diff --git "a/notebook3ef4b26252_(1).ipynb" "b/notebook3ef4b26252_(1).ipynb"
new file mode 100644--- /dev/null
+++ "b/notebook3ef4b26252_(1).ipynb"
@@ -0,0 +1,6404 @@
+{
+ "metadata": {
+ "accelerator": "GPU",
+ "colab": {
+ "provenance": []
+ },
+ "kernelspec": {
+ "name": "python3",
+ "display_name": "Python 3",
+ "language": "python"
+ },
+ "language_info": {
+ "name": "python",
+ "version": "3.10.10",
+ "mimetype": "text/x-python",
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 3
+ },
+ "pygments_lexer": "ipython3",
+ "nbconvert_exporter": "python",
+ "file_extension": ".py"
+ },
+ "widgets": {
+ "application/vnd.jupyter.widget-state+json": {
+ "73361761a76d4889882844e561635d73": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "VBoxModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "VBoxModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "VBoxView",
+ "box_style": "",
+ "children": [
+ "IPY_MODEL_d00d28d5a8da40d2b2daf050d11f35bd",
+ "IPY_MODEL_d50395d307f74618bd1f7bc779de9917",
+ "IPY_MODEL_952b2b041fd641d7a574ecdce087a253",
+ "IPY_MODEL_3c5fb8df94b14e70803d694df1970489",
+ "IPY_MODEL_53ca6eeb14934f8bae3d91005d7c8d67"
+ ],
+ "layout": "IPY_MODEL_46d95a0e50b34b9091850a0d6a3db2de"
+ }
+ },
+ "d00d28d5a8da40d2b2daf050d11f35bd": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_77b1c53abd094c50819653688d97f47d",
+ "placeholder": "",
+ "style": "IPY_MODEL_1b6f7d1e344e44e7baa789c28411e5c9",
+ "value": "
Copy a token from your Hugging Face\ntokens page and paste it below.
Immediately click login after copying\nyour token or it might be stored in plain text in this notebook file. "
+ }
+ },
+ "d50395d307f74618bd1f7bc779de9917": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "PasswordModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "PasswordModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "PasswordView",
+ "continuous_update": true,
+ "description": "Token:",
+ "description_tooltip": null,
+ "disabled": false,
+ "layout": "IPY_MODEL_cb7a15b0f32a493bacea8b577679bdfb",
+ "placeholder": "",
+ "style": "IPY_MODEL_21c40f33301c47fbb608102923de85f8",
+ "value": ""
+ }
+ },
+ "952b2b041fd641d7a574ecdce087a253": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "CheckboxModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "CheckboxModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "CheckboxView",
+ "description": "Add token as git credential?",
+ "description_tooltip": null,
+ "disabled": false,
+ "indent": true,
+ "layout": "IPY_MODEL_cffc36cf5d5b4e90b1c84539db353748",
+ "style": "IPY_MODEL_87883364cb514bdf9c28a05a9eb1cb77",
+ "value": true
+ }
+ },
+ "3c5fb8df94b14e70803d694df1970489": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "ButtonModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "ButtonModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "ButtonView",
+ "button_style": "",
+ "description": "Login",
+ "disabled": false,
+ "icon": "",
+ "layout": "IPY_MODEL_fe85cb9d4e404a74bdd1d297749cb997",
+ "style": "IPY_MODEL_e394a62914984ca3b7af0e6a3112f5b9",
+ "tooltip": ""
+ }
+ },
+ "53ca6eeb14934f8bae3d91005d7c8d67": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_28e488b6026744b6863f1a290549c316",
+ "placeholder": "",
+ "style": "IPY_MODEL_be8149c67e3d4ff9bf579a432d5ad701",
+ "value": "\nPro Tip: If you don't already have one, you can create a dedicated\n'notebooks' token with 'write' access, that you can then easily reuse for all\nnotebooks. "
+ }
+ },
+ "46d95a0e50b34b9091850a0d6a3db2de": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": "center",
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": "flex",
+ "flex": null,
+ "flex_flow": "column",
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": "50%"
+ }
+ },
+ "77b1c53abd094c50819653688d97f47d": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "1b6f7d1e344e44e7baa789c28411e5c9": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "cb7a15b0f32a493bacea8b577679bdfb": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "21c40f33301c47fbb608102923de85f8": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "cffc36cf5d5b4e90b1c84539db353748": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "87883364cb514bdf9c28a05a9eb1cb77": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "fe85cb9d4e404a74bdd1d297749cb997": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "e394a62914984ca3b7af0e6a3112f5b9": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "ButtonStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "ButtonStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "button_color": null,
+ "font_weight": ""
+ }
+ },
+ "28e488b6026744b6863f1a290549c316": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "be8149c67e3d4ff9bf579a432d5ad701": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "04a3c13a1746496a9873e5fd3f5b11a6": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HBoxModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HBoxModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HBoxView",
+ "box_style": "",
+ "children": [
+ "IPY_MODEL_dbdb3a69e0a44c7fb2b5894518138043",
+ "IPY_MODEL_957ae41e697541e189b4d632b31d9001",
+ "IPY_MODEL_cfa958d4a2e4405b9406a7ae8c766f69"
+ ],
+ "layout": "IPY_MODEL_73553f98a68c47c7b6b2428683d9ba38"
+ }
+ },
+ "dbdb3a69e0a44c7fb2b5894518138043": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_39aff9458ec24affbc2c12de84bb3713",
+ "placeholder": "",
+ "style": "IPY_MODEL_e910e8a9f278470a91cf22beffc006dd",
+ "value": "Downloading data files: 100%"
+ }
+ },
+ "957ae41e697541e189b4d632b31d9001": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "FloatProgressModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "FloatProgressModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "ProgressView",
+ "bar_style": "success",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_6c77b1450be444d1892216a933bbec84",
+ "max": 3,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_88308ae466eb4b7fae5673bd9b216501",
+ "value": 3
+ }
+ },
+ "cfa958d4a2e4405b9406a7ae8c766f69": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_6addf054438846b6bb43560b50091ca9",
+ "placeholder": "",
+ "style": "IPY_MODEL_27c560f9c7504f12a0616cf1f17ed2d0",
+ "value": " 3/3 [00:00<00:00, 104.19it/s]"
+ }
+ },
+ "73553f98a68c47c7b6b2428683d9ba38": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "39aff9458ec24affbc2c12de84bb3713": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "e910e8a9f278470a91cf22beffc006dd": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "6c77b1450be444d1892216a933bbec84": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "88308ae466eb4b7fae5673bd9b216501": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "ProgressStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "ProgressStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "bar_color": null,
+ "description_width": ""
+ }
+ },
+ "6addf054438846b6bb43560b50091ca9": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "27c560f9c7504f12a0616cf1f17ed2d0": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "9415ba91d08f47c39c65d7f854e5c8e9": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HBoxModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HBoxModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HBoxView",
+ "box_style": "",
+ "children": [
+ "IPY_MODEL_0f7b33b9cc1b43aa8c1b44578e09755d",
+ "IPY_MODEL_6b4d3c067c08487fa4f32388bd83faa1",
+ "IPY_MODEL_3b518faba51c4795a981afe2bc054dfd"
+ ],
+ "layout": "IPY_MODEL_718fc400aa644ba19c60f718c7582013"
+ }
+ },
+ "0f7b33b9cc1b43aa8c1b44578e09755d": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_6ef0d6ef3db4479dad01279d3458b4ad",
+ "placeholder": "",
+ "style": "IPY_MODEL_dd6095d8c103441e8ddfba1f7b75e0c2",
+ "value": "Extracting data files: 100%"
+ }
+ },
+ "6b4d3c067c08487fa4f32388bd83faa1": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "FloatProgressModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "FloatProgressModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "ProgressView",
+ "bar_style": "success",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_3db9a8b87fb84d5795b2f5a8bbb89f0c",
+ "max": 3,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_b1aeb5e3c837472e82d72d57fb0a2bf0",
+ "value": 3
+ }
+ },
+ "3b518faba51c4795a981afe2bc054dfd": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_0843f83b02084a9c97868f16c8400ff4",
+ "placeholder": "",
+ "style": "IPY_MODEL_c939c6f20e41473ba5ad0bc52077f80e",
+ "value": " 3/3 [00:00<00:00, 87.30it/s]"
+ }
+ },
+ "718fc400aa644ba19c60f718c7582013": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "6ef0d6ef3db4479dad01279d3458b4ad": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "dd6095d8c103441e8ddfba1f7b75e0c2": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "3db9a8b87fb84d5795b2f5a8bbb89f0c": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "b1aeb5e3c837472e82d72d57fb0a2bf0": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "ProgressStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "ProgressStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "bar_color": null,
+ "description_width": ""
+ }
+ },
+ "0843f83b02084a9c97868f16c8400ff4": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "c939c6f20e41473ba5ad0bc52077f80e": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "306dba5e40354e94a9499ed35049e8f0": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HBoxModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HBoxModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HBoxView",
+ "box_style": "",
+ "children": [
+ "IPY_MODEL_98f7e1cf59bf42bfa7ec524b04da1ed3",
+ "IPY_MODEL_4bc67f9b17d44dd48a4e0d8dda95f227",
