - at ../dataset/shuffle-word-3935-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 2845 max words - at ../dataset/shuffle-word-2845-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 905 max words, 200 samples - at ../dataset/gen-word-905-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2320 max words - at ../dataset/shuffle-word-2320-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3455 max words - at ../dataset/shuffle-word-3455-count.jsonl\n"
+      "Generated JSONL file with - 530 max words, 200 samples - at ../dataset/gen-word-530-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1175 max words, 200 samples - at ../dataset/gen-word-1175-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3055 max words - at ../dataset/shuffle-word-3055-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2280 max words - at ../dataset/shuffle-word-2280-count.jsonl\n"
+      "Generated JSONL file with - 1815 max words, 200 samples - at ../dataset/gen-word-1815-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 100 samples (20 token repeat) - 575 max words - at ../dataset/shuffle-word-575-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3005 max words - at ../dataset/shuffle-word-3005-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2150 max words - at ../dataset/shuffle-word-2150-count.jsonl\n"
+      "Generated JSONL file with - 1485 max words, 200 samples - at ../dataset/gen-word-1485-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3240 max words - at ../dataset/shuffle-word-3240-count.jsonl\n"
+      "Generated JSONL file with - 1245 max words, 200 samples - at ../dataset/gen-word-1245-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2780 max words, 200 samples - at ../dataset/gen-word-2780-count.jsonl\n"
+      "Generated JSONL file with - 2755 max words, 200 samples - at ../dataset/gen-word-2755-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3790 max words - at ../dataset/shuffle-word-3790-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3245 max words - at ../dataset/shuffle-word-3245-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1840 max words, 200 samples - at ../dataset/gen-word-1840-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 2980 max words - at ../dataset/shuffle-word-2980-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3850 max words - at ../dataset/shuffle-word-3850-count.jsonl\n"
+      "Generated a single JSONL file with 37 samples (20 token repeat) - 2460 max words - at ../dataset/shuffle-word-2460-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2125 max words - at ../dataset/shuffle-word-2125-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3015 max words - at ../dataset/shuffle-word-3015-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 38 samples (20 token repeat) - 2450 max words - at ../dataset/shuffle-word-2450-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3630 max words - at ../dataset/shuffle-word-3630-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1370 max words, 200 samples - at ../dataset/gen-word-1370-count.jsonl\n"
+      "Generated JSONL file with - 950 max words, 200 samples - at ../dataset/gen-word-950-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3460 max words - at ../dataset/shuffle-word-3460-count.jsonl\n"
+      "Generated a single JSONL file with 21 samples (20 token repeat) - 2760 max words - at ../dataset/shuffle-word-2760-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3465 max words - at ../dataset/shuffle-word-3465-count.jsonl\n"
+      "Generated JSONL file with - 2765 max words, 200 samples - at ../dataset/gen-word-2765-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 465 max words, 100 samples - at ../dataset/gen-word-465-count.jsonl\n"
+      "Generated JSONL file with - 2010 max words, 200 samples - at ../dataset/gen-word-2010-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1960 max words - at ../dataset/shuffle-word-1960-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 2850 max words - at ../dataset/shuffle-word-2850-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2340 max words - at ../dataset/shuffle-word-2340-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 2855 max words - at ../dataset/shuffle-word-2855-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2295 max words - at ../dataset/shuffle-word-2295-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3710 max words - at ../dataset/shuffle-word-3710-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1935 max words - at ../dataset/shuffle-word-1935-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2075 max words - at ../dataset/shuffle-word-2075-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 530 max words, 200 samples - at ../dataset/gen-word-530-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3940 max words - at ../dataset/shuffle-word-3940-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1730 max words, 200 samples - at ../dataset/gen-word-1730-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 2895 max words - at ../dataset/shuffle-word-2895-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2115 max words - at ../dataset/shuffle-word-2115-count.jsonl\n"
+      "Generated JSONL file with - 1995 max words, 200 samples - at ../dataset/gen-word-1995-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2020 max words - at ../dataset/shuffle-word-2020-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2385 max words - at ../dataset/shuffle-word-2385-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1170 max words, 200 samples - at ../dataset/gen-word-1170-count.jsonl\n"
+      "Generated a single JSONL file with 80 samples (20 token repeat) - 715 max words - at ../dataset/shuffle-word-715-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 2790 max words - at ../dataset/shuffle-word-2790-count.jsonl\n"
+      "Generated a single JSONL file with 23 samples (20 token repeat) - 2615 max words - at ../dataset/shuffle-word-2615-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2090 max words - at ../dataset/shuffle-word-2090-count.jsonl\n"
+      "Generated JSONL file with - 890 max words, 200 samples - at ../dataset/gen-word-890-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1025 max words, 200 samples - at ../dataset/gen-word-1025-count.jsonl\n"
+      "Generated JSONL file with - 975 max words, 200 samples - at ../dataset/gen-word-975-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3425 max words - at ../dataset/shuffle-word-3425-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3190 max words - at ../dataset/shuffle-word-3190-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 39 samples (20 token repeat) - 2380 max words - at ../dataset/shuffle-word-2380-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3225 max words - at ../dataset/shuffle-word-3225-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 310 max words, 100 samples - at ../dataset/gen-word-310-count.jsonl\n"
+      "Generated a single JSONL file with 60 samples (20 token repeat) - 1140 max words - at ../dataset/shuffle-word-1140-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 80 samples (20 token repeat) - 735 max words - at ../dataset/shuffle-word-735-count.jsonl\n"
+      "Generated a single JSONL file with 48 samples (20 token repeat) - 1225 max words - at ../dataset/shuffle-word-1225-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3880 max words - at ../dataset/shuffle-word-3880-count.jsonl\n"
+      "Generated a single JSONL file with 22 samples (20 token repeat) - 2625 max words - at ../dataset/shuffle-word-2625-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 6 samples (1 token repeat) - 440 max words - at ../dataset/shuffle-word-440-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2240 max words - at ../dataset/shuffle-word-2240-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3775 max words - at ../dataset/shuffle-word-3775-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 2820 max words - at ../dataset/shuffle-word-2820-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 6 samples (1 token repeat) - 475 max words - at ../dataset/shuffle-word-475-count.jsonl\n"
+      "Generated JSONL file with - 2800 max words, 200 samples - at ../dataset/gen-word-2800-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 31 samples (20 token repeat) - 2550 max words - at ../dataset/shuffle-word-2550-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3315 max words - at ../dataset/shuffle-word-3315-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2120 max words - at ../dataset/shuffle-word-2120-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3555 max words - at ../dataset/shuffle-word-3555-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 320 max words, 100 samples - at ../dataset/gen-word-320-count.jsonl\n"
+      "Generated a single JSONL file with 37 samples (20 token repeat) - 2445 max words - at ../dataset/shuffle-word-2445-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3025 max words - at ../dataset/shuffle-word-3025-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 2710 max words - at ../dataset/shuffle-word-2710-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1230 max words, 200 samples - at ../dataset/gen-word-1230-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 100 samples (20 token repeat) - 580 max words - at ../dataset/shuffle-word-580-count.jsonl\n"
+      "Generated JSONL file with - 1140 max words, 200 samples - at ../dataset/gen-word-1140-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1400 max words, 200 samples - at ../dataset/gen-word-1400-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 2930 max words - at ../dataset/shuffle-word-2930-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1465 max words, 200 samples - at ../dataset/gen-word-1465-count.jsonl\n"
+      "Generated JSONL file with - 2565 max words, 200 samples - at ../dataset/gen-word-2565-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 60 samples (20 token repeat) - 970 max words - at ../dataset/shuffle-word-970-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 2830 max words - at ../dataset/shuffle-word-2830-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1865 max words - at ../dataset/shuffle-word-1865-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1570 max words - at ../dataset/shuffle-word-1570-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 60 samples (20 token repeat) - 1195 max words - at ../dataset/shuffle-word-1195-count.jsonl\n"
+      "Generated JSONL file with - 1475 max words, 200 samples - at ../dataset/gen-word-1475-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1890 max words - at ../dataset/shuffle-word-1890-count.jsonl\n"
+      "Generated JSONL file with - 1860 max words, 200 samples - at ../dataset/gen-word-1860-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3440 max words - at ../dataset/shuffle-word-3440-count.jsonl\n"
+      "Generated JSONL file with - 1835 max words, 200 samples - at ../dataset/gen-word-1835-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3020 max words - at ../dataset/shuffle-word-3020-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 2890 max words - at ../dataset/shuffle-word-2890-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1745 max words - at ../dataset/shuffle-word-1745-count.jsonl\n"
+      "Generated JSONL file with - 685 max words, 200 samples - at ../dataset/gen-word-685-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1065 max words, 200 samples - at ../dataset/gen-word-1065-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3695 max words - at ../dataset/shuffle-word-3695-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1405 max words, 200 samples - at ../dataset/gen-word-1405-count.jsonl\n"
+      "Generated JSONL file with - 2540 max words, 200 samples - at ../dataset/gen-word-2540-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2080 max words, 200 samples - at ../dataset/gen-word-2080-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3370 max words - at ../dataset/shuffle-word-3370-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2315 max words - at ../dataset/shuffle-word-2315-count.jsonl\n"
+      "Generated JSONL file with - 1765 max words, 200 samples - at ../dataset/gen-word-1765-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 285 max words, 100 samples - at ../dataset/gen-word-285-count.jsonl\n"
+      "Generated JSONL file with - 885 max words, 200 samples - at ../dataset/gen-word-885-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1690 max words - at ../dataset/shuffle-word-1690-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3755 max words - at ../dataset/shuffle-word-3755-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1950 max words, 200 samples - at ../dataset/gen-word-1950-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 2900 max words - at ../dataset/shuffle-word-2900-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2765 max words, 200 samples - at ../dataset/gen-word-2765-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3215 max words - at ../dataset/shuffle-word-3215-count.jsonl\n"
      ]
     },
     {
@@ -9005,4165 +8885,3311 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2805 max words, 200 samples - at ../dataset/gen-word-2805-count.jsonl\n"
+      "Generated JSONL file with - 2940 max words, 200 samples - at ../dataset/gen-word-2940-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2910 max words, 200 samples - at ../dataset/gen-word-2910-count.jsonl\n"
+      "Generated a single JSONL file with 63 samples (20 token repeat) - 885 max words - at ../dataset/shuffle-word-885-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1830 max words - at ../dataset/shuffle-word-1830-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3180 max words - at ../dataset/shuffle-word-3180-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3495 max words, 200 samples - at ../dataset/gen-word-3495-count.jsonl\n"
+      "Generated a single JSONL file with 44 samples (20 token repeat) - 1330 max words - at ../dataset/shuffle-word-1330-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3690 max words - at ../dataset/shuffle-word-3690-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 40 samples (20 token repeat) - 1650 max words - at ../dataset/shuffle-word-1650-count.jsonl\n"
+      "Generated a single JSONL file with 63 samples (20 token repeat) - 855 max words - at ../dataset/shuffle-word-855-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3660 max words - at ../dataset/shuffle-word-3660-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3415 max words - at ../dataset/shuffle-word-3415-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1795 max words, 200 samples - at ../dataset/gen-word-1795-count.jsonl\n"
+      "Generated JSONL file with - 1040 max words, 200 samples - at ../dataset/gen-word-1040-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 41 samples (20 token repeat) - 1335 max words - at ../dataset/shuffle-word-1335-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3335 max words - at ../dataset/shuffle-word-3335-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 22 samples (20 token repeat) - 2735 max words - at ../dataset/shuffle-word-2735-count.jsonl\n"
+      "Generated a single JSONL file with 41 samples (20 token repeat) - 1385 max words - at ../dataset/shuffle-word-1385-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1760 max words - at ../dataset/shuffle-word-1760-count.jsonl\n"
+      "Generated JSONL file with - 1190 max words, 200 samples - at ../dataset/gen-word-1190-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 2745 max words - at ../dataset/shuffle-word-2745-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3845 max words - at ../dataset/shuffle-word-3845-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 60 samples (20 token repeat) - 1050 max words - at ../dataset/shuffle-word-1050-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3615 max words - at ../dataset/shuffle-word-3615-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1685 max words, 200 samples - at ../dataset/gen-word-1685-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3655 max words - at ../dataset/shuffle-word-3655-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1395 max words - at ../dataset/shuffle-word-1395-count.jsonl\n"
+      "Generated JSONL file with - 1870 max words, 200 samples - at ../dataset/gen-word-1870-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 48 samples (20 token repeat) - 1265 max words - at ../dataset/shuffle-word-1265-count.jsonl\n"
+      "Generated JSONL file with - 1135 max words, 200 samples - at ../dataset/gen-word-1135-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2035 max words - at ../dataset/shuffle-word-2035-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3830 max words - at ../dataset/shuffle-word-3830-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3105 max words - at ../dataset/shuffle-word-3105-count.jsonl\n"
+      "Generated a single JSONL file with 23 samples (20 token repeat) - 2775 max words - at ../dataset/shuffle-word-2775-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 44 samples (20 token repeat) - 1245 max words - at ../dataset/shuffle-word-1245-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3665 max words - at ../dataset/shuffle-word-3665-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) - 3470 max words - at ../dataset/shuffle-word-3470-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2325 max words, 200 samples - at ../dataset/gen-word-2325-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3430 max words - at ../dataset/shuffle-word-3430-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3160 max words - at ../dataset/shuffle-word-3160-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3425 max words - at ../dataset/shuffle-word-3425-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1375 max words - at ../dataset/shuffle-word-1375-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3270 max words - at ../dataset/shuffle-word-3270-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2775 max words, 200 samples - at ../dataset/gen-word-2775-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3050 max words - at ../dataset/shuffle-word-3050-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3745 max words - at ../dataset/shuffle-word-3745-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3465 max words - at ../dataset/shuffle-word-3465-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 28 samples (20 token repeat) - 2595 max words - at ../dataset/shuffle-word-2595-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3640 max words - at ../dataset/shuffle-word-3640-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3885 max words - at ../dataset/shuffle-word-3885-count.jsonl\n"
+      "Generated a single JSONL file with 80 samples (20 token repeat) - 785 max words - at ../dataset/shuffle-word-785-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3715 max words - at ../dataset/shuffle-word-3715-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3620 max words - at ../dataset/shuffle-word-3620-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2030 max words, 200 samples - at ../dataset/gen-word-2030-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3310 max words - at ../dataset/shuffle-word-3310-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1225 max words, 200 samples - at ../dataset/gen-word-1225-count.jsonl\n"
+      "Generated JSONL file with - 980 max words, 200 samples - at ../dataset/gen-word-980-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2115 max words, 200 samples - at ../dataset/gen-word-2115-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2060 max words - at ../dataset/shuffle-word-2060-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 975 max words, 200 samples - at ../dataset/gen-word-975-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3530 max words - at ../dataset/shuffle-word-3530-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1565 max words, 200 samples - at ../dataset/gen-word-1565-count.jsonl\n"
+      "Generated a single JSONL file with 59 samples (20 token repeat) - 1195 max words - at ../dataset/shuffle-word-1195-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1930 max words, 200 samples - at ../dataset/gen-word-1930-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3730 max words - at ../dataset/shuffle-word-3730-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 605 max words, 200 samples - at ../dataset/gen-word-605-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3365 max words - at ../dataset/shuffle-word-3365-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 34 samples (20 token repeat) - 2410 max words - at ../dataset/shuffle-word-2410-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3490 max words - at ../dataset/shuffle-word-3490-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) - 3340 max words - at ../dataset/shuffle-word-3340-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3175 max words - at ../dataset/shuffle-word-3175-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3890 max words - at ../dataset/shuffle-word-3890-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2890 max words, 200 samples - at ../dataset/gen-word-2890-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 JSONL file with - 1535 max words, 200 samples - at ../dataset/gen-word-1535-count.jsonl\n"
+      "Generated JSONL file with - 2515 max words, 200 samples - at ../dataset/gen-word-2515-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 41 samples (20 token repeat) - 1340 max words - at ../dataset/shuffle-word-1340-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3380 max words - at ../dataset/shuffle-word-3380-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 455 max words, 100 samples - at ../dataset/gen-word-455-count.jsonl\n"
+      "Generated JSONL file with - 1920 max words, 200 samples - at ../dataset/gen-word-1920-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1500 max words, 200 samples - at ../dataset/gen-word-1500-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3330 max words - at ../dataset/shuffle-word-3330-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2990 max words, 200 samples - at ../dataset/gen-word-2990-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3390 max words - at ../dataset/shuffle-word-3390-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 33 samples (20 token repeat) - 2535 max words - at ../dataset/shuffle-word-2535-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3560 max words - at ../dataset/shuffle-word-3560-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 335 max words, 100 samples - at ../dataset/gen-word-335-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3540 max words - at ../dataset/shuffle-word-3540-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1570 max words, 200 samples - at ../dataset/gen-word-1570-count.jsonl\n"
+      "Generated JSONL file with - 2130 max words, 200 samples - at ../dataset/gen-word-2130-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2175 max words - at ../dataset/shuffle-word-2175-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3305 max words - at ../dataset/shuffle-word-3305-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1835 max words, 200 samples - at ../dataset/gen-word-1835-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2080 max words - at ../dataset/shuffle-word-2080-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 460 max words, 100 samples - at ../dataset/gen-word-460-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3770 max words - at ../dataset/shuffle-word-3770-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3015 max words - at ../dataset/shuffle-word-3015-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3290 max words - at ../dataset/shuffle-word-3290-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 30 samples (20 token repeat) - 2510 max words - at ../dataset/shuffle-word-2510-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3265 max words - at ../dataset/shuffle-word-3265-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 445 max words, 100 samples - at ../dataset/gen-word-445-count.jsonl\n"
+      "Generated JSONL file with - 2915 max words, 200 samples - at ../dataset/gen-word-2915-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2095 max words - at ../dataset/shuffle-word-2095-count.jsonl\n"
+      "Generated a single JSONL file with 60 samples (20 token repeat) - 1015 max words - at ../dataset/shuffle-word-1015-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2170 max words, 200 samples - at ../dataset/gen-word-2170-count.jsonl\n"
+      "Generated JSONL file with - 2790 max words, 200 samples - at ../dataset/gen-word-2790-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 50 samples (20 token repeat) - 1285 max words - at ../dataset/shuffle-word-1285-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3700 max words - at ../dataset/shuffle-word-3700-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 31 samples (20 token repeat) - 2575 max words - at ../dataset/shuffle-word-2575-count.jsonl\n"
+      "Generated a single JSONL file with 29 samples (20 token repeat) - 2540 max words - at ../dataset/shuffle-word-2540-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3100 max words - at ../dataset/shuffle-word-3100-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3275 max words - at ../dataset/shuffle-word-3275-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1595 max words - at ../dataset/shuffle-word-1595-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3155 max words - at ../dataset/shuffle-word-3155-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 32 samples (20 token repeat) - 2545 max words - at ../dataset/shuffle-word-2545-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3535 max words - at ../dataset/shuffle-word-3535-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1445 max words, 200 samples - at ../dataset/gen-word-1445-count.jsonl\n"
+      "Generated a single JSONL file with 51 samples (20 token repeat) - 1240 max words - at ../dataset/shuffle-word-1240-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 41 samples (20 token repeat) - 1315 max words - at ../dataset/shuffle-word-1315-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3685 max words - at ../dataset/shuffle-word-3685-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1385 max words, 200 samples - at ../dataset/gen-word-1385-count.jsonl\n"
+      "Generated JSONL file with - 2570 max words, 200 samples - at ../dataset/gen-word-2570-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3075 max words - at ../dataset/shuffle-word-3075-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3325 max words - at ../dataset/shuffle-word-3325-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 33 samples (20 token repeat) - 2580 max words - at ../dataset/shuffle-word-2580-count.jsonl\n"
+      "Generated JSONL file with - 825 max words, 200 samples - at ../dataset/gen-word-825-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1505 max words, 200 samples - at ../dataset/gen-word-1505-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3780 max words - at ../dataset/shuffle-word-3780-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 39 samples (20 token repeat) - 2395 max words - at ../dataset/shuffle-word-2395-count.jsonl\n"
+      "Generated a single JSONL file with 59 samples (20 token repeat) - 1115 max words - at ../dataset/shuffle-word-1115-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2260 max words, 200 samples - at ../dataset/gen-word-2260-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3875 max words - at ../dataset/shuffle-word-3875-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 36 samples (20 token repeat) - 2495 max words - at ../dataset/shuffle-word-2495-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3580 max words - at ../dataset/shuffle-word-3580-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3415 max words - at ../dataset/shuffle-word-3415-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3980 max words - at ../dataset/shuffle-word-3980-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2125 max words, 200 samples - at ../dataset/gen-word-2125-count.jsonl\n"
+      "Generated JSONL file with - 660 max words, 200 samples - at ../dataset/gen-word-660-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 2795 max words - at ../dataset/shuffle-word-2795-count.jsonl\n"
+      "Generated JSONL file with - 1285 max words, 200 samples - at ../dataset/gen-word-1285-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1760 max words, 200 samples - at ../dataset/gen-word-1760-count.jsonl\n"
+      "Generated JSONL file with - 3110 max words, 200 samples - at ../dataset/gen-word-3110-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1245 max words, 200 samples - at ../dataset/gen-word-1245-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3525 max words - at ../dataset/shuffle-word-3525-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1795 max words - at ../dataset/shuffle-word-1795-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3790 max words - at ../dataset/shuffle-word-3790-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3435 max words - at ../dataset/shuffle-word-3435-count.jsonl\n"
+      "Generated JSONL file with - 695 max words, 200 samples - at ../dataset/gen-word-695-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3095 max words - at ../dataset/shuffle-word-3095-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3420 max words - at ../dataset/shuffle-word-3420-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1965 max words, 200 samples - at ../dataset/gen-word-1965-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3660 max words - at ../dataset/shuffle-word-3660-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 23 samples (20 token repeat) - 2695 max words - at ../dataset/shuffle-word-2695-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3295 max words - at ../dataset/shuffle-word-3295-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2315 max words, 200 samples - at ../dataset/gen-word-2315-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3130 max words - at ../dataset/shuffle-word-3130-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3140 max words - at ../dataset/shuffle-word-3140-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3825 max words - at ../dataset/shuffle-word-3825-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1420 max words, 200 samples - at ../dataset/gen-word-1420-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3605 max words - at ../dataset/shuffle-word-3605-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3110 max words - at ../dataset/shuffle-word-3110-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1970 max words - at ../dataset/shuffle-word-1970-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1310 max words, 200 samples - at ../dataset/gen-word-1310-count.jsonl\n"
+      "Generated JSONL file with - 1695 max words, 200 samples - at ../dataset/gen-word-1695-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 52 samples (20 token repeat) - 1210 max words - at ../dataset/shuffle-word-1210-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3570 max words - at ../dataset/shuffle-word-3570-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1735 max words, 200 samples - at ../dataset/gen-word-1735-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3060 max words - at ../dataset/shuffle-word-3060-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 275 max words, 100 samples - at ../dataset/gen-word-275-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3865 max words - at ../dataset/shuffle-word-3865-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 30 samples (20 token repeat) - 2585 max words - at ../dataset/shuffle-word-2585-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3705 max words - at ../dataset/shuffle-word-3705-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1860 max words, 200 samples - at ../dataset/gen-word-1860-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3740 max words - at ../dataset/shuffle-word-3740-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3780 max words - at ../dataset/shuffle-word-3780-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3805 max words - at ../dataset/shuffle-word-3805-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 2990 max words - at ../dataset/shuffle-word-2990-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) - 1575 max words - at ../dataset/shuffle-word-1575-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3960 max words - at ../dataset/shuffle-word-3960-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2255 max words, 200 samples - at ../dataset/gen-word-2255-count.jsonl\n"
+      "Generated a single JSONL file with 41 samples (20 token repeat) - 1380 max words - at ../dataset/shuffle-word-1380-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2135 max words, 200 samples - at ../dataset/gen-word-2135-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3545 max words - at ../dataset/shuffle-word-3545-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2540 max words, 200 samples - at ../dataset/gen-word-2540-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3720 max words - at ../dataset/shuffle-word-3720-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1980 max words - at ../dataset/shuffle-word-1980-count.jsonl\n"
+      "Generated a single JSONL file with 60 samples (20 token repeat) - 995 max words - at ../dataset/shuffle-word-995-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1600 max words, 200 samples - at ../dataset/gen-word-1600-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3785 max words - at ../dataset/shuffle-word-3785-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3340 max words - at ../dataset/shuffle-word-3340-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3650 max words - at ../dataset/shuffle-word-3650-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3185 max words - at ../dataset/shuffle-word-3185-count.jsonl\n"
+      "Generated JSONL file with - 1745 max words, 200 samples - at ../dataset/gen-word-1745-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3310 max words - at ../dataset/shuffle-word-3310-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3670 max words - at ../dataset/shuffle-word-3670-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 25 samples (20 token repeat) - 2605 max words - at ../dataset/shuffle-word-2605-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3145 max words - at ../dataset/shuffle-word-3145-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1585 max words - at ../dataset/shuffle-word-1585-count.jsonl\n"
+      "Generated JSONL file with - 3100 max words, 200 samples - at ../dataset/gen-word-3100-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1525 max words, 200 samples - at ../dataset/gen-word-1525-count.jsonl\n"
+      "Generated JSONL file with - 710 max words, 200 samples - at ../dataset/gen-word-710-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 2875 max words - at ../dataset/shuffle-word-2875-count.jsonl\n"
+      "Generated JSONL file with - 2505 max words, 200 samples - at ../dataset/gen-word-2505-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 52 samples (20 token repeat) - 1205 max words - at ../dataset/shuffle-word-1205-count.jsonl\n"
+      "Generated JSONL file with - 1770 max words, 200 samples - at ../dataset/gen-word-1770-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 760 max words, 200 samples - at ../dataset/gen-word-760-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3350 max words - at ../dataset/shuffle-word-3350-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3645 max words - at ../dataset/shuffle-word-3645-count.jsonl\n"
+      "Generated JSONL file with - 1965 max words, 200 samples - at ../dataset/gen-word-1965-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 JSONL file with - 1865 max words, 200 samples - at ../dataset/gen-word-1865-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 2815 max words - at ../dataset/shuffle-word-2815-count.jsonl\n"
+      "Generated JSONL file with - 2625 max words, 200 samples - at ../dataset/gen-word-2625-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 2860 max words - at ../dataset/shuffle-word-2860-count.jsonl\n"
+      "Generated JSONL file with - 2085 max words, 200 samples - at ../dataset/gen-word-2085-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3035 max words - at ../dataset/shuffle-word-3035-count.jsonl\n"
+      "Generated JSONL file with - 1195 max words, 200 samples - at ../dataset/gen-word-1195-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3200 max words - at ../dataset/shuffle-word-3200-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3550 max words - at ../dataset/shuffle-word-3550-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3810 max words - at ../dataset/shuffle-word-3810-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3595 max words - at ../dataset/shuffle-word-3595-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3920 max words - at ../dataset/shuffle-word-3920-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3820 max words - at ../dataset/shuffle-word-3820-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2585 max words, 200 samples - at ../dataset/gen-word-2585-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1460 max words - at ../dataset/shuffle-word-1460-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1745 max words, 200 samples - at ../dataset/gen-word-1745-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3975 max words - at ../dataset/shuffle-word-3975-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 2935 max words - at ../dataset/shuffle-word-2935-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) - 3305 max words - at ../dataset/shuffle-word-3305-count.jsonl\n"
+      "Generated JSONL file with - 1070 max words, 200 samples - at ../dataset/gen-word-1070-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3220 max words - at ../dataset/shuffle-word-3220-count.jsonl\n"
+      "Generated JSONL file with - 2205 max words, 200 samples - at ../dataset/gen-word-2205-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 JSONL file with - 2075 max words, 200 samples - at ../dataset/gen-word-2075-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3290 max words, 200 samples - at ../dataset/gen-word-3290-count.jsonl\n"
+      "Generated JSONL file with - 1675 max words, 200 samples - at ../dataset/gen-word-1675-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2985 max words, 200 samples - at ../dataset/gen-word-2985-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3990 max words - at ../dataset/shuffle-word-3990-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3040 max words - at ../dataset/shuffle-word-3040-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 2920 max words - at ../dataset/shuffle-word-2920-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1905 max words, 200 samples - at ../dataset/gen-word-1905-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3745 max words - at ../dataset/shuffle-word-3745-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3590 max words - at ../dataset/shuffle-word-3590-count.jsonl\n"
+      "Generated JSONL file with - 2190 max words, 200 samples - at ../dataset/gen-word-2190-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 21 samples (20 token repeat) - 2710 max words - at ../dataset/shuffle-word-2710-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3475 max words - at ../dataset/shuffle-word-3475-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2395 max words, 200 samples - at ../dataset/gen-word-2395-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3880 max words - at ../dataset/shuffle-word-3880-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3130 max words - at ../dataset/shuffle-word-3130-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1415 max words - at ../dataset/shuffle-word-1415-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) - 3590 max words - at ../dataset/shuffle-word-3590-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3405 max words - at ../dataset/shuffle-word-3405-count.jsonl\n"
+      "Generated JSONL file with - 1385 max words, 200 samples - at ../dataset/gen-word-1385-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2770 max words, 200 samples - at ../dataset/gen-word-2770-count.jsonl\n"
+      "Generated a single JSONL file with 50 samples (20 token repeat) - 1260 max words - at ../dataset/shuffle-word-1260-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3010 max words - at ../dataset/shuffle-word-3010-count.jsonl\n"
+      "Generated a single JSONL file with 49 samples (20 token repeat) - 1205 max words - at ../dataset/shuffle-word-1205-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3910 max words - at ../dataset/shuffle-word-3910-count.jsonl\n"
+      "Generated JSONL file with - 855 max words, 200 samples - at ../dataset/gen-word-855-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3000 max words - at ../dataset/shuffle-word-3000-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3135 max words - at ../dataset/shuffle-word-3135-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1680 max words - at ../dataset/shuffle-word-1680-count.jsonl\n"
+      "Generated JSONL file with - 690 max words, 200 samples - at ../dataset/gen-word-690-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3030 max words - at ../dataset/shuffle-word-3030-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3045 max words - at ../dataset/shuffle-word-3045-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 2995 max words - at ../dataset/shuffle-word-2995-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1685 max words - at ../dataset/shuffle-word-1685-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2120 max words, 200 samples - at ../dataset/gen-word-2120-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3965 max words - at ../dataset/shuffle-word-3965-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3050 max words - at ../dataset/shuffle-word-3050-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3220 max words - at ../dataset/shuffle-word-3220-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3365 max words - at ../dataset/shuffle-word-3365-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2370 max words - at ../dataset/shuffle-word-2370-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3080 max words - at ../dataset/shuffle-word-3080-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2205 max words - at ../dataset/shuffle-word-2205-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 30 samples (20 token repeat) - 2590 max words - at ../dataset/shuffle-word-2590-count.jsonl\n"
+      "Generated JSONL file with - 1440 max words, 200 samples - at ../dataset/gen-word-1440-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2725 max words, 200 samples - at ../dataset/gen-word-2725-count.jsonl\n"
+      "Generated JSONL file with - 1940 max words, 200 samples - at ../dataset/gen-word-1940-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 2855 max words - at ../dataset/shuffle-word-2855-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3235 max words - at ../dataset/shuffle-word-3235-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3350 max words - at ../dataset/shuffle-word-3350-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2145 max words - at ../dataset/shuffle-word-2145-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2265 max words, 200 samples - at ../dataset/gen-word-2265-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3970 max words - at ../dataset/shuffle-word-3970-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2140 max words, 200 samples - at ../dataset/gen-word-2140-count.jsonl\n"
+      "Generated a single JSONL file with 29 samples (20 token repeat) - 2675 max words - at ../dataset/shuffle-word-2675-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 620 max words, 200 samples - at ../dataset/gen-word-620-count.jsonl\n"
+      "Generated JSONL file with - 1560 max words, 200 samples - at ../dataset/gen-word-1560-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1620 max words, 200 samples - at ../dataset/gen-word-1620-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3675 max words - at ../dataset/shuffle-word-3675-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3975 max words - at ../dataset/shuffle-word-3975-count.jsonl\n"
+      "Generated JSONL file with - 2440 max words, 200 samples - at ../dataset/gen-word-2440-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3380 max words - at ../dataset/shuffle-word-3380-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2015 max words - at ../dataset/shuffle-word-2015-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 2825 max words - at ../dataset/shuffle-word-2825-count.jsonl\n"
+      "Generated a single JSONL file with 23 samples (20 token repeat) - 2655 max words - at ../dataset/shuffle-word-2655-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3370 max words - at ../dataset/shuffle-word-3370-count.jsonl\n"
+      "Generated a single JSONL file with 78 samples (20 token repeat) - 710 max words - at ../dataset/shuffle-word-710-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1080 max words, 200 samples - at ../dataset/gen-word-1080-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2225 max words - at ../dataset/shuffle-word-2225-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3395 max words, 200 samples - at ../dataset/gen-word-3395-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3115 max words - at ../dataset/shuffle-word-3115-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3275 max words - at ../dataset/shuffle-word-3275-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) - 3410 max words - at ../dataset/shuffle-word-3410-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3405 max words - at ../dataset/shuffle-word-3405-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3375 max words - at ../dataset/shuffle-word-3375-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1485 max words - at ../dataset/shuffle-word-1485-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3930 max words - at ../dataset/shuffle-word-3930-count.jsonl\n"
+      "Generated JSONL file with - 2140 max words, 200 samples - at ../dataset/gen-word-2140-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3520 max words - at ../dataset/shuffle-word-3520-count.jsonl\n"
+      "Generated JSONL file with - 1205 max words, 200 samples - at ../dataset/gen-word-1205-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3445 max words - at ../dataset/shuffle-word-3445-count.jsonl\n"
+      "Generated JSONL file with - 2340 max words, 200 samples - at ../dataset/gen-word-2340-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3860 max words - at ../dataset/shuffle-word-3860-count.jsonl\n"
+      "Generated JSONL file with - 1685 max words, 200 samples - at ../dataset/gen-word-1685-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3170 max words - at ../dataset/shuffle-word-3170-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2295 max words - at ../dataset/shuffle-word-2295-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3400 max words - at ../dataset/shuffle-word-3400-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1625 max words - at ../dataset/shuffle-word-1625-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2310 max words, 200 samples - at ../dataset/gen-word-2310-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3930 max words - at ../dataset/shuffle-word-3930-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1400 max words - at ../dataset/shuffle-word-1400-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3760 max words - at ../dataset/shuffle-word-3760-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3525 max words - at ../dataset/shuffle-word-3525-count.jsonl\n"
+      "Generated JSONL file with - 3755 max words, 200 samples - at ../dataset/gen-word-3755-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3870 max words - at ../dataset/shuffle-word-3870-count.jsonl\n"
+      "Generated a single JSONL file with 21 samples (20 token repeat) - 2765 max words - at ../dataset/shuffle-word-2765-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1490 max words - at ../dataset/shuffle-word-1490-count.jsonl\n"
+      "Generated a single JSONL file with 29 samples (20 token repeat) - 2595 max words - at ../dataset/shuffle-word-2595-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1960 max words, 200 samples - at ../dataset/gen-word-1960-count.jsonl\n"
+      "Generated JSONL file with - 1715 max words, 200 samples - at ../dataset/gen-word-1715-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 49 samples (20 token repeat) - 1290 max words - at ../dataset/shuffle-word-1290-count.jsonl\n"
+      "Generated JSONL file with - 3220 max words, 200 samples - at ../dataset/gen-word-3220-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1280 max words, 200 samples - at ../dataset/gen-word-1280-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3170 max words - at ../dataset/shuffle-word-3170-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3150 max words - at ../dataset/shuffle-word-3150-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3945 max words - at ../dataset/shuffle-word-3945-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2545 max words, 200 samples - at ../dataset/gen-word-2545-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3080 max words - at ../dataset/shuffle-word-3080-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3550 max words - at ../dataset/shuffle-word-3550-count.jsonl\n"
+      "Generated JSONL file with - 1985 max words, 200 samples - at ../dataset/gen-word-1985-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3995 max words - at ../dataset/shuffle-word-3995-count.jsonl\n"
+      "Generated JSONL file with - 1585 max words, 200 samples - at ../dataset/gen-word-1585-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3480 max words - at ../dataset/shuffle-word-3480-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3435 max words - at ../dataset/shuffle-word-3435-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3740 max words - at ../dataset/shuffle-word-3740-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2230 max words - at ../dataset/shuffle-word-2230-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1435 max words, 200 samples - at ../dataset/gen-word-1435-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3510 max words - at ../dataset/shuffle-word-3510-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1050 max words, 200 samples - at ../dataset/gen-word-1050-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3575 max words - at ../dataset/shuffle-word-3575-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3395 max words - at ../dataset/shuffle-word-3395-count.jsonl\n"
+      "Generated JSONL file with - 2145 max words, 200 samples - at ../dataset/gen-word-2145-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2365 max words, 200 samples - at ../dataset/gen-word-2365-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3910 max words - at ../dataset/shuffle-word-3910-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1610 max words, 200 samples - at ../dataset/gen-word-1610-count.jsonl\n"
+      "Generated JSONL file with - 1945 max words, 200 samples - at ../dataset/gen-word-1945-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3490 max words - at ../dataset/shuffle-word-3490-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3715 max words - at ../dataset/shuffle-word-3715-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1950 max words - at ../dataset/shuffle-word-1950-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2170 max words - at ../dataset/shuffle-word-2170-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1750 max words, 200 samples - at ../dataset/gen-word-1750-count.jsonl\n"
