diff --git "a/xlm_longformer_mgtd_italian_epochs_3.ipynb" "b/xlm_longformer_mgtd_italian_epochs_3.ipynb" new file mode 100644--- /dev/null +++ "b/xlm_longformer_mgtd_italian_epochs_3.ipynb" @@ -0,0 +1,14549 @@ +{ + "nbformat": 4, + "nbformat_minor": 0, + "metadata": { + "colab": { + "provenance": [], + "machine_shape": "hm", + "gpuType": "A100" + }, + "kernelspec": { + "name": "python3", + "display_name": "Python 3" + }, + "language_info": { + "name": "python" + }, + "accelerator": "GPU", + "widgets": { + "application/vnd.jupyter.widget-state+json": { + "2081b497fb2e47b199896b4594ab05f1": { + "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": [], + "layout": "IPY_MODEL_5640111928d54835a2559b8b67ea4dbe" + } + }, + "6b61efb318784788b49e7b34eac97e19": { + "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_78e67dbc66c942d5be8000e38ed734b4", + "placeholder": "​", + "style": "IPY_MODEL_1eea9656cf294cb596da6a6b44c593a0", + "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.
" + } + }, + "02a9cdcba3ff4bef987c0cb61e878244": { + "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_ac4c958f873f49c58180bf4e35d61945", + "placeholder": "​", + "style": "IPY_MODEL_481be2d56a10425a9b26b2d4d711414b", + "value": "" + } + }, + "f2fb420c625a4d0e978d3adbe21e8229": { + "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_6235c281177a4c959bed2f288cb279ca", + "style": "IPY_MODEL_64ab4e05dcdc49978762a406b030c621", + "value": true + } + }, + "ffe2e057ad824852bee3c5b3a5bd4885": { + "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_82889bcd764d4b169f4d1db84291c314", + "style": "IPY_MODEL_c006340b49674251a8e00328559b7574", + "tooltip": "" + } + }, + "107aed6805aa4e51830b72413c878e8e": { + "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_0da3cd1c52dd468fbfeab57ebbe36843", + "placeholder": "​", + "style": "IPY_MODEL_9369682c0e70482a80d1f5203e9e4790", + "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. " + } + }, + "5640111928d54835a2559b8b67ea4dbe": { + "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%" + } + }, + "78e67dbc66c942d5be8000e38ed734b4": { + "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 + } + }, + "1eea9656cf294cb596da6a6b44c593a0": { + "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": "" + } + }, + "ac4c958f873f49c58180bf4e35d61945": { + "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 + } + }, + "481be2d56a10425a9b26b2d4d711414b": { + "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": "" + } + }, + "6235c281177a4c959bed2f288cb279ca": { + "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 + } + }, + "64ab4e05dcdc49978762a406b030c621": { + "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": "" + } + }, + "82889bcd764d4b169f4d1db84291c314": { + "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 + } + }, + "c006340b49674251a8e00328559b7574": { + "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": "" + } + }, + "0da3cd1c52dd468fbfeab57ebbe36843": { + "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 + } + }, + "9369682c0e70482a80d1f5203e9e4790": { + "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": "" + } + }, + "3d5d8d4fccae4cf98282b4d3f61e3a2d": { + "model_module": "@jupyter-widgets/controls", + "model_name": "LabelModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "LabelModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "LabelView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_68cd5f2a0c4443d4b5a115b684331ea0", + "placeholder": "​", + "style": "IPY_MODEL_131557dd866642a6b2a5dacf23fad6c5", + "value": "Connecting..." + } + }, + "68cd5f2a0c4443d4b5a115b684331ea0": { + "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 + } + }, + "131557dd866642a6b2a5dacf23fad6c5": { + "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": "" + } + }, + "d21f5a4689504a7ca014a2d7aed04e2b": { + "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_a34ae57d3b1f47fdb8fa2e78ea87353f", + "IPY_MODEL_c71e120a2bd843829d10ccce7a73ce0c", + "IPY_MODEL_b3abd92d47c64bd9abc34965240cc330" + ], + "layout": "IPY_MODEL_9df1021268a34b279d5c8cf688a368e2" + } + }, + "a34ae57d3b1f47fdb8fa2e78ea87353f": { + "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_8770fa6872d941589a1d3fa095112e99", + "placeholder": "​", + "style": "IPY_MODEL_62a253ec992642bdb2bf00063462098f", + "value": "tokenizer_config.json: 100%" + } + }, + "c71e120a2bd843829d10ccce7a73ce0c": { + "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_2b3f220f28ba4fc6b5ae6f4d19703d01", + "max": 453, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_76339c1d38e840b1b730ef35d7b1d9ff", + "value": 453 + } + }, + "b3abd92d47c64bd9abc34965240cc330": { + "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_dd59db74d57448c793a0e04da22da6cc", + "placeholder": "​", + "style": "IPY_MODEL_783911e293d143f3907a0bbaca202713", + "value": " 453/453 [00:00<00:00, 44.5kB/s]" + } + }, + "9df1021268a34b279d5c8cf688a368e2": { + "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 + } + }, + "8770fa6872d941589a1d3fa095112e99": { + "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 + } + }, + "62a253ec992642bdb2bf00063462098f": { + "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": "" + } + }, + "2b3f220f28ba4fc6b5ae6f4d19703d01": { + "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 + } + }, + "76339c1d38e840b1b730ef35d7b1d9ff": { + "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": "" + } + }, + "dd59db74d57448c793a0e04da22da6cc": { + "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 + } + }, + "783911e293d143f3907a0bbaca202713": { + "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": "" + } + }, + "6e1a91af884248f2bbfb78fabbe95e14": { + "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_412b1a4e5f6f4e03bb297c66111f984f", + "IPY_MODEL_9b55737674da45a3b023c02cf83abeb8", + "IPY_MODEL_3bb2ee1ea8ff496c88f3f4844cfeceb4" + ], + "layout": "IPY_MODEL_baf90a1ec4814bd3b09a4ad15303a992" + } + }, + "412b1a4e5f6f4e03bb297c66111f984f": { + "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_f7f5618808c542ba8aad476d96100ae5", + "placeholder": "​", + "style": "IPY_MODEL_cd35bde91abc46a39e4d96aafbab46c5", + "value": "tokenizer.json: 100%" + } + }, + "9b55737674da45a3b023c02cf83abeb8": { + "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_f71b3a42b3c844d3bffa7074beb776c6", + "max": 17082660, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_de91e1cee5174f8e82ff9839a7185063", + "value": 17082660 + } + }, + "3bb2ee1ea8ff496c88f3f4844cfeceb4": { + "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_87540f9e929e43b3ac3961ab7ad8a82d", + "placeholder": "​", + "style": "IPY_MODEL_eb8b49129c294c8096d6ccc8c1069f82", + "value": " 17.1M/17.1M [00:00<00:00, 31.7MB/s]" + } + }, + "baf90a1ec4814bd3b09a4ad15303a992": { + "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 + } + }, + "f7f5618808c542ba8aad476d96100ae5": { + "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 + } + }, + "cd35bde91abc46a39e4d96aafbab46c5": { + "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": "" + } + }, + "f71b3a42b3c844d3bffa7074beb776c6": { + "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 + } + }, + "de91e1cee5174f8e82ff9839a7185063": { + "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": "" + } + }, + "87540f9e929e43b3ac3961ab7ad8a82d": { + "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 + } + }, + "eb8b49129c294c8096d6ccc8c1069f82": { + "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": "" + } + }, + "04a02e49ebec4ea4a4891c14470d187d": { + "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_456d6f0353e349f38bc164c812ddc97a", + "IPY_MODEL_b67249ced0ba4e6298fc320020b21f75", + "IPY_MODEL_495d5c07ca6242019a66da31f252d60c" + ], + "layout": "IPY_MODEL_bd6f16353a53417d8e45e9cdce8a2354" + } + }, + "456d6f0353e349f38bc164c812ddc97a": { + "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_2d3ef84af7d442dc9542869d94b6bcdd", + "placeholder": "​", + "style": "IPY_MODEL_2fba0f1a144048ffb6c110c66674903c", + "value": "special_tokens_map.json: 100%" + } + }, + "b67249ced0ba4e6298fc320020b21f75": { + "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_25bd1432d1b84b07a2d448bc16b8103a", + "max": 280, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_da98b612f9e84861a07f334ab06ae2bc", + "value": 280 + } + }, + "495d5c07ca6242019a66da31f252d60c": { + "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_d4c4017cbbcb470dbe50f6578705f1b8", + "placeholder": "​", + "style": "IPY_MODEL_57bad45670f742918f398dcf46d84ba1", + "value": " 280/280 [00:00<00:00, 25.5kB/s]" + } + }, + "bd6f16353a53417d8e45e9cdce8a2354": { + "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 + } + }, + "2d3ef84af7d442dc9542869d94b6bcdd": { + "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 + } + }, + "2fba0f1a144048ffb6c110c66674903c": { + "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": "" + } + }, + "25bd1432d1b84b07a2d448bc16b8103a": { + "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 + } + }, + "da98b612f9e84861a07f334ab06ae2bc": { + "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": "" + } + }, + "d4c4017cbbcb470dbe50f6578705f1b8": { + "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 + } + }, + "57bad45670f742918f398dcf46d84ba1": { + "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": "" + } + }, + "7e33ab5539484be887a33acf5815f7db": { + "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_bde5ee4c9af7498da085fcfbc46aaa68", + "IPY_MODEL_371c95e5795e4444bba017ec4c310e3c", + "IPY_MODEL_7edc2bb25fb348068f93af986603d928" + ], + "layout": "IPY_MODEL_8184d3c404bb490cad6da3b46d117e75" + } + }, + "bde5ee4c9af7498da085fcfbc46aaa68": { + "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_d5c489f1273a40df93a1f56433024149", + "placeholder": "​", + "style": "IPY_MODEL_79a4538894814e08b0d2ecf9b6028c4a", + "value": "hyperonym-xlm-roberta-longformer-base-16384-epoch-3.pt: 