+ "IPY_MODEL_678bc5a171154742bab6ac3fd356cb7e"
+ ],
+ "layout": "IPY_MODEL_216fbd674834407092ee2939863fa10f"
+ }
+ },
+ "98f7e1cf59bf42bfa7ec524b04da1ed3": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_3ef0ab61269a4143858c82a43ac24a9d",
+ "placeholder": "",
+ "style": "IPY_MODEL_d1a39f25bc924361814cdd2ac2dff5af",
+ "value": "Generating train split: "
+ }
+ },
+ "4bc67f9b17d44dd48a4e0d8dda95f227": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "FloatProgressModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "FloatProgressModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "ProgressView",
+ "bar_style": "info",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_47f3a327ddac440da5345a29a1316ab3",
+ "max": 1,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_b64c940a262a46d6837dae79b1a9a929",
+ "value": 1
+ }
+ },
+ "678bc5a171154742bab6ac3fd356cb7e": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_de7bbf04699547f5ae87d9857cf5ee4d",
+ "placeholder": "",
+ "style": "IPY_MODEL_9968510ff93e44d9b2359746940873a4",
+ "value": " 59330/0 [00:21<00:00, 6301.86 examples/s]"
+ }
+ },
+ "216fbd674834407092ee2939863fa10f": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": "hidden",
+ "width": null
+ }
+ },
+ "3ef0ab61269a4143858c82a43ac24a9d": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "d1a39f25bc924361814cdd2ac2dff5af": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "47f3a327ddac440da5345a29a1316ab3": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": "20px"
+ }
+ },
+ "b64c940a262a46d6837dae79b1a9a929": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "ProgressStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "ProgressStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "bar_color": null,
+ "description_width": ""
+ }
+ },
+ "de7bbf04699547f5ae87d9857cf5ee4d": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "9968510ff93e44d9b2359746940873a4": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "263c5324770f40fe85bdd0b7213eb73f": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HBoxModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HBoxModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HBoxView",
+ "box_style": "",
+ "children": [
+ "IPY_MODEL_e5ed238d7287449ca268336e19eeb59b",
+ "IPY_MODEL_2712d9833a0c493286a1f3d267c8d28b",
+ "IPY_MODEL_17aa55e778194775a63c61ea4d606039"
+ ],
+ "layout": "IPY_MODEL_5113637b8e8248d18bb86e9c310f2609"
+ }
+ },
+ "e5ed238d7287449ca268336e19eeb59b": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_e2ee0abf6bb74f7d9779786b57f0f198",
+ "placeholder": "",
+ "style": "IPY_MODEL_2c281093fd23419483bdeea7cd6bc158",
+ "value": "Generating validation split: "
+ }
+ },
+ "2712d9833a0c493286a1f3d267c8d28b": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "FloatProgressModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "FloatProgressModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "ProgressView",
+ "bar_style": "info",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_ee717b1fee0c47e29853efbc2e411d38",
+ "max": 1,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_e77b30ec501040e9b6fa10921f531178",
+ "value": 1
+ }
+ },
+ "17aa55e778194775a63c61ea4d606039": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_cd8f7a6e12124d70974e5e7561be38af",
+ "placeholder": "",
+ "style": "IPY_MODEL_5d7288c4532a460aa3fc52cddef5189a",
+ "value": " 8178/0 [00:02<00:00, 4151.55 examples/s]"
+ }
+ },
+ "5113637b8e8248d18bb86e9c310f2609": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": "hidden",
+ "width": null
+ }
+ },
+ "e2ee0abf6bb74f7d9779786b57f0f198": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "2c281093fd23419483bdeea7cd6bc158": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "ee717b1fee0c47e29853efbc2e411d38": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": "20px"
+ }
+ },
+ "e77b30ec501040e9b6fa10921f531178": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "ProgressStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "ProgressStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "bar_color": null,
+ "description_width": ""
+ }
+ },
+ "cd8f7a6e12124d70974e5e7561be38af": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "5d7288c4532a460aa3fc52cddef5189a": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "a1e73c264a6544249560ff20b6bc2952": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HBoxModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HBoxModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HBoxView",
+ "box_style": "",
+ "children": [
+ "IPY_MODEL_25a8fda472d340e4add5b95f95f124ec",
+ "IPY_MODEL_653ced58d62342b89c5cb73102837683",
+ "IPY_MODEL_5e73f010e5574c46bee2e741cbc48e70"
+ ],
+ "layout": "IPY_MODEL_8070e47dec5147feaaf3d3b887eaf9af"
+ }
+ },
+ "25a8fda472d340e4add5b95f95f124ec": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_c03da00e61e3431b8a7658eed5fa8c4c",
+ "placeholder": "",
+ "style": "IPY_MODEL_9209861487a045a694f6f5a7ce05059b",
+ "value": "Generating test split: "
+ }
+ },
+ "653ced58d62342b89c5cb73102837683": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "FloatProgressModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "FloatProgressModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "ProgressView",
+ "bar_style": "info",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_d50150bab4184cba861854a0dec25b26",
+ "max": 1,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_36d4c064e7e941d280cac64c27fa7ed5",
+ "value": 1
+ }
+ },
+ "5e73f010e5574c46bee2e741cbc48e70": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_109a9674fb374fd093d5ca411081e639",
+ "placeholder": "",
+ "style": "IPY_MODEL_1704fe9ebb2c45ec992a3024758f1fe9",
+ "value": " 8000/0 [00:02<00:00, 4322.00 examples/s]"
+ }
+ },
+ "8070e47dec5147feaaf3d3b887eaf9af": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": "hidden",
+ "width": null
+ }
+ },
+ "c03da00e61e3431b8a7658eed5fa8c4c": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "9209861487a045a694f6f5a7ce05059b": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "d50150bab4184cba861854a0dec25b26": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": "20px"
+ }
+ },
+ "36d4c064e7e941d280cac64c27fa7ed5": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "ProgressStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "ProgressStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "bar_color": null,
+ "description_width": ""
+ }
+ },
+ "109a9674fb374fd093d5ca411081e639": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "1704fe9ebb2c45ec992a3024758f1fe9": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "aa65f73e671f4ca886d5243786cff482": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HBoxModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HBoxModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HBoxView",
+ "box_style": "",
+ "children": [
+ "IPY_MODEL_6f4b59e106bb4559a62cb6ef1e317930",
+ "IPY_MODEL_ec71c84bceab40eca3e274dd5525ff83",
+ "IPY_MODEL_56fd51be14bb432cbe747f5c1a51468d"
+ ],
+ "layout": "IPY_MODEL_e65095d8e9d4478e9f57fa19b2cdf0e8"
+ }
+ },
+ "6f4b59e106bb4559a62cb6ef1e317930": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_baf0e820f5e142f8ab4c8d3deed72608",
+ "placeholder": "",
+ "style": "IPY_MODEL_c30629a840b3456eaac6a9702b2cedc9",
+ "value": "Downloading (…)okenizer_config.json: 100%"
+ }
+ },
+ "ec71c84bceab40eca3e274dd5525ff83": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "FloatProgressModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "FloatProgressModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "ProgressView",
+ "bar_style": "success",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_68a503ffb12448078dc402947faf2403",
+ "max": 28,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_199c0f0bb9634539a33329334eb1609c",
+ "value": 28
+ }
+ },
+ "56fd51be14bb432cbe747f5c1a51468d": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_004ae3ec389244b6abe1fce26f7d5573",
+ "placeholder": "",
+ "style": "IPY_MODEL_9339dfdc705c4f7fa6cb259a382d26d2",
+ "value": " 28.0/28.0 [00:00<00:00, 453B/s]"
+ }
+ },
+ "e65095d8e9d4478e9f57fa19b2cdf0e8": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "baf0e820f5e142f8ab4c8d3deed72608": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "c30629a840b3456eaac6a9702b2cedc9": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "68a503ffb12448078dc402947faf2403": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "199c0f0bb9634539a33329334eb1609c": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "ProgressStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "ProgressStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "bar_color": null,
+ "description_width": ""
+ }
+ },
+ "004ae3ec389244b6abe1fce26f7d5573": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "9339dfdc705c4f7fa6cb259a382d26d2": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "5d01a359f54b45a49bc2b69f6b769b61": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HBoxModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HBoxModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HBoxView",
+ "box_style": "",
+ "children": [
+ "IPY_MODEL_4f12daad8f3c4b7da5e190956971ae43",
+ "IPY_MODEL_51a10089effe460a8eb5959a6720898c",
+ "IPY_MODEL_31eeccc5c83a4a6d8b609415065affdd"
+ ],
+ "layout": "IPY_MODEL_5a5fb6046e7a44a3a9b7f76f7a8dd0d8"
+ }
+ },
+ "4f12daad8f3c4b7da5e190956971ae43": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_621213d4bf2e454caac49d5d9dc70da0",
+ "placeholder": "",
+ "style": "IPY_MODEL_d866785a13ef4d7a966033f3c5bf0690",
+ "value": "Downloading (…)lve/main/config.json: 100%"
+ }
+ },