+      "Generated JSONL file with - 875 max words, 200 samples - at ../dataset/gen-word-875-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3770 max words - at ../dataset/shuffle-word-3770-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 4000 max words - at ../dataset/shuffle-word-4000-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3755 max words - at ../dataset/shuffle-word-3755-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3775 max words - at ../dataset/shuffle-word-3775-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2165 max words, 200 samples - at ../dataset/gen-word-2165-count.jsonl\n"
+      "Generated JSONL file with - 1340 max words, 200 samples - at ../dataset/gen-word-1340-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2330 max words, 200 samples - at ../dataset/gen-word-2330-count.jsonl\n"
+      "Generated a single JSONL file with 38 samples (20 token repeat) - 2425 max words - at ../dataset/shuffle-word-2425-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3725 max words - at ../dataset/shuffle-word-3725-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3285 max words - at ../dataset/shuffle-word-3285-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1430 max words - at ../dataset/shuffle-word-1430-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3515 max words - at ../dataset/shuffle-word-3515-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3670 max words - at ../dataset/shuffle-word-3670-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1445 max words - at ../dataset/shuffle-word-1445-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 60 samples (20 token repeat) - 1085 max words - at ../dataset/shuffle-word-1085-count.jsonl\n"
+      "Generated JSONL file with - 1520 max words, 200 samples - at ../dataset/gen-word-1520-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1670 max words, 200 samples - at ../dataset/gen-word-1670-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3035 max words - at ../dataset/shuffle-word-3035-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 7 samples (1 token repeat) - 345 max words - at ../dataset/shuffle-word-345-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3460 max words - at ../dataset/shuffle-word-3460-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2855 max words, 200 samples - at ../dataset/gen-word-2855-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3450 max words - at ../dataset/shuffle-word-3450-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2865 max words, 200 samples - at ../dataset/gen-word-2865-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3440 max words - at ../dataset/shuffle-word-3440-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3710 max words - at ../dataset/shuffle-word-3710-count.jsonl\n"
+      "Generated a single JSONL file with 36 samples (20 token repeat) - 2420 max words - at ../dataset/shuffle-word-2420-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3610 max words - at ../dataset/shuffle-word-3610-count.jsonl\n"
+      "Generated JSONL file with - 3075 max words, 200 samples - at ../dataset/gen-word-3075-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3360 max words - at ../dataset/shuffle-word-3360-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3230 max words - at ../dataset/shuffle-word-3230-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3385 max words - at ../dataset/shuffle-word-3385-count.jsonl\n"
+      "Generated JSONL file with - 1980 max words, 200 samples - at ../dataset/gen-word-1980-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1560 max words, 200 samples - at ../dataset/gen-word-1560-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 1495 max words - at ../dataset/shuffle-word-1495-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2690 max words, 200 samples - at ../dataset/gen-word-2690-count.jsonl\n"
+      "Generated JSONL file with - 1005 max words, 200 samples - at ../dataset/gen-word-1005-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2685 max words, 200 samples - at ../dataset/gen-word-2685-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3385 max words - at ../dataset/shuffle-word-3385-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2195 max words, 200 samples - at ../dataset/gen-word-2195-count.jsonl\n"
+      "Generated JSONL file with - 1500 max words, 200 samples - at ../dataset/gen-word-1500-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3485 max words - at ../dataset/shuffle-word-3485-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3920 max words - at ../dataset/shuffle-word-3920-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3320 max words - at ../dataset/shuffle-word-3320-count.jsonl\n"
+      "Generated a single JSONL file with 62 samples (20 token repeat) - 810 max words - at ../dataset/shuffle-word-810-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1140 max words, 200 samples - at ../dataset/gen-word-1140-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3010 max words - at ../dataset/shuffle-word-3010-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3420 max words - at ../dataset/shuffle-word-3420-count.jsonl\n"
+      "Generated JSONL file with - 910 max words, 200 samples - at ../dataset/gen-word-910-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2830 max words, 200 samples - at ../dataset/gen-word-2830-count.jsonl\n"
+      "Generated a single JSONL file with 35 samples (20 token repeat) - 2470 max words - at ../dataset/shuffle-word-2470-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 60 samples (20 token repeat) - 1170 max words - at ../dataset/shuffle-word-1170-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2350 max words - at ../dataset/shuffle-word-2350-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3390 max words - at ../dataset/shuffle-word-3390-count.jsonl\n"
+      "Generated JSONL file with - 2430 max words, 200 samples - at ../dataset/gen-word-2430-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 840 max words, 200 samples - at ../dataset/gen-word-840-count.jsonl\n"
+      "Generated a single JSONL file with 21 samples (20 token repeat) - 2715 max words - at ../dataset/shuffle-word-2715-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2035 max words, 200 samples - at ../dataset/gen-word-2035-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3810 max words - at ../dataset/shuffle-word-3810-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3030 max words, 200 samples - at ../dataset/gen-word-3030-count.jsonl\n"
+      "Generated a single JSONL file with 32 samples (20 token repeat) - 2485 max words - at ../dataset/shuffle-word-2485-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1445 max words - at ../dataset/shuffle-word-1445-count.jsonl\n"
+      "Generated a single JSONL file with 60 samples (20 token repeat) - 1095 max words - at ../dataset/shuffle-word-1095-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3255 max words - at ../dataset/shuffle-word-3255-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3815 max words - at ../dataset/shuffle-word-3815-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3570 max words - at ../dataset/shuffle-word-3570-count.jsonl\n"
+      "Generated a single JSONL file with 49 samples (20 token repeat) - 1220 max words - at ../dataset/shuffle-word-1220-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3585 max words - at ../dataset/shuffle-word-3585-count.jsonl\n"
+      "Generated a single JSONL file with 24 samples (20 token repeat) - 2660 max words - at ../dataset/shuffle-word-2660-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 430 max words, 100 samples - at ../dataset/gen-word-430-count.jsonl\n"
+      "Generated a single JSONL file with 40 samples (20 token repeat) - 2085 max words - at ../dataset/shuffle-word-2085-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1755 max words, 200 samples - at ../dataset/gen-word-1755-count.jsonl\n"
+      "Generated JSONL file with - 1200 max words, 200 samples - at ../dataset/gen-word-1200-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2660 max words, 200 samples - at ../dataset/gen-word-2660-count.jsonl\n"
+      "Generated JSONL file with - 2655 max words, 200 samples - at ../dataset/gen-word-2655-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2055 max words, 200 samples - at ../dataset/gen-word-2055-count.jsonl\n"
+      "Generated JSONL file with - 640 max words, 200 samples - at ../dataset/gen-word-640-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1410 max words - at ../dataset/shuffle-word-1410-count.jsonl\n"
+      "Generated JSONL file with - 1050 max words, 200 samples - at ../dataset/gen-word-1050-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3580 max words - at ../dataset/shuffle-word-3580-count.jsonl\n"
+      "Generated JSONL file with - 2480 max words, 200 samples - at ../dataset/gen-word-2480-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1725 max words - at ../dataset/shuffle-word-1725-count.jsonl\n"
+      "Generated JSONL file with - 2155 max words, 200 samples - at ../dataset/gen-word-2155-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 60 samples (20 token repeat) - 1045 max words - at ../dataset/shuffle-word-1045-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3840 max words - at ../dataset/shuffle-word-3840-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1530 max words - at ../dataset/shuffle-word-1530-count.jsonl\n"
+      "Generated JSONL file with - 3195 max words, 200 samples - at ../dataset/gen-word-3195-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2980 max words, 200 samples - at ../dataset/gen-word-2980-count.jsonl\n"
+      "Generated JSONL file with - 1635 max words, 200 samples - at ../dataset/gen-word-1635-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2280 max words, 200 samples - at ../dataset/gen-word-2280-count.jsonl\n"
+      "Generated JSONL file with - 2825 max words, 200 samples - at ../dataset/gen-word-2825-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2840 max words, 200 samples - at ../dataset/gen-word-2840-count.jsonl\n"
+      "Generated JSONL file with - 2455 max words, 200 samples - at ../dataset/gen-word-2455-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 2775 max words - at ../dataset/shuffle-word-2775-count.jsonl\n"
+      "Generated JSONL file with - 1270 max words, 200 samples - at ../dataset/gen-word-1270-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3145 max words - at ../dataset/shuffle-word-3145-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3855 max words - at ../dataset/shuffle-word-3855-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1845 max words - at ../dataset/shuffle-word-1845-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3625 max words - at ../dataset/shuffle-word-3625-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3410 max words, 200 samples - at ../dataset/gen-word-3410-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3505 max words - at ../dataset/shuffle-word-3505-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2235 max words - at ../dataset/shuffle-word-2235-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3645 max words - at ../dataset/shuffle-word-3645-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3990 max words - at ../dataset/shuffle-word-3990-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3950 max words - at ../dataset/shuffle-word-3950-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3555 max words - at ../dataset/shuffle-word-3555-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3320 max words - at ../dataset/shuffle-word-3320-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1410 max words, 200 samples - at ../dataset/gen-word-1410-count.jsonl\n"
+      "Generated JSONL file with - 1060 max words, 200 samples - at ../dataset/gen-word-1060-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 7 samples (1 token repeat) - 335 max words - at ../dataset/shuffle-word-335-count.jsonl\n"
+      "Generated JSONL file with - 1895 max words, 200 samples - at ../dataset/gen-word-1895-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2645 max words, 200 samples - at ../dataset/gen-word-2645-count.jsonl\n"
+      "Generated JSONL file with - 2025 max words, 200 samples - at ../dataset/gen-word-2025-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3530 max words - at ../dataset/shuffle-word-3530-count.jsonl\n"
+      "Generated a single JSONL file with 20 samples (20 token repeat) - 3360 max words - at ../dataset/shuffle-word-3360-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 60 samples (20 token repeat) - 940 max words - at ../dataset/shuffle-word-940-count.jsonl\n"
+      "Generated JSONL file with - 605 max words, 200 samples - at ../dataset/gen-word-605-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1665 max words - at ../dataset/shuffle-word-1665-count.jsonl\n"
+      "Generated JSONL file with - 3180 max words, 200 samples - at ../dataset/gen-word-3180-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2975 max words, 200 samples - at ../dataset/gen-word-2975-count.jsonl\n"
+      "Generated JSONL file with - 1225 max words, 200 samples - at ../dataset/gen-word-1225-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 JSONL file with - 1310 max words, 200 samples - at ../dataset/gen-word-1310-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3655 max words - at ../dataset/shuffle-word-3655-count.jsonl\n"
+      "Generated JSONL file with - 1640 max words, 200 samples - at ../dataset/gen-word-1640-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2595 max words, 200 samples - at ../dataset/gen-word-2595-count.jsonl\n"
+      "Generated JSONL file with - 1720 max words, 200 samples - at ../dataset/gen-word-1720-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2090 max words, 200 samples - at ../dataset/gen-word-2090-count.jsonl\n"
+      "Generated JSONL file with - 3135 max words, 200 samples - at ../dataset/gen-word-3135-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1465 max words - at ../dataset/shuffle-word-1465-count.jsonl\n"
+      "Generated JSONL file with - 2635 max words, 200 samples - at ../dataset/gen-word-2635-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2170 max words - at ../dataset/shuffle-word-2170-count.jsonl\n"
+      "Generated JSONL file with - 2240 max words, 200 samples - at ../dataset/gen-word-2240-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 JSONL file with - 2680 max words, 200 samples - at ../dataset/gen-word-2680-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3225 max words - at ../dataset/shuffle-word-3225-count.jsonl\n"
+      "Generated JSONL file with - 2660 max words, 200 samples - at ../dataset/gen-word-2660-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3680 max words - at ../dataset/shuffle-word-3680-count.jsonl\n"
+      "Generated JSONL file with - 1510 max words, 200 samples - at ../dataset/gen-word-1510-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3575 max words - at ../dataset/shuffle-word-3575-count.jsonl\n"
+      "Generated JSONL file with - 2925 max words, 200 samples - at ../dataset/gen-word-2925-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3825 max words - at ../dataset/shuffle-word-3825-count.jsonl\n"
+      "Generated JSONL file with - 2600 max words, 200 samples - at ../dataset/gen-word-2600-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1525 max words - at ../dataset/shuffle-word-1525-count.jsonl\n"
+      "Generated JSONL file with - 2070 max words, 200 samples - at ../dataset/gen-word-2070-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3840 max words - at ../dataset/shuffle-word-3840-count.jsonl\n"
+      "Generated JSONL file with - 1905 max words, 200 samples - at ../dataset/gen-word-1905-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 9 samples (1 token repeat) - 265 max words - at ../dataset/shuffle-word-265-count.jsonl\n"
+      "Generated JSONL file with - 1615 max words, 200 samples - at ../dataset/gen-word-1615-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1925 max words - at ../dataset/shuffle-word-1925-count.jsonl\n"
+      "Generated JSONL file with - 2285 max words, 200 samples - at ../dataset/gen-word-2285-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3925 max words - at ../dataset/shuffle-word-3925-count.jsonl\n"
+      "Generated JSONL file with - 1950 max words, 200 samples - at ../dataset/gen-word-1950-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3615 max words - at ../dataset/shuffle-word-3615-count.jsonl\n"
+      "Generated JSONL file with - 2005 max words, 200 samples - at ../dataset/gen-word-2005-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1415 max words - at ../dataset/shuffle-word-1415-count.jsonl\n"
+      "Generated JSONL file with - 1705 max words, 200 samples - at ../dataset/gen-word-1705-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1975 max words, 200 samples - at ../dataset/gen-word-1975-count.jsonl\n"
+      "Generated JSONL file with - 925 max words, 200 samples - at ../dataset/gen-word-925-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1670 max words - at ../dataset/shuffle-word-1670-count.jsonl\n"
+      "Generated JSONL file with - 3275 max words, 200 samples - at ../dataset/gen-word-3275-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3560 max words - at ../dataset/shuffle-word-3560-count.jsonl\n"
+      "Generated JSONL file with - 2830 max words, 200 samples - at ../dataset/gen-word-2830-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 100 samples (20 token repeat) - 570 max words - at ../dataset/shuffle-word-570-count.jsonl\n"
+      "Generated JSONL file with - 2235 max words, 200 samples - at ../dataset/gen-word-2235-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3540 max words - at ../dataset/shuffle-word-3540-count.jsonl\n"
+      "Generated JSONL file with - 1900 max words, 200 samples - at ../dataset/gen-word-1900-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2060 max words, 200 samples - at ../dataset/gen-word-2060-count.jsonl\n"
+      "Generated JSONL file with - 2105 max words, 200 samples - at ../dataset/gen-word-2105-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 JSONL file with - 795 max words, 200 samples - at ../dataset/gen-word-795-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 935 max words, 200 samples - at ../dataset/gen-word-935-count.jsonl\n"
+      "Generated JSONL file with - 1915 max words, 200 samples - at ../dataset/gen-word-1915-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1590 max words, 200 samples - at ../dataset/gen-word-1590-count.jsonl\n"
+      "Generated JSONL file with - 865 max words, 200 samples - at ../dataset/gen-word-865-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1970 max words - at ../dataset/shuffle-word-1970-count.jsonl\n"
+      "Generated JSONL file with - 1730 max words, 200 samples - at ../dataset/gen-word-1730-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3605 max words - at ../dataset/shuffle-word-3605-count.jsonl\n"
+      "Generated JSONL file with - 2245 max words, 200 samples - at ../dataset/gen-word-2245-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1355 max words - at ../dataset/shuffle-word-1355-count.jsonl\n"
+      "Generated JSONL file with - 2310 max words, 200 samples - at ../dataset/gen-word-2310-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3495 max words - at ../dataset/shuffle-word-3495-count.jsonl\n"
+      "Generated JSONL file with - 800 max words, 200 samples - at ../dataset/gen-word-800-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2225 max words - at ../dataset/shuffle-word-2225-count.jsonl\n"
+      "Generated JSONL file with - 1660 max words, 200 samples - at ../dataset/gen-word-1660-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3280 max words - at ../dataset/shuffle-word-3280-count.jsonl\n"
+      "Generated JSONL file with - 2360 max words, 200 samples - at ../dataset/gen-word-2360-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 995 max words, 200 samples - at ../dataset/gen-word-995-count.jsonl\n"
+      "Generated JSONL file with - 2015 max words, 200 samples - at ../dataset/gen-word-2015-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2010 max words, 200 samples - at ../dataset/gen-word-2010-count.jsonl\n"
+      "Generated JSONL file with - 2200 max words, 200 samples - at ../dataset/gen-word-2200-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1330 max words, 200 samples - at ../dataset/gen-word-1330-count.jsonl\n"
+      "Generated JSONL file with - 1015 max words, 200 samples - at ../dataset/gen-word-1015-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2500 max words, 200 samples - at ../dataset/gen-word-2500-count.jsonl\n"
+      "Generated JSONL file with - 2690 max words, 200 samples - at ../dataset/gen-word-2690-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1890 max words, 200 samples - at ../dataset/gen-word-1890-count.jsonl\n"
+      "Generated JSONL file with - 2345 max words, 200 samples - at ../dataset/gen-word-2345-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3570 max words, 200 samples - at ../dataset/gen-word-3570-count.jsonl\n"
+      "Generated JSONL file with - 2320 max words, 200 samples - at ../dataset/gen-word-2320-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3735 max words - at ../dataset/shuffle-word-3735-count.jsonl\n"
+      "Generated JSONL file with - 1095 max words, 200 samples - at ../dataset/gen-word-1095-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3625 max words - at ../dataset/shuffle-word-3625-count.jsonl\n"
+      "Generated JSONL file with - 2525 max words, 200 samples - at ../dataset/gen-word-2525-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3475 max words - at ../dataset/shuffle-word-3475-count.jsonl\n"
+      "Generated JSONL file with - 1125 max words, 200 samples - at ../dataset/gen-word-1125-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2635 max words, 200 samples - at ../dataset/gen-word-2635-count.jsonl\n"
+      "Generated JSONL file with - 1065 max words, 200 samples - at ../dataset/gen-word-1065-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 100 samples (20 token repeat) - 505 max words - at ../dataset/shuffle-word-505-count.jsonl\n"
+      "Generated JSONL file with - 2425 max words, 200 samples - at ../dataset/gen-word-2425-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 6 samples (1 token repeat) - 425 max words - at ../dataset/shuffle-word-425-count.jsonl\n"
+      "Generated JSONL file with - 1260 max words, 200 samples - at ../dataset/gen-word-1260-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2305 max words, 200 samples - at ../dataset/gen-word-2305-count.jsonl\n"
+      "Generated JSONL file with - 2520 max words, 200 samples - at ../dataset/gen-word-2520-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 260 max words, 100 samples - at ../dataset/gen-word-260-count.jsonl\n"
+      "Generated JSONL file with - 2120 max words, 200 samples - at ../dataset/gen-word-2120-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1355 max words, 200 samples - at ../dataset/gen-word-1355-count.jsonl\n"
+      "Generated JSONL file with - 2305 max words, 200 samples - at ../dataset/gen-word-2305-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 60 samples (20 token repeat) - 1080 max words - at ../dataset/shuffle-word-1080-count.jsonl\n"
+      "Generated JSONL file with - 2905 max words, 200 samples - at ../dataset/gen-word-2905-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2270 max words, 200 samples - at ../dataset/gen-word-2270-count.jsonl\n"
+      "Generated JSONL file with - 2090 max words, 200 samples - at ../dataset/gen-word-2090-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2650 max words, 200 samples - at ../dataset/gen-word-2650-count.jsonl\n"
+      "Generated JSONL file with - 2900 max words, 200 samples - at ../dataset/gen-word-2900-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3675 max words, 200 samples - at ../dataset/gen-word-3675-count.jsonl\n"
+      "Generated JSONL file with - 1250 max words, 200 samples - at ../dataset/gen-word-1250-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3750 max words - at ../dataset/shuffle-word-3750-count.jsonl\n"
+      "Generated JSONL file with - 880 max words, 200 samples - at ../dataset/gen-word-880-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2020 max words, 200 samples - at ../dataset/gen-word-2020-count.jsonl\n"
+      "Generated JSONL file with - 2165 max words, 200 samples - at ../dataset/gen-word-2165-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2130 max words, 200 samples - at ../dataset/gen-word-2130-count.jsonl\n"
+      "Generated JSONL file with - 1955 max words, 200 samples - at ../dataset/gen-word-1955-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1885 max words - at ../dataset/shuffle-word-1885-count.jsonl\n"
+      "Generated JSONL file with - 2675 max words, 200 samples - at ../dataset/gen-word-2675-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1920 max words, 200 samples - at ../dataset/gen-word-1920-count.jsonl\n"
+      "Generated JSONL file with - 1930 max words, 200 samples - at ../dataset/gen-word-1930-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3510 max words - at ../dataset/shuffle-word-3510-count.jsonl\n"
+      "Generated JSONL file with - 960 max words, 200 samples - at ../dataset/gen-word-960-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2440 max words, 200 samples - at ../dataset/gen-word-2440-count.jsonl\n"
+      "Generated JSONL file with - 1610 max words, 200 samples - at ../dataset/gen-word-1610-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3015 max words, 200 samples - at ../dataset/gen-word-3015-count.jsonl\n"
+      "Generated JSONL file with - 3280 max words, 200 samples - at ../dataset/gen-word-3280-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3505 max words - at ../dataset/shuffle-word-3505-count.jsonl\n"
+      "Generated JSONL file with - 2115 max words, 200 samples - at ../dataset/gen-word-2115-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1870 max words, 200 samples - at ../dataset/gen-word-1870-count.jsonl\n"
+      "Generated JSONL file with - 2275 max words, 200 samples - at ../dataset/gen-word-2275-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3180 max words, 200 samples - at ../dataset/gen-word-3180-count.jsonl\n"
+      "Generated JSONL file with - 2950 max words, 200 samples - at ../dataset/gen-word-2950-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2350 max words, 200 samples - at ../dataset/gen-word-2350-count.jsonl\n"
+      "Generated JSONL file with - 2670 max words, 200 samples - at ../dataset/gen-word-2670-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2005 max words - at ../dataset/shuffle-word-2005-count.jsonl\n"
+      "Generated JSONL file with - 2405 max words, 200 samples - at ../dataset/gen-word-2405-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3290 max words - at ../dataset/shuffle-word-3290-count.jsonl\n"
+      "Generated JSONL file with - 1990 max words, 200 samples - at ../dataset/gen-word-1990-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1875 max words, 200 samples - at ../dataset/gen-word-1875-count.jsonl\n"
+      "Generated JSONL file with - 3000 max words, 200 samples - at ../dataset/gen-word-3000-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3260 max words - at ../dataset/shuffle-word-3260-count.jsonl\n"
+      "Generated JSONL file with - 3415 max words, 200 samples - at ../dataset/gen-word-3415-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2215 max words, 200 samples - at ../dataset/gen-word-2215-count.jsonl\n"
+      "Generated JSONL file with - 2030 max words, 200 samples - at ../dataset/gen-word-2030-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3695 max words - at ../dataset/shuffle-word-3695-count.jsonl\n"
+      "Generated JSONL file with - 995 max words, 200 samples - at ../dataset/gen-word-995-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2665 max words, 200 samples - at ../dataset/gen-word-2665-count.jsonl\n"
+      "Generated JSONL file with - 1645 max words, 200 samples - at ../dataset/gen-word-1645-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3630 max words - at ../dataset/shuffle-word-3630-count.jsonl\n"
+      "Generated JSONL file with - 2225 max words, 200 samples - at ../dataset/gen-word-2225-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3235 max words - at ../dataset/shuffle-word-3235-count.jsonl\n"
+      "Generated JSONL file with - 2615 max words, 200 samples - at ../dataset/gen-word-2615-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 585 max words, 200 samples - at ../dataset/gen-word-585-count.jsonl\n"
+      "Generated JSONL file with - 2050 max words, 200 samples - at ../dataset/gen-word-2050-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1305 max words, 200 samples - at ../dataset/gen-word-1305-count.jsonl\n"
+      "Generated JSONL file with - 2500 max words, 200 samples - at ../dataset/gen-word-2500-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2575 max words, 200 samples - at ../dataset/gen-word-2575-count.jsonl\n"
+      "Generated JSONL file with - 2175 max words, 200 samples - at ../dataset/gen-word-2175-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3230 max words, 200 samples - at ../dataset/gen-word-3230-count.jsonl\n"
+      "Generated JSONL file with - 2185 max words, 200 samples - at ../dataset/gen-word-2185-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 800 max words, 200 samples - at ../dataset/gen-word-800-count.jsonl\n"
+      "Generated JSONL file with - 3995 max words, 200 samples - at ../dataset/gen-word-3995-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3090 max words, 200 samples - at ../dataset/gen-word-3090-count.jsonl\n"
+      "Generated JSONL file with - 2435 max words, 200 samples - at ../dataset/gen-word-2435-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2110 max words - at ../dataset/shuffle-word-2110-count.jsonl\n"
+      "Generated JSONL file with - 3430 max words, 200 samples - at ../dataset/gen-word-3430-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3745 max words, 200 samples - at ../dataset/gen-word-3745-count.jsonl\n"
+      "Generated JSONL file with - 2535 max words, 200 samples - at ../dataset/gen-word-2535-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3120 max words, 200 samples - at ../dataset/gen-word-3120-count.jsonl\n"
+      "Generated JSONL file with - 2640 max words, 200 samples - at ../dataset/gen-word-2640-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1720 max words, 200 samples - at ../dataset/gen-word-1720-count.jsonl\n"
+      "Generated JSONL file with - 3060 max words, 200 samples - at ../dataset/gen-word-3060-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3305 max words, 200 samples - at ../dataset/gen-word-3305-count.jsonl\n"
+      "Generated JSONL file with - 2710 max words, 200 samples - at ../dataset/gen-word-2710-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1510 max words, 200 samples - at ../dataset/gen-word-1510-count.jsonl\n"
+      "Generated JSONL file with - 3465 max words, 200 samples - at ../dataset/gen-word-3465-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3785 max words - at ../dataset/shuffle-word-3785-count.jsonl\n"
+      "Generated JSONL file with - 1655 max words, 200 samples - at ../dataset/gen-word-1655-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3285 max words, 200 samples - at ../dataset/gen-word-3285-count.jsonl\n"
+      "Generated JSONL file with - 2990 max words, 200 samples - at ../dataset/gen-word-2990-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2105 max words, 200 samples - at ../dataset/gen-word-2105-count.jsonl\n"
+      "Generated JSONL file with - 3985 max words, 200 samples - at ../dataset/gen-word-3985-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1905 max words - at ../dataset/shuffle-word-1905-count.jsonl\n"
+      "Generated JSONL file with - 2125 max words, 200 samples - at ../dataset/gen-word-2125-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2935 max words, 200 samples - at ../dataset/gen-word-2935-count.jsonl\n"
+      "Generated JSONL file with - 3185 max words, 200 samples - at ../dataset/gen-word-3185-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1435 max words - at ../dataset/shuffle-word-1435-count.jsonl\n"
+      "Generated JSONL file with - 2080 max words, 200 samples - at ../dataset/gen-word-2080-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2070 max words, 200 samples - at ../dataset/gen-word-2070-count.jsonl\n"
+      "Generated JSONL file with - 2745 max words, 200 samples - at ../dataset/gen-word-2745-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2360 max words, 200 samples - at ../dataset/gen-word-2360-count.jsonl\n"
+      "Generated JSONL file with - 2150 max words, 200 samples - at ../dataset/gen-word-2150-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2180 max words, 200 samples - at ../dataset/gen-word-2180-count.jsonl\n"
+      "Generated JSONL file with - 2095 max words, 200 samples - at ../dataset/gen-word-2095-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2140 max words - at ../dataset/shuffle-word-2140-count.jsonl\n"
+      "Generated JSONL file with - 2580 max words, 200 samples - at ../dataset/gen-word-2580-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3790 max words, 200 samples - at ../dataset/gen-word-3790-count.jsonl\n"
+      "Generated JSONL file with - 2630 max words, 200 samples - at ../dataset/gen-word-2630-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 6 samples (1 token repeat) - 495 max words - at ../dataset/shuffle-word-495-count.jsonl\n"
+      "Generated JSONL file with - 2445 max words, 200 samples - at ../dataset/gen-word-2445-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2230 max words - at ../dataset/shuffle-word-2230-count.jsonl\n"
+      "Generated JSONL file with - 2740 max words, 200 samples - at ../dataset/gen-word-2740-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3245 max words - at ../dataset/shuffle-word-3245-count.jsonl\n"
+      "Generated JSONL file with - 2295 max words, 200 samples - at ../dataset/gen-word-2295-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3865 max words - at ../dataset/shuffle-word-3865-count.jsonl\n"
+      "Generated JSONL file with - 2400 max words, 200 samples - at ../dataset/gen-word-2400-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1490 max words, 200 samples - at ../dataset/gen-word-1490-count.jsonl\n"
+      "Generated JSONL file with - 2135 max words, 200 samples - at ../dataset/gen-word-2135-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1345 max words, 200 samples - at ../dataset/gen-word-1345-count.jsonl\n"
+      "Generated JSONL file with - 1845 max words, 200 samples - at ../dataset/gen-word-1845-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2085 max words, 200 samples - at ../dataset/gen-word-2085-count.jsonl\n"
+      "Generated JSONL file with - 2280 max words, 200 samples - at ../dataset/gen-word-2280-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1970 max words, 200 samples - at ../dataset/gen-word-1970-count.jsonl\n"
+      "Generated JSONL file with - 3035 max words, 200 samples - at ../dataset/gen-word-3035-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1510 max words - at ../dataset/shuffle-word-1510-count.jsonl\n"
+      "Generated JSONL file with - 2180 max words, 200 samples - at ../dataset/gen-word-2180-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2045 max words - at ../dataset/shuffle-word-2045-count.jsonl\n"
+      "Generated JSONL file with - 2470 max words, 200 samples - at ../dataset/gen-word-2470-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1315 max words, 200 samples - at ../dataset/gen-word-1315-count.jsonl\n"
+      "Generated JSONL file with - 3760 max words, 200 samples - at ../dataset/gen-word-3760-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2950 max words, 200 samples - at ../dataset/gen-word-2950-count.jsonl\n"
+      "Generated JSONL file with - 3445 max words, 200 samples - at ../dataset/gen-word-3445-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3875 max words - at ../dataset/shuffle-word-3875-count.jsonl\n"
+      "Generated JSONL file with - 3810 max words, 200 samples - at ../dataset/gen-word-3810-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 860 max words, 200 samples - at ../dataset/gen-word-860-count.jsonl\n"
+      "Generated JSONL file with - 2700 max words, 200 samples - at ../dataset/gen-word-2700-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1640 max words - at ../dataset/shuffle-word-1640-count.jsonl\n"
+      "Generated JSONL file with - 3965 max words, 200 samples - at ../dataset/gen-word-3965-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 36 samples (20 token repeat) - 2425 max words - at ../dataset/shuffle-word-2425-count.jsonl\n"
+      "Generated JSONL file with - 2350 max words, 200 samples - at ../dataset/gen-word-2350-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2345 max words, 200 samples - at ../dataset/gen-word-2345-count.jsonl\n"
+      "Generated JSONL file with - 2560 max words, 200 samples - at ../dataset/gen-word-2560-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2900 max words, 200 samples - at ../dataset/gen-word-2900-count.jsonl\n"
+      "Generated JSONL file with - 2650 max words, 200 samples - at ../dataset/gen-word-2650-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3805 max words - at ../dataset/shuffle-word-3805-count.jsonl\n"
+      "Generated JSONL file with - 3040 max words, 200 samples - at ../dataset/gen-word-3040-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2385 max words, 200 samples - at ../dataset/gen-word-2385-count.jsonl\n"
+      "Generated JSONL file with - 3230 max words, 200 samples - at ../dataset/gen-word-3230-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3730 max words - at ../dataset/shuffle-word-3730-count.jsonl\n"
+      "Generated JSONL file with - 2195 max words, 200 samples - at ../dataset/gen-word-2195-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 570 max words, 200 samples - at ../dataset/gen-word-570-count.jsonl\n"
+      "Generated JSONL file with - 1220 max words, 200 samples - at ../dataset/gen-word-1220-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 34 samples (20 token repeat) - 2470 max words - at ../dataset/shuffle-word-2470-count.jsonl\n"
+      "Generated JSONL file with - 2945 max words, 200 samples - at ../dataset/gen-word-2945-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2640 max words, 200 samples - at ../dataset/gen-word-2640-count.jsonl\n"
+      "Generated JSONL file with - 2355 max words, 200 samples - at ../dataset/gen-word-2355-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 JSONL file with - 3260 max words, 200 samples - at ../dataset/gen-word-3260-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2230 max words, 200 samples - at ../dataset/gen-word-2230-count.jsonl\n"
+      "Generated JSONL file with - 3285 max words, 200 samples - at ../dataset/gen-word-3285-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2580 max words, 200 samples - at ../dataset/gen-word-2580-count.jsonl\n"
+      "Generated JSONL file with - 2000 max words, 200 samples - at ../dataset/gen-word-2000-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3815 max words - at ../dataset/shuffle-word-3815-count.jsonl\n"
+      "Generated JSONL file with - 2040 max words, 200 samples - at ../dataset/gen-word-2040-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 41 samples (20 token repeat) - 1380 max words - at ../dataset/shuffle-word-1380-count.jsonl\n"
+      "Generated JSONL file with - 1455 max words, 200 samples - at ../dataset/gen-word-1455-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1100 max words, 200 samples - at ../dataset/gen-word-1100-count.jsonl\n"
+      "Generated JSONL file with - 2820 max words, 200 samples - at ../dataset/gen-word-2820-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 130 max words, 100 samples - at ../dataset/gen-word-130-count.jsonl\n"
+      "Generated JSONL file with - 3090 max words, 200 samples - at ../dataset/gen-word-3090-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3820 max words - at ../dataset/shuffle-word-3820-count.jsonl\n"
+      "Generated JSONL file with - 1925 max words, 200 samples - at ../dataset/gen-word-1925-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 54 samples (20 token repeat) - 1260 max words - at ../dataset/shuffle-word-1260-count.jsonl\n"
+      "Generated JSONL file with - 3255 max words, 200 samples - at ../dataset/gen-word-3255-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1955 max words - at ../dataset/shuffle-word-1955-count.jsonl\n"
+      "Generated JSONL file with - 3115 max words, 200 samples - at ../dataset/gen-word-3115-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1920 max words - at ../dataset/shuffle-word-1920-count.jsonl\n"
+      "Generated JSONL file with - 3375 max words, 200 samples - at ../dataset/gen-word-3375-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3905 max words - at ../dataset/shuffle-word-3905-count.jsonl\n"
+      "Generated JSONL file with - 3845 max words, 200 samples - at ../dataset/gen-word-3845-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2965 max words, 200 samples - at ../dataset/gen-word-2965-count.jsonl\n"
+      "Generated JSONL file with - 3145 max words, 200 samples - at ../dataset/gen-word-3145-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2385 max words - at ../dataset/shuffle-word-2385-count.jsonl\n"
+      "Generated JSONL file with - 2835 max words, 200 samples - at ../dataset/gen-word-2835-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2445 max words, 200 samples - at ../dataset/gen-word-2445-count.jsonl\n"
+      "Generated JSONL file with - 2770 max words, 200 samples - at ../dataset/gen-word-2770-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3485 max words, 200 samples - at ../dataset/gen-word-3485-count.jsonl\n"
+      "Generated JSONL file with - 2255 max words, 200 samples - at ../dataset/gen-word-2255-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1110 max words, 200 samples - at ../dataset/gen-word-1110-count.jsonl\n"
+      "Generated JSONL file with - 2750 max words, 200 samples - at ../dataset/gen-word-2750-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2295 max words, 200 samples - at ../dataset/gen-word-2295-count.jsonl\n"
+      "Generated JSONL file with - 3710 max words, 200 samples - at ../dataset/gen-word-3710-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2450 max words, 200 samples - at ../dataset/gen-word-2450-count.jsonl\n"
+      "Generated JSONL file with - 2210 max words, 200 samples - at ../dataset/gen-word-2210-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 9 samples (1 token repeat) - 275 max words - at ../dataset/shuffle-word-275-count.jsonl\n"
+      "Generated JSONL file with - 3770 max words, 200 samples - at ../dataset/gen-word-3770-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2275 max words, 200 samples - at ../dataset/gen-word-2275-count.jsonl\n"
+      "Generated JSONL file with - 2460 max words, 200 samples - at ../dataset/gen-word-2460-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 39 samples (20 token repeat) - 2480 max words - at ../dataset/shuffle-word-2480-count.jsonl\n"
+      "Generated JSONL file with - 3245 max words, 200 samples - at ../dataset/gen-word-3245-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1150 max words, 200 samples - at ../dataset/gen-word-1150-count.jsonl\n"
+      "Generated JSONL file with - 2860 max words, 200 samples - at ../dataset/gen-word-2860-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 955 max words, 200 samples - at ../dataset/gen-word-955-count.jsonl\n"
+      "Generated JSONL file with - 3990 max words, 200 samples - at ../dataset/gen-word-3990-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1785 max words, 200 samples - at ../dataset/gen-word-1785-count.jsonl\n"
+      "Generated JSONL file with - 2410 max words, 200 samples - at ../dataset/gen-word-2410-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2240 max words, 200 samples - at ../dataset/gen-word-2240-count.jsonl\n"
+      "Generated JSONL file with - 2875 max words, 200 samples - at ../dataset/gen-word-2875-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1470 max words, 200 samples - at ../dataset/gen-word-1470-count.jsonl\n"
+      "Generated JSONL file with - 3515 max words, 200 samples - at ../dataset/gen-word-3515-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 35 samples (20 token repeat) - 2415 max words - at ../dataset/shuffle-word-2415-count.jsonl\n"
+      "Generated JSONL file with - 2620 max words, 200 samples - at ../dataset/gen-word-2620-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 37 samples (20 token repeat) - 2485 max words - at ../dataset/shuffle-word-2485-count.jsonl\n"
+      "Generated JSONL file with - 2160 max words, 200 samples - at ../dataset/gen-word-2160-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2310 max words - at ../dataset/shuffle-word-2310-count.jsonl\n"
+      "Generated JSONL file with - 2450 max words, 200 samples - at ../dataset/gen-word-2450-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1990 max words, 200 samples - at ../dataset/gen-word-1990-count.jsonl\n"
+      "Generated JSONL file with - 3385 max words, 200 samples - at ../dataset/gen-word-3385-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1615 max words - at ../dataset/shuffle-word-1615-count.jsonl\n"
+      "Generated JSONL file with - 2330 max words, 200 samples - at ../dataset/gen-word-2330-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3650 max words - at ../dataset/shuffle-word-3650-count.jsonl\n"
+      "Generated JSONL file with - 2490 max words, 200 samples - at ../dataset/gen-word-2490-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2930 max words, 200 samples - at ../dataset/gen-word-2930-count.jsonl\n"
+      "Generated JSONL file with - 2585 max words, 200 samples - at ../dataset/gen-word-2585-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 38 samples (20 token repeat) - 2440 max words - at ../dataset/shuffle-word-2440-count.jsonl\n"
+      "Generated JSONL file with - 2420 max words, 200 samples - at ../dataset/gen-word-2420-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2825 max words, 200 samples - at ../dataset/gen-word-2825-count.jsonl\n"
+      "Generated JSONL file with - 1740 max words, 200 samples - at ../dataset/gen-word-1740-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2730 max words, 200 samples - at ../dataset/gen-word-2730-count.jsonl\n"
+      "Generated JSONL file with - 2985 max words, 200 samples - at ../dataset/gen-word-2985-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2370 max words, 200 samples - at ../dataset/gen-word-2370-count.jsonl\n"
+      "Generated JSONL file with - 1570 max words, 200 samples - at ../dataset/gen-word-1570-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 48 samples (20 token repeat) - 1280 max words - at ../dataset/shuffle-word-1280-count.jsonl\n"
+      "Generated JSONL file with - 3030 max words, 200 samples - at ../dataset/gen-word-3030-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 32 samples (20 token repeat) - 2555 max words - at ../dataset/shuffle-word-2555-count.jsonl\n"
+      "Generated JSONL file with - 1760 max words, 200 samples - at ../dataset/gen-word-1760-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2750 max words, 200 samples - at ../dataset/gen-word-2750-count.jsonl\n"
+      "Generated JSONL file with - 2260 max words, 200 samples - at ../dataset/gen-word-2260-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1075 max words, 200 samples - at ../dataset/gen-word-1075-count.jsonl\n"
+      "Generated JSONL file with - 2550 max words, 200 samples - at ../dataset/gen-word-2550-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1850 max words, 200 samples - at ../dataset/gen-word-1850-count.jsonl\n"
+      "Generated JSONL file with - 2250 max words, 200 samples - at ../dataset/gen-word-2250-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 39 samples (20 token repeat) - 2500 max words - at ../dataset/shuffle-word-2500-count.jsonl\n"
+      "Generated JSONL file with - 2510 max words, 200 samples - at ../dataset/gen-word-2510-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2165 max words - at ../dataset/shuffle-word-2165-count.jsonl\n"
+      "Generated JSONL file with - 3125 max words, 200 samples - at ../dataset/gen-word-3125-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1785 max words - at ../dataset/shuffle-word-1785-count.jsonl\n"
+      "Generated JSONL file with - 3615 max words, 200 samples - at ../dataset/gen-word-3615-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3755 max words, 200 samples - at ../dataset/gen-word-3755-count.jsonl\n"
+      "Generated JSONL file with - 3010 max words, 200 samples - at ../dataset/gen-word-3010-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 37 samples (20 token repeat) - 2455 max words - at ../dataset/shuffle-word-2455-count.jsonl\n"
+      "Generated JSONL file with - 3955 max words, 200 samples - at ../dataset/gen-word-3955-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2590 max words, 200 samples - at ../dataset/gen-word-2590-count.jsonl\n"
+      "Generated JSONL file with - 3630 max words, 200 samples - at ../dataset/gen-word-3630-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3475 max words, 200 samples - at ../dataset/gen-word-3475-count.jsonl\n"
+      "Generated JSONL file with - 3270 max words, 200 samples - at ../dataset/gen-word-3270-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1915 max words, 200 samples - at ../dataset/gen-word-1915-count.jsonl\n"
+      "Generated JSONL file with - 2785 max words, 200 samples - at ../dataset/gen-word-2785-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 JSONL file with - 2475 max words, 200 samples - at ../dataset/gen-word-2475-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3945 max words - at ../dataset/shuffle-word-3945-count.jsonl\n"
+      "Generated JSONL file with - 3840 max words, 200 samples - at ../dataset/gen-word-3840-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 80 samples (20 token repeat) - 625 max words - at ../dataset/shuffle-word-625-count.jsonl\n"
+      "Generated JSONL file with - 2705 max words, 200 samples - at ../dataset/gen-word-2705-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 365 max words, 100 samples - at ../dataset/gen-word-365-count.jsonl\n"
+      "Generated JSONL file with - 2780 max words, 200 samples - at ../dataset/gen-word-2780-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 375 max words, 100 samples - at ../dataset/gen-word-375-count.jsonl\n"
+      "Generated JSONL file with - 2395 max words, 200 samples - at ../dataset/gen-word-2395-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2320 max words, 200 samples - at ../dataset/gen-word-2320-count.jsonl\n"
+      "Generated JSONL file with - 2530 max words, 200 samples - at ../dataset/gen-word-2530-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2785 max words, 200 samples - at ../dataset/gen-word-2785-count.jsonl\n"
+      "Generated JSONL file with - 3805 max words, 200 samples - at ../dataset/gen-word-3805-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 360 max words, 100 samples - at ../dataset/gen-word-360-count.jsonl\n"
+      "Generated JSONL file with - 3205 max words, 200 samples - at ../dataset/gen-word-3205-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 - 2895 max words, 200 samples - at ../dataset/gen-word-2895-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 60 samples (20 token repeat) - 1040 max words - at ../dataset/shuffle-word-1040-count.jsonl\n"
+      "Generated JSONL file with - 2735 max words, 200 samples - at ../dataset/gen-word-2735-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 36 samples (20 token repeat) - 2460 max words - at ../dataset/shuffle-word-2460-count.jsonl\n"
+      "Generated JSONL file with - 3190 max words, 200 samples - at ../dataset/gen-word-3190-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2710 max words, 200 samples - at ../dataset/gen-word-2710-count.jsonl\n"
+      "Generated JSONL file with - 3405 max words, 200 samples - at ../dataset/gen-word-3405-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3890 max words, 200 samples - at ../dataset/gen-word-3890-count.jsonl\n"
+      "Generated JSONL file with - 2290 max words, 200 samples - at ../dataset/gen-word-2290-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1985 max words - at ../dataset/shuffle-word-1985-count.jsonl\n"