+ "51a10089effe460a8eb5959a6720898c": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "FloatProgressModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "FloatProgressModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "ProgressView",
+ "bar_style": "success",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_9df336bca8af42909fe4d0e0bf0e4801",
+ "max": 483,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_1f773bd126a64ed7a2811285ee649c53",
+ "value": 483
+ }
+ },
+ "31eeccc5c83a4a6d8b609415065affdd": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_f085350218b145978f245a512d5b4a0b",
+ "placeholder": "",
+ "style": "IPY_MODEL_b76b2fb808f449f79c03ab826a061aaf",
+ "value": " 483/483 [00:00<00:00, 11.2kB/s]"
+ }
+ },
+ "5a5fb6046e7a44a3a9b7f76f7a8dd0d8": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "621213d4bf2e454caac49d5d9dc70da0": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "d866785a13ef4d7a966033f3c5bf0690": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "9df336bca8af42909fe4d0e0bf0e4801": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "1f773bd126a64ed7a2811285ee649c53": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "ProgressStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "ProgressStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "bar_color": null,
+ "description_width": ""
+ }
+ },
+ "f085350218b145978f245a512d5b4a0b": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "b76b2fb808f449f79c03ab826a061aaf": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "6934e0438d6e45039b843dfb8d7fcdf9": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HBoxModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HBoxModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HBoxView",
+ "box_style": "",
+ "children": [
+ "IPY_MODEL_c98119f661fe4bfaaf892dffa017e379",
+ "IPY_MODEL_0210001520d24f96b83f79602cc7219a",
+ "IPY_MODEL_38470542986a4fad891a1a54b4e99433"
+ ],
+ "layout": "IPY_MODEL_cd0768aba1fe48c09209cde3f35f8644"
+ }
+ },
+ "c98119f661fe4bfaaf892dffa017e379": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_be34f467900b400ebec1e39b7a98bd16",
+ "placeholder": "",
+ "style": "IPY_MODEL_10508fc470bd436a87a8d5554b9cccb3",
+ "value": "Downloading (…)solve/main/vocab.txt: 100%"
+ }
+ },
+ "0210001520d24f96b83f79602cc7219a": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "FloatProgressModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "FloatProgressModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "ProgressView",
+ "bar_style": "success",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_3006d2dd77f54dc18c0d98ae5332281f",
+ "max": 231508,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_67170aa447104b5e94f4233863c5a7fb",
+ "value": 231508
+ }
+ },
+ "38470542986a4fad891a1a54b4e99433": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_847b52f433454cd5911c9f2f1ec1af26",
+ "placeholder": "",
+ "style": "IPY_MODEL_142e2e4e197c4cf5b22c0a8e033ba464",
+ "value": " 232k/232k [00:00<00:00, 2.28MB/s]"
+ }
+ },
+ "cd0768aba1fe48c09209cde3f35f8644": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "be34f467900b400ebec1e39b7a98bd16": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "10508fc470bd436a87a8d5554b9cccb3": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "3006d2dd77f54dc18c0d98ae5332281f": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "67170aa447104b5e94f4233863c5a7fb": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "ProgressStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "ProgressStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "bar_color": null,
+ "description_width": ""
+ }
+ },
+ "847b52f433454cd5911c9f2f1ec1af26": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "142e2e4e197c4cf5b22c0a8e033ba464": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "65912f982b064948831a3ec46298fc7f": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HBoxModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HBoxModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HBoxView",
+ "box_style": "",
+ "children": [
+ "IPY_MODEL_dd1b40c935ae404ba9cecf01d28ee438",
+ "IPY_MODEL_1da9adffdda74b34b7ec92653e851cd3",
+ "IPY_MODEL_e5ed339ec9c444e3b12e8ea2de3d1a26"
+ ],
+ "layout": "IPY_MODEL_36c80c2f79534088afbb5c46b80f3d18"
+ }
+ },
+ "dd1b40c935ae404ba9cecf01d28ee438": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_3a3edad4cfd649399d149341ba0fd25d",
+ "placeholder": "",
+ "style": "IPY_MODEL_52699e5a36864f6ea7d88e3240d9b56d",
+ "value": "Downloading (…)/main/tokenizer.json: 100%"
+ }
+ },
+ "1da9adffdda74b34b7ec92653e851cd3": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "FloatProgressModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "FloatProgressModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "ProgressView",
+ "bar_style": "success",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_4aa81a5f34894f6b928c849d6b088d1d",
+ "max": 466062,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_70830c4ee13c4947825c4977968f8151",
+ "value": 466062
+ }
+ },
+ "e5ed339ec9c444e3b12e8ea2de3d1a26": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_068b13bef47444ffbb5d646f8e2b2ef5",
+ "placeholder": "",
+ "style": "IPY_MODEL_89a5f0be6c444b84a4b43a8c83151c9f",
+ "value": " 466k/466k [00:00<00:00, 7.30MB/s]"
+ }
+ },
+ "36c80c2f79534088afbb5c46b80f3d18": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "3a3edad4cfd649399d149341ba0fd25d": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "52699e5a36864f6ea7d88e3240d9b56d": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "4aa81a5f34894f6b928c849d6b088d1d": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "70830c4ee13c4947825c4977968f8151": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "ProgressStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "ProgressStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "bar_color": null,
+ "description_width": ""
+ }
+ },
+ "068b13bef47444ffbb5d646f8e2b2ef5": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "89a5f0be6c444b84a4b43a8c83151c9f": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "40dabcd04a784ccb818a7b634e61b173": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HBoxModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HBoxModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HBoxView",
+ "box_style": "",
+ "children": [
+ "IPY_MODEL_0458edaaec1e48c781fcc16202357089",
+ "IPY_MODEL_db27d69a64be4ddda3cbe9494aa63d5e",
+ "IPY_MODEL_6405244b8880496e9621f9521d42161b"
+ ],
+ "layout": "IPY_MODEL_cf7107e22bee470791637e09877d50fe"
+ }
+ },
+ "0458edaaec1e48c781fcc16202357089": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_b1a72c432be34987bdea3d8e6d4db9cf",
+ "placeholder": "",
+ "style": "IPY_MODEL_3e04042eb88d4807a94999919a400559",
+ "value": "Map: 100%"
+ }
+ },
+ "db27d69a64be4ddda3cbe9494aa63d5e": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "FloatProgressModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "FloatProgressModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "ProgressView",
+ "bar_style": "",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_c6adaba4760f454f8c3929e088a83f9a",
+ "max": 53931,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_9deded080d784c67837b34fb8d76947c",
+ "value": 53931
+ }
+ },
+ "6405244b8880496e9621f9521d42161b": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_0e59a284de2e4d42916be734575c0fff",
+ "placeholder": "",
+ "style": "IPY_MODEL_13e693d4dc8243e8a0b99a531e5055b0",
+ "value": " 53931/53931 [00:24<00:00, 1974.25 examples/s]"
+ }
+ },
+ "cf7107e22bee470791637e09877d50fe": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": "hidden",
+ "width": null
+ }
+ },
+ "b1a72c432be34987bdea3d8e6d4db9cf": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "3e04042eb88d4807a94999919a400559": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "c6adaba4760f454f8c3929e088a83f9a": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "9deded080d784c67837b34fb8d76947c": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "ProgressStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "ProgressStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "bar_color": null,
+ "description_width": ""
+ }
+ },
+ "0e59a284de2e4d42916be734575c0fff": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "13e693d4dc8243e8a0b99a531e5055b0": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "7158b44c8f0e469381997180c1047995": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HBoxModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HBoxModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HBoxView",
+ "box_style": "",
+ "children": [
+ "IPY_MODEL_e8be574a0e194b55ae12bf26a6309483",
+ "IPY_MODEL_7cd37438898742169ec46510e1128b31",
+ "IPY_MODEL_b1f37f108ade458c9e655568f2eb86b7"
+ ],
+ "layout": "IPY_MODEL_b9f9cd99297f4b16b93d2c8bdcea94e9"
+ }
+ },
+ "e8be574a0e194b55ae12bf26a6309483": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_53edf50124eb4b03abaa5428c5bde2c9",
+ "placeholder": "",
+ "style": "IPY_MODEL_25a9977492f342e19603749dc824104c",
+ "value": "Map: 100%"
+ }
+ },
+ "7cd37438898742169ec46510e1128b31": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "FloatProgressModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "FloatProgressModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "ProgressView",
+ "bar_style": "",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_55712f37a3ba4db2a018a1b7734a8030",
+ "max": 5993,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_0e3b01157a324c948342c950cc8d4d77",
+ "value": 5993
+ }
+ },
+ "b1f37f108ade458c9e655568f2eb86b7": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_1fbdb596d823448b8026ddb14792808e",