+      "Generated JSONL file with - 2805 max words, 200 samples - at ../dataset/gen-word-2805-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 2365 max words - at ../dataset/shuffle-word-2365-count.jsonl\n"
+      "Generated JSONL file with - 3675 max words, 200 samples - at ../dataset/gen-word-3675-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2940 max words, 200 samples - at ../dataset/gen-word-2940-count.jsonl\n"
+      "Generated JSONL file with - 3470 max words, 200 samples - at ../dataset/gen-word-3470-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3695 max words, 200 samples - at ../dataset/gen-word-3695-count.jsonl\n"
+      "Generated JSONL file with - 2365 max words, 200 samples - at ../dataset/gen-word-2365-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2625 max words, 200 samples - at ../dataset/gen-word-2625-count.jsonl\n"
+      "Generated JSONL file with - 2055 max words, 200 samples - at ../dataset/gen-word-2055-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3635 max words - at ../dataset/shuffle-word-3635-count.jsonl\n"
+      "Generated JSONL file with - 2265 max words, 200 samples - at ../dataset/gen-word-2265-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3535 max words - at ../dataset/shuffle-word-3535-count.jsonl\n"
+      "Generated JSONL file with - 3490 max words, 200 samples - at ../dataset/gen-word-3490-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1270 max words, 200 samples - at ../dataset/gen-word-1270-count.jsonl\n"
+      "Generated JSONL file with - 3790 max words, 200 samples - at ../dataset/gen-word-3790-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1530 max words, 200 samples - at ../dataset/gen-word-1530-count.jsonl\n"
+      "Generated JSONL file with - 3240 max words, 200 samples - at ../dataset/gen-word-3240-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 425 max words, 100 samples - at ../dataset/gen-word-425-count.jsonl\n"
+      "Generated JSONL file with - 2300 max words, 200 samples - at ../dataset/gen-word-2300-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1645 max words - at ../dataset/shuffle-word-1645-count.jsonl\n"
+      "Generated JSONL file with - 3610 max words, 200 samples - at ../dataset/gen-word-3610-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1220 max words, 200 samples - at ../dataset/gen-word-1220-count.jsonl\n"
+      "Generated JSONL file with - 1555 max words, 200 samples - at ../dataset/gen-word-1555-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1350 max words, 200 samples - at ../dataset/gen-word-1350-count.jsonl\n"
+      "Generated JSONL file with - 2545 max words, 200 samples - at ../dataset/gen-word-2545-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3640 max words - at ../dataset/shuffle-word-3640-count.jsonl\n"
+      "Generated JSONL file with - 3365 max words, 200 samples - at ../dataset/gen-word-3365-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2335 max words, 200 samples - at ../dataset/gen-word-2335-count.jsonl\n"
+      "Generated JSONL file with - 2390 max words, 200 samples - at ../dataset/gen-word-2390-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3050 max words, 200 samples - at ../dataset/gen-word-3050-count.jsonl\n"
+      "Generated JSONL file with - 3390 max words, 200 samples - at ../dataset/gen-word-3390-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 500 max words, 100 samples - at ../dataset/gen-word-500-count.jsonl\n"
+      "Generated JSONL file with - 3305 max words, 200 samples - at ../dataset/gen-word-3305-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3545 max words - at ../dataset/shuffle-word-3545-count.jsonl\n"
+      "Generated JSONL file with - 2910 max words, 200 samples - at ../dataset/gen-word-2910-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2560 max words, 200 samples - at ../dataset/gen-word-2560-count.jsonl\n"
+      "Generated JSONL file with - 3945 max words, 200 samples - at ../dataset/gen-word-3945-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3110 max words, 200 samples - at ../dataset/gen-word-3110-count.jsonl\n"
+      "Generated JSONL file with - 3950 max words, 200 samples - at ../dataset/gen-word-3950-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1605 max words, 200 samples - at ../dataset/gen-word-1605-count.jsonl\n"
+      "Generated JSONL file with - 2730 max words, 200 samples - at ../dataset/gen-word-2730-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2110 max words, 200 samples - at ../dataset/gen-word-2110-count.jsonl\n"
+      "Generated JSONL file with - 2315 max words, 200 samples - at ../dataset/gen-word-2315-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3295 max words - at ../dataset/shuffle-word-3295-count.jsonl\n"
+      "Generated JSONL file with - 2035 max words, 200 samples - at ../dataset/gen-word-2035-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1460 max words, 200 samples - at ../dataset/gen-word-1460-count.jsonl\n"
+      "Generated JSONL file with - 3070 max words, 200 samples - at ../dataset/gen-word-3070-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 20 samples (20 token repeat) - 3705 max words - at ../dataset/shuffle-word-3705-count.jsonl\n"
+      "Generated JSONL file with - 2465 max words, 200 samples - at ../dataset/gen-word-2465-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2875 max words, 200 samples - at ../dataset/gen-word-2875-count.jsonl\n"
+      "Generated JSONL file with - 3400 max words, 200 samples - at ../dataset/gen-word-3400-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated a single JSONL file with 40 samples (20 token repeat) - 1480 max words - at ../dataset/shuffle-word-1480-count.jsonl\n"
+      "Generated JSONL file with - 3885 max words, 200 samples - at ../dataset/gen-word-3885-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1135 max words, 200 samples - at ../dataset/gen-word-1135-count.jsonl\n"
+      "Generated JSONL file with - 3500 max words, 200 samples - at ../dataset/gen-word-3500-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1085 max words, 200 samples - at ../dataset/gen-word-1085-count.jsonl\n"
+      "Generated JSONL file with - 2885 max words, 200 samples - at ../dataset/gen-word-2885-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2835 max words, 200 samples - at ../dataset/gen-word-2835-count.jsonl\n"
+      "Generated JSONL file with - 3650 max words, 200 samples - at ../dataset/gen-word-3650-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2655 max words, 200 samples - at ../dataset/gen-word-2655-count.jsonl\n"
+      "Generated JSONL file with - 3935 max words, 200 samples - at ../dataset/gen-word-3935-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1845 max words, 200 samples - at ../dataset/gen-word-1845-count.jsonl\n"
+      "Generated JSONL file with - 3665 max words, 200 samples - at ../dataset/gen-word-3665-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2150 max words, 200 samples - at ../dataset/gen-word-2150-count.jsonl\n"
+      "Generated JSONL file with - 2170 max words, 200 samples - at ../dataset/gen-word-2170-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2205 max words, 200 samples - at ../dataset/gen-word-2205-count.jsonl\n"
+      "Generated JSONL file with - 3550 max words, 200 samples - at ../dataset/gen-word-3550-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2960 max words, 200 samples - at ../dataset/gen-word-2960-count.jsonl\n"
+      "Generated JSONL file with - 2975 max words, 200 samples - at ../dataset/gen-word-2975-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2525 max words, 200 samples - at ../dataset/gen-word-2525-count.jsonl\n"
+      "Generated JSONL file with - 2590 max words, 200 samples - at ../dataset/gen-word-2590-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2520 max words, 200 samples - at ../dataset/gen-word-2520-count.jsonl\n"
+      "Generated JSONL file with - 2020 max words, 200 samples - at ../dataset/gen-word-2020-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2745 max words, 200 samples - at ../dataset/gen-word-2745-count.jsonl\n"
+      "Generated JSONL file with - 2960 max words, 200 samples - at ../dataset/gen-word-2960-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2050 max words, 200 samples - at ../dataset/gen-word-2050-count.jsonl\n"
+      "Generated JSONL file with - 2855 max words, 200 samples - at ../dataset/gen-word-2855-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1340 max words, 200 samples - at ../dataset/gen-word-1340-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 2555 max words, 200 samples - at ../dataset/gen-word-2555-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 2485 max words, 200 samples - at ../dataset/gen-word-2485-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 2160 max words, 200 samples - at ../dataset/gen-word-2160-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 1615 max words, 200 samples - at ../dataset/gen-word-1615-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 1775 max words, 200 samples - at ../dataset/gen-word-1775-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 2225 max words, 200 samples - at ../dataset/gen-word-2225-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 1595 max words, 200 samples - at ../dataset/gen-word-1595-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 1125 max words, 200 samples - at ../dataset/gen-word-1125-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 2045 max words, 200 samples - at ../dataset/gen-word-2045-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 1485 max words, 200 samples - at ../dataset/gen-word-1485-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 1725 max words, 200 samples - at ../dataset/gen-word-1725-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 3825 max words, 200 samples - at ../dataset/gen-word-3825-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 3380 max words, 200 samples - at ../dataset/gen-word-3380-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 1820 max words, 200 samples - at ../dataset/gen-word-1820-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 1645 max words, 200 samples - at ../dataset/gen-word-1645-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 2100 max words, 200 samples - at ../dataset/gen-word-2100-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 2300 max words, 200 samples - at ../dataset/gen-word-2300-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 3340 max words, 200 samples - at ../dataset/gen-word-3340-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 2490 max words, 200 samples - at ../dataset/gen-word-2490-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 2145 max words, 200 samples - at ../dataset/gen-word-2145-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 1710 max words, 200 samples - at ../dataset/gen-word-1710-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 1680 max words, 200 samples - at ../dataset/gen-word-1680-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 3730 max words, 200 samples - at ../dataset/gen-word-3730-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 1780 max words, 200 samples - at ../dataset/gen-word-1780-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 2355 max words, 200 samples - at ../dataset/gen-word-2355-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 3665 max words, 200 samples - at ../dataset/gen-word-3665-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 3645 max words, 200 samples - at ../dataset/gen-word-3645-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 2015 max words, 200 samples - at ../dataset/gen-word-2015-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 2675 max words, 200 samples - at ../dataset/gen-word-2675-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 3780 max words, 200 samples - at ../dataset/gen-word-3780-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 2390 max words, 200 samples - at ../dataset/gen-word-2390-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 2465 max words, 200 samples - at ../dataset/gen-word-2465-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 2570 max words, 200 samples - at ../dataset/gen-word-2570-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 1980 max words, 200 samples - at ../dataset/gen-word-1980-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 1825 max words, 200 samples - at ../dataset/gen-word-1825-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 2375 max words, 200 samples - at ../dataset/gen-word-2375-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 2605 max words, 200 samples - at ../dataset/gen-word-2605-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 3610 max words, 200 samples - at ../dataset/gen-word-3610-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 3460 max words, 200 samples - at ../dataset/gen-word-3460-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 1675 max words, 200 samples - at ../dataset/gen-word-1675-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 3840 max words, 200 samples - at ../dataset/gen-word-3840-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 1715 max words, 200 samples - at ../dataset/gen-word-1715-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 2945 max words, 200 samples - at ../dataset/gen-word-2945-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 2285 max words, 200 samples - at ../dataset/gen-word-2285-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 1380 max words, 200 samples - at ../dataset/gen-word-1380-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 3900 max words, 200 samples - at ../dataset/gen-word-3900-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 3145 max words, 200 samples - at ../dataset/gen-word-3145-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 3215 max words, 200 samples - at ../dataset/gen-word-3215-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 3465 max words, 200 samples - at ../dataset/gen-word-3465-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 2075 max words, 200 samples - at ../dataset/gen-word-2075-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 3980 max words, 200 samples - at ../dataset/gen-word-3980-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 1810 max words, 200 samples - at ../dataset/gen-word-1810-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 3545 max words, 200 samples - at ../dataset/gen-word-3545-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 3035 max words, 200 samples - at ../dataset/gen-word-3035-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 1360 max words, 200 samples - at ../dataset/gen-word-1360-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 3440 max words, 200 samples - at ../dataset/gen-word-3440-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 2235 max words, 200 samples - at ../dataset/gen-word-2235-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 2970 max words, 200 samples - at ../dataset/gen-word-2970-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 2790 max words, 200 samples - at ../dataset/gen-word-2790-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 1545 max words, 200 samples - at ../dataset/gen-word-1545-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 2025 max words, 200 samples - at ../dataset/gen-word-2025-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 3080 max words, 200 samples - at ../dataset/gen-word-3080-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 2715 max words, 200 samples - at ../dataset/gen-word-2715-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 3190 max words, 200 samples - at ../dataset/gen-word-3190-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 1540 max words, 200 samples - at ../dataset/gen-word-1540-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 3750 max words, 200 samples - at ../dataset/gen-word-3750-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 3205 max words, 200 samples - at ../dataset/gen-word-3205-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 3250 max words, 200 samples - at ../dataset/gen-word-3250-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 2380 max words, 200 samples - at ../dataset/gen-word-2380-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 3000 max words, 200 samples - at ../dataset/gen-word-3000-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 2615 max words, 200 samples - at ../dataset/gen-word-2615-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 1585 max words, 200 samples - at ../dataset/gen-word-1585-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 3070 max words, 200 samples - at ../dataset/gen-word-3070-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 3225 max words, 200 samples - at ../dataset/gen-word-3225-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 3185 max words, 200 samples - at ../dataset/gen-word-3185-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 2755 max words, 200 samples - at ../dataset/gen-word-2755-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 3280 max words, 200 samples - at ../dataset/gen-word-3280-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 3095 max words, 200 samples - at ../dataset/gen-word-3095-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 2995 max words, 200 samples - at ../dataset/gen-word-2995-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 3625 max words, 200 samples - at ../dataset/gen-word-3625-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 3660 max words, 200 samples - at ../dataset/gen-word-3660-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 3325 max words, 200 samples - at ../dataset/gen-word-3325-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 3540 max words, 200 samples - at ../dataset/gen-word-3540-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 1030 max words, 200 samples - at ../dataset/gen-word-1030-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 3535 max words, 200 samples - at ../dataset/gen-word-3535-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 2720 max words, 200 samples - at ../dataset/gen-word-2720-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 2405 max words, 200 samples - at ../dataset/gen-word-2405-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 3815 max words, 200 samples - at ../dataset/gen-word-3815-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 2815 max words, 200 samples - at ../dataset/gen-word-2815-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 2845 max words, 200 samples - at ../dataset/gen-word-2845-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 3350 max words, 200 samples - at ../dataset/gen-word-3350-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 3820 max words, 200 samples - at ../dataset/gen-word-3820-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 1395 max words, 200 samples - at ../dataset/gen-word-1395-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 2700 max words, 200 samples - at ../dataset/gen-word-2700-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 2245 max words, 200 samples - at ../dataset/gen-word-2245-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 3420 max words, 200 samples - at ../dataset/gen-word-3420-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 2200 max words, 200 samples - at ../dataset/gen-word-2200-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 1575 max words, 200 samples - at ../dataset/gen-word-1575-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 2870 max words, 200 samples - at ../dataset/gen-word-2870-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 1925 max words, 200 samples - at ../dataset/gen-word-1925-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 3275 max words, 200 samples - at ../dataset/gen-word-3275-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 3255 max words, 200 samples - at ../dataset/gen-word-3255-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 2735 max words, 200 samples - at ../dataset/gen-word-2735-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 3555 max words, 200 samples - at ../dataset/gen-word-3555-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 1665 max words, 200 samples - at ../dataset/gen-word-1665-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 1765 max words, 200 samples - at ../dataset/gen-word-1765-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 1260 max words, 200 samples - at ../dataset/gen-word-1260-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 3315 max words, 200 samples - at ../dataset/gen-word-3315-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 3130 max words, 200 samples - at ../dataset/gen-word-3130-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 2565 max words, 200 samples - at ../dataset/gen-word-2565-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 1295 max words, 200 samples - at ../dataset/gen-word-1295-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 1480 max words, 200 samples - at ../dataset/gen-word-1480-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 3990 max words, 200 samples - at ../dataset/gen-word-3990-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 3195 max words, 200 samples - at ../dataset/gen-word-3195-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 3565 max words, 200 samples - at ../dataset/gen-word-3565-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 2475 max words, 200 samples - at ../dataset/gen-word-2475-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 2190 max words, 200 samples - at ../dataset/gen-word-2190-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 1910 max words, 200 samples - at ../dataset/gen-word-1910-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 2415 max words, 200 samples - at ../dataset/gen-word-2415-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 2400 max words, 200 samples - at ../dataset/gen-word-2400-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 3320 max words, 200 samples - at ../dataset/gen-word-3320-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 2220 max words, 200 samples - at ../dataset/gen-word-2220-count.jsonl\n"
+      "Generated JSONL file with - 2865 max words, 200 samples - at ../dataset/gen-word-2865-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3960 max words, 200 samples - at ../dataset/gen-word-3960-count.jsonl\n"
+      "Generated JSONL file with - 3865 max words, 200 samples - at ../dataset/gen-word-3865-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2340 max words, 200 samples - at ../dataset/gen-word-2340-count.jsonl\n"
+      "Generated JSONL file with - 2760 max words, 200 samples - at ../dataset/gen-word-2760-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3450 max words, 200 samples - at ../dataset/gen-word-3450-count.jsonl\n"
+      "Generated JSONL file with - 2850 max words, 200 samples - at ../dataset/gen-word-2850-count.jsonl\n"
      ]
     },
     {
@@ -13177,1197 +12203,1176 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1690 max words, 200 samples - at ../dataset/gen-word-1690-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 2495 max words, 200 samples - at ../dataset/gen-word-2495-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 2955 max words, 200 samples - at ../dataset/gen-word-2955-count.jsonl\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated JSONL file with - 3405 max words, 200 samples - at ../dataset/gen-word-3405-count.jsonl\n"
+      "Generated JSONL file with - 2810 max words, 200 samples - at ../dataset/gen-word-2810-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3100 max words, 200 samples - at ../dataset/gen-word-3100-count.jsonl\n"
+      "Generated JSONL file with - 3265 max words, 200 samples - at ../dataset/gen-word-3265-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3175 max words, 200 samples - at ../dataset/gen-word-3175-count.jsonl\n"
+      "Generated JSONL file with - 3475 max words, 200 samples - at ../dataset/gen-word-3475-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3915 max words, 200 samples - at ../dataset/gen-word-3915-count.jsonl\n"
+      "Generated JSONL file with - 3555 max words, 200 samples - at ../dataset/gen-word-3555-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3715 max words, 200 samples - at ../dataset/gen-word-3715-count.jsonl\n"
+      "Generated JSONL file with - 3355 max words, 200 samples - at ../dataset/gen-word-3355-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2480 max words, 200 samples - at ../dataset/gen-word-2480-count.jsonl\n"
+      "Generated JSONL file with - 3940 max words, 200 samples - at ../dataset/gen-word-3940-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3830 max words, 200 samples - at ../dataset/gen-word-3830-count.jsonl\n"
+      "Generated JSONL file with - 3660 max words, 200 samples - at ../dataset/gen-word-3660-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1790 max words, 200 samples - at ../dataset/gen-word-1790-count.jsonl\n"
+      "Generated JSONL file with - 3685 max words, 200 samples - at ../dataset/gen-word-3685-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1865 max words, 200 samples - at ../dataset/gen-word-1865-count.jsonl\n"
+      "Generated JSONL file with - 3175 max words, 200 samples - at ../dataset/gen-word-3175-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2680 max words, 200 samples - at ../dataset/gen-word-2680-count.jsonl\n"
+      "Generated JSONL file with - 2610 max words, 200 samples - at ../dataset/gen-word-2610-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3435 max words, 200 samples - at ../dataset/gen-word-3435-count.jsonl\n"
+      "Generated JSONL file with - 2965 max words, 200 samples - at ../dataset/gen-word-2965-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3455 max words, 200 samples - at ../dataset/gen-word-3455-count.jsonl\n"
+      "Generated JSONL file with - 3020 max words, 200 samples - at ../dataset/gen-word-3020-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3680 max words, 200 samples - at ../dataset/gen-word-3680-count.jsonl\n"
+      "Generated JSONL file with - 3170 max words, 200 samples - at ../dataset/gen-word-3170-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2470 max words, 200 samples - at ../dataset/gen-word-2470-count.jsonl\n"
+      "Generated JSONL file with - 2385 max words, 200 samples - at ../dataset/gen-word-2385-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3580 max words, 200 samples - at ../dataset/gen-word-3580-count.jsonl\n"
+      "Generated JSONL file with - 3930 max words, 200 samples - at ../dataset/gen-word-3930-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1995 max words, 200 samples - at ../dataset/gen-word-1995-count.jsonl\n"
+      "Generated JSONL file with - 3065 max words, 200 samples - at ../dataset/gen-word-3065-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3710 max words, 200 samples - at ../dataset/gen-word-3710-count.jsonl\n"
+      "Generated JSONL file with - 2575 max words, 200 samples - at ../dataset/gen-word-2575-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3045 max words, 200 samples - at ../dataset/gen-word-3045-count.jsonl\n"
+      "Generated JSONL file with - 3120 max words, 200 samples - at ../dataset/gen-word-3120-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2435 max words, 200 samples - at ../dataset/gen-word-2435-count.jsonl\n"
+      "Generated JSONL file with - 2890 max words, 200 samples - at ../dataset/gen-word-2890-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1625 max words, 200 samples - at ../dataset/gen-word-1625-count.jsonl\n"
+      "Generated JSONL file with - 2415 max words, 200 samples - at ../dataset/gen-word-2415-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2600 max words, 200 samples - at ../dataset/gen-word-2600-count.jsonl\n"
+      "Generated JSONL file with - 3130 max words, 200 samples - at ../dataset/gen-word-3130-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2760 max words, 200 samples - at ../dataset/gen-word-2760-count.jsonl\n"
+      "Generated JSONL file with - 2955 max words, 200 samples - at ../dataset/gen-word-2955-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3085 max words, 200 samples - at ../dataset/gen-word-3085-count.jsonl\n"
+      "Generated JSONL file with - 3095 max words, 200 samples - at ../dataset/gen-word-3095-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2740 max words, 200 samples - at ../dataset/gen-word-2740-count.jsonl\n"
+      "Generated JSONL file with - 3160 max words, 200 samples - at ../dataset/gen-word-3160-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2530 max words, 200 samples - at ../dataset/gen-word-2530-count.jsonl\n"
+      "Generated JSONL file with - 2720 max words, 200 samples - at ../dataset/gen-word-2720-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3640 max words, 200 samples - at ../dataset/gen-word-3640-count.jsonl\n"
+      "Generated JSONL file with - 2380 max words, 200 samples - at ../dataset/gen-word-2380-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3200 max words, 200 samples - at ../dataset/gen-word-3200-count.jsonl\n"
+      "Generated JSONL file with - 2555 max words, 200 samples - at ../dataset/gen-word-2555-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3075 max words, 200 samples - at ../dataset/gen-word-3075-count.jsonl\n"
+      "Generated JSONL file with - 2325 max words, 200 samples - at ../dataset/gen-word-2325-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3870 max words, 200 samples - at ../dataset/gen-word-3870-count.jsonl\n"
+      "Generated JSONL file with - 3300 max words, 200 samples - at ../dataset/gen-word-3300-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3735 max words, 200 samples - at ../dataset/gen-word-3735-count.jsonl\n"
+      "Generated JSONL file with - 3290 max words, 200 samples - at ../dataset/gen-word-3290-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1805 max words, 200 samples - at ../dataset/gen-word-1805-count.jsonl\n"
+      "Generated JSONL file with - 2880 max words, 200 samples - at ../dataset/gen-word-2880-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3270 max words, 200 samples - at ../dataset/gen-word-3270-count.jsonl\n"
+      "Generated JSONL file with - 2495 max words, 200 samples - at ../dataset/gen-word-2495-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2000 max words, 200 samples - at ../dataset/gen-word-2000-count.jsonl\n"
+      "Generated JSONL file with - 2685 max words, 200 samples - at ../dataset/gen-word-2685-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2630 max words, 200 samples - at ../dataset/gen-word-2630-count.jsonl\n"
+      "Generated JSONL file with - 3105 max words, 200 samples - at ../dataset/gen-word-3105-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3955 max words, 200 samples - at ../dataset/gen-word-3955-count.jsonl\n"
+      "Generated JSONL file with - 3780 max words, 200 samples - at ../dataset/gen-word-3780-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3895 max words, 200 samples - at ../dataset/gen-word-3895-count.jsonl\n"
+      "Generated JSONL file with - 2840 max words, 200 samples - at ../dataset/gen-word-2840-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3240 max words, 200 samples - at ../dataset/gen-word-3240-count.jsonl\n"
+      "Generated JSONL file with - 3310 max words, 200 samples - at ../dataset/gen-word-3310-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2880 max words, 200 samples - at ../dataset/gen-word-2880-count.jsonl\n"
+      "Generated JSONL file with - 3720 max words, 200 samples - at ../dataset/gen-word-3720-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3010 max words, 200 samples - at ../dataset/gen-word-3010-count.jsonl\n"
+      "Generated JSONL file with - 2935 max words, 200 samples - at ../dataset/gen-word-2935-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2610 max words, 200 samples - at ../dataset/gen-word-2610-count.jsonl\n"
+      "Generated JSONL file with - 3435 max words, 200 samples - at ../dataset/gen-word-3435-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3150 max words, 200 samples - at ../dataset/gen-word-3150-count.jsonl\n"
+      "Generated JSONL file with - 2595 max words, 200 samples - at ../dataset/gen-word-2595-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2800 max words, 200 samples - at ../dataset/gen-word-2800-count.jsonl\n"
+      "Generated JSONL file with - 3480 max words, 200 samples - at ../dataset/gen-word-3480-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2885 max words, 200 samples - at ../dataset/gen-word-2885-count.jsonl\n"
+      "Generated JSONL file with - 3025 max words, 200 samples - at ../dataset/gen-word-3025-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3935 max words, 200 samples - at ../dataset/gen-word-3935-count.jsonl\n"
+      "Generated JSONL file with - 3425 max words, 200 samples - at ../dataset/gen-word-3425-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3470 max words, 200 samples - at ../dataset/gen-word-3470-count.jsonl\n"
+      "Generated JSONL file with - 3015 max words, 200 samples - at ../dataset/gen-word-3015-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2705 max words, 200 samples - at ../dataset/gen-word-2705-count.jsonl\n"
+      "Generated JSONL file with - 3695 max words, 200 samples - at ../dataset/gen-word-3695-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3920 max words, 200 samples - at ../dataset/gen-word-3920-count.jsonl\n"
+      "Generated JSONL file with - 3725 max words, 200 samples - at ../dataset/gen-word-3725-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3725 max words, 200 samples - at ../dataset/gen-word-3725-count.jsonl\n"
+      "Generated JSONL file with - 3750 max words, 200 samples - at ../dataset/gen-word-3750-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2515 max words, 200 samples - at ../dataset/gen-word-2515-count.jsonl\n"
+      "Generated JSONL file with - 3295 max words, 200 samples - at ../dataset/gen-word-3295-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2925 max words, 200 samples - at ../dataset/gen-word-2925-count.jsonl\n"
+      "Generated JSONL file with - 3590 max words, 200 samples - at ../dataset/gen-word-3590-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1880 max words, 200 samples - at ../dataset/gen-word-1880-count.jsonl\n"
+      "Generated JSONL file with - 3210 max words, 200 samples - at ../dataset/gen-word-3210-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3335 max words, 200 samples - at ../dataset/gen-word-3335-count.jsonl\n"
+      "Generated JSONL file with - 3585 max words, 200 samples - at ../dataset/gen-word-3585-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 1935 max words, 200 samples - at ../dataset/gen-word-1935-count.jsonl\n"
+      "Generated JSONL file with - 3315 max words, 200 samples - at ../dataset/gen-word-3315-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2175 max words, 200 samples - at ../dataset/gen-word-2175-count.jsonl\n"
+      "Generated JSONL file with - 2335 max words, 200 samples - at ../dataset/gen-word-2335-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3775 max words, 200 samples - at ../dataset/gen-word-3775-count.jsonl\n"
+      "Generated JSONL file with - 2665 max words, 200 samples - at ../dataset/gen-word-2665-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3925 max words, 200 samples - at ../dataset/gen-word-3925-count.jsonl\n"
+      "Generated JSONL file with - 3575 max words, 200 samples - at ../dataset/gen-word-3575-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3220 max words, 200 samples - at ../dataset/gen-word-3220-count.jsonl\n"
+      "Generated JSONL file with - 3155 max words, 200 samples - at ../dataset/gen-word-3155-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3880 max words, 200 samples - at ../dataset/gen-word-3880-count.jsonl\n"
+      "Generated JSONL file with - 3455 max words, 200 samples - at ../dataset/gen-word-3455-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3020 max words, 200 samples - at ../dataset/gen-word-3020-count.jsonl\n"
+      "Generated JSONL file with - 3360 max words, 200 samples - at ../dataset/gen-word-3360-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3740 max words, 200 samples - at ../dataset/gen-word-3740-count.jsonl\n"
+      "Generated JSONL file with - 2370 max words, 200 samples - at ../dataset/gen-word-2370-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3995 max words, 200 samples - at ../dataset/gen-word-3995-count.jsonl\n"
+      "Generated JSONL file with - 2270 max words, 200 samples - at ../dataset/gen-word-2270-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2820 max words, 200 samples - at ../dataset/gen-word-2820-count.jsonl\n"
+      "Generated JSONL file with - 3420 max words, 200 samples - at ../dataset/gen-word-3420-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3720 max words, 200 samples - at ../dataset/gen-word-3720-count.jsonl\n"
+      "Generated JSONL file with - 2930 max words, 200 samples - at ../dataset/gen-word-2930-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3850 max words, 200 samples - at ../dataset/gen-word-3850-count.jsonl\n"
+      "Generated JSONL file with - 2485 max words, 200 samples - at ../dataset/gen-word-2485-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3345 max words, 200 samples - at ../dataset/gen-word-3345-count.jsonl\n"
+      "Generated JSONL file with - 3225 max words, 200 samples - at ../dataset/gen-word-3225-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3810 max words, 200 samples - at ../dataset/gen-word-3810-count.jsonl\n"
+      "Generated JSONL file with - 3080 max words, 200 samples - at ../dataset/gen-word-3080-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2795 max words, 200 samples - at ../dataset/gen-word-2795-count.jsonl\n"
+      "Generated JSONL file with - 1650 max words, 200 samples - at ../dataset/gen-word-1650-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2210 max words, 200 samples - at ../dataset/gen-word-2210-count.jsonl\n"
+      "Generated JSONL file with - 2110 max words, 200 samples - at ../dataset/gen-word-2110-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3140 max words, 200 samples - at ../dataset/gen-word-3140-count.jsonl\n"
+      "Generated JSONL file with - 3200 max words, 200 samples - at ../dataset/gen-word-3200-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2155 max words, 200 samples - at ../dataset/gen-word-2155-count.jsonl\n"
+      "Generated JSONL file with - 3410 max words, 200 samples - at ../dataset/gen-word-3410-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3025 max words, 200 samples - at ../dataset/gen-word-3025-count.jsonl\n"
+      "Generated JSONL file with - 2645 max words, 200 samples - at ../dataset/gen-word-2645-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3060 max words, 200 samples - at ../dataset/gen-word-3060-count.jsonl\n"
+      "Generated JSONL file with - 3730 max words, 200 samples - at ../dataset/gen-word-3730-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3375 max words, 200 samples - at ../dataset/gen-word-3375-count.jsonl\n"
+      "Generated JSONL file with - 3510 max words, 200 samples - at ../dataset/gen-word-3510-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2420 max words, 200 samples - at ../dataset/gen-word-2420-count.jsonl\n"
+      "Generated JSONL file with - 3345 max words, 200 samples - at ../dataset/gen-word-3345-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3860 max words, 200 samples - at ../dataset/gen-word-3860-count.jsonl\n"
+      "Generated JSONL file with - 2715 max words, 200 samples - at ../dataset/gen-word-2715-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3265 max words, 200 samples - at ../dataset/gen-word-3265-count.jsonl\n"
+      "Generated JSONL file with - 3565 max words, 200 samples - at ../dataset/gen-word-3565-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3040 max words, 200 samples - at ../dataset/gen-word-3040-count.jsonl\n"
+      "Generated JSONL file with - 3680 max words, 200 samples - at ../dataset/gen-word-3680-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2860 max words, 200 samples - at ../dataset/gen-word-2860-count.jsonl\n"
+      "Generated JSONL file with - 3545 max words, 200 samples - at ../dataset/gen-word-3545-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3425 max words, 200 samples - at ../dataset/gen-word-3425-count.jsonl\n"
+      "Generated JSONL file with - 2725 max words, 200 samples - at ../dataset/gen-word-2725-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2915 max words, 200 samples - at ../dataset/gen-word-2915-count.jsonl\n"
+      "Generated JSONL file with - 2375 max words, 200 samples - at ../dataset/gen-word-2375-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3945 max words, 200 samples - at ../dataset/gen-word-3945-count.jsonl\n"
+      "Generated JSONL file with - 2970 max words, 200 samples - at ../dataset/gen-word-2970-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3445 max words, 200 samples - at ../dataset/gen-word-3445-count.jsonl\n"
+      "Generated JSONL file with - 3795 max words, 200 samples - at ../dataset/gen-word-3795-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3065 max words, 200 samples - at ../dataset/gen-word-3065-count.jsonl\n"
+      "Generated JSONL file with - 2870 max words, 200 samples - at ../dataset/gen-word-2870-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2905 max words, 200 samples - at ../dataset/gen-word-2905-count.jsonl\n"
+      "Generated JSONL file with - 3370 max words, 200 samples - at ../dataset/gen-word-3370-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3125 max words, 200 samples - at ../dataset/gen-word-3125-count.jsonl\n"
+      "Generated JSONL file with - 3495 max words, 200 samples - at ../dataset/gen-word-3495-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2850 max words, 200 samples - at ../dataset/gen-word-2850-count.jsonl\n"
+      "Generated JSONL file with - 3045 max words, 200 samples - at ../dataset/gen-word-3045-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3210 max words, 200 samples - at ../dataset/gen-word-3210-count.jsonl\n"
+      "Generated JSONL file with - 2065 max words, 200 samples - at ../dataset/gen-word-2065-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3835 max words, 200 samples - at ../dataset/gen-word-3835-count.jsonl\n"
+      "Generated JSONL file with - 3440 max words, 200 samples - at ../dataset/gen-word-3440-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3160 max words, 200 samples - at ../dataset/gen-word-3160-count.jsonl\n"
+      "Generated JSONL file with - 2815 max words, 200 samples - at ../dataset/gen-word-2815-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3480 max words, 200 samples - at ../dataset/gen-word-3480-count.jsonl\n"
+      "Generated JSONL file with - 2220 max words, 200 samples - at ../dataset/gen-word-2220-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3530 max words, 200 samples - at ../dataset/gen-word-3530-count.jsonl\n"
+      "Generated JSONL file with - 3485 max words, 200 samples - at ../dataset/gen-word-3485-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3575 max words, 200 samples - at ../dataset/gen-word-3575-count.jsonl\n"
+      "Generated JSONL file with - 3540 max words, 200 samples - at ../dataset/gen-word-3540-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3595 max words, 200 samples - at ../dataset/gen-word-3595-count.jsonl\n"
+      "Generated JSONL file with - 3320 max words, 200 samples - at ../dataset/gen-word-3320-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3985 max words, 200 samples - at ../dataset/gen-word-3985-count.jsonl\n"
+      "Generated JSONL file with - 2215 max words, 200 samples - at ../dataset/gen-word-2215-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3135 max words, 200 samples - at ../dataset/gen-word-3135-count.jsonl\n"
+      "Generated JSONL file with - 3600 max words, 200 samples - at ../dataset/gen-word-3600-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3365 max words, 200 samples - at ../dataset/gen-word-3365-count.jsonl\n"
+      "Generated JSONL file with - 3625 max words, 200 samples - at ../dataset/gen-word-3625-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3560 max words, 200 samples - at ../dataset/gen-word-3560-count.jsonl\n"
+      "Generated JSONL file with - 3700 max words, 200 samples - at ../dataset/gen-word-3700-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3615 max words, 200 samples - at ../dataset/gen-word-3615-count.jsonl\n"
+      "Generated JSONL file with - 3535 max words, 200 samples - at ../dataset/gen-word-3535-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2425 max words, 200 samples - at ../dataset/gen-word-2425-count.jsonl\n"
+      "Generated JSONL file with - 3340 max words, 200 samples - at ../dataset/gen-word-3340-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3500 max words, 200 samples - at ../dataset/gen-word-3500-count.jsonl\n"
+      "Generated JSONL file with - 3460 max words, 200 samples - at ../dataset/gen-word-3460-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2455 max words, 200 samples - at ../dataset/gen-word-2455-count.jsonl\n"
+      "Generated JSONL file with - 3800 max words, 200 samples - at ../dataset/gen-word-3800-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3585 max words, 200 samples - at ../dataset/gen-word-3585-count.jsonl\n"
+      "Generated JSONL file with - 4000 max words, 200 samples - at ../dataset/gen-word-4000-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3165 max words, 200 samples - at ../dataset/gen-word-3165-count.jsonl\n"
+      "Generated JSONL file with - 3815 max words, 200 samples - at ../dataset/gen-word-3815-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3310 max words, 200 samples - at ../dataset/gen-word-3310-count.jsonl\n"
+      "Generated JSONL file with - 3635 max words, 200 samples - at ../dataset/gen-word-3635-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2695 max words, 200 samples - at ../dataset/gen-word-2695-count.jsonl\n"
+      "Generated JSONL file with - 2845 max words, 200 samples - at ../dataset/gen-word-2845-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3055 max words, 200 samples - at ../dataset/gen-word-3055-count.jsonl\n"
+      "Generated JSONL file with - 3520 max words, 200 samples - at ../dataset/gen-word-3520-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3550 max words, 200 samples - at ../dataset/gen-word-3550-count.jsonl\n"
+      "Generated JSONL file with - 3085 max words, 200 samples - at ../dataset/gen-word-3085-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3330 max words, 200 samples - at ../dataset/gen-word-3330-count.jsonl\n"
+      "Generated JSONL file with - 3595 max words, 200 samples - at ../dataset/gen-word-3595-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2550 max words, 200 samples - at ../dataset/gen-word-2550-count.jsonl\n"
+      "Generated JSONL file with - 3560 max words, 200 samples - at ../dataset/gen-word-3560-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3600 max words, 200 samples - at ../dataset/gen-word-3600-count.jsonl\n"
+      "Generated JSONL file with - 3165 max words, 200 samples - at ../dataset/gen-word-3165-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3170 max words, 200 samples - at ../dataset/gen-word-3170-count.jsonl\n"
+      "Generated JSONL file with - 3140 max words, 200 samples - at ../dataset/gen-word-3140-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3355 max words, 200 samples - at ../dataset/gen-word-3355-count.jsonl\n"
+      "Generated JSONL file with - 3380 max words, 200 samples - at ../dataset/gen-word-3380-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2535 max words, 200 samples - at ../dataset/gen-word-2535-count.jsonl\n"
+      "Generated JSONL file with - 3875 max words, 200 samples - at ../dataset/gen-word-3875-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2410 max words, 200 samples - at ../dataset/gen-word-2410-count.jsonl\n"
+      "Generated JSONL file with - 2920 max words, 200 samples - at ../dataset/gen-word-2920-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3295 max words, 200 samples - at ../dataset/gen-word-3295-count.jsonl\n"
+      "Generated JSONL file with - 2230 max words, 200 samples - at ../dataset/gen-word-2230-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3400 max words, 200 samples - at ../dataset/gen-word-3400-count.jsonl\n"
+      "Generated JSONL file with - 3325 max words, 200 samples - at ../dataset/gen-word-3325-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3905 max words, 200 samples - at ../dataset/gen-word-3905-count.jsonl\n"
+      "Generated JSONL file with - 2695 max words, 200 samples - at ../dataset/gen-word-2695-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3245 max words, 200 samples - at ../dataset/gen-word-3245-count.jsonl\n"
+      "Generated JSONL file with - 3860 max words, 200 samples - at ../dataset/gen-word-3860-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 2430 max words, 200 samples - at ../dataset/gen-word-2430-count.jsonl\n"
+      "Generated JSONL file with - 3235 max words, 200 samples - at ../dataset/gen-word-3235-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3975 max words, 200 samples - at ../dataset/gen-word-3975-count.jsonl\n"
+      "Generated JSONL file with - 3350 max words, 200 samples - at ../dataset/gen-word-3350-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3370 max words, 200 samples - at ../dataset/gen-word-3370-count.jsonl\n"
+      "Generated JSONL file with - 3395 max words, 200 samples - at ../dataset/gen-word-3395-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3605 max words, 200 samples - at ../dataset/gen-word-3605-count.jsonl\n"
+      "Generated JSONL file with - 3890 max words, 200 samples - at ../dataset/gen-word-3890-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3115 max words, 200 samples - at ../dataset/gen-word-3115-count.jsonl\n"
+      "Generated JSONL file with - 3850 max words, 200 samples - at ../dataset/gen-word-3850-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3105 max words, 200 samples - at ../dataset/gen-word-3105-count.jsonl\n"
+      "Generated JSONL file with - 3640 max words, 200 samples - at ../dataset/gen-word-3640-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3770 max words, 200 samples - at ../dataset/gen-word-3770-count.jsonl\n"
+      "Generated JSONL file with - 3250 max words, 200 samples - at ../dataset/gen-word-3250-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3630 max words, 200 samples - at ../dataset/gen-word-3630-count.jsonl\n"
+      "Generated JSONL file with - 3645 max words, 200 samples - at ../dataset/gen-word-3645-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3385 max words, 200 samples - at ../dataset/gen-word-3385-count.jsonl\n"
+      "Generated JSONL file with - 3775 max words, 200 samples - at ../dataset/gen-word-3775-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3155 max words, 200 samples - at ../dataset/gen-word-3155-count.jsonl\n"
+      "Generated JSONL file with - 3895 max words, 200 samples - at ../dataset/gen-word-3895-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3845 max words, 200 samples - at ../dataset/gen-word-3845-count.jsonl\n"
+      "Generated JSONL file with - 3900 max words, 200 samples - at ../dataset/gen-word-3900-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3260 max words, 200 samples - at ../dataset/gen-word-3260-count.jsonl\n"
+      "Generated JSONL file with - 3605 max words, 200 samples - at ../dataset/gen-word-3605-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3705 max words, 200 samples - at ../dataset/gen-word-3705-count.jsonl\n"
+      "Generated JSONL file with - 3785 max words, 200 samples - at ../dataset/gen-word-3785-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3685 max words, 200 samples - at ../dataset/gen-word-3685-count.jsonl\n"
+      "Generated JSONL file with - 3855 max words, 200 samples - at ../dataset/gen-word-3855-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3300 max words, 200 samples - at ../dataset/gen-word-3300-count.jsonl\n"
+      "Generated JSONL file with - 3915 max words, 200 samples - at ../dataset/gen-word-3915-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3390 max words, 200 samples - at ../dataset/gen-word-3390-count.jsonl\n"
+      "Generated JSONL file with - 3005 max words, 200 samples - at ../dataset/gen-word-3005-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3670 max words, 200 samples - at ../dataset/gen-word-3670-count.jsonl\n"
+      "Generated JSONL file with - 3820 max words, 200 samples - at ../dataset/gen-word-3820-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3505 max words, 200 samples - at ../dataset/gen-word-3505-count.jsonl\n"
+      "Generated JSONL file with - 3835 max words, 200 samples - at ../dataset/gen-word-3835-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3875 max words, 200 samples - at ../dataset/gen-word-3875-count.jsonl\n"
+      "Generated JSONL file with - 3765 max words, 200 samples - at ../dataset/gen-word-3765-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3235 max words, 200 samples - at ../dataset/gen-word-3235-count.jsonl\n"
+      "Generated JSONL file with - 3570 max words, 200 samples - at ../dataset/gen-word-3570-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3930 max words, 200 samples - at ../dataset/gen-word-3930-count.jsonl\n"
+      "Generated JSONL file with - 3975 max words, 200 samples - at ../dataset/gen-word-3975-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3360 max words, 200 samples - at ../dataset/gen-word-3360-count.jsonl\n"
+      "Generated JSONL file with - 3745 max words, 200 samples - at ../dataset/gen-word-3745-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3760 max words, 200 samples - at ../dataset/gen-word-3760-count.jsonl\n"
+      "Generated JSONL file with - 3450 max words, 200 samples - at ../dataset/gen-word-3450-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3650 max words, 200 samples - at ../dataset/gen-word-3650-count.jsonl\n"
+      "Generated JSONL file with - 3735 max words, 200 samples - at ../dataset/gen-word-3735-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3700 max words, 200 samples - at ../dataset/gen-word-3700-count.jsonl\n"
+      "Generated JSONL file with - 3705 max words, 200 samples - at ../dataset/gen-word-3705-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3690 max words, 200 samples - at ../dataset/gen-word-3690-count.jsonl\n"
+      "Generated JSONL file with - 2995 max words, 200 samples - at ../dataset/gen-word-2995-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 4000 max words, 200 samples - at ../dataset/gen-word-4000-count.jsonl\n"
+      "Generated JSONL file with - 3530 max words, 200 samples - at ../dataset/gen-word-3530-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3805 max words, 200 samples - at ../dataset/gen-word-3805-count.jsonl\n"
+      "Generated JSONL file with - 3980 max words, 200 samples - at ../dataset/gen-word-3980-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3635 max words, 200 samples - at ../dataset/gen-word-3635-count.jsonl\n"
+      "Generated JSONL file with - 3655 max words, 200 samples - at ../dataset/gen-word-3655-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3655 max words, 200 samples - at ../dataset/gen-word-3655-count.jsonl\n"
+      "Generated JSONL file with - 3690 max words, 200 samples - at ../dataset/gen-word-3690-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3940 max words, 200 samples - at ../dataset/gen-word-3940-count.jsonl\n"
+      "Generated JSONL file with - 3830 max words, 200 samples - at ../dataset/gen-word-3830-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3795 max words, 200 samples - at ../dataset/gen-word-3795-count.jsonl\n"
+      "Generated JSONL file with - 3335 max words, 200 samples - at ../dataset/gen-word-3335-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3620 max words, 200 samples - at ../dataset/gen-word-3620-count.jsonl\n"
+      "Generated JSONL file with - 3870 max words, 200 samples - at ../dataset/gen-word-3870-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3590 max words, 200 samples - at ../dataset/gen-word-3590-count.jsonl\n"
+      "Generated JSONL file with - 3505 max words, 200 samples - at ../dataset/gen-word-3505-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3865 max words, 200 samples - at ../dataset/gen-word-3865-count.jsonl\n"
+      "Generated JSONL file with - 3150 max words, 200 samples - at ../dataset/gen-word-3150-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3415 max words, 200 samples - at ../dataset/gen-word-3415-count.jsonl\n"
+      "Generated JSONL file with - 3580 max words, 200 samples - at ../dataset/gen-word-3580-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3910 max words, 200 samples - at ../dataset/gen-word-3910-count.jsonl\n"
+      "Generated JSONL file with - 3970 max words, 200 samples - at ../dataset/gen-word-3970-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3785 max words, 200 samples - at ../dataset/gen-word-3785-count.jsonl\n"
+      "Generated JSONL file with - 3330 max words, 200 samples - at ../dataset/gen-word-3330-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3520 max words, 200 samples - at ../dataset/gen-word-3520-count.jsonl\n"
+      "Generated JSONL file with - 3920 max words, 200 samples - at ../dataset/gen-word-3920-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3515 max words, 200 samples - at ../dataset/gen-word-3515-count.jsonl\n"
+      "Generated JSONL file with - 3740 max words, 200 samples - at ../dataset/gen-word-3740-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3510 max words, 200 samples - at ../dataset/gen-word-3510-count.jsonl\n"
+      "Generated JSONL file with - 3215 max words, 200 samples - at ../dataset/gen-word-3215-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3855 max words, 200 samples - at ../dataset/gen-word-3855-count.jsonl\n"
+      "Generated JSONL file with - 3825 max words, 200 samples - at ../dataset/gen-word-3825-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3950 max words, 200 samples - at ../dataset/gen-word-3950-count.jsonl\n"
+      "Generated JSONL file with - 3960 max words, 200 samples - at ../dataset/gen-word-3960-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3970 max words, 200 samples - at ../dataset/gen-word-3970-count.jsonl\n"
+      "Generated JSONL file with - 3715 max words, 200 samples - at ../dataset/gen-word-3715-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3885 max words, 200 samples - at ../dataset/gen-word-3885-count.jsonl\n"
+      "Generated JSONL file with - 3670 max words, 200 samples - at ../dataset/gen-word-3670-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3430 max words, 200 samples - at ../dataset/gen-word-3430-count.jsonl\n"
+      "Generated JSONL file with - 3620 max words, 200 samples - at ../dataset/gen-word-3620-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3765 max words, 200 samples - at ../dataset/gen-word-3765-count.jsonl\n"
+      "Generated JSONL file with - 3905 max words, 200 samples - at ../dataset/gen-word-3905-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3800 max words, 200 samples - at ../dataset/gen-word-3800-count.jsonl\n"
+      "Generated JSONL file with - 3910 max words, 200 samples - at ../dataset/gen-word-3910-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3490 max words, 200 samples - at ../dataset/gen-word-3490-count.jsonl\n"
+      "Generated JSONL file with - 3925 max words, 200 samples - at ../dataset/gen-word-3925-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Generated JSONL file with - 3965 max words, 200 samples - at ../dataset/gen-word-3965-count.jsonl\n"
+      "Generated JSONL file with - 3880 max words, 200 samples - at ../dataset/gen-word-3880-count.jsonl\n"
      ]
     },
     {
@@ -14388,11221 +13393,11221 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "drwxr-xr-x  2 root root   72K Sep  1 13:54 .\n"
+      "drwxr-xr-x  2 root root   72K Sep  1 14:30 .\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "drwxr-xr-x 14 root root   302 Sep  1 13:54 ..\n"
+      "drwxr-xr-x 14 root root   302 Sep  1 14:30 ..\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   20K Sep  1 13:54 gen-word-10-count.jsonl\n"
+      "-rw-r--r--  1 root root   20K Sep  1 14:30 gen-word-10-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  107K Sep  1 13:54 gen-word-100-count.jsonl\n"
+      "-rw-r--r--  1 root root  106K Sep  1 14:30 gen-word-100-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.0M Sep  1 13:54 gen-word-1000-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.0M Sep  1 14:30 gen-word-1000-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.0M Sep  1 13:54 gen-word-1005-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.0M Sep  1 14:30 gen-word-1005-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.0M Sep  1 13:54 gen-word-1010-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.0M Sep  1 14:30 gen-word-1010-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.0M Sep  1 13:54 gen-word-1015-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.0M Sep  1 14:30 gen-word-1015-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.0M Sep  1 13:54 gen-word-1020-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.0M Sep  1 14:30 gen-word-1020-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.0M Sep  1 13:54 gen-word-1025-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.0M Sep  1 14:30 gen-word-1025-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.0M Sep  1 13:54 gen-word-1030-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.0M Sep  1 14:30 gen-word-1030-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.0M Sep  1 13:54 gen-word-1035-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.0M Sep  1 14:30 gen-word-1035-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.1M Sep  1 13:54 gen-word-1040-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.1M Sep  1 14:30 gen-word-1040-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.1M Sep  1 13:54 gen-word-1045-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.0M Sep  1 14:30 gen-word-1045-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  115K Sep  1 13:54 gen-word-105-count.jsonl\n"
+      "-rw-r--r--  1 root root  114K Sep  1 14:30 gen-word-105-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.1M Sep  1 13:54 gen-word-1050-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.1M Sep  1 14:30 gen-word-1050-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.1M Sep  1 13:54 gen-word-1055-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.1M Sep  1 14:30 gen-word-1055-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.1M Sep  1 13:54 gen-word-1060-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.1M Sep  1 14:30 gen-word-1060-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.1M Sep  1 13:54 gen-word-1065-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.1M Sep  1 14:30 gen-word-1065-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.1M Sep  1 13:54 gen-word-1070-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.1M Sep  1 14:30 gen-word-1070-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.1M Sep  1 13:54 gen-word-1075-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.1M Sep  1 14:30 gen-word-1075-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.1M Sep  1 13:54 gen-word-1080-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.1M Sep  1 14:30 gen-word-1080-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.1M Sep  1 13:54 gen-word-1085-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.1M Sep  1 14:30 gen-word-1085-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.1M Sep  1 13:54 gen-word-1090-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.1M Sep  1 14:30 gen-word-1090-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.1M Sep  1 13:54 gen-word-1095-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.2M Sep  1 14:30 gen-word-1095-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  117K Sep  1 13:54 gen-word-110-count.jsonl\n"
+      "-rw-r--r--  1 root root  117K Sep  1 14:30 gen-word-110-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.2M Sep  1 13:54 gen-word-1100-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.2M Sep  1 14:30 gen-word-1100-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.2M Sep  1 13:54 gen-word-1105-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.2M Sep  1 14:30 gen-word-1105-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.2M Sep  1 13:54 gen-word-1110-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.2M Sep  1 14:30 gen-word-1110-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.2M Sep  1 13:54 gen-word-1115-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.2M Sep  1 14:30 gen-word-1115-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.2M Sep  1 13:54 gen-word-1120-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.2M Sep  1 14:30 gen-word-1120-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.2M Sep  1 13:54 gen-word-1125-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.2M Sep  1 14:30 gen-word-1125-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.2M Sep  1 13:54 gen-word-1130-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.2M Sep  1 14:30 gen-word-1130-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.2M Sep  1 13:54 gen-word-1135-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.2M Sep  1 14:30 gen-word-1135-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.2M Sep  1 13:54 gen-word-1140-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.2M Sep  1 14:30 gen-word-1140-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.2M Sep  1 13:54 gen-word-1145-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.2M Sep  1 14:30 gen-word-1145-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  121K Sep  1 13:54 gen-word-115-count.jsonl\n"
+      "-rw-r--r--  1 root root  123K Sep  1 14:30 gen-word-115-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.3M Sep  1 13:54 gen-word-1150-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.3M Sep  1 14:30 gen-word-1150-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.3M Sep  1 13:54 gen-word-1155-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.3M Sep  1 14:30 gen-word-1155-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.3M Sep  1 13:54 gen-word-1160-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.3M Sep  1 14:30 gen-word-1160-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.3M Sep  1 13:54 gen-word-1165-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.3M Sep  1 14:30 gen-word-1165-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.3M Sep  1 13:54 gen-word-1170-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.3M Sep  1 14:30 gen-word-1170-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.3M Sep  1 13:54 gen-word-1175-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.3M Sep  1 14:30 gen-word-1175-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.3M Sep  1 13:54 gen-word-1180-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.3M Sep  1 14:30 gen-word-1180-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.3M Sep  1 13:54 gen-word-1185-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.3M Sep  1 14:30 gen-word-1185-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.3M Sep  1 13:54 gen-word-1190-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.3M Sep  1 14:30 gen-word-1190-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.3M Sep  1 13:54 gen-word-1195-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.3M Sep  1 14:30 gen-word-1195-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  125K Sep  1 13:54 gen-word-120-count.jsonl\n"
+      "-rw-r--r--  1 root root  129K Sep  1 14:30 gen-word-120-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.3M Sep  1 13:54 gen-word-1200-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.3M Sep  1 14:30 gen-word-1200-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.3M Sep  1 13:54 gen-word-1205-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.4M Sep  1 14:30 gen-word-1205-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.4M Sep  1 13:54 gen-word-1210-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.4M Sep  1 14:30 gen-word-1210-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.4M Sep  1 13:54 gen-word-1215-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.4M Sep  1 14:30 gen-word-1215-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.4M Sep  1 13:54 gen-word-1220-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.4M Sep  1 14:30 gen-word-1220-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.4M Sep  1 13:54 gen-word-1225-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.4M Sep  1 14:30 gen-word-1225-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.4M Sep  1 13:54 gen-word-1230-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.4M Sep  1 14:30 gen-word-1230-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.4M Sep  1 13:54 gen-word-1235-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.4M Sep  1 14:30 gen-word-1235-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.4M Sep  1 13:54 gen-word-1240-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.4M Sep  1 14:30 gen-word-1240-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.4M Sep  1 13:54 gen-word-1245-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.4M Sep  1 14:30 gen-word-1245-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  132K Sep  1 13:54 gen-word-125-count.jsonl\n"
+      "-rw-r--r--  1 root root  132K Sep  1 14:30 gen-word-125-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.4M Sep  1 13:54 gen-word-1250-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.4M Sep  1 14:30 gen-word-1250-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.4M Sep  1 13:54 gen-word-1255-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.4M Sep  1 14:30 gen-word-1255-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.5M Sep  1 13:54 gen-word-1260-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.5M Sep  1 14:30 gen-word-1260-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.5M Sep  1 13:54 gen-word-1265-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.5M Sep  1 14:30 gen-word-1265-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.5M Sep  1 13:54 gen-word-1270-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.5M Sep  1 14:30 gen-word-1270-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.5M Sep  1 13:54 gen-word-1275-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.5M Sep  1 14:30 gen-word-1275-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.5M Sep  1 13:54 gen-word-1280-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.5M Sep  1 14:30 gen-word-1280-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.5M Sep  1 13:54 gen-word-1285-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.5M Sep  1 14:30 gen-word-1285-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.5M Sep  1 13:54 gen-word-1290-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.5M Sep  1 14:30 gen-word-1290-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.5M Sep  1 13:54 gen-word-1295-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.5M Sep  1 14:30 gen-word-1295-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  138K Sep  1 13:54 gen-word-130-count.jsonl\n"
+      "-rw-r--r--  1 root root  137K Sep  1 14:30 gen-word-130-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.6M Sep  1 13:54 gen-word-1300-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.6M Sep  1 14:30 gen-word-1300-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.5M Sep  1 13:54 gen-word-1305-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.6M Sep  1 14:30 gen-word-1305-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.5M Sep  1 13:54 gen-word-1310-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.6M Sep  1 14:30 gen-word-1310-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.6M Sep  1 13:54 gen-word-1315-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.6M Sep  1 14:30 gen-word-1315-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.6M Sep  1 13:54 gen-word-1320-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.6M Sep  1 14:30 gen-word-1320-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.6M Sep  1 13:54 gen-word-1325-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.6M Sep  1 14:30 gen-word-1325-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.6M Sep  1 13:54 gen-word-1330-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.6M Sep  1 14:30 gen-word-1330-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.6M Sep  1 13:54 gen-word-1335-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.6M Sep  1 14:30 gen-word-1335-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.6M Sep  1 13:54 gen-word-1340-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.6M Sep  1 14:30 gen-word-1340-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.6M Sep  1 13:54 gen-word-1345-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.6M Sep  1 14:30 gen-word-1345-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  144K Sep  1 13:54 gen-word-135-count.jsonl\n"
+      "-rw-r--r--  1 root root  144K Sep  1 14:30 gen-word-135-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.6M Sep  1 13:54 gen-word-1350-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.6M Sep  1 14:30 gen-word-1350-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.6M Sep  1 13:54 gen-word-1355-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.6M Sep  1 14:30 gen-word-1355-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.6M Sep  1 13:54 gen-word-1360-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.7M Sep  1 14:30 gen-word-1360-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.7M Sep  1 13:54 gen-word-1365-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.7M Sep  1 14:30 gen-word-1365-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.7M Sep  1 13:54 gen-word-1370-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.7M Sep  1 14:30 gen-word-1370-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.7M Sep  1 13:54 gen-word-1375-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.7M Sep  1 14:30 gen-word-1375-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.7M Sep  1 13:54 gen-word-1380-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.7M Sep  1 14:30 gen-word-1380-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.7M Sep  1 13:54 gen-word-1385-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.7M Sep  1 14:30 gen-word-1385-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.7M Sep  1 13:54 gen-word-1390-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.7M Sep  1 14:30 gen-word-1390-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.7M Sep  1 13:54 gen-word-1395-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.7M Sep  1 14:30 gen-word-1395-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  145K Sep  1 13:54 gen-word-140-count.jsonl\n"
+      "-rw-r--r--  1 root root  148K Sep  1 14:30 gen-word-140-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.7M Sep  1 13:54 gen-word-1400-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.7M Sep  1 14:30 gen-word-1400-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.7M Sep  1 13:54 gen-word-1405-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.7M Sep  1 14:30 gen-word-1405-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.7M Sep  1 13:54 gen-word-1410-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.7M Sep  1 14:30 gen-word-1410-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.8M Sep  1 13:54 gen-word-1415-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.8M Sep  1 14:30 gen-word-1415-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.8M Sep  1 13:54 gen-word-1420-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.8M Sep  1 14:30 gen-word-1420-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.8M Sep  1 13:54 gen-word-1425-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.8M Sep  1 14:30 gen-word-1425-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.8M Sep  1 13:54 gen-word-1430-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.8M Sep  1 14:30 gen-word-1430-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.8M Sep  1 13:54 gen-word-1435-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.8M Sep  1 14:30 gen-word-1435-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.8M Sep  1 13:54 gen-word-1440-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.8M Sep  1 14:30 gen-word-1440-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.8M Sep  1 13:54 gen-word-1445-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.8M Sep  1 14:30 gen-word-1445-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  150K Sep  1 13:54 gen-word-145-count.jsonl\n"
+      "-rw-r--r--  1 root root  152K Sep  1 14:30 gen-word-145-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.8M Sep  1 13:54 gen-word-1450-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.8M Sep  1 14:30 gen-word-1450-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.8M Sep  1 13:54 gen-word-1455-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.8M Sep  1 14:30 gen-word-1455-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.8M Sep  1 13:54 gen-word-1460-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.9M Sep  1 14:30 gen-word-1460-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.8M Sep  1 13:54 gen-word-1465-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.8M Sep  1 14:30 gen-word-1465-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.8M Sep  1 13:54 gen-word-1470-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.8M Sep  1 14:30 gen-word-1470-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.9M Sep  1 13:54 gen-word-1475-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.9M Sep  1 14:30 gen-word-1475-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.9M Sep  1 13:54 gen-word-1480-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.9M Sep  1 14:30 gen-word-1480-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.9M Sep  1 13:54 gen-word-1485-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.9M Sep  1 14:30 gen-word-1485-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.9M Sep  1 13:54 gen-word-1490-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.9M Sep  1 14:30 gen-word-1490-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.9M Sep  1 13:54 gen-word-1495-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.9M Sep  1 14:30 gen-word-1495-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   25K Sep  1 13:54 gen-word-15-count.jsonl\n"
+      "-rw-r--r--  1 root root   24K Sep  1 14:30 gen-word-15-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  160K Sep  1 13:54 gen-word-150-count.jsonl\n"
+      "-rw-r--r--  1 root root  157K Sep  1 14:30 gen-word-150-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.9M Sep  1 13:54 gen-word-1500-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.9M Sep  1 14:30 gen-word-1500-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.9M Sep  1 13:54 gen-word-1505-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.9M Sep  1 14:30 gen-word-1505-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.9M Sep  1 13:54 gen-word-1510-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.9M Sep  1 14:30 gen-word-1510-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.9M Sep  1 13:54 gen-word-1515-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.9M Sep  1 14:30 gen-word-1515-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.9M Sep  1 13:54 gen-word-1520-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.0M Sep  1 14:30 gen-word-1520-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.0M Sep  1 13:54 gen-word-1525-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.0M Sep  1 14:30 gen-word-1525-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.0M Sep  1 13:54 gen-word-1530-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.0M Sep  1 14:30 gen-word-1530-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.0M Sep  1 13:54 gen-word-1535-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.0M Sep  1 14:30 gen-word-1535-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.0M Sep  1 13:54 gen-word-1540-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.0M Sep  1 14:30 gen-word-1540-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.0M Sep  1 13:54 gen-word-1545-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.0M Sep  1 14:30 gen-word-1545-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  163K Sep  1 13:54 gen-word-155-count.jsonl\n"
+      "-rw-r--r--  1 root root  160K Sep  1 14:30 gen-word-155-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.0M Sep  1 13:54 gen-word-1550-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.0M Sep  1 14:30 gen-word-1550-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.0M Sep  1 13:54 gen-word-1555-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.0M Sep  1 14:30 gen-word-1555-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.0M Sep  1 13:54 gen-word-1560-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.0M Sep  1 14:30 gen-word-1560-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.1M Sep  1 13:54 gen-word-1565-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.0M Sep  1 14:30 gen-word-1565-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.1M Sep  1 13:54 gen-word-1570-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.1M Sep  1 14:30 gen-word-1570-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.0M Sep  1 13:54 gen-word-1575-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.1M Sep  1 14:30 gen-word-1575-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.1M Sep  1 13:54 gen-word-1580-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.1M Sep  1 14:30 gen-word-1580-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.1M Sep  1 13:54 gen-word-1585-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.1M Sep  1 14:30 gen-word-1585-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.1M Sep  1 13:54 gen-word-1590-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.1M Sep  1 14:30 gen-word-1590-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.1M Sep  1 13:54 gen-word-1595-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.1M Sep  1 14:30 gen-word-1595-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  163K Sep  1 13:54 gen-word-160-count.jsonl\n"
+      "-rw-r--r--  1 root root  166K Sep  1 14:30 gen-word-160-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.1M Sep  1 13:54 gen-word-1600-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.1M Sep  1 14:30 gen-word-1600-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.1M Sep  1 13:54 gen-word-1605-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.1M Sep  1 14:30 gen-word-1605-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.1M Sep  1 13:54 gen-word-1610-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.1M Sep  1 14:30 gen-word-1610-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.1M Sep  1 13:54 gen-word-1615-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.1M Sep  1 14:30 gen-word-1615-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.1M Sep  1 13:54 gen-word-1620-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.2M Sep  1 14:30 gen-word-1620-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.2M Sep  1 13:54 gen-word-1625-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.1M Sep  1 14:30 gen-word-1625-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.2M Sep  1 13:54 gen-word-1630-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.1M Sep  1 14:30 gen-word-1630-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.2M Sep  1 13:54 gen-word-1635-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.2M Sep  1 14:30 gen-word-1635-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.2M Sep  1 13:54 gen-word-1640-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.2M Sep  1 14:30 gen-word-1640-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.2M Sep  1 13:54 gen-word-1645-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.2M Sep  1 14:30 gen-word-1645-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  170K Sep  1 13:54 gen-word-165-count.jsonl\n"
+      "-rw-r--r--  1 root root  171K Sep  1 14:30 gen-word-165-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.2M Sep  1 13:54 gen-word-1650-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.2M Sep  1 14:30 gen-word-1650-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.2M Sep  1 13:54 gen-word-1655-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.2M Sep  1 14:30 gen-word-1655-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.2M Sep  1 13:54 gen-word-1660-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.2M Sep  1 14:30 gen-word-1660-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.2M Sep  1 13:54 gen-word-1665-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.2M Sep  1 14:30 gen-word-1665-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.2M Sep  1 13:54 gen-word-1670-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.2M Sep  1 14:30 gen-word-1670-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.3M Sep  1 13:54 gen-word-1675-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.2M Sep  1 14:30 gen-word-1675-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.3M Sep  1 13:54 gen-word-1680-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.2M Sep  1 14:30 gen-word-1680-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.3M Sep  1 13:54 gen-word-1685-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.3M Sep  1 14:30 gen-word-1685-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.3M Sep  1 13:54 gen-word-1690-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.3M Sep  1 14:30 gen-word-1690-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.3M Sep  1 13:54 gen-word-1695-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.3M Sep  1 14:30 gen-word-1695-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  172K Sep  1 13:54 gen-word-170-count.jsonl\n"
+      "-rw-r--r--  1 root root  179K Sep  1 14:30 gen-word-170-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.3M Sep  1 13:54 gen-word-1700-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.3M Sep  1 14:30 gen-word-1700-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.3M Sep  1 13:54 gen-word-1705-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.3M Sep  1 14:30 gen-word-1705-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.3M Sep  1 13:54 gen-word-1710-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.3M Sep  1 14:30 gen-word-1710-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.3M Sep  1 13:54 gen-word-1715-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.3M Sep  1 14:30 gen-word-1715-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.3M Sep  1 13:54 gen-word-1720-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.3M Sep  1 14:30 gen-word-1720-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.3M Sep  1 13:54 gen-word-1725-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.4M Sep  1 14:30 gen-word-1725-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.3M Sep  1 13:54 gen-word-1730-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.3M Sep  1 14:30 gen-word-1730-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.4M Sep  1 13:54 gen-word-1735-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.3M Sep  1 14:30 gen-word-1735-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.4M Sep  1 13:54 gen-word-1740-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.4M Sep  1 14:30 gen-word-1740-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.4M Sep  1 13:54 gen-word-1745-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.4M Sep  1 14:30 gen-word-1745-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  179K Sep  1 13:54 gen-word-175-count.jsonl\n"
+      "-rw-r--r--  1 root root  180K Sep  1 14:30 gen-word-175-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.4M Sep  1 13:54 gen-word-1750-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.4M Sep  1 14:30 gen-word-1750-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.4M Sep  1 13:54 gen-word-1755-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.4M Sep  1 14:30 gen-word-1755-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.4M Sep  1 13:54 gen-word-1760-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.4M Sep  1 14:30 gen-word-1760-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.4M Sep  1 13:54 gen-word-1765-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.4M Sep  1 14:30 gen-word-1765-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.4M Sep  1 13:54 gen-word-1770-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.4M Sep  1 14:30 gen-word-1770-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.4M Sep  1 13:54 gen-word-1775-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.4M Sep  1 14:30 gen-word-1775-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.5M Sep  1 13:54 gen-word-1780-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.5M Sep  1 14:30 gen-word-1780-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.5M Sep  1 13:54 gen-word-1785-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.4M Sep  1 14:30 gen-word-1785-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.4M Sep  1 13:54 gen-word-1790-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.5M Sep  1 14:30 gen-word-1790-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.5M Sep  1 13:54 gen-word-1795-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.5M Sep  1 14:30 gen-word-1795-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  185K Sep  1 13:54 gen-word-180-count.jsonl\n"
+      "-rw-r--r--  1 root root  186K Sep  1 14:30 gen-word-180-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.5M Sep  1 13:54 gen-word-1800-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.5M Sep  1 14:30 gen-word-1800-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.5M Sep  1 13:54 gen-word-1805-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.5M Sep  1 14:30 gen-word-1805-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.5M Sep  1 13:54 gen-word-1810-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.5M Sep  1 14:30 gen-word-1810-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.5M Sep  1 13:54 gen-word-1815-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.5M Sep  1 14:30 gen-word-1815-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.5M Sep  1 13:54 gen-word-1820-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.5M Sep  1 14:30 gen-word-1820-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.5M Sep  1 13:54 gen-word-1825-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.5M Sep  1 14:30 gen-word-1825-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.6M Sep  1 13:54 gen-word-1830-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.6M Sep  1 14:30 gen-word-1830-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.6M Sep  1 13:54 gen-word-1835-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.6M Sep  1 14:30 gen-word-1835-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.6M Sep  1 13:54 gen-word-1840-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.6M Sep  1 14:30 gen-word-1840-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.6M Sep  1 13:54 gen-word-1845-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.6M Sep  1 14:30 gen-word-1845-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  193K Sep  1 13:54 gen-word-185-count.jsonl\n"
+      "-rw-r--r--  1 root root  188K Sep  1 14:30 gen-word-185-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.6M Sep  1 13:54 gen-word-1850-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.6M Sep  1 14:30 gen-word-1850-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.6M Sep  1 13:54 gen-word-1855-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.6M Sep  1 14:30 gen-word-1855-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.6M Sep  1 13:54 gen-word-1860-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.6M Sep  1 14:30 gen-word-1860-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.6M Sep  1 13:54 gen-word-1865-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.6M Sep  1 14:30 gen-word-1865-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.6M Sep  1 13:54 gen-word-1870-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.6M Sep  1 14:30 gen-word-1870-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.6M Sep  1 13:54 gen-word-1875-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.6M Sep  1 14:30 gen-word-1875-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.6M Sep  1 13:54 gen-word-1880-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.6M Sep  1 14:30 gen-word-1880-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.6M Sep  1 13:54 gen-word-1885-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.7M Sep  1 14:30 gen-word-1885-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.7M Sep  1 13:54 gen-word-1890-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.6M Sep  1 14:30 gen-word-1890-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.7M Sep  1 13:54 gen-word-1895-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.7M Sep  1 14:30 gen-word-1895-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  200K Sep  1 13:54 gen-word-190-count.jsonl\n"
+      "-rw-r--r--  1 root root  195K Sep  1 14:30 gen-word-190-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.7M Sep  1 13:54 gen-word-1900-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.7M Sep  1 14:30 gen-word-1900-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.7M Sep  1 13:54 gen-word-1905-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.7M Sep  1 14:30 gen-word-1905-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.7M Sep  1 13:54 gen-word-1910-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.7M Sep  1 14:30 gen-word-1910-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.7M Sep  1 13:54 gen-word-1915-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.7M Sep  1 14:30 gen-word-1915-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.7M Sep  1 13:54 gen-word-1920-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.7M Sep  1 14:30 gen-word-1920-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.7M Sep  1 13:54 gen-word-1925-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.7M Sep  1 14:30 gen-word-1925-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.7M Sep  1 13:54 gen-word-1930-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.7M Sep  1 14:30 gen-word-1930-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.7M Sep  1 13:54 gen-word-1935-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.7M Sep  1 14:30 gen-word-1935-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.7M Sep  1 13:54 gen-word-1940-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.8M Sep  1 14:30 gen-word-1940-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.8M Sep  1 13:54 gen-word-1945-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.8M Sep  1 14:30 gen-word-1945-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  202K Sep  1 13:54 gen-word-195-count.jsonl\n"
+      "-rw-r--r--  1 root root  201K Sep  1 14:30 gen-word-195-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.7M Sep  1 13:54 gen-word-1950-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.8M Sep  1 14:30 gen-word-1950-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.8M Sep  1 13:54 gen-word-1955-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.8M Sep  1 14:30 gen-word-1955-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.8M Sep  1 13:54 gen-word-1960-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.8M Sep  1 14:30 gen-word-1960-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.8M Sep  1 13:54 gen-word-1965-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.8M Sep  1 14:30 gen-word-1965-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.8M Sep  1 13:54 gen-word-1970-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.8M Sep  1 14:30 gen-word-1970-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.8M Sep  1 13:54 gen-word-1975-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.8M Sep  1 14:30 gen-word-1975-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.8M Sep  1 13:54 gen-word-1980-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.8M Sep  1 14:30 gen-word-1980-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.9M Sep  1 13:54 gen-word-1985-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.9M Sep  1 14:30 gen-word-1985-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.9M Sep  1 13:54 gen-word-1990-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.8M Sep  1 14:30 gen-word-1990-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.9M Sep  1 13:54 gen-word-1995-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.8M Sep  1 14:30 gen-word-1995-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   31K Sep  1 13:54 gen-word-20-count.jsonl\n"
+      "-rw-r--r--  1 root root   30K Sep  1 14:30 gen-word-20-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  205K Sep  1 13:54 gen-word-200-count.jsonl\n"
+      "-rw-r--r--  1 root root  204K Sep  1 14:30 gen-word-200-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.9M Sep  1 13:54 gen-word-2000-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.9M Sep  1 14:30 gen-word-2000-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.9M Sep  1 13:54 gen-word-2005-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.9M Sep  1 14:30 gen-word-2005-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.9M Sep  1 13:54 gen-word-2010-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.9M Sep  1 14:30 gen-word-2010-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.9M Sep  1 13:54 gen-word-2015-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.9M Sep  1 14:30 gen-word-2015-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.9M Sep  1 13:54 gen-word-2020-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.9M Sep  1 14:30 gen-word-2020-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.9M Sep  1 13:54 gen-word-2025-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.9M Sep  1 14:30 gen-word-2025-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.9M Sep  1 13:54 gen-word-2030-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.9M Sep  1 14:30 gen-word-2030-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.9M Sep  1 13:54 gen-word-2035-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.9M Sep  1 14:30 gen-word-2035-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  3.9M Sep  1 13:54 gen-word-2040-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.0M Sep  1 14:30 gen-word-2040-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.0M Sep  1 13:54 gen-word-2045-count.jsonl\n"
+      "-rw-r--r--  1 root root  3.9M Sep  1 14:30 gen-word-2045-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  204K Sep  1 13:54 gen-word-205-count.jsonl\n"
+      "-rw-r--r--  1 root root  209K Sep  1 14:30 gen-word-205-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.0M Sep  1 13:54 gen-word-2050-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.0M Sep  1 14:30 gen-word-2050-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.0M Sep  1 13:54 gen-word-2055-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.0M Sep  1 14:30 gen-word-2055-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.0M Sep  1 13:54 gen-word-2060-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.0M Sep  1 14:30 gen-word-2060-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.0M Sep  1 13:54 gen-word-2065-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.0M Sep  1 14:30 gen-word-2065-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.0M Sep  1 13:54 gen-word-2070-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.0M Sep  1 14:30 gen-word-2070-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.0M Sep  1 13:54 gen-word-2075-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.0M Sep  1 14:30 gen-word-2075-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.0M Sep  1 13:54 gen-word-2080-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.0M Sep  1 14:30 gen-word-2080-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.0M Sep  1 13:54 gen-word-2085-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.0M Sep  1 14:30 gen-word-2085-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.0M Sep  1 13:54 gen-word-2090-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.0M Sep  1 14:30 gen-word-2090-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.1M Sep  1 13:54 gen-word-2095-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.0M Sep  1 14:30 gen-word-2095-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  214K Sep  1 13:54 gen-word-210-count.jsonl\n"
+      "-rw-r--r--  1 root root  218K Sep  1 14:30 gen-word-210-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.1M Sep  1 13:54 gen-word-2100-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.1M Sep  1 14:30 gen-word-2100-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.1M Sep  1 13:54 gen-word-2105-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.1M Sep  1 14:30 gen-word-2105-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.1M Sep  1 13:54 gen-word-2110-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.1M Sep  1 14:30 gen-word-2110-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.1M Sep  1 13:54 gen-word-2115-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.1M Sep  1 14:30 gen-word-2115-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.1M Sep  1 13:54 gen-word-2120-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.1M Sep  1 14:30 gen-word-2120-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.1M Sep  1 13:54 gen-word-2125-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.1M Sep  1 14:30 gen-word-2125-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.1M Sep  1 13:54 gen-word-2130-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.1M Sep  1 14:30 gen-word-2130-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.1M Sep  1 13:54 gen-word-2135-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.1M Sep  1 14:30 gen-word-2135-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.1M Sep  1 13:54 gen-word-2140-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.1M Sep  1 14:30 gen-word-2140-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.1M Sep  1 13:54 gen-word-2145-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.2M Sep  1 14:30 gen-word-2145-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  217K Sep  1 13:54 gen-word-215-count.jsonl\n"
+      "-rw-r--r--  1 root root  221K Sep  1 14:30 gen-word-215-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.2M Sep  1 13:54 gen-word-2150-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.2M Sep  1 14:30 gen-word-2150-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.2M Sep  1 13:54 gen-word-2155-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.1M Sep  1 14:30 gen-word-2155-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.2M Sep  1 13:54 gen-word-2160-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.2M Sep  1 14:30 gen-word-2160-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.2M Sep  1 13:54 gen-word-2165-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.2M Sep  1 14:30 gen-word-2165-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.2M Sep  1 13:54 gen-word-2170-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.2M Sep  1 14:30 gen-word-2170-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.2M Sep  1 13:54 gen-word-2175-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.2M Sep  1 14:30 gen-word-2175-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.2M Sep  1 13:54 gen-word-2180-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.2M Sep  1 14:30 gen-word-2180-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.2M Sep  1 13:54 gen-word-2185-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.2M Sep  1 14:30 gen-word-2185-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.2M Sep  1 13:54 gen-word-2190-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.2M Sep  1 14:30 gen-word-2190-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.3M Sep  1 13:54 gen-word-2195-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.2M Sep  1 14:30 gen-word-2195-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  222K Sep  1 13:54 gen-word-220-count.jsonl\n"