+ "placeholder": "",
+ "style": "IPY_MODEL_da715f9146ab4f148e46c81237d10274",
+ "value": " 5993/5993 [00:03<00:00, 1527.03 examples/s]"
+ }
+ },
+ "b9f9cd99297f4b16b93d2c8bdcea94e9": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": "hidden",
+ "width": null
+ }
+ },
+ "53edf50124eb4b03abaa5428c5bde2c9": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "25a9977492f342e19603749dc824104c": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "55712f37a3ba4db2a018a1b7734a8030": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "0e3b01157a324c948342c950cc8d4d77": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "ProgressStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "ProgressStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "bar_color": null,
+ "description_width": ""
+ }
+ },
+ "1fbdb596d823448b8026ddb14792808e": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "da715f9146ab4f148e46c81237d10274": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "bf2647ee9662453f89fb10449fa38967": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HBoxModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HBoxModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HBoxView",
+ "box_style": "",
+ "children": [
+ "IPY_MODEL_0c6ca1c0e6e54c688de51567fb77c7c6",
+ "IPY_MODEL_92ab3fa24b3e464e80d8890c8e37e378",
+ "IPY_MODEL_83b6c91550e540a99ebdf165ad37707f"
+ ],
+ "layout": "IPY_MODEL_9bc86a1e81464ae88b79a3e7685caf91"
+ }
+ },
+ "0c6ca1c0e6e54c688de51567fb77c7c6": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_8c15e2d94a3642c7b5d9dc3a309e275c",
+ "placeholder": "",
+ "style": "IPY_MODEL_11a347f8e76c466aacdb24f7bc660a52",
+ "value": "Downloading model.safetensors: 100%"
+ }
+ },
+ "92ab3fa24b3e464e80d8890c8e37e378": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "FloatProgressModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "FloatProgressModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "ProgressView",
+ "bar_style": "success",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_588a66fec2a04571a49c5a02e43230b5",
+ "max": 267954768,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_804228726a0d4aa582259234b3de86fb",
+ "value": 267954768
+ }
+ },
+ "83b6c91550e540a99ebdf165ad37707f": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_866b385c0d3a4680a21ac457083b9b7e",
+ "placeholder": "",
+ "style": "IPY_MODEL_1ca527c7678449d5a8d91400369bdf3d",
+ "value": " 268M/268M [00:02<00:00, 101MB/s]"
+ }
+ },
+ "9bc86a1e81464ae88b79a3e7685caf91": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "8c15e2d94a3642c7b5d9dc3a309e275c": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "11a347f8e76c466aacdb24f7bc660a52": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "588a66fec2a04571a49c5a02e43230b5": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "804228726a0d4aa582259234b3de86fb": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "ProgressStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "ProgressStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "bar_color": null,
+ "description_width": ""
+ }
+ },
+ "866b385c0d3a4680a21ac457083b9b7e": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "1ca527c7678449d5a8d91400369bdf3d": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ }
+ }
+ }
+ },
+ "nbformat_minor": 0,
+ "nbformat": 4,
+ "cells": [
+ {
+ "cell_type": "code",
+ "source": [
+ "!pip install datasets transformers seqeval\n",
+ "!pip install -U accelerate --quiet"
+ ],
+ "metadata": {
+ "execution": {
+ "iopub.status.busy": "2023-06-16T00:35:55.719489Z",
+ "iopub.execute_input": "2023-06-16T00:35:55.720821Z",
+ "iopub.status.idle": "2023-06-16T00:36:31.032977Z",
+ "shell.execute_reply.started": "2023-06-16T00:35:55.720775Z",
+ "shell.execute_reply": "2023-06-16T00:36:31.031623Z"
+ },
+ "trusted": true,
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "xnQ_RK2Mo6h6",
+ "outputId": "3d27b4dd-21ff-48e9-d6cf-e5175e0c6879"
+ },
+ "execution_count": null,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n",
+ "Collecting datasets\n",
+ " Downloading datasets-2.13.0-py3-none-any.whl (485 kB)\n",
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m485.6/485.6 kB\u001b[0m \u001b[31m13.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hCollecting transformers\n",
+ " Downloading transformers-4.30.2-py3-none-any.whl (7.2 MB)\n",
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m7.2/7.2 MB\u001b[0m \u001b[31m119.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hCollecting seqeval\n",
+ " Downloading seqeval-1.2.2.tar.gz (43 kB)\n",
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m43.6/43.6 kB\u001b[0m \u001b[31m4.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25h Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
+ "Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from datasets) (1.22.4)\n",
+ "Requirement already satisfied: pyarrow>=8.0.0 in /usr/local/lib/python3.10/dist-packages (from datasets) (9.0.0)\n",
+ "Collecting dill<0.3.7,>=0.3.0 (from datasets)\n",
+ " Downloading dill-0.3.6-py3-none-any.whl (110 kB)\n",
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m110.5/110.5 kB\u001b[0m \u001b[31m14.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hRequirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (from datasets) (1.5.3)\n",
+ "Requirement already satisfied: requests>=2.19.0 in /usr/local/lib/python3.10/dist-packages (from datasets) (2.27.1)\n",
+ "Requirement already satisfied: tqdm>=4.62.1 in /usr/local/lib/python3.10/dist-packages (from datasets) (4.65.0)\n",
+ "Collecting xxhash (from datasets)\n",
+ " Downloading xxhash-3.2.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (212 kB)\n",
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m212.5/212.5 kB\u001b[0m \u001b[31m23.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hCollecting multiprocess (from datasets)\n",
+ " Downloading multiprocess-0.70.14-py310-none-any.whl (134 kB)\n",
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m134.3/134.3 kB\u001b[0m \u001b[31m16.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hRequirement already satisfied: fsspec[http]>=2021.11.1 in /usr/local/lib/python3.10/dist-packages (from datasets) (2023.4.0)\n",
+ "Collecting aiohttp (from datasets)\n",
+ " Downloading aiohttp-3.8.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.0 MB)\n",
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.0/1.0 MB\u001b[0m \u001b[31m73.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hCollecting huggingface-hub<1.0.0,>=0.11.0 (from datasets)\n",
+ " Downloading huggingface_hub-0.15.1-py3-none-any.whl (236 kB)\n",
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m236.8/236.8 kB\u001b[0m \u001b[31m24.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hRequirement already satisfied: packaging in /usr/local/lib/python3.10/dist-packages (from datasets) (23.1)\n",
+ "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from datasets) (6.0)\n",
+ "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from transformers) (3.12.0)\n",
+ "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers) (2022.10.31)\n",
+ "Collecting tokenizers!=0.11.3,<0.14,>=0.11.1 (from transformers)\n",
+ " Downloading tokenizers-0.13.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (7.8 MB)\n",
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m7.8/7.8 MB\u001b[0m \u001b[31m136.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hCollecting safetensors>=0.3.1 (from transformers)\n",
+ " Downloading safetensors-0.3.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.3 MB)\n",
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.3/1.3 MB\u001b[0m \u001b[31m96.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hRequirement already satisfied: scikit-learn>=0.21.3 in /usr/local/lib/python3.10/dist-packages (from seqeval) (1.2.2)\n",
+ "Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (23.1.0)\n",
+ "Requirement already satisfied: charset-normalizer<4.0,>=2.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (2.0.12)\n",
+ "Collecting multidict<7.0,>=4.5 (from aiohttp->datasets)\n",
+ " Downloading multidict-6.0.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (114 kB)\n",
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m114.5/114.5 kB\u001b[0m \u001b[31m14.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hCollecting async-timeout<5.0,>=4.0.0a3 (from aiohttp->datasets)\n",
+ " Downloading async_timeout-4.0.2-py3-none-any.whl (5.8 kB)\n",
+ "Collecting yarl<2.0,>=1.0 (from aiohttp->datasets)\n",
+ " Downloading yarl-1.9.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (268 kB)\n",
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m268.8/268.8 kB\u001b[0m \u001b[31m31.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hCollecting frozenlist>=1.1.1 (from aiohttp->datasets)\n",
+ " Downloading frozenlist-1.3.3-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (149 kB)\n",
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m149.6/149.6 kB\u001b[0m \u001b[31m18.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hCollecting aiosignal>=1.1.2 (from aiohttp->datasets)\n",
+ " Downloading aiosignal-1.3.1-py3-none-any.whl (7.6 kB)\n",
+ "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub<1.0.0,>=0.11.0->datasets) (4.5.0)\n",
+ "Requirement already satisfied: urllib3<1.27,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->datasets) (1.26.15)\n",
+ "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->datasets) (2022.12.7)\n",
+ "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->datasets) (3.4)\n",
+ "Requirement already satisfied: scipy>=1.3.2 in /usr/local/lib/python3.10/dist-packages (from scikit-learn>=0.21.3->seqeval) (1.10.1)\n",