+      "-rw-r--r--  1 root root  228K Sep  1 14:30 gen-word-220-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.2M Sep  1 13:54 gen-word-2200-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.3M Sep  1 14:30 gen-word-2200-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.3M Sep  1 13:54 gen-word-2205-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.3M Sep  1 14:30 gen-word-2205-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.3M Sep  1 13:54 gen-word-2210-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.3M Sep  1 14:30 gen-word-2210-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.3M Sep  1 13:54 gen-word-2215-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.2M Sep  1 14:30 gen-word-2215-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.3M Sep  1 13:54 gen-word-2220-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.3M Sep  1 14:30 gen-word-2220-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.3M Sep  1 13:54 gen-word-2225-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.3M Sep  1 14:30 gen-word-2225-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.3M Sep  1 13:54 gen-word-2230-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.3M Sep  1 14:30 gen-word-2230-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.3M Sep  1 13:54 gen-word-2235-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.3M Sep  1 14:30 gen-word-2235-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.3M Sep  1 13:54 gen-word-2240-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.3M Sep  1 14:30 gen-word-2240-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.3M Sep  1 13:54 gen-word-2245-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.3M Sep  1 14:30 gen-word-2245-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  229K Sep  1 13:54 gen-word-225-count.jsonl\n"
+      "-rw-r--r--  1 root root  230K Sep  1 14:30 gen-word-225-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.4M Sep  1 13:54 gen-word-2250-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.4M Sep  1 14:30 gen-word-2250-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.4M Sep  1 13:54 gen-word-2255-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.4M Sep  1 14:30 gen-word-2255-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.4M Sep  1 13:54 gen-word-2260-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.3M Sep  1 14:30 gen-word-2260-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.4M Sep  1 13:54 gen-word-2265-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.4M Sep  1 14:30 gen-word-2265-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.4M Sep  1 13:54 gen-word-2270-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.4M Sep  1 14:30 gen-word-2270-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.4M Sep  1 13:54 gen-word-2275-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.4M Sep  1 14:30 gen-word-2275-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.4M Sep  1 13:54 gen-word-2280-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.4M Sep  1 14:30 gen-word-2280-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.4M Sep  1 13:54 gen-word-2285-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.4M Sep  1 14:30 gen-word-2285-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.4M Sep  1 13:54 gen-word-2290-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.4M Sep  1 14:30 gen-word-2290-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.4M Sep  1 13:54 gen-word-2295-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.4M Sep  1 14:30 gen-word-2295-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  226K Sep  1 13:54 gen-word-230-count.jsonl\n"
+      "-rw-r--r--  1 root root  236K Sep  1 14:30 gen-word-230-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.4M Sep  1 13:54 gen-word-2300-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.4M Sep  1 14:30 gen-word-2300-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.5M Sep  1 13:54 gen-word-2305-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.4M Sep  1 14:30 gen-word-2305-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.5M Sep  1 13:54 gen-word-2310-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.5M Sep  1 14:30 gen-word-2310-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.5M Sep  1 13:54 gen-word-2315-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.5M Sep  1 14:30 gen-word-2315-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.5M Sep  1 13:54 gen-word-2320-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.5M Sep  1 14:30 gen-word-2320-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.5M Sep  1 13:54 gen-word-2325-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.5M Sep  1 14:30 gen-word-2325-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.5M Sep  1 13:54 gen-word-2330-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.5M Sep  1 14:30 gen-word-2330-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.5M Sep  1 13:54 gen-word-2335-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.5M Sep  1 14:30 gen-word-2335-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.5M Sep  1 13:54 gen-word-2340-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.5M Sep  1 14:30 gen-word-2340-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.5M Sep  1 13:54 gen-word-2345-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.5M Sep  1 14:30 gen-word-2345-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  240K Sep  1 13:54 gen-word-235-count.jsonl\n"
+      "-rw-r--r--  1 root root  240K Sep  1 14:30 gen-word-235-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.5M Sep  1 13:54 gen-word-2350-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.5M Sep  1 14:30 gen-word-2350-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.5M Sep  1 13:54 gen-word-2355-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.5M Sep  1 14:30 gen-word-2355-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.6M Sep  1 13:54 gen-word-2360-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.6M Sep  1 14:30 gen-word-2360-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.5M Sep  1 13:54 gen-word-2365-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.6M Sep  1 14:30 gen-word-2365-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.6M Sep  1 13:54 gen-word-2370-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.6M Sep  1 14:30 gen-word-2370-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.6M Sep  1 13:54 gen-word-2375-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.6M Sep  1 14:30 gen-word-2375-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.6M Sep  1 13:54 gen-word-2380-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.6M Sep  1 14:30 gen-word-2380-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.6M Sep  1 13:54 gen-word-2385-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.6M Sep  1 14:30 gen-word-2385-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.6M Sep  1 13:54 gen-word-2390-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.6M Sep  1 14:30 gen-word-2390-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.6M Sep  1 13:54 gen-word-2395-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.6M Sep  1 14:30 gen-word-2395-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  244K Sep  1 13:54 gen-word-240-count.jsonl\n"
+      "-rw-r--r--  1 root root  249K Sep  1 14:30 gen-word-240-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.6M Sep  1 13:54 gen-word-2400-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.6M Sep  1 14:30 gen-word-2400-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.6M Sep  1 13:54 gen-word-2405-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.6M Sep  1 14:30 gen-word-2405-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.6M Sep  1 13:54 gen-word-2410-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.6M Sep  1 14:30 gen-word-2410-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.7M Sep  1 13:54 gen-word-2415-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.7M Sep  1 14:30 gen-word-2415-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.7M Sep  1 13:54 gen-word-2420-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.7M Sep  1 14:30 gen-word-2420-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.7M Sep  1 13:54 gen-word-2425-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.7M Sep  1 14:30 gen-word-2425-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.7M Sep  1 13:54 gen-word-2430-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.7M Sep  1 14:30 gen-word-2430-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.7M Sep  1 13:54 gen-word-2435-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.7M Sep  1 14:30 gen-word-2435-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.7M Sep  1 13:54 gen-word-2440-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.7M Sep  1 14:30 gen-word-2440-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.7M Sep  1 13:54 gen-word-2445-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.7M Sep  1 14:30 gen-word-2445-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  251K Sep  1 13:54 gen-word-245-count.jsonl\n"
+      "-rw-r--r--  1 root root  248K Sep  1 14:30 gen-word-245-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.7M Sep  1 13:54 gen-word-2450-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.7M Sep  1 14:30 gen-word-2450-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.7M Sep  1 13:54 gen-word-2455-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.7M Sep  1 14:30 gen-word-2455-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.7M Sep  1 13:54 gen-word-2460-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.7M Sep  1 14:30 gen-word-2460-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.8M Sep  1 13:54 gen-word-2465-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.8M Sep  1 14:30 gen-word-2465-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.8M Sep  1 13:54 gen-word-2470-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.8M Sep  1 14:30 gen-word-2470-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.8M Sep  1 13:54 gen-word-2475-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.8M Sep  1 14:30 gen-word-2475-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.8M Sep  1 13:54 gen-word-2480-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.8M Sep  1 14:30 gen-word-2480-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.8M Sep  1 13:54 gen-word-2485-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.8M Sep  1 14:30 gen-word-2485-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.8M Sep  1 13:54 gen-word-2490-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.8M Sep  1 14:30 gen-word-2490-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.8M Sep  1 13:54 gen-word-2495-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.8M Sep  1 14:30 gen-word-2495-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   34K Sep  1 13:54 gen-word-25-count.jsonl\n"
+      "-rw-r--r--  1 root root   34K Sep  1 14:30 gen-word-25-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  250K Sep  1 13:54 gen-word-250-count.jsonl\n"
+      "-rw-r--r--  1 root root  255K Sep  1 14:30 gen-word-250-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.8M Sep  1 13:54 gen-word-2500-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.8M Sep  1 14:30 gen-word-2500-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.8M Sep  1 13:54 gen-word-2505-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.8M Sep  1 14:30 gen-word-2505-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.8M Sep  1 13:54 gen-word-2510-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.8M Sep  1 14:30 gen-word-2510-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.8M Sep  1 13:54 gen-word-2515-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.8M Sep  1 14:30 gen-word-2515-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.9M Sep  1 13:54 gen-word-2520-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.9M Sep  1 14:30 gen-word-2520-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.9M Sep  1 13:54 gen-word-2525-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.9M Sep  1 14:30 gen-word-2525-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.9M Sep  1 13:54 gen-word-2530-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.9M Sep  1 14:30 gen-word-2530-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.9M Sep  1 13:54 gen-word-2535-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.9M Sep  1 14:30 gen-word-2535-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.9M Sep  1 13:54 gen-word-2540-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.9M Sep  1 14:30 gen-word-2540-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.9M Sep  1 13:54 gen-word-2545-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.9M Sep  1 14:30 gen-word-2545-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  260K Sep  1 13:54 gen-word-255-count.jsonl\n"
+      "-rw-r--r--  1 root root  259K Sep  1 14:30 gen-word-255-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.9M Sep  1 13:54 gen-word-2550-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.9M Sep  1 14:30 gen-word-2550-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.9M Sep  1 13:54 gen-word-2555-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.9M Sep  1 14:30 gen-word-2555-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.9M Sep  1 13:54 gen-word-2560-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.9M Sep  1 14:30 gen-word-2560-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.0M Sep  1 13:54 gen-word-2565-count.jsonl\n"
+      "-rw-r--r--  1 root root  4.9M Sep  1 14:30 gen-word-2565-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  4.9M Sep  1 13:54 gen-word-2570-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.0M Sep  1 14:30 gen-word-2570-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.0M Sep  1 13:54 gen-word-2575-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.0M Sep  1 14:30 gen-word-2575-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.0M Sep  1 13:54 gen-word-2580-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.0M Sep  1 14:30 gen-word-2580-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.0M Sep  1 13:54 gen-word-2585-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.0M Sep  1 14:30 gen-word-2585-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.0M Sep  1 13:54 gen-word-2590-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.0M Sep  1 14:30 gen-word-2590-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.0M Sep  1 13:54 gen-word-2595-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.0M Sep  1 14:30 gen-word-2595-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  259K Sep  1 13:54 gen-word-260-count.jsonl\n"
+      "-rw-r--r--  1 root root  266K Sep  1 14:30 gen-word-260-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.0M Sep  1 13:54 gen-word-2600-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.0M Sep  1 14:30 gen-word-2600-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.0M Sep  1 13:54 gen-word-2605-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.0M Sep  1 14:30 gen-word-2605-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.0M Sep  1 13:54 gen-word-2610-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.0M Sep  1 14:30 gen-word-2610-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.0M Sep  1 13:54 gen-word-2615-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.0M Sep  1 14:30 gen-word-2615-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.0M Sep  1 13:54 gen-word-2620-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.1M Sep  1 14:30 gen-word-2620-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.1M Sep  1 13:54 gen-word-2625-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.0M Sep  1 14:30 gen-word-2625-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.1M Sep  1 13:54 gen-word-2630-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.1M Sep  1 14:30 gen-word-2630-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.1M Sep  1 13:54 gen-word-2635-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.1M Sep  1 14:30 gen-word-2635-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.1M Sep  1 13:54 gen-word-2640-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.1M Sep  1 14:30 gen-word-2640-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.1M Sep  1 13:54 gen-word-2645-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.1M Sep  1 14:30 gen-word-2645-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  271K Sep  1 13:54 gen-word-265-count.jsonl\n"
+      "-rw-r--r--  1 root root  269K Sep  1 14:30 gen-word-265-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.1M Sep  1 13:54 gen-word-2650-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.1M Sep  1 14:30 gen-word-2650-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.1M Sep  1 13:54 gen-word-2655-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.1M Sep  1 14:30 gen-word-2655-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.1M Sep  1 13:54 gen-word-2660-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.1M Sep  1 14:30 gen-word-2660-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.1M Sep  1 13:54 gen-word-2665-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.1M Sep  1 14:30 gen-word-2665-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.1M Sep  1 13:54 gen-word-2670-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.1M Sep  1 14:30 gen-word-2670-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.1M Sep  1 13:54 gen-word-2675-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.1M Sep  1 14:30 gen-word-2675-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.2M Sep  1 13:54 gen-word-2680-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.2M Sep  1 14:30 gen-word-2680-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.2M Sep  1 13:54 gen-word-2685-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.2M Sep  1 14:30 gen-word-2685-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.2M Sep  1 13:54 gen-word-2690-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.2M Sep  1 14:30 gen-word-2690-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.2M Sep  1 13:54 gen-word-2695-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.2M Sep  1 14:30 gen-word-2695-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  272K Sep  1 13:54 gen-word-270-count.jsonl\n"
+      "-rw-r--r--  1 root root  276K Sep  1 14:30 gen-word-270-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.2M Sep  1 13:54 gen-word-2700-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.2M Sep  1 14:30 gen-word-2700-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.2M Sep  1 13:54 gen-word-2705-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.2M Sep  1 14:30 gen-word-2705-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.2M Sep  1 13:54 gen-word-2710-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.2M Sep  1 14:30 gen-word-2710-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.2M Sep  1 13:54 gen-word-2715-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.2M Sep  1 14:30 gen-word-2715-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.2M Sep  1 13:54 gen-word-2720-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.2M Sep  1 14:30 gen-word-2720-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.2M Sep  1 13:54 gen-word-2725-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.2M Sep  1 14:30 gen-word-2725-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.3M Sep  1 13:54 gen-word-2730-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.3M Sep  1 14:30 gen-word-2730-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.3M Sep  1 13:54 gen-word-2735-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.3M Sep  1 14:30 gen-word-2735-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.2M Sep  1 13:54 gen-word-2740-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.3M Sep  1 14:30 gen-word-2740-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.3M Sep  1 13:54 gen-word-2745-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.3M Sep  1 14:30 gen-word-2745-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  280K Sep  1 13:54 gen-word-275-count.jsonl\n"
+      "-rw-r--r--  1 root root  277K Sep  1 14:30 gen-word-275-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.3M Sep  1 13:54 gen-word-2750-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.3M Sep  1 14:30 gen-word-2750-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.3M Sep  1 13:54 gen-word-2755-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.3M Sep  1 14:30 gen-word-2755-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.3M Sep  1 13:54 gen-word-2760-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.3M Sep  1 14:30 gen-word-2760-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.3M Sep  1 13:54 gen-word-2765-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.3M Sep  1 14:30 gen-word-2765-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.3M Sep  1 13:54 gen-word-2770-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.3M Sep  1 14:30 gen-word-2770-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.4M Sep  1 13:54 gen-word-2775-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.3M Sep  1 14:30 gen-word-2775-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.4M Sep  1 13:54 gen-word-2780-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.4M Sep  1 14:30 gen-word-2780-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.4M Sep  1 13:54 gen-word-2785-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.4M Sep  1 14:30 gen-word-2785-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.4M Sep  1 13:54 gen-word-2790-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.3M Sep  1 14:30 gen-word-2790-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.4M Sep  1 13:54 gen-word-2795-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.4M Sep  1 14:30 gen-word-2795-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  282K Sep  1 13:54 gen-word-280-count.jsonl\n"
+      "-rw-r--r--  1 root root  281K Sep  1 14:30 gen-word-280-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.4M Sep  1 13:54 gen-word-2800-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.4M Sep  1 14:30 gen-word-2800-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.4M Sep  1 13:54 gen-word-2805-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.4M Sep  1 14:30 gen-word-2805-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.4M Sep  1 13:54 gen-word-2810-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.4M Sep  1 14:30 gen-word-2810-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.4M Sep  1 13:54 gen-word-2815-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.4M Sep  1 14:30 gen-word-2815-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.4M Sep  1 13:54 gen-word-2820-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.4M Sep  1 14:30 gen-word-2820-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.4M Sep  1 13:54 gen-word-2825-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.4M Sep  1 14:30 gen-word-2825-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.4M Sep  1 13:54 gen-word-2830-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.4M Sep  1 14:30 gen-word-2830-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.4M Sep  1 13:54 gen-word-2835-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.5M Sep  1 14:30 gen-word-2835-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.4M Sep  1 13:54 gen-word-2840-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.5M Sep  1 14:30 gen-word-2840-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.5M Sep  1 13:54 gen-word-2845-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.5M Sep  1 14:30 gen-word-2845-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  284K Sep  1 13:54 gen-word-285-count.jsonl\n"
+      "-rw-r--r--  1 root root  286K Sep  1 14:30 gen-word-285-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.5M Sep  1 13:54 gen-word-2850-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.5M Sep  1 14:30 gen-word-2850-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.5M Sep  1 13:54 gen-word-2855-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.5M Sep  1 14:30 gen-word-2855-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.5M Sep  1 13:54 gen-word-2860-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.5M Sep  1 14:30 gen-word-2860-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.5M Sep  1 13:54 gen-word-2865-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.5M Sep  1 14:30 gen-word-2865-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.5M Sep  1 13:54 gen-word-2870-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.5M Sep  1 14:30 gen-word-2870-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.5M Sep  1 13:54 gen-word-2875-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.5M Sep  1 14:30 gen-word-2875-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.5M Sep  1 13:54 gen-word-2880-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.6M Sep  1 14:30 gen-word-2880-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.5M Sep  1 13:54 gen-word-2885-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.5M Sep  1 14:30 gen-word-2885-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.5M Sep  1 13:54 gen-word-2890-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.5M Sep  1 14:30 gen-word-2890-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.6M Sep  1 13:54 gen-word-2895-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.5M Sep  1 14:30 gen-word-2895-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  294K Sep  1 13:54 gen-word-290-count.jsonl\n"
+      "-rw-r--r--  1 root root  295K Sep  1 14:30 gen-word-290-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.6M Sep  1 13:54 gen-word-2900-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.6M Sep  1 14:30 gen-word-2900-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.6M Sep  1 13:54 gen-word-2905-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.6M Sep  1 14:30 gen-word-2905-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.6M Sep  1 13:54 gen-word-2910-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.6M Sep  1 14:30 gen-word-2910-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.6M Sep  1 13:54 gen-word-2915-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.6M Sep  1 14:30 gen-word-2915-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.6M Sep  1 13:54 gen-word-2920-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.6M Sep  1 14:30 gen-word-2920-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.6M Sep  1 13:54 gen-word-2925-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.6M Sep  1 14:30 gen-word-2925-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.6M Sep  1 13:54 gen-word-2930-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.6M Sep  1 14:30 gen-word-2930-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.7M Sep  1 13:54 gen-word-2935-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.6M Sep  1 14:30 gen-word-2935-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.7M Sep  1 13:54 gen-word-2940-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.7M Sep  1 14:30 gen-word-2940-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.7M Sep  1 13:54 gen-word-2945-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.6M Sep  1 14:30 gen-word-2945-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  299K Sep  1 13:54 gen-word-295-count.jsonl\n"
+      "-rw-r--r--  1 root root  295K Sep  1 14:30 gen-word-295-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.7M Sep  1 13:54 gen-word-2950-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.7M Sep  1 14:30 gen-word-2950-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.7M Sep  1 13:54 gen-word-2955-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.7M Sep  1 14:30 gen-word-2955-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.7M Sep  1 13:54 gen-word-2960-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.7M Sep  1 14:30 gen-word-2960-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.7M Sep  1 13:54 gen-word-2965-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.7M Sep  1 14:30 gen-word-2965-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.7M Sep  1 13:54 gen-word-2970-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.7M Sep  1 14:30 gen-word-2970-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.7M Sep  1 13:54 gen-word-2975-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.7M Sep  1 14:30 gen-word-2975-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.8M Sep  1 13:54 gen-word-2980-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.7M Sep  1 14:30 gen-word-2980-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.7M Sep  1 13:54 gen-word-2985-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.7M Sep  1 14:30 gen-word-2985-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.7M Sep  1 13:54 gen-word-2990-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.7M Sep  1 14:30 gen-word-2990-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.8M Sep  1 13:54 gen-word-2995-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.8M Sep  1 14:30 gen-word-2995-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   39K Sep  1 13:54 gen-word-30-count.jsonl\n"
+      "-rw-r--r--  1 root root   39K Sep  1 14:30 gen-word-30-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  300K Sep  1 13:54 gen-word-300-count.jsonl\n"
+      "-rw-r--r--  1 root root  303K Sep  1 14:30 gen-word-300-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.8M Sep  1 13:54 gen-word-3000-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.8M Sep  1 14:30 gen-word-3000-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.8M Sep  1 13:54 gen-word-3005-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.8M Sep  1 14:30 gen-word-3005-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.8M Sep  1 13:54 gen-word-3010-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.8M Sep  1 14:30 gen-word-3010-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.8M Sep  1 13:54 gen-word-3015-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.8M Sep  1 14:30 gen-word-3015-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.8M Sep  1 13:54 gen-word-3020-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.8M Sep  1 14:30 gen-word-3020-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.8M Sep  1 13:54 gen-word-3025-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.8M Sep  1 14:30 gen-word-3025-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.8M Sep  1 13:54 gen-word-3030-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.8M Sep  1 14:30 gen-word-3030-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.8M Sep  1 13:54 gen-word-3035-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.8M Sep  1 14:30 gen-word-3035-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.9M Sep  1 13:54 gen-word-3040-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.8M Sep  1 14:30 gen-word-3040-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.8M Sep  1 13:54 gen-word-3045-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.8M Sep  1 14:30 gen-word-3045-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  300K Sep  1 13:54 gen-word-305-count.jsonl\n"
+      "-rw-r--r--  1 root root  312K Sep  1 14:30 gen-word-305-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.8M Sep  1 13:54 gen-word-3050-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.9M Sep  1 14:30 gen-word-3050-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.9M Sep  1 13:54 gen-word-3055-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.9M Sep  1 14:30 gen-word-3055-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.9M Sep  1 13:54 gen-word-3060-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.9M Sep  1 14:30 gen-word-3060-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.9M Sep  1 13:54 gen-word-3065-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.9M Sep  1 14:30 gen-word-3065-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.9M Sep  1 13:54 gen-word-3070-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.9M Sep  1 14:30 gen-word-3070-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.9M Sep  1 13:54 gen-word-3075-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.9M Sep  1 14:30 gen-word-3075-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.9M Sep  1 13:54 gen-word-3080-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.9M Sep  1 14:30 gen-word-3080-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.9M Sep  1 13:54 gen-word-3085-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.9M Sep  1 14:30 gen-word-3085-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  5.9M Sep  1 13:54 gen-word-3090-count.jsonl\n"
+      "-rw-r--r--  1 root root  5.9M Sep  1 14:30 gen-word-3090-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.0M Sep  1 13:54 gen-word-3095-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.0M Sep  1 14:30 gen-word-3095-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  315K Sep  1 13:54 gen-word-310-count.jsonl\n"
+      "-rw-r--r--  1 root root  310K Sep  1 14:30 gen-word-310-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.0M Sep  1 13:54 gen-word-3100-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.0M Sep  1 14:30 gen-word-3100-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.0M Sep  1 13:54 gen-word-3105-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.0M Sep  1 14:30 gen-word-3105-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.0M Sep  1 13:54 gen-word-3110-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.0M Sep  1 14:30 gen-word-3110-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.0M Sep  1 13:54 gen-word-3115-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.0M Sep  1 14:30 gen-word-3115-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.0M Sep  1 13:54 gen-word-3120-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.0M Sep  1 14:30 gen-word-3120-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.0M Sep  1 13:54 gen-word-3125-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.0M Sep  1 14:30 gen-word-3125-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.0M Sep  1 13:54 gen-word-3130-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.0M Sep  1 14:30 gen-word-3130-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.0M Sep  1 13:54 gen-word-3135-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.0M Sep  1 14:30 gen-word-3135-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.1M Sep  1 13:54 gen-word-3140-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.0M Sep  1 14:30 gen-word-3140-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.0M Sep  1 13:54 gen-word-3145-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.0M Sep  1 14:30 gen-word-3145-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  313K Sep  1 13:54 gen-word-315-count.jsonl\n"
+      "-rw-r--r--  1 root root  315K Sep  1 14:30 gen-word-315-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.0M Sep  1 13:54 gen-word-3150-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.1M Sep  1 14:30 gen-word-3150-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.1M Sep  1 13:54 gen-word-3155-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.1M Sep  1 14:30 gen-word-3155-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.1M Sep  1 13:54 gen-word-3160-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.1M Sep  1 14:30 gen-word-3160-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.1M Sep  1 13:54 gen-word-3165-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.1M Sep  1 14:30 gen-word-3165-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.1M Sep  1 13:54 gen-word-3170-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.1M Sep  1 14:30 gen-word-3170-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.1M Sep  1 13:54 gen-word-3175-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.1M Sep  1 14:30 gen-word-3175-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.1M Sep  1 13:54 gen-word-3180-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.1M Sep  1 14:30 gen-word-3180-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.1M Sep  1 13:54 gen-word-3185-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.1M Sep  1 14:30 gen-word-3185-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.1M Sep  1 13:54 gen-word-3190-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.1M Sep  1 14:30 gen-word-3190-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.1M Sep  1 13:54 gen-word-3195-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.1M Sep  1 14:30 gen-word-3195-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  323K Sep  1 13:54 gen-word-320-count.jsonl\n"
+      "-rw-r--r--  1 root root  316K Sep  1 14:30 gen-word-320-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.1M Sep  1 13:54 gen-word-3200-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.1M Sep  1 14:30 gen-word-3200-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.1M Sep  1 13:54 gen-word-3205-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.2M Sep  1 14:30 gen-word-3205-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.2M Sep  1 13:54 gen-word-3210-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.1M Sep  1 14:30 gen-word-3210-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.2M Sep  1 13:54 gen-word-3215-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.2M Sep  1 14:30 gen-word-3215-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.1M Sep  1 13:54 gen-word-3220-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.2M Sep  1 14:30 gen-word-3220-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.2M Sep  1 13:54 gen-word-3225-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.2M Sep  1 14:30 gen-word-3225-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.2M Sep  1 13:54 gen-word-3230-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.2M Sep  1 14:30 gen-word-3230-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.2M Sep  1 13:54 gen-word-3235-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.2M Sep  1 14:30 gen-word-3235-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.2M Sep  1 13:54 gen-word-3240-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.2M Sep  1 14:30 gen-word-3240-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.2M Sep  1 13:54 gen-word-3245-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.2M Sep  1 14:30 gen-word-3245-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  326K Sep  1 13:54 gen-word-325-count.jsonl\n"
+      "-rw-r--r--  1 root root  324K Sep  1 14:30 gen-word-325-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.2M Sep  1 13:54 gen-word-3250-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.3M Sep  1 14:30 gen-word-3250-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.2M Sep  1 13:54 gen-word-3255-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.3M Sep  1 14:30 gen-word-3255-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.3M Sep  1 13:54 gen-word-3260-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.3M Sep  1 14:30 gen-word-3260-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.3M Sep  1 13:54 gen-word-3265-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.3M Sep  1 14:30 gen-word-3265-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.3M Sep  1 13:54 gen-word-3270-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.3M Sep  1 14:30 gen-word-3270-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.3M Sep  1 13:54 gen-word-3275-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.3M Sep  1 14:30 gen-word-3275-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.3M Sep  1 13:54 gen-word-3280-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.3M Sep  1 14:30 gen-word-3280-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.3M Sep  1 13:54 gen-word-3285-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.3M Sep  1 14:30 gen-word-3285-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.3M Sep  1 13:54 gen-word-3290-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.4M Sep  1 14:30 gen-word-3290-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.3M Sep  1 13:54 gen-word-3295-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.3M Sep  1 14:30 gen-word-3295-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  328K Sep  1 13:54 gen-word-330-count.jsonl\n"
+      "-rw-r--r--  1 root root  336K Sep  1 14:30 gen-word-330-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.3M Sep  1 13:54 gen-word-3300-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.3M Sep  1 14:30 gen-word-3300-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.3M Sep  1 13:54 gen-word-3305-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.3M Sep  1 14:30 gen-word-3305-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.3M Sep  1 13:54 gen-word-3310-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.3M Sep  1 14:30 gen-word-3310-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.3M Sep  1 13:54 gen-word-3315-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.4M Sep  1 14:30 gen-word-3315-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.4M Sep  1 13:54 gen-word-3320-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.4M Sep  1 14:30 gen-word-3320-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.4M Sep  1 13:54 gen-word-3325-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.3M Sep  1 14:30 gen-word-3325-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.4M Sep  1 13:54 gen-word-3330-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.4M Sep  1 14:30 gen-word-3330-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.4M Sep  1 13:54 gen-word-3335-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.4M Sep  1 14:30 gen-word-3335-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.4M Sep  1 13:54 gen-word-3340-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.4M Sep  1 14:30 gen-word-3340-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.4M Sep  1 13:54 gen-word-3345-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.4M Sep  1 14:30 gen-word-3345-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  335K Sep  1 13:54 gen-word-335-count.jsonl\n"
+      "-rw-r--r--  1 root root  340K Sep  1 14:30 gen-word-335-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.4M Sep  1 13:54 gen-word-3350-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.5M Sep  1 14:30 gen-word-3350-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.4M Sep  1 13:54 gen-word-3355-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.4M Sep  1 14:30 gen-word-3355-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.4M Sep  1 13:54 gen-word-3360-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.4M Sep  1 14:30 gen-word-3360-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.5M Sep  1 13:54 gen-word-3365-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.5M Sep  1 14:30 gen-word-3365-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.5M Sep  1 13:54 gen-word-3370-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.4M Sep  1 14:30 gen-word-3370-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.5M Sep  1 13:54 gen-word-3375-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.5M Sep  1 14:30 gen-word-3375-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.5M Sep  1 13:54 gen-word-3380-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.5M Sep  1 14:30 gen-word-3380-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.5M Sep  1 13:54 gen-word-3385-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.5M Sep  1 14:30 gen-word-3385-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.5M Sep  1 13:54 gen-word-3390-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.5M Sep  1 14:30 gen-word-3390-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.5M Sep  1 13:54 gen-word-3395-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.5M Sep  1 14:30 gen-word-3395-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  336K Sep  1 13:54 gen-word-340-count.jsonl\n"
+      "-rw-r--r--  1 root root  347K Sep  1 14:30 gen-word-340-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.5M Sep  1 13:54 gen-word-3400-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.5M Sep  1 14:30 gen-word-3400-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.5M Sep  1 13:54 gen-word-3405-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.5M Sep  1 14:30 gen-word-3405-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.5M Sep  1 13:54 gen-word-3410-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.5M Sep  1 14:30 gen-word-3410-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.6M Sep  1 13:54 gen-word-3415-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.6M Sep  1 14:30 gen-word-3415-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.6M Sep  1 13:54 gen-word-3420-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.5M Sep  1 14:30 gen-word-3420-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.6M Sep  1 13:54 gen-word-3425-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.6M Sep  1 14:30 gen-word-3425-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.6M Sep  1 13:54 gen-word-3430-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.6M Sep  1 14:30 gen-word-3430-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.6M Sep  1 13:54 gen-word-3435-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.6M Sep  1 14:30 gen-word-3435-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.6M Sep  1 13:54 gen-word-3440-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.6M Sep  1 14:30 gen-word-3440-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.6M Sep  1 13:54 gen-word-3445-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.6M Sep  1 14:30 gen-word-3445-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  346K Sep  1 13:54 gen-word-345-count.jsonl\n"
+      "-rw-r--r--  1 root root  350K Sep  1 14:30 gen-word-345-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.6M Sep  1 13:54 gen-word-3450-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.6M Sep  1 14:30 gen-word-3450-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.6M Sep  1 13:54 gen-word-3455-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.6M Sep  1 14:30 gen-word-3455-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.6M Sep  1 13:54 gen-word-3460-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.6M Sep  1 14:30 gen-word-3460-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.6M Sep  1 13:54 gen-word-3465-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.7M Sep  1 14:30 gen-word-3465-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.6M Sep  1 13:54 gen-word-3470-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.7M Sep  1 14:30 gen-word-3470-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.7M Sep  1 13:54 gen-word-3475-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.7M Sep  1 14:30 gen-word-3475-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.6M Sep  1 13:54 gen-word-3480-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.7M Sep  1 14:30 gen-word-3480-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.7M Sep  1 13:54 gen-word-3485-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.6M Sep  1 14:30 gen-word-3485-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.7M Sep  1 13:54 gen-word-3490-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.7M Sep  1 14:30 gen-word-3490-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.7M Sep  1 13:54 gen-word-3495-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.7M Sep  1 14:30 gen-word-3495-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   44K Sep  1 13:54 gen-word-35-count.jsonl\n"
+      "-rw-r--r--  1 root root   44K Sep  1 14:30 gen-word-35-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  345K Sep  1 13:54 gen-word-350-count.jsonl\n"
+      "-rw-r--r--  1 root root  349K Sep  1 14:30 gen-word-350-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.7M Sep  1 13:54 gen-word-3500-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.7M Sep  1 14:30 gen-word-3500-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.7M Sep  1 13:54 gen-word-3505-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.7M Sep  1 14:30 gen-word-3505-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.8M Sep  1 13:54 gen-word-3510-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.7M Sep  1 14:30 gen-word-3510-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.8M Sep  1 13:54 gen-word-3515-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.7M Sep  1 14:30 gen-word-3515-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.7M Sep  1 13:54 gen-word-3520-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.7M Sep  1 14:30 gen-word-3520-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.8M Sep  1 13:54 gen-word-3525-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.8M Sep  1 14:30 gen-word-3525-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.8M Sep  1 13:54 gen-word-3530-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.8M Sep  1 14:30 gen-word-3530-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.8M Sep  1 13:54 gen-word-3535-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.8M Sep  1 14:30 gen-word-3535-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.8M Sep  1 13:54 gen-word-3540-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.8M Sep  1 14:30 gen-word-3540-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.8M Sep  1 13:54 gen-word-3545-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.8M Sep  1 14:30 gen-word-3545-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  359K Sep  1 13:54 gen-word-355-count.jsonl\n"
+      "-rw-r--r--  1 root root  348K Sep  1 14:30 gen-word-355-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.8M Sep  1 13:54 gen-word-3550-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.8M Sep  1 14:30 gen-word-3550-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.9M Sep  1 13:54 gen-word-3555-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.8M Sep  1 14:30 gen-word-3555-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.8M Sep  1 13:54 gen-word-3560-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.8M Sep  1 14:30 gen-word-3560-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.8M Sep  1 13:54 gen-word-3565-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.8M Sep  1 14:30 gen-word-3565-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.9M Sep  1 13:54 gen-word-3570-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.9M Sep  1 14:30 gen-word-3570-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.9M Sep  1 13:54 gen-word-3575-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.9M Sep  1 14:30 gen-word-3575-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.9M Sep  1 13:54 gen-word-3580-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.9M Sep  1 14:30 gen-word-3580-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.9M Sep  1 13:54 gen-word-3585-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.9M Sep  1 14:30 gen-word-3585-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.9M Sep  1 13:54 gen-word-3590-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.9M Sep  1 14:30 gen-word-3590-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.9M Sep  1 13:54 gen-word-3595-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.9M Sep  1 14:30 gen-word-3595-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  358K Sep  1 13:54 gen-word-360-count.jsonl\n"
+      "-rw-r--r--  1 root root  358K Sep  1 14:30 gen-word-360-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.9M Sep  1 13:54 gen-word-3600-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.9M Sep  1 14:30 gen-word-3600-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.9M Sep  1 13:54 gen-word-3605-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.9M Sep  1 14:30 gen-word-3605-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.9M Sep  1 13:54 gen-word-3610-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.9M Sep  1 14:30 gen-word-3610-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.9M Sep  1 13:54 gen-word-3615-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.9M Sep  1 14:30 gen-word-3615-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  6.9M Sep  1 13:54 gen-word-3620-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.0M Sep  1 14:30 gen-word-3620-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.0M Sep  1 13:54 gen-word-3625-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.0M Sep  1 14:30 gen-word-3625-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.0M Sep  1 13:54 gen-word-3630-count.jsonl\n"
+      "-rw-r--r--  1 root root  6.9M Sep  1 14:30 gen-word-3630-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.0M Sep  1 13:54 gen-word-3635-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.0M Sep  1 14:30 gen-word-3635-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.0M Sep  1 13:54 gen-word-3640-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.0M Sep  1 14:30 gen-word-3640-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.0M Sep  1 13:54 gen-word-3645-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.0M Sep  1 14:30 gen-word-3645-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  370K Sep  1 13:54 gen-word-365-count.jsonl\n"
+      "-rw-r--r--  1 root root  362K Sep  1 14:30 gen-word-365-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.0M Sep  1 13:54 gen-word-3650-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.0M Sep  1 14:30 gen-word-3650-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.0M Sep  1 13:54 gen-word-3655-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.0M Sep  1 14:30 gen-word-3655-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.0M Sep  1 13:54 gen-word-3660-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.0M Sep  1 14:30 gen-word-3660-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.0M Sep  1 13:54 gen-word-3665-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.0M Sep  1 14:30 gen-word-3665-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.0M Sep  1 13:54 gen-word-3670-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.1M Sep  1 14:30 gen-word-3670-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.0M Sep  1 13:54 gen-word-3675-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.0M Sep  1 14:30 gen-word-3675-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.1M Sep  1 13:54 gen-word-3680-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.1M Sep  1 14:30 gen-word-3680-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.1M Sep  1 13:54 gen-word-3685-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.0M Sep  1 14:30 gen-word-3685-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.1M Sep  1 13:54 gen-word-3690-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.1M Sep  1 14:30 gen-word-3690-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.1M Sep  1 13:54 gen-word-3695-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.1M Sep  1 14:30 gen-word-3695-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  370K Sep  1 13:54 gen-word-370-count.jsonl\n"
+      "-rw-r--r--  1 root root  373K Sep  1 14:30 gen-word-370-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.1M Sep  1 13:54 gen-word-3700-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.1M Sep  1 14:30 gen-word-3700-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.1M Sep  1 13:54 gen-word-3705-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.1M Sep  1 14:30 gen-word-3705-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.1M Sep  1 13:54 gen-word-3710-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.1M Sep  1 14:30 gen-word-3710-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.1M Sep  1 13:54 gen-word-3715-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.1M Sep  1 14:30 gen-word-3715-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.1M Sep  1 13:54 gen-word-3720-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.1M Sep  1 14:30 gen-word-3720-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.1M Sep  1 13:54 gen-word-3725-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.1M Sep  1 14:30 gen-word-3725-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.2M Sep  1 13:54 gen-word-3730-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.1M Sep  1 14:30 gen-word-3730-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.1M Sep  1 13:54 gen-word-3735-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.2M Sep  1 14:30 gen-word-3735-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.2M Sep  1 13:54 gen-word-3740-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.2M Sep  1 14:30 gen-word-3740-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.2M Sep  1 13:54 gen-word-3745-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.2M Sep  1 14:30 gen-word-3745-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  374K Sep  1 13:54 gen-word-375-count.jsonl\n"
+      "-rw-r--r--  1 root root  380K Sep  1 14:30 gen-word-375-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.2M Sep  1 13:54 gen-word-3750-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.2M Sep  1 14:30 gen-word-3750-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.2M Sep  1 13:54 gen-word-3755-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.2M Sep  1 14:30 gen-word-3755-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.2M Sep  1 13:54 gen-word-3760-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.2M Sep  1 14:30 gen-word-3760-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.2M Sep  1 13:54 gen-word-3765-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.2M Sep  1 14:30 gen-word-3765-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.2M Sep  1 13:54 gen-word-3770-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.2M Sep  1 14:30 gen-word-3770-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.3M Sep  1 13:54 gen-word-3775-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.2M Sep  1 14:30 gen-word-3775-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.3M Sep  1 13:54 gen-word-3780-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.3M Sep  1 14:30 gen-word-3780-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.3M Sep  1 13:54 gen-word-3785-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.3M Sep  1 14:30 gen-word-3785-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.3M Sep  1 13:54 gen-word-3790-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.3M Sep  1 14:30 gen-word-3790-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.3M Sep  1 13:54 gen-word-3795-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.3M Sep  1 14:30 gen-word-3795-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  382K Sep  1 13:54 gen-word-380-count.jsonl\n"
+      "-rw-r--r--  1 root root  376K Sep  1 14:30 gen-word-380-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.3M Sep  1 13:54 gen-word-3800-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.3M Sep  1 14:30 gen-word-3800-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.3M Sep  1 13:54 gen-word-3805-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.3M Sep  1 14:30 gen-word-3805-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.3M Sep  1 13:54 gen-word-3810-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.3M Sep  1 14:30 gen-word-3810-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.3M Sep  1 13:54 gen-word-3815-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.3M Sep  1 14:30 gen-word-3815-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.3M Sep  1 13:54 gen-word-3820-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.3M Sep  1 14:30 gen-word-3820-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.4M Sep  1 13:54 gen-word-3825-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.3M Sep  1 14:30 gen-word-3825-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.3M Sep  1 13:54 gen-word-3830-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.4M Sep  1 14:30 gen-word-3830-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.4M Sep  1 13:54 gen-word-3835-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.4M Sep  1 14:30 gen-word-3835-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.3M Sep  1 13:54 gen-word-3840-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.3M Sep  1 14:30 gen-word-3840-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.4M Sep  1 13:54 gen-word-3845-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.4M Sep  1 14:30 gen-word-3845-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  383K Sep  1 13:54 gen-word-385-count.jsonl\n"
+      "-rw-r--r--  1 root root  384K Sep  1 14:30 gen-word-385-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.4M Sep  1 13:54 gen-word-3850-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.4M Sep  1 14:30 gen-word-3850-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.4M Sep  1 13:54 gen-word-3855-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.4M Sep  1 14:30 gen-word-3855-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.4M Sep  1 13:54 gen-word-3860-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.4M Sep  1 14:30 gen-word-3860-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.4M Sep  1 13:54 gen-word-3865-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.4M Sep  1 14:30 gen-word-3865-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.4M Sep  1 13:54 gen-word-3870-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.4M Sep  1 14:30 gen-word-3870-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.4M Sep  1 13:54 gen-word-3875-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.4M Sep  1 14:30 gen-word-3875-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.4M Sep  1 13:54 gen-word-3880-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.5M Sep  1 14:30 gen-word-3880-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.4M Sep  1 13:54 gen-word-3885-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.4M Sep  1 14:30 gen-word-3885-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.5M Sep  1 13:54 gen-word-3890-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.4M Sep  1 14:30 gen-word-3890-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.5M Sep  1 13:54 gen-word-3895-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.5M Sep  1 14:30 gen-word-3895-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  385K Sep  1 13:54 gen-word-390-count.jsonl\n"
+      "-rw-r--r--  1 root root  389K Sep  1 14:30 gen-word-390-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.5M Sep  1 13:54 gen-word-3900-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.5M Sep  1 14:30 gen-word-3900-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.5M Sep  1 13:54 gen-word-3905-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.5M Sep  1 14:30 gen-word-3905-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.5M Sep  1 13:54 gen-word-3910-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.5M Sep  1 14:30 gen-word-3910-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.5M Sep  1 13:54 gen-word-3915-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.5M Sep  1 14:30 gen-word-3915-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.5M Sep  1 13:54 gen-word-3920-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.5M Sep  1 14:30 gen-word-3920-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.5M Sep  1 13:54 gen-word-3925-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.5M Sep  1 14:30 gen-word-3925-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.5M Sep  1 13:54 gen-word-3930-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.5M Sep  1 14:30 gen-word-3930-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.6M Sep  1 13:54 gen-word-3935-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.5M Sep  1 14:30 gen-word-3935-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.6M Sep  1 13:54 gen-word-3940-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.5M Sep  1 14:30 gen-word-3940-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.5M Sep  1 13:54 gen-word-3945-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.6M Sep  1 14:30 gen-word-3945-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  390K Sep  1 13:54 gen-word-395-count.jsonl\n"
+      "-rw-r--r--  1 root root  391K Sep  1 14:30 gen-word-395-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.5M Sep  1 13:54 gen-word-3950-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.5M Sep  1 14:30 gen-word-3950-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.5M Sep  1 13:54 gen-word-3955-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.6M Sep  1 14:30 gen-word-3955-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.6M Sep  1 13:54 gen-word-3960-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.6M Sep  1 14:30 gen-word-3960-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.6M Sep  1 13:54 gen-word-3965-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.6M Sep  1 14:30 gen-word-3965-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.6M Sep  1 13:54 gen-word-3970-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.6M Sep  1 14:30 gen-word-3970-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.7M Sep  1 13:54 gen-word-3975-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.6M Sep  1 14:30 gen-word-3975-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.6M Sep  1 13:54 gen-word-3980-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.6M Sep  1 14:30 gen-word-3980-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.6M Sep  1 13:54 gen-word-3985-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.6M Sep  1 14:30 gen-word-3985-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.6M Sep  1 13:54 gen-word-3990-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.6M Sep  1 14:30 gen-word-3990-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.7M Sep  1 13:54 gen-word-3995-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.7M Sep  1 14:30 gen-word-3995-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   49K Sep  1 13:54 gen-word-40-count.jsonl\n"
+      "-rw-r--r--  1 root root   49K Sep  1 14:30 gen-word-40-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  401K Sep  1 13:54 gen-word-400-count.jsonl\n"
+      "-rw-r--r--  1 root root  403K Sep  1 14:30 gen-word-400-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  7.7M Sep  1 13:54 gen-word-4000-count.jsonl\n"
+      "-rw-r--r--  1 root root  7.7M Sep  1 14:30 gen-word-4000-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  405K Sep  1 13:54 gen-word-405-count.jsonl\n"
+      "-rw-r--r--  1 root root  401K Sep  1 14:30 gen-word-405-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  405K Sep  1 13:54 gen-word-410-count.jsonl\n"
+      "-rw-r--r--  1 root root  412K Sep  1 14:30 gen-word-410-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  415K Sep  1 13:54 gen-word-415-count.jsonl\n"
+      "-rw-r--r--  1 root root  417K Sep  1 14:30 gen-word-415-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  418K Sep  1 13:54 gen-word-420-count.jsonl\n"
+      "-rw-r--r--  1 root root  420K Sep  1 14:30 gen-word-420-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  419K Sep  1 13:54 gen-word-425-count.jsonl\n"
+      "-rw-r--r--  1 root root  422K Sep  1 14:30 gen-word-425-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  429K Sep  1 13:54 gen-word-430-count.jsonl\n"
+      "-rw-r--r--  1 root root  428K Sep  1 14:30 gen-word-430-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  431K Sep  1 13:54 gen-word-435-count.jsonl\n"
+      "-rw-r--r--  1 root root  430K Sep  1 14:30 gen-word-435-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  441K Sep  1 13:54 gen-word-440-count.jsonl\n"
+      "-rw-r--r--  1 root root  433K Sep  1 14:30 gen-word-440-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  441K Sep  1 13:54 gen-word-445-count.jsonl\n"
+      "-rw-r--r--  1 root root  446K Sep  1 14:30 gen-word-445-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   54K Sep  1 13:54 gen-word-45-count.jsonl\n"
+      "-rw-r--r--  1 root root   54K Sep  1 14:30 gen-word-45-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  445K Sep  1 13:54 gen-word-450-count.jsonl\n"
+      "-rw-r--r--  1 root root  445K Sep  1 14:30 gen-word-450-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  452K Sep  1 13:54 gen-word-455-count.jsonl\n"
+      "-rw-r--r--  1 root root  457K Sep  1 14:30 gen-word-455-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  452K Sep  1 13:54 gen-word-460-count.jsonl\n"
+      "-rw-r--r--  1 root root  455K Sep  1 14:30 gen-word-460-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  462K Sep  1 13:54 gen-word-465-count.jsonl\n"
+      "-rw-r--r--  1 root root  471K Sep  1 14:30 gen-word-465-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  470K Sep  1 13:54 gen-word-470-count.jsonl\n"
+      "-rw-r--r--  1 root root  469K Sep  1 14:30 gen-word-470-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  468K Sep  1 13:54 gen-word-475-count.jsonl\n"
+      "-rw-r--r--  1 root root  463K Sep  1 14:30 gen-word-475-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  476K Sep  1 13:54 gen-word-480-count.jsonl\n"
+      "-rw-r--r--  1 root root  480K Sep  1 14:30 gen-word-480-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  486K Sep  1 13:54 gen-word-485-count.jsonl\n"
+      "-rw-r--r--  1 root root  493K Sep  1 14:30 gen-word-485-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  490K Sep  1 13:54 gen-word-490-count.jsonl\n"
+      "-rw-r--r--  1 root root  487K Sep  1 14:30 gen-word-490-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  498K Sep  1 13:54 gen-word-495-count.jsonl\n"
+      "-rw-r--r--  1 root root  489K Sep  1 14:30 gen-word-495-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   15K Sep  1 13:54 gen-word-5-count.jsonl\n"
+      "-rw-r--r--  1 root root   15K Sep  1 14:30 gen-word-5-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   57K Sep  1 13:54 gen-word-50-count.jsonl\n"
+      "-rw-r--r--  1 root root   60K Sep  1 14:30 gen-word-50-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  499K Sep  1 13:54 gen-word-500-count.jsonl\n"
+      "-rw-r--r--  1 root root  498K Sep  1 14:30 gen-word-500-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root 1009K Sep  1 13:54 gen-word-505-count.jsonl\n"
+      "-rw-r--r--  1 root root 1006K Sep  1 14:30 gen-word-505-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root 1021K Sep  1 13:54 gen-word-510-count.jsonl\n"
+      "-rw-r--r--  1 root root 1013K Sep  1 14:30 gen-word-510-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.0M Sep  1 13:54 gen-word-515-count.jsonl\n"
+      "-rw-r--r--  1 root root 1015K Sep  1 14:30 gen-word-515-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.1M Sep  1 13:54 gen-word-520-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.1M Sep  1 14:30 gen-word-520-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.1M Sep  1 13:54 gen-word-525-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.1M Sep  1 14:30 gen-word-525-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.1M Sep  1 13:54 gen-word-530-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.1M Sep  1 14:30 gen-word-530-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.1M Sep  1 13:54 gen-word-535-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.1M Sep  1 14:30 gen-word-535-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.1M Sep  1 13:54 gen-word-540-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.1M Sep  1 14:30 gen-word-540-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.1M Sep  1 13:54 gen-word-545-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.1M Sep  1 14:30 gen-word-545-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   64K Sep  1 13:54 gen-word-55-count.jsonl\n"
+      "-rw-r--r--  1 root root   64K Sep  1 14:30 gen-word-55-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.1M Sep  1 13:54 gen-word-550-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.1M Sep  1 14:30 gen-word-550-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.1M Sep  1 13:54 gen-word-555-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.1M Sep  1 14:30 gen-word-555-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.1M Sep  1 13:54 gen-word-560-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.1M Sep  1 14:30 gen-word-560-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.1M Sep  1 13:54 gen-word-565-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.1M Sep  1 14:30 gen-word-565-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.1M Sep  1 13:54 gen-word-570-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.2M Sep  1 14:30 gen-word-570-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.1M Sep  1 13:54 gen-word-575-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.2M Sep  1 14:30 gen-word-575-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.2M Sep  1 13:54 gen-word-580-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.2M Sep  1 14:30 gen-word-580-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.2M Sep  1 13:54 gen-word-585-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.2M Sep  1 14:30 gen-word-585-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.2M Sep  1 13:54 gen-word-590-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.2M Sep  1 14:30 gen-word-590-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.2M Sep  1 13:54 gen-word-595-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.2M Sep  1 14:30 gen-word-595-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   67K Sep  1 13:54 gen-word-60-count.jsonl\n"
+      "-rw-r--r--  1 root root   68K Sep  1 14:30 gen-word-60-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.2M Sep  1 13:54 gen-word-600-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.2M Sep  1 14:30 gen-word-600-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.2M Sep  1 13:54 gen-word-605-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.2M Sep  1 14:30 gen-word-605-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.2M Sep  1 13:54 gen-word-610-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.2M Sep  1 14:30 gen-word-610-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.2M Sep  1 13:54 gen-word-615-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.2M Sep  1 14:30 gen-word-615-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.2M Sep  1 13:54 gen-word-620-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.3M Sep  1 14:30 gen-word-620-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.3M Sep  1 13:54 gen-word-625-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.3M Sep  1 14:30 gen-word-625-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.3M Sep  1 13:54 gen-word-630-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.3M Sep  1 14:30 gen-word-630-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.3M Sep  1 13:54 gen-word-635-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.3M Sep  1 14:30 gen-word-635-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.3M Sep  1 13:54 gen-word-640-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.3M Sep  1 14:30 gen-word-640-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.3M Sep  1 13:54 gen-word-645-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.3M Sep  1 14:30 gen-word-645-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   72K Sep  1 13:54 gen-word-65-count.jsonl\n"
+      "-rw-r--r--  1 root root   71K Sep  1 14:30 gen-word-65-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.3M Sep  1 13:54 gen-word-650-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.3M Sep  1 14:30 gen-word-650-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.3M Sep  1 13:54 gen-word-655-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.3M Sep  1 14:30 gen-word-655-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.3M Sep  1 13:54 gen-word-660-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.3M Sep  1 14:30 gen-word-660-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.3M Sep  1 13:54 gen-word-665-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.3M Sep  1 14:30 gen-word-665-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.3M Sep  1 13:54 gen-word-670-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.3M Sep  1 14:30 gen-word-670-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.4M Sep  1 13:54 gen-word-675-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.3M Sep  1 14:30 gen-word-675-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.3M Sep  1 13:54 gen-word-680-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.4M Sep  1 14:30 gen-word-680-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.4M Sep  1 13:54 gen-word-685-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.4M Sep  1 14:30 gen-word-685-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.4M Sep  1 13:54 gen-word-690-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.4M Sep  1 14:30 gen-word-690-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.4M Sep  1 13:54 gen-word-695-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.4M Sep  1 14:30 gen-word-695-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   79K Sep  1 13:54 gen-word-70-count.jsonl\n"
+      "-rw-r--r--  1 root root   79K Sep  1 14:30 gen-word-70-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.4M Sep  1 13:54 gen-word-700-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.4M Sep  1 14:30 gen-word-700-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.4M Sep  1 13:54 gen-word-705-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.4M Sep  1 14:30 gen-word-705-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.4M Sep  1 13:54 gen-word-710-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.4M Sep  1 14:30 gen-word-710-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.4M Sep  1 13:54 gen-word-715-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.4M Sep  1 14:30 gen-word-715-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.4M Sep  1 13:54 gen-word-720-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.4M Sep  1 14:30 gen-word-720-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.4M Sep  1 13:54 gen-word-725-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.4M Sep  1 14:30 gen-word-725-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.5M Sep  1 13:54 gen-word-730-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.5M Sep  1 14:30 gen-word-730-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.5M Sep  1 13:54 gen-word-735-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.5M Sep  1 14:30 gen-word-735-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.5M Sep  1 13:54 gen-word-740-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.5M Sep  1 14:30 gen-word-740-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.5M Sep  1 13:54 gen-word-745-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.5M Sep  1 14:30 gen-word-745-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   81K Sep  1 13:54 gen-word-75-count.jsonl\n"
+      "-rw-r--r--  1 root root   83K Sep  1 14:30 gen-word-75-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.5M Sep  1 13:54 gen-word-750-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.5M Sep  1 14:30 gen-word-750-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.5M Sep  1 13:54 gen-word-755-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.5M Sep  1 14:30 gen-word-755-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.5M Sep  1 13:54 gen-word-760-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.5M Sep  1 14:30 gen-word-760-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.5M Sep  1 13:54 gen-word-765-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.5M Sep  1 14:30 gen-word-765-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.5M Sep  1 13:54 gen-word-770-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.5M Sep  1 14:30 gen-word-770-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.5M Sep  1 13:54 gen-word-775-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.5M Sep  1 14:30 gen-word-775-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.5M Sep  1 13:54 gen-word-780-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.6M Sep  1 14:30 gen-word-780-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.6M Sep  1 13:54 gen-word-785-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.6M Sep  1 14:30 gen-word-785-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.6M Sep  1 13:54 gen-word-790-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.6M Sep  1 14:30 gen-word-790-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.6M Sep  1 13:54 gen-word-795-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.6M Sep  1 14:30 gen-word-795-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   88K Sep  1 13:54 gen-word-80-count.jsonl\n"
+      "-rw-r--r--  1 root root   88K Sep  1 14:30 gen-word-80-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.6M Sep  1 13:54 gen-word-800-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.6M Sep  1 14:30 gen-word-800-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.6M Sep  1 13:54 gen-word-805-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.6M Sep  1 14:30 gen-word-805-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.6M Sep  1 13:54 gen-word-810-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.6M Sep  1 14:30 gen-word-810-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.6M Sep  1 13:54 gen-word-815-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.6M Sep  1 14:30 gen-word-815-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.6M Sep  1 13:54 gen-word-820-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.6M Sep  1 14:30 gen-word-820-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.6M Sep  1 13:54 gen-word-825-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.6M Sep  1 14:30 gen-word-825-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.6M Sep  1 13:54 gen-word-830-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.6M Sep  1 14:30 gen-word-830-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.7M Sep  1 13:54 gen-word-835-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.7M Sep  1 14:30 gen-word-835-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.7M Sep  1 13:54 gen-word-840-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.7M Sep  1 14:30 gen-word-840-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.7M Sep  1 13:54 gen-word-845-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.7M Sep  1 14:30 gen-word-845-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   94K Sep  1 13:54 gen-word-85-count.jsonl\n"
+      "-rw-r--r--  1 root root   93K Sep  1 14:30 gen-word-85-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.7M Sep  1 13:54 gen-word-850-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.7M Sep  1 14:30 gen-word-850-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.7M Sep  1 13:54 gen-word-855-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.7M Sep  1 14:30 gen-word-855-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.7M Sep  1 13:54 gen-word-860-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.7M Sep  1 14:30 gen-word-860-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.7M Sep  1 13:54 gen-word-865-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.7M Sep  1 14:30 gen-word-865-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.7M Sep  1 13:54 gen-word-870-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.7M Sep  1 14:30 gen-word-870-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.7M Sep  1 13:54 gen-word-875-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.7M Sep  1 14:30 gen-word-875-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.7M Sep  1 13:54 gen-word-880-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.7M Sep  1 14:30 gen-word-880-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.7M Sep  1 13:54 gen-word-885-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.7M Sep  1 14:30 gen-word-885-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.8M Sep  1 13:54 gen-word-890-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.8M Sep  1 14:30 gen-word-890-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.8M Sep  1 13:54 gen-word-895-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.8M Sep  1 14:30 gen-word-895-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   99K Sep  1 13:54 gen-word-90-count.jsonl\n"
+      "-rw-r--r--  1 root root   98K Sep  1 14:30 gen-word-90-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.8M Sep  1 13:54 gen-word-900-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.8M Sep  1 14:30 gen-word-900-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.8M Sep  1 13:54 gen-word-905-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.8M Sep  1 14:30 gen-word-905-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.8M Sep  1 13:54 gen-word-910-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.8M Sep  1 14:30 gen-word-910-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.8M Sep  1 13:54 gen-word-915-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.8M Sep  1 14:30 gen-word-915-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.8M Sep  1 13:54 gen-word-920-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.8M Sep  1 14:30 gen-word-920-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.8M Sep  1 13:54 gen-word-925-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.8M Sep  1 14:30 gen-word-925-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.8M Sep  1 13:54 gen-word-930-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.8M Sep  1 14:30 gen-word-930-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.8M Sep  1 13:54 gen-word-935-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.8M Sep  1 14:30 gen-word-935-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.9M Sep  1 13:54 gen-word-940-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.9M Sep  1 14:30 gen-word-940-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.9M Sep  1 13:54 gen-word-945-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.9M Sep  1 14:30 gen-word-945-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  100K Sep  1 13:54 gen-word-95-count.jsonl\n"
+      "-rw-r--r--  1 root root  100K Sep  1 14:30 gen-word-95-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.9M Sep  1 13:54 gen-word-950-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.9M Sep  1 14:30 gen-word-950-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.9M Sep  1 13:54 gen-word-955-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.9M Sep  1 14:30 gen-word-955-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.9M Sep  1 13:54 gen-word-960-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.9M Sep  1 14:30 gen-word-960-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.9M Sep  1 13:54 gen-word-965-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.9M Sep  1 14:30 gen-word-965-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.9M Sep  1 13:54 gen-word-970-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.9M Sep  1 14:30 gen-word-970-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.9M Sep  1 13:54 gen-word-975-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.9M Sep  1 14:30 gen-word-975-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.9M Sep  1 13:54 gen-word-980-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.9M Sep  1 14:30 gen-word-980-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  1.9M Sep  1 13:54 gen-word-985-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.9M Sep  1 14:30 gen-word-985-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.0M Sep  1 13:54 gen-word-990-count.jsonl\n"
+      "-rw-r--r--  1 root root  1.9M Sep  1 14:30 gen-word-990-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  2.0M Sep  1 13:54 gen-word-995-count.jsonl\n"
+      "-rw-r--r--  1 root root  2.0M Sep  1 14:30 gen-word-995-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   52K Sep  1 13:54 shuffle-word-10-count.jsonl\n"
+      "-rw-r--r--  1 root root   51K Sep  1 14:30 shuffle-word-10-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   28K Sep  1 13:54 shuffle-word-100-count.jsonl\n"
+      "-rw-r--r--  1 root root   29K Sep  1 14:30 shuffle-word-100-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  524K Sep  1 13:54 shuffle-word-1000-count.jsonl\n"
+      "-rw-r--r--  1 root root  523K Sep  1 14:30 shuffle-word-1000-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  523K Sep  1 13:54 shuffle-word-1005-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-1005-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  525K Sep  1 13:54 shuffle-word-1010-count.jsonl\n"
+      "-rw-r--r--  1 root root  523K Sep  1 14:30 shuffle-word-1010-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  523K Sep  1 13:54 shuffle-word-1015-count.jsonl\n"
+      "-rw-r--r--  1 root root  526K Sep  1 14:30 shuffle-word-1015-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  524K Sep  1 13:54 shuffle-word-1020-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-1020-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  522K Sep  1 13:54 shuffle-word-1025-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-1025-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  524K Sep  1 13:54 shuffle-word-1030-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-1030-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  518K Sep  1 13:54 shuffle-word-1035-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-1035-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  523K Sep  1 13:54 shuffle-word-1040-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-1040-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  522K Sep  1 13:54 shuffle-word-1045-count.jsonl\n"
+      "-rw-r--r--  1 root root  523K Sep  1 14:30 shuffle-word-1045-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   29K Sep  1 13:54 shuffle-word-105-count.jsonl\n"
+      "-rw-r--r--  1 root root   30K Sep  1 14:30 shuffle-word-105-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-1050-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-1050-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-1055-count.jsonl\n"
+      "-rw-r--r--  1 root root  523K Sep  1 14:30 shuffle-word-1055-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  523K Sep  1 13:54 shuffle-word-1060-count.jsonl\n"
+      "-rw-r--r--  1 root root  523K Sep  1 14:30 shuffle-word-1060-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  524K Sep  1 13:54 shuffle-word-1065-count.jsonl\n"
+      "-rw-r--r--  1 root root  523K Sep  1 14:30 shuffle-word-1065-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-1070-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-1070-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  523K Sep  1 13:54 shuffle-word-1075-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-1075-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-1080-count.jsonl\n"
+      "-rw-r--r--  1 root root  525K Sep  1 14:30 shuffle-word-1080-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  522K Sep  1 13:54 shuffle-word-1085-count.jsonl\n"
+      "-rw-r--r--  1 root root  524K Sep  1 14:30 shuffle-word-1085-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  522K Sep  1 13:54 shuffle-word-1090-count.jsonl\n"
+      "-rw-r--r--  1 root root  524K Sep  1 14:30 shuffle-word-1090-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  519K Sep  1 13:54 shuffle-word-1095-count.jsonl\n"
+      "-rw-r--r--  1 root root  519K Sep  1 14:30 shuffle-word-1095-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   28K Sep  1 13:54 shuffle-word-110-count.jsonl\n"
+      "-rw-r--r--  1 root root   29K Sep  1 14:30 shuffle-word-110-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-1100-count.jsonl\n"
+      "-rw-r--r--  1 root root  525K Sep  1 14:30 shuffle-word-1100-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  525K Sep  1 13:54 shuffle-word-1105-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-1105-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  525K Sep  1 13:54 shuffle-word-1110-count.jsonl\n"
+      "-rw-r--r--  1 root root  524K Sep  1 14:30 shuffle-word-1110-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  519K Sep  1 13:54 shuffle-word-1115-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-1115-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  522K Sep  1 13:54 shuffle-word-1120-count.jsonl\n"
+      "-rw-r--r--  1 root root  525K Sep  1 14:30 shuffle-word-1120-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  523K Sep  1 13:54 shuffle-word-1125-count.jsonl\n"
+      "-rw-r--r--  1 root root  523K Sep  1 14:30 shuffle-word-1125-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  524K Sep  1 13:54 shuffle-word-1130-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-1130-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  523K Sep  1 13:54 shuffle-word-1135-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-1135-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  526K Sep  1 13:54 shuffle-word-1140-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-1140-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  523K Sep  1 13:54 shuffle-word-1145-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-1145-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   28K Sep  1 13:54 shuffle-word-115-count.jsonl\n"
+      "-rw-r--r--  1 root root   28K Sep  1 14:30 shuffle-word-115-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  522K Sep  1 13:54 shuffle-word-1150-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-1150-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  523K Sep  1 13:54 shuffle-word-1155-count.jsonl\n"
+      "-rw-r--r--  1 root root  524K Sep  1 14:30 shuffle-word-1155-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  523K Sep  1 13:54 shuffle-word-1160-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-1160-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  522K Sep  1 13:54 shuffle-word-1165-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-1165-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-1170-count.jsonl\n"
+      "-rw-r--r--  1 root root  523K Sep  1 14:30 shuffle-word-1170-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  526K Sep  1 13:54 shuffle-word-1175-count.jsonl\n"
+      "-rw-r--r--  1 root root  517K Sep  1 14:30 shuffle-word-1175-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  523K Sep  1 13:54 shuffle-word-1180-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-1180-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-1185-count.jsonl\n"
+      "-rw-r--r--  1 root root  523K Sep  1 14:30 shuffle-word-1185-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  525K Sep  1 13:54 shuffle-word-1190-count.jsonl\n"
+      "-rw-r--r--  1 root root  524K Sep  1 14:30 shuffle-word-1190-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  524K Sep  1 13:54 shuffle-word-1195-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-1195-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   27K Sep  1 13:54 shuffle-word-120-count.jsonl\n"
+      "-rw-r--r--  1 root root   28K Sep  1 14:30 shuffle-word-120-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-1200-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-1200-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-1205-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-1205-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  523K Sep  1 13:54 shuffle-word-1210-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-1210-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  522K Sep  1 13:54 shuffle-word-1215-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-1215-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-1220-count.jsonl\n"
+      "-rw-r--r--  1 root root  519K Sep  1 14:30 shuffle-word-1220-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  522K Sep  1 13:54 shuffle-word-1225-count.jsonl\n"
+      "-rw-r--r--  1 root root  518K Sep  1 14:30 shuffle-word-1225-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-1230-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-1230-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  523K Sep  1 13:54 shuffle-word-1235-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-1235-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  522K Sep  1 13:54 shuffle-word-1240-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-1240-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-1245-count.jsonl\n"
+      "-rw-r--r--  1 root root  524K Sep  1 14:30 shuffle-word-1245-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   28K Sep  1 13:54 shuffle-word-125-count.jsonl\n"
+      "-rw-r--r--  1 root root   30K Sep  1 14:30 shuffle-word-125-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  522K Sep  1 13:54 shuffle-word-1250-count.jsonl\n"
+      "-rw-r--r--  1 root root  523K Sep  1 14:30 shuffle-word-1250-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-1255-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-1255-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  524K Sep  1 13:54 shuffle-word-1260-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-1260-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-1265-count.jsonl\n"
+      "-rw-r--r--  1 root root  523K Sep  1 14:30 shuffle-word-1265-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  526K Sep  1 13:54 shuffle-word-1270-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-1270-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  522K Sep  1 13:54 shuffle-word-1275-count.jsonl\n"
+      "-rw-r--r--  1 root root  519K Sep  1 14:30 shuffle-word-1275-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  517K Sep  1 13:54 shuffle-word-1280-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-1280-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  522K Sep  1 13:54 shuffle-word-1285-count.jsonl\n"
+      "-rw-r--r--  1 root root  523K Sep  1 14:30 shuffle-word-1285-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  522K Sep  1 13:54 shuffle-word-1290-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-1290-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-1295-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-1295-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   28K Sep  1 13:54 shuffle-word-130-count.jsonl\n"
+      "-rw-r--r--  1 root root   29K Sep  1 14:30 shuffle-word-130-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  522K Sep  1 13:54 shuffle-word-1300-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-1300-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  522K Sep  1 13:54 shuffle-word-1305-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-1305-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  519K Sep  1 13:54 shuffle-word-1310-count.jsonl\n"
+      "-rw-r--r--  1 root root  517K Sep  1 14:30 shuffle-word-1310-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  517K Sep  1 13:54 shuffle-word-1315-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-1315-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-1320-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-1320-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-1325-count.jsonl\n"
+      "-rw-r--r--  1 root root  519K Sep  1 14:30 shuffle-word-1325-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-1330-count.jsonl\n"
+      "-rw-r--r--  1 root root  519K Sep  1 14:30 shuffle-word-1330-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  522K Sep  1 13:54 shuffle-word-1335-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-1335-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  518K Sep  1 13:54 shuffle-word-1340-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-1340-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-1345-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-1345-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   27K Sep  1 13:54 shuffle-word-135-count.jsonl\n"
+      "-rw-r--r--  1 root root   27K Sep  1 14:30 shuffle-word-135-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-1350-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-1350-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-1355-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-1355-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-1360-count.jsonl\n"
+      "-rw-r--r--  1 root root  519K Sep  1 14:30 shuffle-word-1360-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-1365-count.jsonl\n"
+      "-rw-r--r--  1 root root  519K Sep  1 14:30 shuffle-word-1365-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-1370-count.jsonl\n"
+      "-rw-r--r--  1 root root  517K Sep  1 14:30 shuffle-word-1370-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  522K Sep  1 13:54 shuffle-word-1375-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-1375-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-1380-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-1380-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  518K Sep  1 13:54 shuffle-word-1385-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-1385-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-1390-count.jsonl\n"
+      "-rw-r--r--  1 root root  519K Sep  1 14:30 shuffle-word-1390-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-1395-count.jsonl\n"
+      "-rw-r--r--  1 root root  519K Sep  1 14:30 shuffle-word-1395-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   30K Sep  1 13:54 shuffle-word-140-count.jsonl\n"
+      "-rw-r--r--  1 root root   28K Sep  1 14:30 shuffle-word-140-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-1400-count.jsonl\n"
+      "-rw-r--r--  1 root root  519K Sep  1 14:30 shuffle-word-1400-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-1405-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-1405-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  522K Sep  1 13:54 shuffle-word-1410-count.jsonl\n"
+      "-rw-r--r--  1 root root  518K Sep  1 14:30 shuffle-word-1410-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  518K Sep  1 13:54 shuffle-word-1415-count.jsonl\n"
+      "-rw-r--r--  1 root root  518K Sep  1 14:30 shuffle-word-1415-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  523K Sep  1 13:54 shuffle-word-1420-count.jsonl\n"
+      "-rw-r--r--  1 root root  519K Sep  1 14:30 shuffle-word-1420-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  522K Sep  1 13:54 shuffle-word-1425-count.jsonl\n"
+      "-rw-r--r--  1 root root  519K Sep  1 14:30 shuffle-word-1425-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  519K Sep  1 13:54 shuffle-word-1430-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-1430-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-1435-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-1435-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-1440-count.jsonl\n"
+      "-rw-r--r--  1 root root  519K Sep  1 14:30 shuffle-word-1440-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-1445-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-1445-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   28K Sep  1 13:54 shuffle-word-145-count.jsonl\n"
+      "-rw-r--r--  1 root root   29K Sep  1 14:30 shuffle-word-145-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  518K Sep  1 13:54 shuffle-word-1450-count.jsonl\n"
+      "-rw-r--r--  1 root root  518K Sep  1 14:30 shuffle-word-1450-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-1455-count.jsonl\n"
+      "-rw-r--r--  1 root root  519K Sep  1 14:30 shuffle-word-1455-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-1460-count.jsonl\n"
+      "-rw-r--r--  1 root root  518K Sep  1 14:30 shuffle-word-1460-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-1465-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-1465-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-1470-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-1470-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  518K Sep  1 13:54 shuffle-word-1475-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-1475-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-1480-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-1480-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-1485-count.jsonl\n"
+      "-rw-r--r--  1 root root  519K Sep  1 14:30 shuffle-word-1485-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  524K Sep  1 13:54 shuffle-word-1490-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-1490-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  522K Sep  1 13:54 shuffle-word-1495-count.jsonl\n"
+      "-rw-r--r--  1 root root  517K Sep  1 14:30 shuffle-word-1495-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   43K Sep  1 13:54 shuffle-word-15-count.jsonl\n"
+      "-rw-r--r--  1 root root   44K Sep  1 14:30 shuffle-word-15-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   28K Sep  1 13:54 shuffle-word-150-count.jsonl\n"