+ "Requirement already satisfied: joblib>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from scikit-learn>=0.21.3->seqeval) (1.2.0)\n",
+ "Requirement already satisfied: threadpoolctl>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from scikit-learn>=0.21.3->seqeval) (3.1.0)\n",
+ "Requirement already satisfied: python-dateutil>=2.8.1 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets) (2.8.2)\n",
+ "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets) (2022.7.1)\n",
+ "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.8.1->pandas->datasets) (1.16.0)\n",
+ "Building wheels for collected packages: seqeval\n",
+ " Building wheel for seqeval (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
+ " Created wheel for seqeval: filename=seqeval-1.2.2-py3-none-any.whl size=16165 sha256=8c569b02052f1855e8a176b3c168fba5d7098b50603c297f4a8fde144852e7d2\n",
+ " Stored in directory: /root/.cache/pip/wheels/1a/67/4a/ad4082dd7dfc30f2abfe4d80a2ed5926a506eb8a972b4767fa\n",
+ "Successfully built seqeval\n",
+ "Installing collected packages: tokenizers, safetensors, xxhash, multidict, frozenlist, dill, async-timeout, yarl, multiprocess, huggingface-hub, aiosignal, transformers, seqeval, aiohttp, datasets\n",
+ "Successfully installed aiohttp-3.8.4 aiosignal-1.3.1 async-timeout-4.0.2 datasets-2.13.0 dill-0.3.6 frozenlist-1.3.3 huggingface-hub-0.15.1 multidict-6.0.4 multiprocess-0.70.14 safetensors-0.3.1 seqeval-1.2.2 tokenizers-0.13.3 transformers-4.30.2 xxhash-3.2.0 yarl-1.9.2\n",
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m227.6/227.6 kB\u001b[0m \u001b[31m8.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25h"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "If you're opening this notebook locally, make sure your environment has an install from the last version of those libraries.\n",
+ "\n",
+ "To be able to share your model with the community and generate results like the one shown in the picture below via the inference API, there are a few more steps to follow.\n",
+ "\n",
+ "First you have to store your authentication token from the Hugging Face website (in your account) then execute the following cell and input your username and password:"
+ ],
+ "metadata": {
+ "id": "u4MhZpe_BA6-"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "from huggingface_hub import notebook_login\n",
+ "\n",
+ "notebook_login()"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 359,
+ "referenced_widgets": [
+ "73361761a76d4889882844e561635d73",
+ "d00d28d5a8da40d2b2daf050d11f35bd",
+ "d50395d307f74618bd1f7bc779de9917",
+ "952b2b041fd641d7a574ecdce087a253",
+ "3c5fb8df94b14e70803d694df1970489",
+ "53ca6eeb14934f8bae3d91005d7c8d67",
+ "46d95a0e50b34b9091850a0d6a3db2de",
+ "77b1c53abd094c50819653688d97f47d",
+ "1b6f7d1e344e44e7baa789c28411e5c9",
+ "cb7a15b0f32a493bacea8b577679bdfb",
+ "21c40f33301c47fbb608102923de85f8",
+ "cffc36cf5d5b4e90b1c84539db353748",
+ "87883364cb514bdf9c28a05a9eb1cb77",
+ "fe85cb9d4e404a74bdd1d297749cb997",
+ "e394a62914984ca3b7af0e6a3112f5b9",
+ "28e488b6026744b6863f1a290549c316",
+ "be8149c67e3d4ff9bf579a432d5ad701"
+ ]
+ },
+ "id": "U-J05hwfBL08",
+ "outputId": "ec39411a-9448-45fc-f1c3-172c14f91859"
+ },
+ "execution_count": null,
+ "outputs": [
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/plain": [
+ "VBox(children=(HTML(value='
\", \"\"\n",
+ "]\n",
+ "# if you want to train the tokenizer on both sets\n",
+ "# files = [\"train.txt\", \"test.txt\"]\n",
+ "# training the tokenizer on the training set\n",
+ "files = [\"train.txt\"]\n",
+ "# 30,522 vocab is BERT's default vocab size, feel free to tweak\n",
+ "vocab_size = 30_522\n",
+ "# maximum sequence length, lowering will result to faster training (when increasing batch size)\n",
+ "max_length = 512\n",
+ "# whether to truncate\n",
+ "truncate_longer_samples = False"
+ ],
+ "metadata": {
+ "id": "bOBSHkbFuu5H",
+ "execution": {
+ "iopub.status.busy": "2023-06-16T00:28:15.046095Z",
+ "iopub.execute_input": "2023-06-16T00:28:15.046442Z",
+ "iopub.status.idle": "2023-06-16T00:28:15.052095Z",
+ "shell.execute_reply.started": "2023-06-16T00:28:15.046420Z",
+ "shell.execute_reply": "2023-06-16T00:28:15.050980Z"
+ },
+ "trusted": true
+ },
+ "execution_count": null,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "import transformers\n",
+ "from transformers import AutoTokenizer\n",
+ "\n",
+ "\n",
+ "tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)\n",
+ "assert isinstance(tokenizer, transformers.PreTrainedTokenizerFast)\n",
+ "\n",
+ "\n",
+ "# # initialize the WordPiece tokenizer\n",
+ "# tokenizer = BertWordPieceTokenizer()\n",
+ "# # train the tokenizer\n",
+ "# tokenizer.train(files=files, vocab_size=vocab_size, special_tokens=special_tokens)\n",
+ "# # enable truncation up to the maximum 512 tokens\n",
+ "# tokenizer.enable_truncation(max_length=max_length)"
+ ],
+ "metadata": {
+ "id": "-CVoZ3bC_j6K",
+ "execution": {
+ "iopub.status.busy": "2023-06-16T00:29:11.214924Z",
+ "iopub.execute_input": "2023-06-16T00:29:11.215259Z",
+ "iopub.status.idle": "2023-06-16T00:29:12.766231Z",
+ "shell.execute_reply.started": "2023-06-16T00:29:11.215236Z",
+ "shell.execute_reply": "2023-06-16T00:29:12.764863Z"
+ },
+ "trusted": true,
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 145,
+ "referenced_widgets": [
+ "aa65f73e671f4ca886d5243786cff482",
+ "6f4b59e106bb4559a62cb6ef1e317930",
+ "ec71c84bceab40eca3e274dd5525ff83",
+ "56fd51be14bb432cbe747f5c1a51468d",
+ "e65095d8e9d4478e9f57fa19b2cdf0e8",
+ "baf0e820f5e142f8ab4c8d3deed72608",
+ "c30629a840b3456eaac6a9702b2cedc9",
+ "68a503ffb12448078dc402947faf2403",
+ "199c0f0bb9634539a33329334eb1609c",
+ "004ae3ec389244b6abe1fce26f7d5573",
+ "9339dfdc705c4f7fa6cb259a382d26d2",
+ "5d01a359f54b45a49bc2b69f6b769b61",
+ "4f12daad8f3c4b7da5e190956971ae43",
+ "51a10089effe460a8eb5959a6720898c",
+ "31eeccc5c83a4a6d8b609415065affdd",
+ "5a5fb6046e7a44a3a9b7f76f7a8dd0d8",
+ "621213d4bf2e454caac49d5d9dc70da0",
+ "d866785a13ef4d7a966033f3c5bf0690",
+ "9df336bca8af42909fe4d0e0bf0e4801",
+ "1f773bd126a64ed7a2811285ee649c53",
+ "f085350218b145978f245a512d5b4a0b",
+ "b76b2fb808f449f79c03ab826a061aaf",
+ "6934e0438d6e45039b843dfb8d7fcdf9",
+ "c98119f661fe4bfaaf892dffa017e379",
+ "0210001520d24f96b83f79602cc7219a",
+ "38470542986a4fad891a1a54b4e99433",
+ "cd0768aba1fe48c09209cde3f35f8644",
+ "be34f467900b400ebec1e39b7a98bd16",
+ "10508fc470bd436a87a8d5554b9cccb3",
+ "3006d2dd77f54dc18c0d98ae5332281f",
+ "67170aa447104b5e94f4233863c5a7fb",
+ "847b52f433454cd5911c9f2f1ec1af26",
+ "142e2e4e197c4cf5b22c0a8e033ba464",
+ "65912f982b064948831a3ec46298fc7f",
+ "dd1b40c935ae404ba9cecf01d28ee438",
+ "1da9adffdda74b34b7ec92653e851cd3",
+ "e5ed339ec9c444e3b12e8ea2de3d1a26",
+ "36c80c2f79534088afbb5c46b80f3d18",
+ "3a3edad4cfd649399d149341ba0fd25d",
+ "52699e5a36864f6ea7d88e3240d9b56d",
+ "4aa81a5f34894f6b928c849d6b088d1d",
+ "70830c4ee13c4947825c4977968f8151",
+ "068b13bef47444ffbb5d646f8e2b2ef5",
+ "89a5f0be6c444b84a4b43a8c83151c9f"
+ ]
+ },
+ "outputId": "36b60e13-3f7d-462c-e3ac-d9bdd037ac35"
+ },
+ "execution_count": null,
+ "outputs": [
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/plain": [
+ "Downloading (…)okenizer_config.json: 0%| | 0.00/28.0 [00:00, ?B/s]"
+ ],
+ "application/vnd.jupyter.widget-view+json": {
+ "version_major": 2,
+ "version_minor": 0,
+ "model_id": "aa65f73e671f4ca886d5243786cff482"
+ }
+ },
+ "metadata": {}
+ },
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/plain": [
+ "Downloading (…)lve/main/config.json: 0%| | 0.00/483 [00:00, ?B/s]"
+ ],
+ "application/vnd.jupyter.widget-view+json": {
+ "version_major": 2,
+ "version_minor": 0,
+ "model_id": "5d01a359f54b45a49bc2b69f6b769b61"
+ }
+ },
+ "metadata": {}
+ },
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/plain": [
+ "Downloading (…)solve/main/vocab.txt: 0%| | 0.00/232k [00:00, ?B/s]"
+ ],
+ "application/vnd.jupyter.widget-view+json": {
+ "version_major": 2,
+ "version_minor": 0,
+ "model_id": "6934e0438d6e45039b843dfb8d7fcdf9"
+ }
+ },
+ "metadata": {}
+ },
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/plain": [
+ "Downloading (…)/main/tokenizer.json: 0%| | 0.00/466k [00:00, ?B/s]"
+ ],
+ "application/vnd.jupyter.widget-view+json": {
+ "version_major": 2,
+ "version_minor": 0,
+ "model_id": "65912f982b064948831a3ec46298fc7f"
+ }
+ },
+ "metadata": {}
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "tokenizer(\"Hello, this is one sentence!\")\n",
+ "tokenizer(d[\"train\"][\"tokens\"][0], is_split_into_words=True)\n",
+ "\n",
+ "\n",
+ "# model_path = \"pretrained-bert\"\n",
+ "# # make the directory if not already there\n",
+ "# if not os.path.isdir(model_path):\n",
+ "# os.mkdir(model_path)"
+ ],
+ "metadata": {
+ "id": "vix0oz7XzI_w",
+ "execution": {
+ "iopub.status.busy": "2023-06-16T00:29:21.392218Z",
+ "iopub.execute_input": "2023-06-16T00:29:21.392580Z",
+ "iopub.status.idle": "2023-06-16T00:29:22.864389Z",
+ "shell.execute_reply.started": "2023-06-16T00:29:21.392554Z",
+ "shell.execute_reply": "2023-06-16T00:29:22.862869Z"
+ },
+ "trusted": true,
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "outputId": "cfd1755c-9581-426b-8cc5-75f37891ded6"
+ },
+ "execution_count": null,
+ "outputs": [
+ {
+ "output_type": "execute_result",
+ "data": {
+ "text/plain": [
+ "{'input_ids': [101, 3100, 1012, 102], 'attention_mask': [1, 1, 1, 1]}"
+ ]
+ },
+ "metadata": {},
+ "execution_count": 24
+ }
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "Note that transformers are often pretrained with subword tokenizers, meaning that even if your inputs have been split into words already, each of those words could be split again by the tokenizer."