+      "-rw-r--r--  1 root root   27K Sep  1 14:30 shuffle-word-150-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-1500-count.jsonl\n"
+      "-rw-r--r--  1 root root  519K Sep  1 14:30 shuffle-word-1500-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  522K Sep  1 13:54 shuffle-word-1505-count.jsonl\n"
+      "-rw-r--r--  1 root root  518K Sep  1 14:30 shuffle-word-1505-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-1510-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-1510-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  519K Sep  1 13:54 shuffle-word-1515-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-1515-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  524K Sep  1 13:54 shuffle-word-1520-count.jsonl\n"
+      "-rw-r--r--  1 root root  519K Sep  1 14:30 shuffle-word-1520-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  519K Sep  1 13:54 shuffle-word-1525-count.jsonl\n"
+      "-rw-r--r--  1 root root  518K Sep  1 14:30 shuffle-word-1525-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  522K Sep  1 13:54 shuffle-word-1530-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-1530-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  522K Sep  1 13:54 shuffle-word-1535-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-1535-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-1540-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-1540-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  523K Sep  1 13:54 shuffle-word-1545-count.jsonl\n"
+      "-rw-r--r--  1 root root  519K Sep  1 14:30 shuffle-word-1545-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   27K Sep  1 13:54 shuffle-word-155-count.jsonl\n"
+      "-rw-r--r--  1 root root   28K Sep  1 14:30 shuffle-word-155-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  518K Sep  1 13:54 shuffle-word-1550-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-1550-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  522K Sep  1 13:54 shuffle-word-1555-count.jsonl\n"
+      "-rw-r--r--  1 root root  519K Sep  1 14:30 shuffle-word-1555-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-1560-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-1560-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  523K Sep  1 13:54 shuffle-word-1565-count.jsonl\n"
+      "-rw-r--r--  1 root root  518K Sep  1 14:30 shuffle-word-1565-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  519K Sep  1 13:54 shuffle-word-1570-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-1570-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  522K Sep  1 13:54 shuffle-word-1575-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-1575-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  518K Sep  1 13:54 shuffle-word-1580-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-1580-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  522K Sep  1 13:54 shuffle-word-1585-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-1585-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  523K Sep  1 13:54 shuffle-word-1590-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-1590-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  518K Sep  1 13:54 shuffle-word-1595-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-1595-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   27K Sep  1 13:54 shuffle-word-160-count.jsonl\n"
+      "-rw-r--r--  1 root root   26K Sep  1 14:30 shuffle-word-160-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-1600-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-1600-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  519K Sep  1 13:54 shuffle-word-1605-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-1605-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-1610-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-1610-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-1615-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-1615-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-1620-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-1620-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-1625-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-1625-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  519K Sep  1 13:54 shuffle-word-1630-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-1630-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  519K Sep  1 13:54 shuffle-word-1635-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-1635-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  523K Sep  1 13:54 shuffle-word-1640-count.jsonl\n"
+      "-rw-r--r--  1 root root  519K Sep  1 14:30 shuffle-word-1640-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-1645-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-1645-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   28K Sep  1 13:54 shuffle-word-165-count.jsonl\n"
+      "-rw-r--r--  1 root root   28K Sep  1 14:30 shuffle-word-165-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  518K Sep  1 13:54 shuffle-word-1650-count.jsonl\n"
+      "-rw-r--r--  1 root root  518K Sep  1 14:30 shuffle-word-1650-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  523K Sep  1 13:54 shuffle-word-1655-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-1655-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-1660-count.jsonl\n"
+      "-rw-r--r--  1 root root  517K Sep  1 14:30 shuffle-word-1660-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-1665-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-1665-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  518K Sep  1 13:54 shuffle-word-1670-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-1670-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-1675-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-1675-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-1680-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-1680-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  523K Sep  1 13:54 shuffle-word-1685-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-1685-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-1690-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-1690-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  522K Sep  1 13:54 shuffle-word-1695-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-1695-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   27K Sep  1 13:54 shuffle-word-170-count.jsonl\n"
+      "-rw-r--r--  1 root root   27K Sep  1 14:30 shuffle-word-170-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-1700-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-1700-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  522K Sep  1 13:54 shuffle-word-1705-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-1705-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-1710-count.jsonl\n"
+      "-rw-r--r--  1 root root  523K Sep  1 14:30 shuffle-word-1710-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  522K Sep  1 13:54 shuffle-word-1715-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-1715-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  519K Sep  1 13:54 shuffle-word-1720-count.jsonl\n"
+      "-rw-r--r--  1 root root  518K Sep  1 14:30 shuffle-word-1720-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  518K Sep  1 13:54 shuffle-word-1725-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-1725-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-1730-count.jsonl\n"
+      "-rw-r--r--  1 root root  519K Sep  1 14:30 shuffle-word-1730-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  523K Sep  1 13:54 shuffle-word-1735-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-1735-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  519K Sep  1 13:54 shuffle-word-1740-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-1740-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  518K Sep  1 13:54 shuffle-word-1745-count.jsonl\n"
+      "-rw-r--r--  1 root root  517K Sep  1 14:30 shuffle-word-1745-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   27K Sep  1 13:54 shuffle-word-175-count.jsonl\n"
+      "-rw-r--r--  1 root root   28K Sep  1 14:30 shuffle-word-175-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  522K Sep  1 13:54 shuffle-word-1750-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-1750-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  518K Sep  1 13:54 shuffle-word-1755-count.jsonl\n"
+      "-rw-r--r--  1 root root  519K Sep  1 14:30 shuffle-word-1755-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-1760-count.jsonl\n"
+      "-rw-r--r--  1 root root  519K Sep  1 14:30 shuffle-word-1760-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-1765-count.jsonl\n"
+      "-rw-r--r--  1 root root  523K Sep  1 14:30 shuffle-word-1765-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  519K Sep  1 13:54 shuffle-word-1770-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-1770-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-1775-count.jsonl\n"
+      "-rw-r--r--  1 root root  519K Sep  1 14:30 shuffle-word-1775-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-1780-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-1780-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-1785-count.jsonl\n"
+      "-rw-r--r--  1 root root  518K Sep  1 14:30 shuffle-word-1785-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-1790-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-1790-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-1795-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-1795-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   27K Sep  1 13:54 shuffle-word-180-count.jsonl\n"
+      "-rw-r--r--  1 root root   28K Sep  1 14:30 shuffle-word-180-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-1800-count.jsonl\n"
+      "-rw-r--r--  1 root root  519K Sep  1 14:30 shuffle-word-1800-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-1805-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-1805-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-1810-count.jsonl\n"
+      "-rw-r--r--  1 root root  519K Sep  1 14:30 shuffle-word-1810-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  522K Sep  1 13:54 shuffle-word-1815-count.jsonl\n"
+      "-rw-r--r--  1 root root  519K Sep  1 14:30 shuffle-word-1815-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  522K Sep  1 13:54 shuffle-word-1820-count.jsonl\n"
+      "-rw-r--r--  1 root root  523K Sep  1 14:30 shuffle-word-1820-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-1825-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-1825-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-1830-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-1830-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-1835-count.jsonl\n"
+      "-rw-r--r--  1 root root  519K Sep  1 14:30 shuffle-word-1835-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  517K Sep  1 13:54 shuffle-word-1840-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-1840-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  517K Sep  1 13:54 shuffle-word-1845-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-1845-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   28K Sep  1 13:54 shuffle-word-185-count.jsonl\n"
+      "-rw-r--r--  1 root root   28K Sep  1 14:30 shuffle-word-185-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  519K Sep  1 13:54 shuffle-word-1850-count.jsonl\n"
+      "-rw-r--r--  1 root root  518K Sep  1 14:30 shuffle-word-1850-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-1855-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-1855-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  522K Sep  1 13:54 shuffle-word-1860-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-1860-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-1865-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-1865-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-1870-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-1870-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  519K Sep  1 13:54 shuffle-word-1875-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-1875-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  523K Sep  1 13:54 shuffle-word-1880-count.jsonl\n"
+      "-rw-r--r--  1 root root  519K Sep  1 14:30 shuffle-word-1880-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-1885-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-1885-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-1890-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-1890-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  518K Sep  1 13:54 shuffle-word-1895-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-1895-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   28K Sep  1 13:54 shuffle-word-190-count.jsonl\n"
+      "-rw-r--r--  1 root root   28K Sep  1 14:30 shuffle-word-190-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-1900-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-1900-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-1905-count.jsonl\n"
+      "-rw-r--r--  1 root root  519K Sep  1 14:30 shuffle-word-1905-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-1910-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-1910-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-1915-count.jsonl\n"
+      "-rw-r--r--  1 root root  518K Sep  1 14:30 shuffle-word-1915-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  522K Sep  1 13:54 shuffle-word-1920-count.jsonl\n"
+      "-rw-r--r--  1 root root  519K Sep  1 14:30 shuffle-word-1920-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  519K Sep  1 13:54 shuffle-word-1925-count.jsonl\n"
+      "-rw-r--r--  1 root root  518K Sep  1 14:30 shuffle-word-1925-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  524K Sep  1 13:54 shuffle-word-1930-count.jsonl\n"
+      "-rw-r--r--  1 root root  523K Sep  1 14:30 shuffle-word-1930-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-1935-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-1935-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-1940-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-1940-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-1945-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-1945-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   27K Sep  1 13:54 shuffle-word-195-count.jsonl\n"
+      "-rw-r--r--  1 root root   27K Sep  1 14:30 shuffle-word-195-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-1950-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-1950-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-1955-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-1955-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-1960-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-1960-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-1965-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-1965-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  523K Sep  1 13:54 shuffle-word-1970-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-1970-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-1975-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-1975-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  518K Sep  1 13:54 shuffle-word-1980-count.jsonl\n"
+      "-rw-r--r--  1 root root  518K Sep  1 14:30 shuffle-word-1980-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-1985-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-1985-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  522K Sep  1 13:54 shuffle-word-1990-count.jsonl\n"
+      "-rw-r--r--  1 root root  523K Sep  1 14:30 shuffle-word-1990-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  522K Sep  1 13:54 shuffle-word-1995-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-1995-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   37K Sep  1 13:54 shuffle-word-20-count.jsonl\n"
+      "-rw-r--r--  1 root root   38K Sep  1 14:30 shuffle-word-20-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   28K Sep  1 13:54 shuffle-word-200-count.jsonl\n"
+      "-rw-r--r--  1 root root   27K Sep  1 14:30 shuffle-word-200-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-2000-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-2000-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  522K Sep  1 13:54 shuffle-word-2005-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-2005-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  523K Sep  1 13:54 shuffle-word-2010-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-2010-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  519K Sep  1 13:54 shuffle-word-2015-count.jsonl\n"
+      "-rw-r--r--  1 root root  519K Sep  1 14:30 shuffle-word-2015-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-2020-count.jsonl\n"
+      "-rw-r--r--  1 root root  523K Sep  1 14:30 shuffle-word-2020-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  523K Sep  1 13:54 shuffle-word-2025-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-2025-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  522K Sep  1 13:54 shuffle-word-2030-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-2030-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-2035-count.jsonl\n"
+      "-rw-r--r--  1 root root  518K Sep  1 14:30 shuffle-word-2035-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  518K Sep  1 13:54 shuffle-word-2040-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-2040-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-2045-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-2045-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   28K Sep  1 13:54 shuffle-word-205-count.jsonl\n"
+      "-rw-r--r--  1 root root   27K Sep  1 14:30 shuffle-word-205-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  522K Sep  1 13:54 shuffle-word-2050-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-2050-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  519K Sep  1 13:54 shuffle-word-2055-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-2055-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-2060-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-2060-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  519K Sep  1 13:54 shuffle-word-2065-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-2065-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  523K Sep  1 13:54 shuffle-word-2070-count.jsonl\n"
+      "-rw-r--r--  1 root root  519K Sep  1 14:30 shuffle-word-2070-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  519K Sep  1 13:54 shuffle-word-2075-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-2075-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  519K Sep  1 13:54 shuffle-word-2080-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-2080-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-2085-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-2085-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-2090-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-2090-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-2095-count.jsonl\n"
+      "-rw-r--r--  1 root root  524K Sep  1 14:30 shuffle-word-2095-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   26K Sep  1 13:54 shuffle-word-210-count.jsonl\n"
+      "-rw-r--r--  1 root root   27K Sep  1 14:30 shuffle-word-210-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  518K Sep  1 13:54 shuffle-word-2100-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-2100-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-2105-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-2105-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  522K Sep  1 13:54 shuffle-word-2110-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-2110-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-2115-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-2115-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-2120-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-2120-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-2125-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-2125-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  516K Sep  1 13:54 shuffle-word-2130-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-2130-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  519K Sep  1 13:54 shuffle-word-2135-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-2135-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-2140-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-2140-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  522K Sep  1 13:54 shuffle-word-2145-count.jsonl\n"
+      "-rw-r--r--  1 root root  519K Sep  1 14:30 shuffle-word-2145-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   27K Sep  1 13:54 shuffle-word-215-count.jsonl\n"
+      "-rw-r--r--  1 root root   28K Sep  1 14:30 shuffle-word-215-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  519K Sep  1 13:54 shuffle-word-2150-count.jsonl\n"
+      "-rw-r--r--  1 root root  518K Sep  1 14:30 shuffle-word-2150-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  519K Sep  1 13:54 shuffle-word-2155-count.jsonl\n"
+      "-rw-r--r--  1 root root  519K Sep  1 14:30 shuffle-word-2155-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  519K Sep  1 13:54 shuffle-word-2160-count.jsonl\n"
+      "-rw-r--r--  1 root root  519K Sep  1 14:30 shuffle-word-2160-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  518K Sep  1 13:54 shuffle-word-2165-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-2165-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  518K Sep  1 13:54 shuffle-word-2170-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-2170-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-2175-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-2175-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  518K Sep  1 13:54 shuffle-word-2180-count.jsonl\n"
+      "-rw-r--r--  1 root root  517K Sep  1 14:30 shuffle-word-2180-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-2185-count.jsonl\n"
+      "-rw-r--r--  1 root root  519K Sep  1 14:30 shuffle-word-2185-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-2190-count.jsonl\n"
+      "-rw-r--r--  1 root root  518K Sep  1 14:30 shuffle-word-2190-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-2195-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-2195-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   28K Sep  1 13:54 shuffle-word-220-count.jsonl\n"
+      "-rw-r--r--  1 root root   27K Sep  1 14:30 shuffle-word-220-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-2200-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-2200-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-2205-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-2205-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  519K Sep  1 13:54 shuffle-word-2210-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-2210-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  518K Sep  1 13:54 shuffle-word-2215-count.jsonl\n"
+      "-rw-r--r--  1 root root  523K Sep  1 14:30 shuffle-word-2215-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  518K Sep  1 13:54 shuffle-word-2220-count.jsonl\n"
+      "-rw-r--r--  1 root root  518K Sep  1 14:30 shuffle-word-2220-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  522K Sep  1 13:54 shuffle-word-2225-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-2225-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-2230-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-2230-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-2235-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-2235-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  519K Sep  1 13:54 shuffle-word-2240-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-2240-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-2245-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-2245-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   28K Sep  1 13:54 shuffle-word-225-count.jsonl\n"
+      "-rw-r--r--  1 root root   28K Sep  1 14:30 shuffle-word-225-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-2250-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-2250-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-2255-count.jsonl\n"
+      "-rw-r--r--  1 root root  524K Sep  1 14:30 shuffle-word-2255-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  519K Sep  1 13:54 shuffle-word-2260-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-2260-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-2265-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-2265-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-2270-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-2270-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  519K Sep  1 13:54 shuffle-word-2275-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-2275-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  519K Sep  1 13:54 shuffle-word-2280-count.jsonl\n"
+      "-rw-r--r--  1 root root  523K Sep  1 14:30 shuffle-word-2280-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-2285-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-2285-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  519K Sep  1 13:54 shuffle-word-2290-count.jsonl\n"
+      "-rw-r--r--  1 root root  519K Sep  1 14:30 shuffle-word-2290-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-2295-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-2295-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   27K Sep  1 13:54 shuffle-word-230-count.jsonl\n"
+      "-rw-r--r--  1 root root   27K Sep  1 14:30 shuffle-word-230-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  519K Sep  1 13:54 shuffle-word-2300-count.jsonl\n"
+      "-rw-r--r--  1 root root  517K Sep  1 14:30 shuffle-word-2300-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  518K Sep  1 13:54 shuffle-word-2305-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-2305-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  518K Sep  1 13:54 shuffle-word-2310-count.jsonl\n"
+      "-rw-r--r--  1 root root  519K Sep  1 14:30 shuffle-word-2310-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  519K Sep  1 13:54 shuffle-word-2315-count.jsonl\n"
+      "-rw-r--r--  1 root root  518K Sep  1 14:30 shuffle-word-2315-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  517K Sep  1 13:54 shuffle-word-2320-count.jsonl\n"
+      "-rw-r--r--  1 root root  518K Sep  1 14:30 shuffle-word-2320-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-2325-count.jsonl\n"
+      "-rw-r--r--  1 root root  518K Sep  1 14:30 shuffle-word-2325-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  523K Sep  1 13:54 shuffle-word-2330-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-2330-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-2335-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-2335-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-2340-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-2340-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  519K Sep  1 13:54 shuffle-word-2345-count.jsonl\n"
+      "-rw-r--r--  1 root root  518K Sep  1 14:30 shuffle-word-2345-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   28K Sep  1 13:54 shuffle-word-235-count.jsonl\n"
+      "-rw-r--r--  1 root root   27K Sep  1 14:30 shuffle-word-235-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-2350-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-2350-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  519K Sep  1 13:54 shuffle-word-2355-count.jsonl\n"
+      "-rw-r--r--  1 root root  518K Sep  1 14:30 shuffle-word-2355-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-2360-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-2360-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-2365-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-2365-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  519K Sep  1 13:54 shuffle-word-2370-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-2370-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-2375-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-2375-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-2380-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-2380-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  523K Sep  1 13:54 shuffle-word-2385-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-2385-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  518K Sep  1 13:54 shuffle-word-2390-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-2390-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-2395-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-2395-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   27K Sep  1 13:54 shuffle-word-240-count.jsonl\n"
+      "-rw-r--r--  1 root root   27K Sep  1 14:30 shuffle-word-240-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  519K Sep  1 13:54 shuffle-word-2400-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-2400-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  517K Sep  1 13:54 shuffle-word-2405-count.jsonl\n"
+      "-rw-r--r--  1 root root  516K Sep  1 14:30 shuffle-word-2405-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  517K Sep  1 13:54 shuffle-word-2410-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-2410-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-2415-count.jsonl\n"
+      "-rw-r--r--  1 root root  518K Sep  1 14:30 shuffle-word-2415-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  519K Sep  1 13:54 shuffle-word-2420-count.jsonl\n"
+      "-rw-r--r--  1 root root  515K Sep  1 14:30 shuffle-word-2420-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  518K Sep  1 13:54 shuffle-word-2425-count.jsonl\n"
+      "-rw-r--r--  1 root root  518K Sep  1 14:30 shuffle-word-2425-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  517K Sep  1 13:54 shuffle-word-2430-count.jsonl\n"
+      "-rw-r--r--  1 root root  516K Sep  1 14:30 shuffle-word-2430-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  518K Sep  1 13:54 shuffle-word-2435-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-2435-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  519K Sep  1 13:54 shuffle-word-2440-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-2440-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  519K Sep  1 13:54 shuffle-word-2445-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-2445-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   27K Sep  1 13:54 shuffle-word-245-count.jsonl\n"
+      "-rw-r--r--  1 root root   28K Sep  1 14:30 shuffle-word-245-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-2450-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-2450-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-2455-count.jsonl\n"
+      "-rw-r--r--  1 root root  516K Sep  1 14:30 shuffle-word-2455-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-2460-count.jsonl\n"
+      "-rw-r--r--  1 root root  519K Sep  1 14:30 shuffle-word-2460-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  515K Sep  1 13:54 shuffle-word-2465-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-2465-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  517K Sep  1 13:54 shuffle-word-2470-count.jsonl\n"
+      "-rw-r--r--  1 root root  518K Sep  1 14:30 shuffle-word-2470-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-2475-count.jsonl\n"
+      "-rw-r--r--  1 root root  516K Sep  1 14:30 shuffle-word-2475-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-2480-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-2480-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-2485-count.jsonl\n"
+      "-rw-r--r--  1 root root  516K Sep  1 14:30 shuffle-word-2485-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-2490-count.jsonl\n"
+      "-rw-r--r--  1 root root  519K Sep  1 14:30 shuffle-word-2490-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  518K Sep  1 13:54 shuffle-word-2495-count.jsonl\n"
+      "-rw-r--r--  1 root root  517K Sep  1 14:30 shuffle-word-2495-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   37K Sep  1 13:54 shuffle-word-25-count.jsonl\n"
+      "-rw-r--r--  1 root root   36K Sep  1 14:30 shuffle-word-25-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   28K Sep  1 13:54 shuffle-word-250-count.jsonl\n"
+      "-rw-r--r--  1 root root   27K Sep  1 14:30 shuffle-word-250-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  522K Sep  1 13:54 shuffle-word-2500-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-2500-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  516K Sep  1 13:54 shuffle-word-2505-count.jsonl\n"
+      "-rw-r--r--  1 root root  516K Sep  1 14:30 shuffle-word-2505-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  515K Sep  1 13:54 shuffle-word-2510-count.jsonl\n"
+      "-rw-r--r--  1 root root  515K Sep  1 14:30 shuffle-word-2510-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  514K Sep  1 13:54 shuffle-word-2515-count.jsonl\n"
+      "-rw-r--r--  1 root root  514K Sep  1 14:30 shuffle-word-2515-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  517K Sep  1 13:54 shuffle-word-2520-count.jsonl\n"
+      "-rw-r--r--  1 root root  516K Sep  1 14:30 shuffle-word-2520-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  514K Sep  1 13:54 shuffle-word-2525-count.jsonl\n"
+      "-rw-r--r--  1 root root  515K Sep  1 14:30 shuffle-word-2525-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  515K Sep  1 13:54 shuffle-word-2530-count.jsonl\n"
+      "-rw-r--r--  1 root root  516K Sep  1 14:30 shuffle-word-2530-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  518K Sep  1 13:54 shuffle-word-2535-count.jsonl\n"
+      "-rw-r--r--  1 root root  513K Sep  1 14:30 shuffle-word-2535-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  514K Sep  1 13:54 shuffle-word-2540-count.jsonl\n"
+      "-rw-r--r--  1 root root  514K Sep  1 14:30 shuffle-word-2540-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  517K Sep  1 13:54 shuffle-word-2545-count.jsonl\n"
+      "-rw-r--r--  1 root root  513K Sep  1 14:30 shuffle-word-2545-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   27K Sep  1 13:54 shuffle-word-255-count.jsonl\n"
+      "-rw-r--r--  1 root root   27K Sep  1 14:30 shuffle-word-255-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  516K Sep  1 13:54 shuffle-word-2550-count.jsonl\n"
+      "-rw-r--r--  1 root root  513K Sep  1 14:30 shuffle-word-2550-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  517K Sep  1 13:54 shuffle-word-2555-count.jsonl\n"
+      "-rw-r--r--  1 root root  514K Sep  1 14:30 shuffle-word-2555-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  516K Sep  1 13:54 shuffle-word-2560-count.jsonl\n"
+      "-rw-r--r--  1 root root  517K Sep  1 14:30 shuffle-word-2560-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  513K Sep  1 13:54 shuffle-word-2565-count.jsonl\n"
+      "-rw-r--r--  1 root root  514K Sep  1 14:30 shuffle-word-2565-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  513K Sep  1 13:54 shuffle-word-2570-count.jsonl\n"
+      "-rw-r--r--  1 root root  514K Sep  1 14:30 shuffle-word-2570-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  515K Sep  1 13:54 shuffle-word-2575-count.jsonl\n"
+      "-rw-r--r--  1 root root  512K Sep  1 14:30 shuffle-word-2575-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  517K Sep  1 13:54 shuffle-word-2580-count.jsonl\n"
+      "-rw-r--r--  1 root root  517K Sep  1 14:30 shuffle-word-2580-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  514K Sep  1 13:54 shuffle-word-2585-count.jsonl\n"
+      "-rw-r--r--  1 root root  515K Sep  1 14:30 shuffle-word-2585-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  513K Sep  1 13:54 shuffle-word-2590-count.jsonl\n"
+      "-rw-r--r--  1 root root  514K Sep  1 14:30 shuffle-word-2590-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  514K Sep  1 13:54 shuffle-word-2595-count.jsonl\n"
+      "-rw-r--r--  1 root root  515K Sep  1 14:30 shuffle-word-2595-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   26K Sep  1 13:54 shuffle-word-260-count.jsonl\n"
+      "-rw-r--r--  1 root root   27K Sep  1 14:30 shuffle-word-260-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  515K Sep  1 13:54 shuffle-word-2600-count.jsonl\n"
+      "-rw-r--r--  1 root root  515K Sep  1 14:30 shuffle-word-2600-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  512K Sep  1 13:54 shuffle-word-2605-count.jsonl\n"
+      "-rw-r--r--  1 root root  510K Sep  1 14:30 shuffle-word-2605-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  513K Sep  1 13:54 shuffle-word-2610-count.jsonl\n"
+      "-rw-r--r--  1 root root  510K Sep  1 14:30 shuffle-word-2610-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  512K Sep  1 13:54 shuffle-word-2615-count.jsonl\n"
+      "-rw-r--r--  1 root root  512K Sep  1 14:30 shuffle-word-2615-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  511K Sep  1 13:54 shuffle-word-2620-count.jsonl\n"
+      "-rw-r--r--  1 root root  510K Sep  1 14:30 shuffle-word-2620-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  510K Sep  1 13:54 shuffle-word-2625-count.jsonl\n"
+      "-rw-r--r--  1 root root  510K Sep  1 14:30 shuffle-word-2625-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  511K Sep  1 13:54 shuffle-word-2630-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-2630-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-2635-count.jsonl\n"
+      "-rw-r--r--  1 root root  512K Sep  1 14:30 shuffle-word-2635-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-2640-count.jsonl\n"
+      "-rw-r--r--  1 root root  511K Sep  1 14:30 shuffle-word-2640-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  510K Sep  1 13:54 shuffle-word-2645-count.jsonl\n"
+      "-rw-r--r--  1 root root  513K Sep  1 14:30 shuffle-word-2645-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   28K Sep  1 13:54 shuffle-word-265-count.jsonl\n"
+      "-rw-r--r--  1 root root   27K Sep  1 14:30 shuffle-word-265-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-2650-count.jsonl\n"
+      "-rw-r--r--  1 root root  512K Sep  1 14:30 shuffle-word-2650-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  515K Sep  1 13:54 shuffle-word-2655-count.jsonl\n"
+      "-rw-r--r--  1 root root  510K Sep  1 14:30 shuffle-word-2655-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  511K Sep  1 13:54 shuffle-word-2660-count.jsonl\n"
+      "-rw-r--r--  1 root root  511K Sep  1 14:30 shuffle-word-2660-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  510K Sep  1 13:54 shuffle-word-2665-count.jsonl\n"
+      "-rw-r--r--  1 root root  511K Sep  1 14:30 shuffle-word-2665-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  512K Sep  1 13:54 shuffle-word-2670-count.jsonl\n"
+      "-rw-r--r--  1 root root  513K Sep  1 14:30 shuffle-word-2670-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  512K Sep  1 13:54 shuffle-word-2675-count.jsonl\n"
+      "-rw-r--r--  1 root root  515K Sep  1 14:30 shuffle-word-2675-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  510K Sep  1 13:54 shuffle-word-2680-count.jsonl\n"
+      "-rw-r--r--  1 root root  512K Sep  1 14:30 shuffle-word-2680-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  510K Sep  1 13:54 shuffle-word-2685-count.jsonl\n"
+      "-rw-r--r--  1 root root  510K Sep  1 14:30 shuffle-word-2685-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  510K Sep  1 13:54 shuffle-word-2690-count.jsonl\n"
+      "-rw-r--r--  1 root root  511K Sep  1 14:30 shuffle-word-2690-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  510K Sep  1 13:54 shuffle-word-2695-count.jsonl\n"
+      "-rw-r--r--  1 root root  511K Sep  1 14:30 shuffle-word-2695-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   27K Sep  1 13:54 shuffle-word-270-count.jsonl\n"
+      "-rw-r--r--  1 root root   27K Sep  1 14:30 shuffle-word-270-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  512K Sep  1 13:54 shuffle-word-2700-count.jsonl\n"
+      "-rw-r--r--  1 root root  511K Sep  1 14:30 shuffle-word-2700-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-2705-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-2705-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-2710-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-2710-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-2715-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-2715-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-2720-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-2720-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-2725-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-2725-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  511K Sep  1 13:54 shuffle-word-2730-count.jsonl\n"
+      "-rw-r--r--  1 root root  510K Sep  1 14:30 shuffle-word-2730-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  510K Sep  1 13:54 shuffle-word-2735-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-2735-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-2740-count.jsonl\n"
+      "-rw-r--r--  1 root root  510K Sep  1 14:30 shuffle-word-2740-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-2745-count.jsonl\n"
+      "-rw-r--r--  1 root root  510K Sep  1 14:30 shuffle-word-2745-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   27K Sep  1 13:54 shuffle-word-275-count.jsonl\n"
+      "-rw-r--r--  1 root root   28K Sep  1 14:30 shuffle-word-275-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-2750-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-2750-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-2755-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-2755-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-2760-count.jsonl\n"
+      "-rw-r--r--  1 root root  510K Sep  1 14:30 shuffle-word-2760-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-2765-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-2765-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-2770-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-2770-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-2775-count.jsonl\n"
+      "-rw-r--r--  1 root root  511K Sep  1 14:30 shuffle-word-2775-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-2780-count.jsonl\n"
+      "-rw-r--r--  1 root root  510K Sep  1 14:30 shuffle-word-2780-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-2785-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-2785-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-2790-count.jsonl\n"
+      "-rw-r--r--  1 root root  511K Sep  1 14:30 shuffle-word-2790-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-2795-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-2795-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   27K Sep  1 13:54 shuffle-word-280-count.jsonl\n"
+      "-rw-r--r--  1 root root   27K Sep  1 14:30 shuffle-word-280-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-2800-count.jsonl\n"
+      "-rw-r--r--  1 root root  508K Sep  1 14:30 shuffle-word-2800-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-2805-count.jsonl\n"
+      "-rw-r--r--  1 root root  508K Sep  1 14:30 shuffle-word-2805-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-2810-count.jsonl\n"
+      "-rw-r--r--  1 root root  508K Sep  1 14:30 shuffle-word-2810-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-2815-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-2815-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-2820-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-2820-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-2825-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-2825-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-2830-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-2830-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-2835-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-2835-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-2840-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-2840-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-2845-count.jsonl\n"
+      "-rw-r--r--  1 root root  508K Sep  1 14:30 shuffle-word-2845-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   27K Sep  1 13:54 shuffle-word-285-count.jsonl\n"
+      "-rw-r--r--  1 root root   27K Sep  1 14:30 shuffle-word-285-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-2850-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-2850-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-2855-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-2855-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-2860-count.jsonl\n"
+      "-rw-r--r--  1 root root  508K Sep  1 14:30 shuffle-word-2860-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-2865-count.jsonl\n"
+      "-rw-r--r--  1 root root  508K Sep  1 14:30 shuffle-word-2865-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-2870-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-2870-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-2875-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-2875-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-2880-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-2880-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-2885-count.jsonl\n"
+      "-rw-r--r--  1 root root  508K Sep  1 14:30 shuffle-word-2885-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-2890-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-2890-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-2895-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-2895-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   27K Sep  1 13:54 shuffle-word-290-count.jsonl\n"
+      "-rw-r--r--  1 root root   27K Sep  1 14:30 shuffle-word-290-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-2900-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-2900-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-2905-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-2905-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-2910-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-2910-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-2915-count.jsonl\n"
+      "-rw-r--r--  1 root root  508K Sep  1 14:30 shuffle-word-2915-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-2920-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-2920-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-2925-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-2925-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-2930-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-2930-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-2935-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-2935-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-2940-count.jsonl\n"
+      "-rw-r--r--  1 root root  508K Sep  1 14:30 shuffle-word-2940-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-2945-count.jsonl\n"
+      "-rw-r--r--  1 root root  508K Sep  1 14:30 shuffle-word-2945-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   27K Sep  1 13:54 shuffle-word-295-count.jsonl\n"
+      "-rw-r--r--  1 root root   26K Sep  1 14:30 shuffle-word-295-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-2950-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-2950-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-2955-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-2955-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-2960-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-2960-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-2965-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-2965-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-2970-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-2970-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-2975-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-2975-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-2980-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-2980-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-2985-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-2985-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-2990-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-2990-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-2995-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-2995-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   33K Sep  1 13:54 shuffle-word-30-count.jsonl\n"
+      "-rw-r--r--  1 root root   35K Sep  1 14:30 shuffle-word-30-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   28K Sep  1 13:54 shuffle-word-300-count.jsonl\n"
+      "-rw-r--r--  1 root root   27K Sep  1 14:30 shuffle-word-300-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-3000-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3000-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3005-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3005-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3010-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3010-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3015-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3015-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3020-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3020-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-3025-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3025-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3030-count.jsonl\n"
+      "-rw-r--r--  1 root root  508K Sep  1 14:30 shuffle-word-3030-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3035-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3035-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3040-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3040-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3045-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3045-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   26K Sep  1 13:54 shuffle-word-305-count.jsonl\n"
+      "-rw-r--r--  1 root root   26K Sep  1 14:30 shuffle-word-305-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3050-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3050-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3055-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3055-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-3060-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3060-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-3065-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3065-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-3070-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3070-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3075-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3075-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3080-count.jsonl\n"
+      "-rw-r--r--  1 root root  508K Sep  1 14:30 shuffle-word-3080-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3085-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3085-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3090-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3090-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3095-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3095-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   26K Sep  1 13:54 shuffle-word-310-count.jsonl\n"
+      "-rw-r--r--  1 root root   27K Sep  1 14:30 shuffle-word-310-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3100-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3100-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3105-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3105-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3110-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3110-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3115-count.jsonl\n"
+      "-rw-r--r--  1 root root  508K Sep  1 14:30 shuffle-word-3115-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3120-count.jsonl\n"
+      "-rw-r--r--  1 root root  508K Sep  1 14:30 shuffle-word-3120-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-3125-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3125-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-3130-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3130-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3135-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3135-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3140-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3140-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3145-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3145-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   26K Sep  1 13:54 shuffle-word-315-count.jsonl\n"