+ ],
+ "metadata": {
+ "id": "MkG43T05o6h-"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "example = d[\"train\"][2]\n",
+ "print(example[\"tokens\"])\n",
+ "\n",
+ "# save the tokenizer\n",
+ "# tokenizer.save_model(model_path)"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "vmeI9Vgx06VB",
+ "outputId": "54d45c0c-8ee5-4aca-fffa-6b7b2b996217",
+ "execution": {
+ "iopub.status.busy": "2023-06-16T00:29:25.423565Z",
+ "iopub.execute_input": "2023-06-16T00:29:25.423911Z",
+ "iopub.status.idle": "2023-06-16T00:29:25.431033Z",
+ "shell.execute_reply.started": "2023-06-16T00:29:25.423886Z",
+ "shell.execute_reply": "2023-06-16T00:29:25.429512Z"
+ },
+ "trusted": true
+ },
+ "execution_count": null,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "['But', ',', 'if', 'he', 'steps', 'down', 'in', 'September', 'next', 'year', ',', 'we', 'will', 'see', 'who', 'on', 'this', 'cabinet', 'will', 'be', 'the', 'prime', 'minister', '.']\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "tokenized_input = tokenizer(example[\"tokens\"], is_split_into_words=True)\n",
+ "tokens = tokenizer.convert_ids_to_tokens(tokenized_input[\"input_ids\"])\n",
+ "print(tokens)\n",
+ "\n",
+ "# # dumping some of the tokenizer config to config file,\n",
+ "# # including special tokens, whether to lower case and the maximum sequence length\n",
+ "# with open(os.path.join(model_path, \"config.json\"), \"w\") as f:\n",
+ "# tokenizer_cfg = {\n",
+ "# \"do_lower_case\": True,\n",
+ "# \"unk_token\": \"[UNK]\",\n",
+ "# \"sep_token\": \"[SEP]\",\n",
+ "# \"pad_token\": \"[PAD]\",\n",
+ "# \"cls_token\": \"[CLS]\",\n",
+ "# \"mask_token\": \"[MASK]\",\n",
+ "# \"model_max_length\": max_length,\n",
+ "# \"max_len\": max_length,\n",
+ "# }\n",
+ "# json.dump(tokenizer_cfg, f)"
+ ],
+ "metadata": {
+ "id": "d-HZAthp0SNk",
+ "execution": {
+ "iopub.status.busy": "2023-06-16T00:29:30.170734Z",
+ "iopub.execute_input": "2023-06-16T00:29:30.171068Z",
+ "iopub.status.idle": "2023-06-16T00:29:30.177022Z",
+ "shell.execute_reply.started": "2023-06-16T00:29:30.171046Z",
+ "shell.execute_reply": "2023-06-16T00:29:30.175959Z"
+ },
+ "trusted": true,
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "outputId": "2266f73c-fba8-4c00-9603-2e8b75368605"
+ },
+ "execution_count": null,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "['[CLS]', 'but', ',', 'if', 'he', 'steps', 'down', 'in', 'september', 'next', 'year', ',', 'we', 'will', 'see', 'who', 'on', 'this', 'cabinet', 'will', 'be', 'the', 'prime', 'minister', '.', '[SEP]']\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "This means that we need to do some processing on our labels as the input ids returned by the tokenizer are longer than the lists of labels our dataset contain, first because some special tokens might be added (we can a [CLS] and a [SEP] above) and then because of those possible splits of words in multiple tokens:"
+ ],
+ "metadata": {
+ "id": "PUj7c3vUo6h_"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "len(example[\"tags\"]), len(tokenized_input[\"input_ids\"])"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "OkJ_tU4B0jNf",
+ "outputId": "b9752fd2-980e-4cca-956a-d2f7ec45ad51",
+ "execution": {
+ "iopub.status.busy": "2023-06-16T00:29:32.302620Z",
+ "iopub.execute_input": "2023-06-16T00:29:32.303404Z",
+ "iopub.status.idle": "2023-06-16T00:29:32.309252Z",
+ "shell.execute_reply.started": "2023-06-16T00:29:32.303357Z",
+ "shell.execute_reply": "2023-06-16T00:29:32.308614Z"
+ },
+ "trusted": true
+ },
+ "execution_count": null,
+ "outputs": [
+ {
+ "output_type": "execute_result",
+ "data": {
+ "text/plain": [
+ "(24, 26)"
+ ]
+ },
+ "metadata": {},
+ "execution_count": 27
+ }
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "Thankfully, the tokenizer returns outputs that have a word_ids method which can help us.\n",
+ "\n"
+ ],
+ "metadata": {
+ "id": "rOv6RTt1o6h_"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "print(tokenized_input.word_ids())"
+ ],
+ "metadata": {
+ "id": "U5OCCo742G3t",
+ "outputId": "aff0527c-837c-4c16-faed-b7dde5f28327",
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "execution": {
+ "iopub.status.busy": "2023-06-16T00:29:52.679032Z",
+ "iopub.execute_input": "2023-06-16T00:29:52.679429Z",
+ "iopub.status.idle": "2023-06-16T00:29:52.686067Z",
+ "shell.execute_reply.started": "2023-06-16T00:29:52.679402Z",
+ "shell.execute_reply": "2023-06-16T00:29:52.684584Z"
+ },
+ "trusted": true
+ },
+ "execution_count": null,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "[None, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, None]\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "As we can see, it returns a list with the same number of elements as our processed input ids, mapping special tokens to None and all other tokens to their respective word. This way, we can align the labels with the processed input ids."
+ ],
+ "metadata": {
+ "id": "8S2ipBHRo6iA"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "word_ids = tokenized_input.word_ids()\n",
+ "aligned_labels = [-100 if i is None else example[\"tags\"][i] for i in word_ids]\n",
+ "print(len(aligned_labels), len(tokenized_input[\"input_ids\"]))"
+ ],
+ "metadata": {
+ "id": "2Qr5J8xE2KaL",
+ "outputId": "5d99796e-cd5f-405b-8fd1-74a3529ef7a2",
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "execution": {
+ "iopub.status.busy": "2023-06-16T00:29:58.562189Z",
+ "iopub.execute_input": "2023-06-16T00:29:58.562527Z",
+ "iopub.status.idle": "2023-06-16T00:29:58.569595Z",
+ "shell.execute_reply.started": "2023-06-16T00:29:58.562503Z",
+ "shell.execute_reply": "2023-06-16T00:29:58.567424Z"
+ },
+ "trusted": true
+ },
+ "execution_count": null,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "26 26\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "Here we set the labels of all special tokens to -100 (the index that is ignored by PyTorch) and the labels of all other tokens to the label of the word they come from. Another strategy is to set the label only on the first token obtained from a given word, and give a label of -100 to the other subtokens from the same word. We propose the two strategies here, just change the value of the following flag:"
+ ],
+ "metadata": {
+ "id": "b2TXNB77o6iA"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "label_all_tokens = True"
+ ],
+ "metadata": {
+ "execution": {
+ "iopub.status.busy": "2023-06-16T00:30:01.658264Z",
+ "iopub.execute_input": "2023-06-16T00:30:01.658646Z",
+ "iopub.status.idle": "2023-06-16T00:30:01.663310Z",
+ "shell.execute_reply.started": "2023-06-16T00:30:01.658622Z",
+ "shell.execute_reply": "2023-06-16T00:30:01.662353Z"
+ },
+ "trusted": true,
+ "id": "salXW9bzo6iA"
+ },
+ "execution_count": null,
+ "outputs": []
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "We're now ready to write the function that will preprocess our samples. We feed them to the tokenizer with the argument `truncation=True` (to truncate texts that are bigger than the maximum size allowed by the model) and `is_split_into_words=True` (as seen above). Then we align the labels with the token ids using the strategy we picked:"
+ ],
+ "metadata": {
+ "id": "FftA8Zb6o6iA"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "def tokenize_and_align_labels(examples):\n",
+ " tokenized_inputs = tokenizer(examples[\"tokens\"], truncation=True, is_split_into_words=True)\n",
+ "\n",
+ " labels = []\n",
+ " for i, label in enumerate(examples[\"tags\"]):\n",
+ " word_ids = tokenized_inputs.word_ids(batch_index=i)\n",
+ " previous_word_idx = None\n",
+ " label_ids = []\n",
+ " for word_idx in word_ids:\n",
+ " # Special tokens have a word id that is None. We set the label to -100 so they are automatically\n",
+ " # ignored in the loss function.\n",
+ " if word_idx is None:\n",
+ " label_ids.append(-100)\n",
+ " # We set the label for the first token of each word.\n",
+ " elif word_idx != previous_word_idx:\n",
+ " label_ids.append(label[word_idx])\n",
+ " # For the other tokens in a word, we set the label to either the current label or -100, depending on\n",
+ " # the label_all_tokens flag.\n",
+ " else:\n",
+ " label_ids.append(label[word_idx] if label_all_tokens else -100)\n",
+ " previous_word_idx = word_idx\n",
+ "\n",
+ " labels.append(label_ids)\n",
+ "\n",
+ " tokenized_inputs[\"labels\"] = labels\n",
+ " return tokenized_inputs\n"
+ ],
+ "metadata": {
+ "execution": {
+ "iopub.status.busy": "2023-06-16T00:30:04.682317Z",
+ "iopub.execute_input": "2023-06-16T00:30:04.682650Z",
+ "iopub.status.idle": "2023-06-16T00:30:04.690258Z",
+ "shell.execute_reply.started": "2023-06-16T00:30:04.682626Z",
+ "shell.execute_reply": "2023-06-16T00:30:04.688956Z"
+ },
+ "trusted": true,
+ "id": "Hgpobeoxo6iA"
+ },
+ "execution_count": null,
+ "outputs": []
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "This function works with one or several examples. In the case of several examples, the tokenizer will return a list of lists for each key:"
+ ],
+ "metadata": {
+ "id": "GyVSJOvuo6iA"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "tokenize_and_align_labels(d['train'][:5])"
+ ],
+ "metadata": {
+ "execution": {
+ "iopub.status.busy": "2023-06-16T00:30:13.948755Z",
+ "iopub.execute_input": "2023-06-16T00:30:13.949101Z",
+ "iopub.status.idle": "2023-06-16T00:30:13.958368Z",
+ "shell.execute_reply.started": "2023-06-16T00:30:13.949078Z",
+ "shell.execute_reply": "2023-06-16T00:30:13.957214Z"
+ },
+ "trusted": true,
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "IMGxH2mro6iA",
+ "outputId": "3af49654-8bcc-4952-b388-c461f1d9f508"
+ },
+ "execution_count": null,
+ "outputs": [
+ {
+ "output_type": "execute_result",
+ "data": {
+ "text/plain": [
+ "{'input_ids': [[101, 3100, 1012, 102], [101, 2057, 4088, 2023, 2431, 3178, 2007, 1996, 6745, 8973, 1999, 1996, 4883, 2602, 1012, 102], [101, 2021, 1010, 2065, 2002, 4084, 2091, 1999, 2244, 2279, 2095, 1010, 2057, 2097, 2156, 2040, 2006, 2023, 5239, 2097, 2022, 1996, 3539, 2704, 1012, 102], [101, 1003, 7910, 1998, 2144, 1045, 6187, 1050, 1005, 1056, 2428, 2175, 5973, 2302, 2216, 2151, 14406, 102], [101, 2005, 1996, 2087, 2112, 1010, 2027, 2031, 1000, 4550, 1998, 4840, 1000, 4871, 1998, 2593, 6170, 5154, 2774, 2030, 11092, 1037, 2715, 2544, 1997, 1996, 3151, 2887, 4372, 2912, 4823, 2806, 1012, 102]], 'attention_mask': [[1, 1, 1, 1], [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]], 'labels': [[-100, 0, 0, -100], [-100, 0, 0, 21, 29, 29, 0, 0, 0, 0, 0, 0, 0, 0, 0, -100], [-100, 0, 0, 0, 0, 0, 0, 0, 2, 3, 3, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, -100], [-100, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, -100], [-100, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 6, 0, 0, 0, 0, 0, -100]]}"
+ ]
+ },
+ "metadata": {},
+ "execution_count": 32
+ }
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "To apply this function on all the sentences (or pairs of sentences) in our dataset, we just use the map method of our dataset object we created earlier. This will apply the function on all the elements of all the splits in dataset, so our training, validation and testing data will be preprocessed in one single command."
+ ],
+ "metadata": {
+ "id": "zIYIpY5zo6iB"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "tokenized_datasets = d.map(tokenize_and_align_labels, batched=True)"
+ ],
+ "metadata": {
+ "execution": {
+ "iopub.status.busy": "2023-06-16T00:30:22.263591Z",
+ "iopub.execute_input": "2023-06-16T00:30:22.263894Z",
+ "iopub.status.idle": "2023-06-16T00:30:28.918158Z",
+ "shell.execute_reply.started": "2023-06-16T00:30:22.263873Z",
+ "shell.execute_reply": "2023-06-16T00:30:28.916267Z"
+ },
+ "trusted": true,
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 17,
+ "referenced_widgets": [
+ "40dabcd04a784ccb818a7b634e61b173",
+ "0458edaaec1e48c781fcc16202357089",
+ "db27d69a64be4ddda3cbe9494aa63d5e",
+ "6405244b8880496e9621f9521d42161b",
+ "cf7107e22bee470791637e09877d50fe",
+ "b1a72c432be34987bdea3d8e6d4db9cf",
+ "3e04042eb88d4807a94999919a400559",
+ "c6adaba4760f454f8c3929e088a83f9a",
+ "9deded080d784c67837b34fb8d76947c",
+ "0e59a284de2e4d42916be734575c0fff",
+ "13e693d4dc8243e8a0b99a531e5055b0",
+ "7158b44c8f0e469381997180c1047995",
+ "e8be574a0e194b55ae12bf26a6309483",
+ "7cd37438898742169ec46510e1128b31",
+ "b1f37f108ade458c9e655568f2eb86b7",
+ "b9f9cd99297f4b16b93d2c8bdcea94e9",
+ "53edf50124eb4b03abaa5428c5bde2c9",
+ "25a9977492f342e19603749dc824104c",
+ "55712f37a3ba4db2a018a1b7734a8030",
+ "0e3b01157a324c948342c950cc8d4d77",
+ "1fbdb596d823448b8026ddb14792808e",
+ "da715f9146ab4f148e46c81237d10274"
+ ]
+ },
+ "id": "mgLrul7Jo6iB",
+ "outputId": "6a9eff5a-cb7c-434d-c52a-30e6e49ba4fd"
+ },
+ "execution_count": null,
+ "outputs": [
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/plain": [
+ "Map: 0%| | 0/53931 [00:00, ? examples/s]"
+ ],
+ "application/vnd.jupyter.widget-view+json": {
+ "version_major": 2,
+ "version_minor": 0,
+ "model_id": "40dabcd04a784ccb818a7b634e61b173"
+ }
+ },
+ "metadata": {}
+ },
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/plain": [
+ "Map: 0%| | 0/5993 [00:00, ? examples/s]"
+ ],
+ "application/vnd.jupyter.widget-view+json": {
+ "version_major": 2,
+ "version_minor": 0,
+ "model_id": "7158b44c8f0e469381997180c1047995"
+ }
+ },
+ "metadata": {}
+ }
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "Even better, the results are automatically cached by the 🤗 Datasets library to avoid spending time on this step the next time you run your notebook. The 🤗 Datasets library is normally smart enough to detect when the function you pass to map has changed (and thus requires to not use the cache data). For instance, it will properly detect if you change the task in the first cell and rerun the notebook. 🤗 Datasets warns you when it uses cached files, you can pass load_from_cache_file=False in the call to map to not use the cached files and force the preprocessing to be applied again.\n",
+ "\n",
+ "Note that we passed batched=True to encode the texts by batches together. This is to leverage the full benefit of the fast tokenizer we loaded earlier, which will use multi-threading to treat the texts in a batch concurrently."
+ ],
+ "metadata": {
+ "id": "2vbNrHi2o6iB"
+ }
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "# Fine-tuning the Model"
+ ],
+ "metadata": {
+ "id": "zYxgGRGyo6iB"
+ }
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "Now that our data is ready, we can download the pretrained model and fine-tune it. Since all our tasks are about token classification, we use the `AutoModelForTokenClassification` class. Like with the tokenizer, the `from_pretrained` method will download and cache the model for us. The only thing we have to specify is the number of labels for our problem (which we can get from the features, as seen before):"
+ ],
+ "metadata": {
+ "id": "k_barrFRo6iB"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "from transformers import AutoModelForTokenClassification, TrainingArguments, Trainer\n",
+ "\n",
+ "model = AutoModelForTokenClassification.from_pretrained(model_checkpoint, num_labels=len(label_list))"
+ ],
+ "metadata": {
+ "execution": {
+ "iopub.status.busy": "2023-06-16T00:32:16.261007Z",
+ "iopub.execute_input": "2023-06-16T00:32:16.261946Z",
+ "iopub.status.idle": "2023-06-16T00:32:33.389188Z",
+ "shell.execute_reply.started": "2023-06-16T00:32:16.261908Z",
+ "shell.execute_reply": "2023-06-16T00:32:33.386260Z"
+ },
+ "trusted": true,
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 156,
+ "referenced_widgets": [
+ "bf2647ee9662453f89fb10449fa38967",
+ "0c6ca1c0e6e54c688de51567fb77c7c6",
+ "92ab3fa24b3e464e80d8890c8e37e378",
+ "83b6c91550e540a99ebdf165ad37707f",
+ "9bc86a1e81464ae88b79a3e7685caf91",
+ "8c15e2d94a3642c7b5d9dc3a309e275c",
+ "11a347f8e76c466aacdb24f7bc660a52",
+ "588a66fec2a04571a49c5a02e43230b5",
+ "804228726a0d4aa582259234b3de86fb",
+ "866b385c0d3a4680a21ac457083b9b7e",
+ "1ca527c7678449d5a8d91400369bdf3d"
+ ]
+ },
+ "id": "1-f8C_ARo6iB",
+ "outputId": "85bedfd9-2902-47f0-82d9-f36c8d6b223b"
+ },
+ "execution_count": null,
+ "outputs": [
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/plain": [
+ "Downloading model.safetensors: 0%| | 0.00/268M [00:00, ?B/s]"
+ ],
+ "application/vnd.jupyter.widget-view+json": {
+ "version_major": 2,
+ "version_minor": 0,
+ "model_id": "bf2647ee9662453f89fb10449fa38967"
+ }
+ },
+ "metadata": {}
+ },
+ {
+ "output_type": "stream",
+ "name": "stderr",
+ "text": [
+ "Some weights of the model checkpoint at distilbert-base-uncased were not used when initializing DistilBertForTokenClassification: ['vocab_layer_norm.bias', 'vocab_projector.bias', 'vocab_transform.weight', 'vocab_transform.bias', 'vocab_layer_norm.weight']\n",
+ "- This IS expected if you are initializing DistilBertForTokenClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).\n",
+ "- This IS NOT expected if you are initializing DistilBertForTokenClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).\n",
+ "Some weights of DistilBertForTokenClassification were not initialized from the model checkpoint at distilbert-base-uncased and are newly initialized: ['classifier.weight', 'classifier.bias']\n",
+ "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "The warning is telling us we are throwing away some weights (the vocab_transform and vocab_layer_norm layers) and randomly initializing some other (the pre_classifier and classifier layers). This is absolutely normal in this case, because we are removing the head used to pretrain the model on a masked language modeling objective and replacing it with a new head for which we don't have pretrained weights, so the library warns us we should fine-tune this model before using it for inference, which is exactly what we are going to do.\n",
+ "\n",
+ "To instantiate a Trainer, we will need to define three more things. The most important is the TrainingArguments, which is a class that contains all the attributes to customize the training. It requires one folder name, which will be used to save the checkpoints of the model, and all other arguments are optional:"
+ ],
+ "metadata": {
+ "id": "XxlGE0cMo6iB"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "model_name = model_checkpoint.split(\"/\")[-1]\n",
+ "args = TrainingArguments(\n",
+ " \"claims-data-model\",\n",
+ " evaluation_strategy = \"epoch\",\n",
+ " learning_rate=2e-5,\n",
+ " per_device_train_batch_size=batch_size,\n",
+ " per_device_eval_batch_size=batch_size,\n",
+ " num_train_epochs=3,\n",
+ " weight_decay=0.01,\n",
+ " push_to_hub=True\n",
+ ")"
+ ],
+ "metadata": {
+ "trusted": true,
+ "id": "itca98NXo6iB",
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 236
+ },
+ "outputId": "7bfc8957-025f-4758-815a-eff9a337b9d1"
+ },
+ "execution_count": null,
+ "outputs": [
+ {
+ "output_type": "error",
+ "ename": "NameError",
+ "evalue": "ignored",
+ "traceback": [
+ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+ "\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)",