+      "-rw-r--r--  1 root root   27K Sep  1 14:30 shuffle-word-315-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-3150-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3150-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3155-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3155-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3160-count.jsonl\n"
+      "-rw-r--r--  1 root root  508K Sep  1 14:30 shuffle-word-3160-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3165-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3165-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3170-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3170-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-3175-count.jsonl\n"
+      "-rw-r--r--  1 root root  508K Sep  1 14:30 shuffle-word-3175-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3180-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3180-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3185-count.jsonl\n"
+      "-rw-r--r--  1 root root  508K Sep  1 14:30 shuffle-word-3185-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-3190-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3190-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3195-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3195-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   27K Sep  1 13:54 shuffle-word-320-count.jsonl\n"
+      "-rw-r--r--  1 root root   28K Sep  1 14:30 shuffle-word-320-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-3200-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3200-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3205-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3205-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3210-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3210-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-3215-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3215-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3220-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3220-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-3225-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3225-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-3230-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3230-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3235-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3235-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3240-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3240-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3245-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3245-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   27K Sep  1 13:54 shuffle-word-325-count.jsonl\n"
+      "-rw-r--r--  1 root root   27K Sep  1 14:30 shuffle-word-325-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-3250-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3250-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3255-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3255-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3260-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3260-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3265-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3265-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3270-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3270-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3275-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3275-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3280-count.jsonl\n"
+      "-rw-r--r--  1 root root  508K Sep  1 14:30 shuffle-word-3280-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3285-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3285-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3290-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3290-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3295-count.jsonl\n"
+      "-rw-r--r--  1 root root  508K Sep  1 14:30 shuffle-word-3295-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   26K Sep  1 13:54 shuffle-word-330-count.jsonl\n"
+      "-rw-r--r--  1 root root   27K Sep  1 14:30 shuffle-word-330-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3300-count.jsonl\n"
+      "-rw-r--r--  1 root root  508K Sep  1 14:30 shuffle-word-3300-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-3305-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3305-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-3310-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3310-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3315-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3315-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-3320-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3320-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-3325-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3325-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3330-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3330-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3335-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3335-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3340-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3340-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3345-count.jsonl\n"
+      "-rw-r--r--  1 root root  508K Sep  1 14:30 shuffle-word-3345-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   27K Sep  1 13:54 shuffle-word-335-count.jsonl\n"
+      "-rw-r--r--  1 root root   26K Sep  1 14:30 shuffle-word-335-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3350-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3350-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3355-count.jsonl\n"
+      "-rw-r--r--  1 root root  508K Sep  1 14:30 shuffle-word-3355-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3360-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3360-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3365-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3365-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-3370-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3370-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3375-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3375-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-3380-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3380-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3385-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3385-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3390-count.jsonl\n"
+      "-rw-r--r--  1 root root  508K Sep  1 14:30 shuffle-word-3390-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3395-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3395-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   27K Sep  1 13:54 shuffle-word-340-count.jsonl\n"
+      "-rw-r--r--  1 root root   27K Sep  1 14:30 shuffle-word-340-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-3400-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3400-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3405-count.jsonl\n"
+      "-rw-r--r--  1 root root  508K Sep  1 14:30 shuffle-word-3405-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3410-count.jsonl\n"
+      "-rw-r--r--  1 root root  508K Sep  1 14:30 shuffle-word-3410-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3415-count.jsonl\n"
+      "-rw-r--r--  1 root root  508K Sep  1 14:30 shuffle-word-3415-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3420-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3420-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3425-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3425-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3430-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3430-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3435-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3435-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3440-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3440-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3445-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3445-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   28K Sep  1 13:54 shuffle-word-345-count.jsonl\n"
+      "-rw-r--r--  1 root root   27K Sep  1 14:30 shuffle-word-345-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-3450-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3450-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3455-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3455-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3460-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3460-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3465-count.jsonl\n"
+      "-rw-r--r--  1 root root  508K Sep  1 14:30 shuffle-word-3465-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3470-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3470-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3475-count.jsonl\n"
+      "-rw-r--r--  1 root root  508K Sep  1 14:30 shuffle-word-3475-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3480-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3480-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3485-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3485-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-3490-count.jsonl\n"
+      "-rw-r--r--  1 root root  508K Sep  1 14:30 shuffle-word-3490-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-3495-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3495-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   34K Sep  1 13:54 shuffle-word-35-count.jsonl\n"
+      "-rw-r--r--  1 root root   31K Sep  1 14:30 shuffle-word-35-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   28K Sep  1 13:54 shuffle-word-350-count.jsonl\n"
+      "-rw-r--r--  1 root root   27K Sep  1 14:30 shuffle-word-350-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-3500-count.jsonl\n"
+      "-rw-r--r--  1 root root  508K Sep  1 14:30 shuffle-word-3500-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3505-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3505-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3510-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3510-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3515-count.jsonl\n"
+      "-rw-r--r--  1 root root  508K Sep  1 14:30 shuffle-word-3515-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-3520-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3520-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3525-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3525-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-3530-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3530-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3535-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3535-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-3540-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3540-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3545-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3545-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   27K Sep  1 13:54 shuffle-word-355-count.jsonl\n"
+      "-rw-r--r--  1 root root   26K Sep  1 14:30 shuffle-word-355-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3550-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3550-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-3555-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3555-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3560-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3560-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3565-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3565-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3570-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3570-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3575-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3575-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3580-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3580-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3585-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3585-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-3590-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3590-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3595-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3595-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   26K Sep  1 13:54 shuffle-word-360-count.jsonl\n"
+      "-rw-r--r--  1 root root   27K Sep  1 14:30 shuffle-word-360-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-3600-count.jsonl\n"
+      "-rw-r--r--  1 root root  508K Sep  1 14:30 shuffle-word-3600-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3605-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3605-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3610-count.jsonl\n"
+      "-rw-r--r--  1 root root  508K Sep  1 14:30 shuffle-word-3610-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3615-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3615-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3620-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3620-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3625-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3625-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3630-count.jsonl\n"
+      "-rw-r--r--  1 root root  508K Sep  1 14:30 shuffle-word-3630-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3635-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3635-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3640-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3640-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3645-count.jsonl\n"
+      "-rw-r--r--  1 root root  508K Sep  1 14:30 shuffle-word-3645-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   27K Sep  1 13:54 shuffle-word-365-count.jsonl\n"
+      "-rw-r--r--  1 root root   26K Sep  1 14:30 shuffle-word-365-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-3650-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3650-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3655-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3655-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3660-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3660-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3665-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3665-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3670-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3670-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3675-count.jsonl\n"
+      "-rw-r--r--  1 root root  508K Sep  1 14:30 shuffle-word-3675-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-3680-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3680-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-3685-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3685-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-3690-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3690-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3695-count.jsonl\n"
+      "-rw-r--r--  1 root root  508K Sep  1 14:30 shuffle-word-3695-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   26K Sep  1 13:54 shuffle-word-370-count.jsonl\n"
+      "-rw-r--r--  1 root root   26K Sep  1 14:30 shuffle-word-370-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3700-count.jsonl\n"
+      "-rw-r--r--  1 root root  508K Sep  1 14:30 shuffle-word-3700-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3705-count.jsonl\n"
+      "-rw-r--r--  1 root root  508K Sep  1 14:30 shuffle-word-3705-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3710-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3710-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3715-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3715-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3720-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3720-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-3725-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3725-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3730-count.jsonl\n"
+      "-rw-r--r--  1 root root  508K Sep  1 14:30 shuffle-word-3730-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3735-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3735-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3740-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3740-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3745-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3745-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   27K Sep  1 13:54 shuffle-word-375-count.jsonl\n"
+      "-rw-r--r--  1 root root   27K Sep  1 14:30 shuffle-word-375-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3750-count.jsonl\n"
+      "-rw-r--r--  1 root root  508K Sep  1 14:30 shuffle-word-3750-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3755-count.jsonl\n"
+      "-rw-r--r--  1 root root  508K Sep  1 14:30 shuffle-word-3755-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-3760-count.jsonl\n"
+      "-rw-r--r--  1 root root  508K Sep  1 14:30 shuffle-word-3760-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-3765-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3765-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3770-count.jsonl\n"
+      "-rw-r--r--  1 root root  508K Sep  1 14:30 shuffle-word-3770-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3775-count.jsonl\n"
+      "-rw-r--r--  1 root root  508K Sep  1 14:30 shuffle-word-3775-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3780-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3780-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-3785-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3785-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3790-count.jsonl\n"
+      "-rw-r--r--  1 root root  508K Sep  1 14:30 shuffle-word-3790-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-3795-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3795-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   26K Sep  1 13:54 shuffle-word-380-count.jsonl\n"
+      "-rw-r--r--  1 root root   27K Sep  1 14:30 shuffle-word-380-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3800-count.jsonl\n"
+      "-rw-r--r--  1 root root  508K Sep  1 14:30 shuffle-word-3800-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-3805-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3805-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3810-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3810-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3815-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3815-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-3820-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3820-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-3825-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3825-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3830-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3830-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3835-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3835-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3840-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3840-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3845-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3845-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   26K Sep  1 13:54 shuffle-word-385-count.jsonl\n"
+      "-rw-r--r--  1 root root   27K Sep  1 14:30 shuffle-word-385-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-3850-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3850-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-3855-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3855-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3860-count.jsonl\n"
+      "-rw-r--r--  1 root root  508K Sep  1 14:30 shuffle-word-3860-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3865-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3865-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3870-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3870-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-3875-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3875-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-3880-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3880-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-3885-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3885-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3890-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3890-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3895-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3895-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   26K Sep  1 13:54 shuffle-word-390-count.jsonl\n"
+      "-rw-r--r--  1 root root   27K Sep  1 14:30 shuffle-word-390-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3900-count.jsonl\n"
+      "-rw-r--r--  1 root root  508K Sep  1 14:30 shuffle-word-3900-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3905-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3905-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3910-count.jsonl\n"
+      "-rw-r--r--  1 root root  508K Sep  1 14:30 shuffle-word-3910-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-3915-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3915-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3920-count.jsonl\n"
+      "-rw-r--r--  1 root root  508K Sep  1 14:30 shuffle-word-3920-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-3925-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3925-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3930-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3930-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3935-count.jsonl\n"
+      "-rw-r--r--  1 root root  508K Sep  1 14:30 shuffle-word-3935-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-3940-count.jsonl\n"
+      "-rw-r--r--  1 root root  508K Sep  1 14:30 shuffle-word-3940-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3945-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3945-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   27K Sep  1 13:54 shuffle-word-395-count.jsonl\n"
+      "-rw-r--r--  1 root root   27K Sep  1 14:30 shuffle-word-395-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3950-count.jsonl\n"
+      "-rw-r--r--  1 root root  508K Sep  1 14:30 shuffle-word-3950-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3955-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3955-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3960-count.jsonl\n"
+      "-rw-r--r--  1 root root  508K Sep  1 14:30 shuffle-word-3960-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3965-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3965-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  508K Sep  1 13:54 shuffle-word-3970-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3970-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3975-count.jsonl\n"
+      "-rw-r--r--  1 root root  508K Sep  1 14:30 shuffle-word-3975-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3980-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3980-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3985-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3985-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3990-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3990-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-3995-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-3995-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   33K Sep  1 13:54 shuffle-word-40-count.jsonl\n"
+      "-rw-r--r--  1 root root   31K Sep  1 14:30 shuffle-word-40-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   28K Sep  1 13:54 shuffle-word-400-count.jsonl\n"
+      "-rw-r--r--  1 root root   27K Sep  1 14:30 shuffle-word-400-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  509K Sep  1 13:54 shuffle-word-4000-count.jsonl\n"
+      "-rw-r--r--  1 root root  509K Sep  1 14:30 shuffle-word-4000-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   27K Sep  1 13:54 shuffle-word-405-count.jsonl\n"
+      "-rw-r--r--  1 root root   27K Sep  1 14:30 shuffle-word-405-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   27K Sep  1 13:54 shuffle-word-410-count.jsonl\n"
+      "-rw-r--r--  1 root root   27K Sep  1 14:30 shuffle-word-410-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   27K Sep  1 13:54 shuffle-word-415-count.jsonl\n"
+      "-rw-r--r--  1 root root   27K Sep  1 14:30 shuffle-word-415-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   27K Sep  1 13:54 shuffle-word-420-count.jsonl\n"
+      "-rw-r--r--  1 root root   28K Sep  1 14:30 shuffle-word-420-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   26K Sep  1 13:54 shuffle-word-425-count.jsonl\n"
+      "-rw-r--r--  1 root root   26K Sep  1 14:30 shuffle-word-425-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   27K Sep  1 13:54 shuffle-word-430-count.jsonl\n"
+      "-rw-r--r--  1 root root   26K Sep  1 14:30 shuffle-word-430-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   27K Sep  1 13:54 shuffle-word-435-count.jsonl\n"
+      "-rw-r--r--  1 root root   27K Sep  1 14:30 shuffle-word-435-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   27K Sep  1 13:54 shuffle-word-440-count.jsonl\n"
+      "-rw-r--r--  1 root root   26K Sep  1 14:30 shuffle-word-440-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   28K Sep  1 13:54 shuffle-word-445-count.jsonl\n"
+      "-rw-r--r--  1 root root   27K Sep  1 14:30 shuffle-word-445-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   29K Sep  1 13:54 shuffle-word-45-count.jsonl\n"
+      "-rw-r--r--  1 root root   31K Sep  1 14:30 shuffle-word-45-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   27K Sep  1 13:54 shuffle-word-450-count.jsonl\n"
+      "-rw-r--r--  1 root root   26K Sep  1 14:30 shuffle-word-450-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   27K Sep  1 13:54 shuffle-word-455-count.jsonl\n"
+      "-rw-r--r--  1 root root   26K Sep  1 14:30 shuffle-word-455-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   26K Sep  1 13:54 shuffle-word-460-count.jsonl\n"
+      "-rw-r--r--  1 root root   27K Sep  1 14:30 shuffle-word-460-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   27K Sep  1 13:54 shuffle-word-465-count.jsonl\n"
+      "-rw-r--r--  1 root root   27K Sep  1 14:30 shuffle-word-465-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   27K Sep  1 13:54 shuffle-word-470-count.jsonl\n"
+      "-rw-r--r--  1 root root   27K Sep  1 14:30 shuffle-word-470-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   28K Sep  1 13:54 shuffle-word-475-count.jsonl\n"
+      "-rw-r--r--  1 root root   27K Sep  1 14:30 shuffle-word-475-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   27K Sep  1 13:54 shuffle-word-480-count.jsonl\n"
+      "-rw-r--r--  1 root root   26K Sep  1 14:30 shuffle-word-480-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   28K Sep  1 13:54 shuffle-word-485-count.jsonl\n"
+      "-rw-r--r--  1 root root   27K Sep  1 14:30 shuffle-word-485-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   27K Sep  1 13:54 shuffle-word-490-count.jsonl\n"
+      "-rw-r--r--  1 root root   27K Sep  1 14:30 shuffle-word-490-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   27K Sep  1 13:54 shuffle-word-495-count.jsonl\n"
+      "-rw-r--r--  1 root root   27K Sep  1 14:30 shuffle-word-495-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   80K Sep  1 13:54 shuffle-word-5-count.jsonl\n"
+      "-rw-r--r--  1 root root   86K Sep  1 14:30 shuffle-word-5-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   30K Sep  1 13:54 shuffle-word-50-count.jsonl\n"
+      "-rw-r--r--  1 root root   30K Sep  1 14:30 shuffle-word-50-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   27K Sep  1 13:54 shuffle-word-500-count.jsonl\n"
+      "-rw-r--r--  1 root root   28K Sep  1 14:30 shuffle-word-500-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  523K Sep  1 13:54 shuffle-word-505-count.jsonl\n"
+      "-rw-r--r--  1 root root  526K Sep  1 14:30 shuffle-word-505-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  527K Sep  1 13:54 shuffle-word-510-count.jsonl\n"
+      "-rw-r--r--  1 root root  526K Sep  1 14:30 shuffle-word-510-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  526K Sep  1 13:54 shuffle-word-515-count.jsonl\n"
+      "-rw-r--r--  1 root root  525K Sep  1 14:30 shuffle-word-515-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  529K Sep  1 13:54 shuffle-word-520-count.jsonl\n"
+      "-rw-r--r--  1 root root  526K Sep  1 14:30 shuffle-word-520-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  526K Sep  1 13:54 shuffle-word-525-count.jsonl\n"
+      "-rw-r--r--  1 root root  527K Sep  1 14:30 shuffle-word-525-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  526K Sep  1 13:54 shuffle-word-530-count.jsonl\n"
+      "-rw-r--r--  1 root root  524K Sep  1 14:30 shuffle-word-530-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  527K Sep  1 13:54 shuffle-word-535-count.jsonl\n"
+      "-rw-r--r--  1 root root  528K Sep  1 14:30 shuffle-word-535-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  527K Sep  1 13:54 shuffle-word-540-count.jsonl\n"
+      "-rw-r--r--  1 root root  530K Sep  1 14:30 shuffle-word-540-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  527K Sep  1 13:54 shuffle-word-545-count.jsonl\n"
+      "-rw-r--r--  1 root root  524K Sep  1 14:30 shuffle-word-545-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   30K Sep  1 13:54 shuffle-word-55-count.jsonl\n"
+      "-rw-r--r--  1 root root   31K Sep  1 14:30 shuffle-word-55-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  526K Sep  1 13:54 shuffle-word-550-count.jsonl\n"
+      "-rw-r--r--  1 root root  528K Sep  1 14:30 shuffle-word-550-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  525K Sep  1 13:54 shuffle-word-555-count.jsonl\n"
+      "-rw-r--r--  1 root root  527K Sep  1 14:30 shuffle-word-555-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  525K Sep  1 13:54 shuffle-word-560-count.jsonl\n"
+      "-rw-r--r--  1 root root  525K Sep  1 14:30 shuffle-word-560-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  524K Sep  1 13:54 shuffle-word-565-count.jsonl\n"
+      "-rw-r--r--  1 root root  527K Sep  1 14:30 shuffle-word-565-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  524K Sep  1 13:54 shuffle-word-570-count.jsonl\n"
+      "-rw-r--r--  1 root root  528K Sep  1 14:30 shuffle-word-570-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  525K Sep  1 13:54 shuffle-word-575-count.jsonl\n"
+      "-rw-r--r--  1 root root  526K Sep  1 14:30 shuffle-word-575-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  524K Sep  1 13:54 shuffle-word-580-count.jsonl\n"
+      "-rw-r--r--  1 root root  527K Sep  1 14:30 shuffle-word-580-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  525K Sep  1 13:54 shuffle-word-585-count.jsonl\n"
+      "-rw-r--r--  1 root root  527K Sep  1 14:30 shuffle-word-585-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  526K Sep  1 13:54 shuffle-word-590-count.jsonl\n"
+      "-rw-r--r--  1 root root  529K Sep  1 14:30 shuffle-word-590-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  525K Sep  1 13:54 shuffle-word-595-count.jsonl\n"
+      "-rw-r--r--  1 root root  524K Sep  1 14:30 shuffle-word-595-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   33K Sep  1 13:54 shuffle-word-60-count.jsonl\n"
+      "-rw-r--r--  1 root root   31K Sep  1 14:30 shuffle-word-60-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  531K Sep  1 13:54 shuffle-word-600-count.jsonl\n"
+      "-rw-r--r--  1 root root  524K Sep  1 14:30 shuffle-word-600-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  523K Sep  1 13:54 shuffle-word-605-count.jsonl\n"
+      "-rw-r--r--  1 root root  528K Sep  1 14:30 shuffle-word-605-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  522K Sep  1 13:54 shuffle-word-610-count.jsonl\n"
+      "-rw-r--r--  1 root root  524K Sep  1 14:30 shuffle-word-610-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  525K Sep  1 13:54 shuffle-word-615-count.jsonl\n"
+      "-rw-r--r--  1 root root  524K Sep  1 14:30 shuffle-word-615-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  525K Sep  1 13:54 shuffle-word-620-count.jsonl\n"
+      "-rw-r--r--  1 root root  525K Sep  1 14:30 shuffle-word-620-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-625-count.jsonl\n"
+      "-rw-r--r--  1 root root  524K Sep  1 14:30 shuffle-word-625-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  523K Sep  1 13:54 shuffle-word-630-count.jsonl\n"
+      "-rw-r--r--  1 root root  526K Sep  1 14:30 shuffle-word-630-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  527K Sep  1 13:54 shuffle-word-635-count.jsonl\n"
+      "-rw-r--r--  1 root root  524K Sep  1 14:30 shuffle-word-635-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  523K Sep  1 13:54 shuffle-word-640-count.jsonl\n"
+      "-rw-r--r--  1 root root  525K Sep  1 14:30 shuffle-word-640-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  524K Sep  1 13:54 shuffle-word-645-count.jsonl\n"
+      "-rw-r--r--  1 root root  523K Sep  1 14:30 shuffle-word-645-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   29K Sep  1 13:54 shuffle-word-65-count.jsonl\n"
+      "-rw-r--r--  1 root root   31K Sep  1 14:30 shuffle-word-65-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  523K Sep  1 13:54 shuffle-word-650-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-650-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  525K Sep  1 13:54 shuffle-word-655-count.jsonl\n"
+      "-rw-r--r--  1 root root  524K Sep  1 14:30 shuffle-word-655-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  527K Sep  1 13:54 shuffle-word-660-count.jsonl\n"
+      "-rw-r--r--  1 root root  523K Sep  1 14:30 shuffle-word-660-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  523K Sep  1 13:54 shuffle-word-665-count.jsonl\n"
+      "-rw-r--r--  1 root root  524K Sep  1 14:30 shuffle-word-665-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  526K Sep  1 13:54 shuffle-word-670-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-670-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  523K Sep  1 13:54 shuffle-word-675-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-675-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  522K Sep  1 13:54 shuffle-word-680-count.jsonl\n"
+      "-rw-r--r--  1 root root  525K Sep  1 14:30 shuffle-word-680-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  525K Sep  1 13:54 shuffle-word-685-count.jsonl\n"
+      "-rw-r--r--  1 root root  524K Sep  1 14:30 shuffle-word-685-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  524K Sep  1 13:54 shuffle-word-690-count.jsonl\n"
+      "-rw-r--r--  1 root root  524K Sep  1 14:30 shuffle-word-690-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  525K Sep  1 13:54 shuffle-word-695-count.jsonl\n"
+      "-rw-r--r--  1 root root  523K Sep  1 14:30 shuffle-word-695-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   29K Sep  1 13:54 shuffle-word-70-count.jsonl\n"
+      "-rw-r--r--  1 root root   29K Sep  1 14:30 shuffle-word-70-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  525K Sep  1 13:54 shuffle-word-700-count.jsonl\n"
+      "-rw-r--r--  1 root root  524K Sep  1 14:30 shuffle-word-700-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  523K Sep  1 13:54 shuffle-word-705-count.jsonl\n"
+      "-rw-r--r--  1 root root  525K Sep  1 14:30 shuffle-word-705-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  525K Sep  1 13:54 shuffle-word-710-count.jsonl\n"
+      "-rw-r--r--  1 root root  523K Sep  1 14:30 shuffle-word-710-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  525K Sep  1 13:54 shuffle-word-715-count.jsonl\n"
+      "-rw-r--r--  1 root root  524K Sep  1 14:30 shuffle-word-715-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  524K Sep  1 13:54 shuffle-word-720-count.jsonl\n"
+      "-rw-r--r--  1 root root  523K Sep  1 14:30 shuffle-word-720-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  524K Sep  1 13:54 shuffle-word-725-count.jsonl\n"
+      "-rw-r--r--  1 root root  525K Sep  1 14:30 shuffle-word-725-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  526K Sep  1 13:54 shuffle-word-730-count.jsonl\n"
+      "-rw-r--r--  1 root root  526K Sep  1 14:30 shuffle-word-730-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  525K Sep  1 13:54 shuffle-word-735-count.jsonl\n"
+      "-rw-r--r--  1 root root  523K Sep  1 14:30 shuffle-word-735-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  527K Sep  1 13:54 shuffle-word-740-count.jsonl\n"
+      "-rw-r--r--  1 root root  524K Sep  1 14:30 shuffle-word-740-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  524K Sep  1 13:54 shuffle-word-745-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-745-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   30K Sep  1 13:54 shuffle-word-75-count.jsonl\n"
+      "-rw-r--r--  1 root root   29K Sep  1 14:30 shuffle-word-75-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  525K Sep  1 13:54 shuffle-word-750-count.jsonl\n"
+      "-rw-r--r--  1 root root  523K Sep  1 14:30 shuffle-word-750-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  522K Sep  1 13:54 shuffle-word-755-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-755-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  525K Sep  1 13:54 shuffle-word-760-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-760-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  525K Sep  1 13:54 shuffle-word-765-count.jsonl\n"
+      "-rw-r--r--  1 root root  524K Sep  1 14:30 shuffle-word-765-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  526K Sep  1 13:54 shuffle-word-770-count.jsonl\n"
+      "-rw-r--r--  1 root root  525K Sep  1 14:30 shuffle-word-770-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  523K Sep  1 13:54 shuffle-word-775-count.jsonl\n"
+      "-rw-r--r--  1 root root  524K Sep  1 14:30 shuffle-word-775-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  522K Sep  1 13:54 shuffle-word-780-count.jsonl\n"
+      "-rw-r--r--  1 root root  524K Sep  1 14:30 shuffle-word-780-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  522K Sep  1 13:54 shuffle-word-785-count.jsonl\n"
+      "-rw-r--r--  1 root root  525K Sep  1 14:30 shuffle-word-785-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  525K Sep  1 13:54 shuffle-word-790-count.jsonl\n"
+      "-rw-r--r--  1 root root  523K Sep  1 14:30 shuffle-word-790-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  526K Sep  1 13:54 shuffle-word-795-count.jsonl\n"
+      "-rw-r--r--  1 root root  523K Sep  1 14:30 shuffle-word-795-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   29K Sep  1 13:54 shuffle-word-80-count.jsonl\n"
+      "-rw-r--r--  1 root root   31K Sep  1 14:30 shuffle-word-80-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  524K Sep  1 13:54 shuffle-word-800-count.jsonl\n"
+      "-rw-r--r--  1 root root  524K Sep  1 14:30 shuffle-word-800-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  523K Sep  1 13:54 shuffle-word-805-count.jsonl\n"
+      "-rw-r--r--  1 root root  523K Sep  1 14:30 shuffle-word-805-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-810-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-810-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  522K Sep  1 13:54 shuffle-word-815-count.jsonl\n"
+      "-rw-r--r--  1 root root  524K Sep  1 14:30 shuffle-word-815-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  524K Sep  1 13:54 shuffle-word-820-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-820-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  525K Sep  1 13:54 shuffle-word-825-count.jsonl\n"
+      "-rw-r--r--  1 root root  525K Sep  1 14:30 shuffle-word-825-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  524K Sep  1 13:54 shuffle-word-830-count.jsonl\n"
+      "-rw-r--r--  1 root root  523K Sep  1 14:30 shuffle-word-830-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  524K Sep  1 13:54 shuffle-word-835-count.jsonl\n"
+      "-rw-r--r--  1 root root  525K Sep  1 14:30 shuffle-word-835-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  522K Sep  1 13:54 shuffle-word-840-count.jsonl\n"
+      "-rw-r--r--  1 root root  523K Sep  1 14:30 shuffle-word-840-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  524K Sep  1 13:54 shuffle-word-845-count.jsonl\n"
+      "-rw-r--r--  1 root root  524K Sep  1 14:30 shuffle-word-845-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   30K Sep  1 13:54 shuffle-word-85-count.jsonl\n"
+      "-rw-r--r--  1 root root   29K Sep  1 14:30 shuffle-word-85-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  522K Sep  1 13:54 shuffle-word-850-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-850-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  523K Sep  1 13:54 shuffle-word-855-count.jsonl\n"
+      "-rw-r--r--  1 root root  526K Sep  1 14:30 shuffle-word-855-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  522K Sep  1 13:54 shuffle-word-860-count.jsonl\n"
+      "-rw-r--r--  1 root root  527K Sep  1 14:30 shuffle-word-860-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  522K Sep  1 13:54 shuffle-word-865-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-865-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  524K Sep  1 13:54 shuffle-word-870-count.jsonl\n"
+      "-rw-r--r--  1 root root  526K Sep  1 14:30 shuffle-word-870-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  519K Sep  1 13:54 shuffle-word-875-count.jsonl\n"
+      "-rw-r--r--  1 root root  519K Sep  1 14:30 shuffle-word-875-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  524K Sep  1 13:54 shuffle-word-880-count.jsonl\n"
+      "-rw-r--r--  1 root root  524K Sep  1 14:30 shuffle-word-880-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  523K Sep  1 13:54 shuffle-word-885-count.jsonl\n"
+      "-rw-r--r--  1 root root  517K Sep  1 14:30 shuffle-word-885-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  519K Sep  1 13:54 shuffle-word-890-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-890-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  524K Sep  1 13:54 shuffle-word-895-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-895-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   29K Sep  1 13:54 shuffle-word-90-count.jsonl\n"
+      "-rw-r--r--  1 root root   31K Sep  1 14:30 shuffle-word-90-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  525K Sep  1 13:54 shuffle-word-900-count.jsonl\n"
+      "-rw-r--r--  1 root root  523K Sep  1 14:30 shuffle-word-900-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-905-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-905-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  522K Sep  1 13:54 shuffle-word-910-count.jsonl\n"
+      "-rw-r--r--  1 root root  524K Sep  1 14:30 shuffle-word-910-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  522K Sep  1 13:54 shuffle-word-915-count.jsonl\n"
+      "-rw-r--r--  1 root root  520K Sep  1 14:30 shuffle-word-915-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  524K Sep  1 13:54 shuffle-word-920-count.jsonl\n"
+      "-rw-r--r--  1 root root  523K Sep  1 14:30 shuffle-word-920-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-925-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-925-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  523K Sep  1 13:54 shuffle-word-930-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-930-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-935-count.jsonl\n"
+      "-rw-r--r--  1 root root  523K Sep  1 14:30 shuffle-word-935-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  525K Sep  1 13:54 shuffle-word-940-count.jsonl\n"
+      "-rw-r--r--  1 root root  524K Sep  1 14:30 shuffle-word-940-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  522K Sep  1 13:54 shuffle-word-945-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-945-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   30K Sep  1 13:54 shuffle-word-95-count.jsonl\n"
+      "-rw-r--r--  1 root root   30K Sep  1 14:30 shuffle-word-95-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  523K Sep  1 13:54 shuffle-word-950-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-950-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  522K Sep  1 13:54 shuffle-word-955-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-955-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  519K Sep  1 13:54 shuffle-word-960-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-960-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  523K Sep  1 13:54 shuffle-word-965-count.jsonl\n"
+      "-rw-r--r--  1 root root  523K Sep  1 14:30 shuffle-word-965-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  526K Sep  1 13:54 shuffle-word-970-count.jsonl\n"
+      "-rw-r--r--  1 root root  524K Sep  1 14:30 shuffle-word-970-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  524K Sep  1 13:54 shuffle-word-975-count.jsonl\n"
+      "-rw-r--r--  1 root root  521K Sep  1 14:30 shuffle-word-975-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  522K Sep  1 13:54 shuffle-word-980-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-980-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-985-count.jsonl\n"
+      "-rw-r--r--  1 root root  519K Sep  1 14:30 shuffle-word-985-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  520K Sep  1 13:54 shuffle-word-990-count.jsonl\n"
+      "-rw-r--r--  1 root root  524K Sep  1 14:30 shuffle-word-990-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root  521K Sep  1 13:54 shuffle-word-995-count.jsonl\n"
+      "-rw-r--r--  1 root root  522K Sep  1 14:30 shuffle-word-995-count.jsonl\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "-rw-r--r--  1 root root   12K Sep  1 13:54 word-2-count.jsonl\n"
+      "-rw-r--r--  1 root root   13K Sep  1 14:30 word-2-count.jsonl\n"
      ]
     }
    ],
@@ -25649,19 +24654,19 @@
   {
    "cell_type": "code",
    "execution_count": 6,
-   "id": "f88c4248",
+   "id": "474827dd",
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2023-09-01T13:54:53.889678Z",
-     "iopub.status.busy": "2023-09-01T13:54:53.889344Z",
-     "iopub.status.idle": "2023-09-01T13:55:10.880595Z",
-     "shell.execute_reply": "2023-09-01T13:55:10.879646Z"
+     "iopub.execute_input": "2023-09-01T14:30:50.819743Z",
+     "iopub.status.busy": "2023-09-01T14:30:50.819469Z",
+     "iopub.status.idle": "2023-09-01T14:31:05.238181Z",
+     "shell.execute_reply": "2023-09-01T14:31:05.237330Z"
     },
     "papermill": {
-     "duration": 17.165851,
-     "end_time": "2023-09-01T13:55:10.882941",
+     "duration": 14.585598,
+     "end_time": "2023-09-01T14:31:05.240111",
      "exception": false,
-     "start_time": "2023-09-01T13:54:53.717090",
+     "start_time": "2023-09-01T14:30:50.654513",
      "status": "completed"
     },
     "tags": []
@@ -25693,9 +24698,9 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "/usr/local/lib/python3.11/dist-packages/lightning/fabric/utilities/seed.py:39: UserWarning: No seed found, seed set to 3943818063\r\n",
+      "/usr/local/lib/python3.11/dist-packages/lightning/fabric/utilities/seed.py:39: UserWarning: No seed found, seed set to 3786586298\r\n",
       "  rank_zero_warn(f\"No seed found, seed set to {seed}\")\r\n",
-      "Global seed set to 3943818063\r\n"
+      "Global seed set to 3786586298\r\n"
      ]
     },
     {
@@ -25710,17 +24715,17 @@
      "output_type": "stream",
      "text": [
       "\u001b[34m\u001b[1mwandb\u001b[0m: Tracking run with wandb version 0.15.9\r\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: Run data is saved locally in \u001b[35m\u001b[1m./wandb/run-20230901_135500-p807ye00\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: Run data is saved locally in \u001b[35m\u001b[1m./wandb/run-20230901_143056-3d0esoou\u001b[0m\r\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: Run \u001b[1m`wandb offline`\u001b[0m to turn off syncing.\r\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: Syncing run \u001b[33mv5-L96-D1024-E0.1 - Mem-Tune ctx-4k (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/3d0esoou\u001b[0m\r\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\u001b[34m\u001b[1mwandb\u001b[0m: Syncing run \u001b[33mv5-L96-D1024-E0.1 - Mem-Tune ctx-4k (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/p807ye00\u001b[0m\r\n",
       "Traceback (most recent call last):\r\n",
       "  File \"/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/RWKV-v5/lightning_trainer.py\", line 254, in <module>\r\n",
       "    cli_main()\r\n",
@@ -25755,10 +24760,10 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\u001b[34m\u001b[1mwandb\u001b[0m: 🚀 View run \u001b[33mv5-L96-D1024-E0.1 - Mem-Tune ctx-4k (train-ctx=4k, deepspeed_stage_1)\u001b[0m at: \u001b[34m\u001b[4mhttps://wandb.ai/rwkv-x-dev/RWKV-X-Experiments/runs/p807ye00\u001b[0m\r\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: 🚀 View run \u001b[33mv5-L96-D1024-E0.1 - Mem-Tune ctx-4k (train-ctx=4k, deepspeed_stage_1)\u001b[0m at: \u001b[34m\u001b[4mhttps://wandb.ai/rwkv-x-dev/RWKV-X-Experiments/runs/3d0esoou\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/v17\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-20230901_135500-p807ye00/logs\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-20230901_143056-3d0esoou/logs\u001b[0m\r\n"
      ]
     }
    ],
@@ -25784,19 +24789,19 @@
   {
    "cell_type": "code",
    "execution_count": 7,
-   "id": "5e713298",
+   "id": "96cc7f3a",
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2023-09-01T13:55:11.230920Z",
-     "iopub.status.busy": "2023-09-01T13:55:11.230681Z",
-     "iopub.status.idle": "2023-09-01T13:55:14.145254Z",
-     "shell.execute_reply": "2023-09-01T13:55:14.144321Z"
+     "iopub.execute_input": "2023-09-01T14:31:05.578334Z",
+     "iopub.status.busy": "2023-09-01T14:31:05.578117Z",
+     "iopub.status.idle": "2023-09-01T14:31:08.323955Z",
+     "shell.execute_reply": "2023-09-01T14:31:08.322940Z"
     },
     "papermill": {
-     "duration": 3.089125,
-     "end_time": "2023-09-01T13:55:14.147065",
+     "duration": 2.916092,
+     "end_time": "2023-09-01T14:31:08.325688",
      "exception": false,
-     "start_time": "2023-09-01T13:55:11.057940",
+     "start_time": "2023-09-01T14:31:05.409596",
      "status": "completed"
     },
     "tags": []
@@ -25844,19 +24849,19 @@
   {
    "cell_type": "code",
    "execution_count": 8,
-   "id": "12df9685",
+   "id": "ead23fca",
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2023-09-01T13:55:14.494885Z",
-     "iopub.status.busy": "2023-09-01T13:55:14.494653Z",
-     "iopub.status.idle": "2023-09-01T13:55:19.695622Z",
-     "shell.execute_reply": "2023-09-01T13:55:19.694174Z"
+     "iopub.execute_input": "2023-09-01T14:31:08.662516Z",
+     "iopub.status.busy": "2023-09-01T14:31:08.662320Z",
+     "iopub.status.idle": "2023-09-01T14:31:13.761964Z",
+     "shell.execute_reply": "2023-09-01T14:31:13.760772Z"
     },
     "papermill": {
-     "duration": 5.376554,
-     "end_time": "2023-09-01T13:55:19.697884",
+     "duration": 5.268905,
+     "end_time": "2023-09-01T14:31:13.763776",
      "exception": false,
-     "start_time": "2023-09-01T13:55:14.321330",
+     "start_time": "2023-09-01T14:31:08.494871",
      "status": "completed"
     },
     "tags": []
@@ -25925,14 +24930,14 @@
   },
   "papermill": {
    "default_parameters": {},
-   "duration": 111.481796,
-   "end_time": "2023-09-01T13:55:20.140631",
+   "duration": 81.807338,
+   "end_time": "2023-09-01T14:31:14.206697",
    "environment_variables": {},
    "exception": null,
    "input_path": "/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/notebook/experiment/rwkv-x-exp/v5-memory/v5-L96-D1024-E1e-1-ctx4k-part4.ipynb",
    "output_path": "/actions-runner/_work/RWKV-infctx-trainer/RWKV-infctx-trainer/output/experiment/rwkv-x-exp/v5-memory/v5-L96-D1024-E1e-1-ctx4k-part4.ipynb",
    "parameters": {},
-   "start_time": "2023-09-01T13:53:28.658835",
+   "start_time": "2023-09-01T14:29:52.399359",
    "version": "2.4.0"
   }
  },