+ "\u001b[0;32m\u001b[0m in \u001b[0;36m\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mmodel_name\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mmodel_checkpoint\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msplit\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"/\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m-\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 2\u001b[0m args = TrainingArguments(\n\u001b[1;32m 3\u001b[0m \u001b[0;34m\"claims-data-model\"\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 4\u001b[0m \u001b[0mevaluation_strategy\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m\"epoch\"\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 5\u001b[0m \u001b[0mlearning_rate\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m2e-5\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+ "\u001b[0;31mNameError\u001b[0m: name 'model_checkpoint' is not defined"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "Here we set the evaluation to be done at the end of each epoch, tweak the learning rate, use the `batch_size` defined at the top of the notebook and customize the number of epochs for training, as well as the weight decay.\n",
+ "\n",
+ "The last argument to setup everything so we can push the model to the Hub regularly during training. Remove it if you didn't follow the installation steps at the top of the notebook. If you want to save your model locally in a name that is different than the name of the repository it will be pushed, or if you want to push your model under an organization and not your name space, use the `hub_model_id` argument to set the repo name (it needs to be the full name, including your namespace: for instance `\"sgugger/bert-finetuned-ner\"` or `\"huggingface/bert-finetuned-ner\"`).\n",
+ "\n",
+ "Then we will need a data collator that will batch our processed examples together while applying padding to make them all the same size (each pad will be padded to the length of its longest example). There is a data collator for this task in the Transformers library, that not only pads the inputs, but also the labels:"
+ ],
+ "metadata": {
+ "id": "BJpVmVpzo6iC"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "from transformers import DataCollatorForTokenClassification\n",
+ "\n",
+ "data_collator = DataCollatorForTokenClassification(tokenizer)"
+ ],
+ "metadata": {
+ "id": "kmFCTByJ1OI3",
+ "trusted": true
+ },
+ "execution_count": null,
+ "outputs": []
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "The last thing to define for our Trainer is how to compute the metrics from the predictions. Here we will load the `seqeval` metric (which is commonly used to evaluate results on the CONLL dataset) via the Datasets library."
+ ],
+ "metadata": {
+ "id": "0ZLL5p95o6iC"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "metric = load_metric(\"seqeval\")"
+ ],
+ "metadata": {
+ "id": "7Bie2oq0o6iC"
+ },
+ "execution_count": null,
+ "outputs": []
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "This metric takes list of labels for the predictions and references:"
+ ],
+ "metadata": {
+ "id": "XdqxwJEOo6iC"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "labels = [label_list[i] for i in example[\"tags\"]]\n",
+ "metric.compute(predictions=[labels], references=[labels])"
+ ],
+ "metadata": {
+ "id": "dVdwnxe8o6iD"
+ },
+ "execution_count": null,
+ "outputs": []
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "So we will need to do a bit of post-processing on our predictions:\n",
+ "\n",
+ "- select the predicted index (with the maximum logit) for each token\n",
+ "- convert it to its string label\n",
+ "- ignore everywhere we set a label of -100\n",
+ "\n",
+ "The following function does all this post-processing on the result of Trainer.evaluate (which is a namedtuple containing predictions and labels) before applying the metric:"
+ ],
+ "metadata": {
+ "id": "gSE2DwIUqvHe"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "import numpy as np\n",
+ "\n",
+ "def compute_metrics(p):\n",
+ " predictions, labels = p\n",
+ " predictions = np.argmax(predictions, axis=2)\n",
+ "\n",
+ " # Remove ignored index (special tokens)\n",
+ " true_predictions = [\n",
+ " [label_list[p] for (p, l) in zip(prediction, label) if l != -100]\n",
+ " for prediction, label in zip(predictions, labels)\n",
+ " ]\n",
+ "\n",
+ " true_labels = [\n",
+ " [label_list[l] for (p, l) in zip (prediction, label) if l != -100]\n",
+ " for prediction, label in zip(predictions, labels)\n",
+ " ]\n",
+ "\n",
+ " results = metric.compute(predictions=true_predictions, references=true_labels)\n",
+ " return {\n",
+ " \"precision\": results[\"overall_precision\"],\n",
+ " \"recall\": results[\"overall_recall\"],\n",
+ " \"f1\": results[\"overall_f1\"],\n",
+ " \"accuracy\": results[\"overall_accuracy\"],\n",
+ " }"
+ ],
+ "metadata": {
+ "id": "OMKVmXZN2o7c",
+ "trusted": true
+ },
+ "execution_count": null,
+ "outputs": []
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "Note that we drop the precision/recall/f1 computed for each category and only focus on the overall precision/recall/f1/accuracy.\n",
+ "\n",
+ "Then we just need to pass all of this along with our datasets to the `Trainer`:"
+ ],
+ "metadata": {
+ "id": "3YlGOBOqsKNK"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "trainer = Trainer(\n",
+ " model,\n",
+ " args,\n",
+ " train_dataset=tokenized_datasets[\"train\"],\n",
+ " eval_dataset=tokenized_datasets[\"test\"],\n",
+ " data_collator=data_collator,\n",
+ " tokenizer=tokenizer,\n",
+ " compute_metrics=compute_metrics\n",
+ ")"
+ ],
+ "metadata": {
+ "id": "HYsgN58E2tFD",
+ "trusted": true
+ },
+ "execution_count": null,
+ "outputs": []
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "We can now finetune our model by just calling the `train` method:"
+ ],
+ "metadata": {
+ "id": "rxgoaktmtw7m"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "trainer.train()"
+ ],
+ "metadata": {
+ "id": "vJO-1w15ARHs",
+ "trusted": true
+ },
+ "execution_count": null,
+ "outputs": []
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "The `evaluate` method allows you to evaluate again on the evaluation dataset or on another dataset:"
+ ],
+ "metadata": {
+ "id": "b8apIxuNz5Li"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "trainer.evaluate()"
+ ],
+ "metadata": {
+ "id": "8ROoCqpssCb9",
+ "trusted": true
+ },
+ "execution_count": null,
+ "outputs": []
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "To get the precision/recall/f1 computed for each category now that we have finished training, we can apply the same function as before on the result of the `predict` method:"
+ ],
+ "metadata": {
+ "id": "GU_4nek00M9z"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "predictions, labels, _ = trainer.predict(tokenized_datasets[\"test\"])\n",
+ "predictions = np.argmax(predictions, axis=2)\n",
+ "\n",
+ "\n",
+ "# Remove ignored index (special tokens)\n",
+ "true_predictions = [\n",
+ " [label_list[p] for (p, l) in zip(prediction, label) if l != -100]\n",
+ " for prediction, label in zip(predictions, labels)\n",
+ "]\n",
+ "\n",
+ "true_labels = [\n",
+ " [label_list[l] for (p, l) in zip (prediction, label) if l != -100]\n",
+ " for prediction, label in zip(predictions, labels)\n",
+ "]\n",
+ "\n",
+ "results = metric.compute(predictions=true_predictions, references=true_labels)\n",
+ "print(results)"
+ ],
+ "metadata": {
+ "id": "WvVnsyQY0TeI"
+ },
+ "execution_count": null,
+ "outputs": []
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "Save the model locally if wanted"
+ ],
+ "metadata": {
+ "id": "PRSEZz_k2ql9"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "# pt_save_directory = \"./pt_save_pretrained\"\n",
+ "# tokenizer.save_pretrained(pt_save_directory)\n",
+ "# model.save_pretrained(pt_save_directory)"
+ ],
+ "metadata": {
+ "id": "TQvM693K2scM"
+ },
+ "execution_count": null,
+ "outputs": []
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "Or upload the result of the training to the hub (requires the login setup from near the start)"
+ ],
+ "metadata": {
+ "id": "fLdNGVfKF4ia"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "trainer.push_to_hub(\"claims-data-model-2\")\n",
+ "tokenizer.push_to_hub(\"claims-data-model-2\")"
+ ],
+ "metadata": {
+ "id": "hBLFQ8NlF-kM"
+ },
+ "execution_count": null,
+ "outputs": []
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "You can now share this model with all your friends, family, favorite pets: they can all load it with the identifier `\"your-username/the-name-you-picked\"` so for instance:\n",
+ "\n",
+ "```python\n",
+ "from transformers import AutoModelForTokenClassification\n",
+ "\n",
+ "model = AutoModelForTokenClassification.from_pretrained(\"sgugger/my-awesome-model\")\n",
+ "```"
+ ],
+ "metadata": {
+ "id": "FLr5pdlzGLrv"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [],
+ "metadata": {
+ "id": "cbnDLuVmGUp9"
+ },
+ "execution_count": null,
+ "outputs": []
+ }
+ ]
+}
\ No newline at end of file
|