100%" + } + }, + "371c95e5795e4444bba017ec4c310e3c": { + "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_59a557eb0de64d7f840cd4b66f2da4f5", + "max": 3563459222, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_72cbe7b1cf254500aaffe7788d56fc7a", + "value": 3563459222 + } + }, + "7edc2bb25fb348068f93af986603d928": { + "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_54eb3d562f8b406b97170286dea123de", + "placeholder": "​", + "style": "IPY_MODEL_63374b1bb0b84393a3cbee7db283e411", + "value": " 3.56G/3.56G [01:17<00:00, 44.9MB/s]" + } + }, + "8184d3c404bb490cad6da3b46d117e75": { + "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 + } + }, + "d5c489f1273a40df93a1f56433024149": { + "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 + } + }, + "79a4538894814e08b0d2ecf9b6028c4a": { + "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": "" + } + }, + "59a557eb0de64d7f840cd4b66f2da4f5": { + "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 + } + }, + "72cbe7b1cf254500aaffe7788d56fc7a": { + "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": "" + } + }, + "54eb3d562f8b406b97170286dea123de": { + "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 + } + }, + "63374b1bb0b84393a3cbee7db283e411": { + "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": "" + } + } + } + } + }, + "cells": [ + { + "cell_type": "code", + "source": [ + "from huggingface_hub import notebook_login\n", + "notebook_login()" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 17, + "referenced_widgets": [ + "2081b497fb2e47b199896b4594ab05f1", + "6b61efb318784788b49e7b34eac97e19", + "02a9cdcba3ff4bef987c0cb61e878244", + "f2fb420c625a4d0e978d3adbe21e8229", + "ffe2e057ad824852bee3c5b3a5bd4885", + "107aed6805aa4e51830b72413c878e8e", + "5640111928d54835a2559b8b67ea4dbe", + "78e67dbc66c942d5be8000e38ed734b4", + "1eea9656cf294cb596da6a6b44c593a0", + "ac4c958f873f49c58180bf4e35d61945", + "481be2d56a10425a9b26b2d4d711414b", + "6235c281177a4c959bed2f288cb279ca", + "64ab4e05dcdc49978762a406b030c621", + "82889bcd764d4b169f4d1db84291c314", + "c006340b49674251a8e00328559b7574", + "0da3cd1c52dd468fbfeab57ebbe36843", + "9369682c0e70482a80d1f5203e9e4790", + "3d5d8d4fccae4cf98282b4d3f61e3a2d", + "68cd5f2a0c4443d4b5a115b684331ea0", + "131557dd866642a6b2a5dacf23fad6c5" + ] + }, + "id": "PuRWQjgGqL--", + "outputId": "88015f6e-5a4b-4d94-fa1c-7ede14d24dbd" + }, + "execution_count": 1, + "outputs": [ + { + "output_type": "display_data", + "data": { + "text/plain": [ + "VBox(children=(HTML(value='
:1: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " df_train['id'] = 'ITA' + df_train.index.astype(str) # Creating the 'id' column\n", + ":3: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " df_dev['id'] = 'ITA' + df_dev.index.astype(str) # Creating the 'id' column\n", + ":5: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " df_test['id'] = 'ITA' + df_test.index.astype(str) # Creating the 'id' column\n" + ] + } + ] + }, + { + "cell_type": "code", + "source": [ + "df_train = pd.concat([df_train, df_dev], ignore_index=True)" + ], + "metadata": { + "id": "6DUNiRgiXkW0" + }, + "execution_count": 7, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "print(len(df_train))\n", + "print(len(df_dev))\n", + "print(len(df_test))" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "Wl-9iTP2XmcA", + "outputId": "2a34622b-05a5-4c2c-c74b-cb77905df193" + }, + "execution_count": 8, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "54929\n", + "10986\n", + "54936\n" + ] + } + ] + }, + { + "cell_type": "code", + "source": [ + "df_train.to_json('ITA_train.jsonl', orient='records', lines=True)\n", + "df_test.to_json('ITA_test.jsonl', orient='records', lines=True)" + ], + "metadata": { + "id": "B2oun_v3xb8V" + }, + "execution_count": 9, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "df_train" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 614 + }, + "id": "yWcWjP7pEjvZ", + "outputId": "2afaa618-f440-4656-f2a0-f845787d56d0" + }, + "execution_count": 10, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + " ISO LLM used Type Data Split \\\n", + "0 ITA Gemini-Flash-1.5 Partial Train \n", + "1 ITA GPT-o1 Partial Train \n", + "2 ITA Mistral-Large-2411 Partial Train \n", + "3 ITA Aya-23 Partial Train \n", + "4 ITA Mistral-Large-2411 Partial Train \n", + "... ... ... ... ... \n", + "54924 ITA Mistral-Large-2411 Partial Dev \n", + "54925 ITA Gemini-Flash-1.5 Rewritten Dev \n", + "54926 ITA Mistral-Large-2411 Partial Dev \n", + "54927 ITA GPT-4o Partial Dev \n", + "54928 ITA Amazon-Nova-Lite-1.0 Partial Dev \n", + "\n", + " Original text Original Word Count \\\n", + "0 I giochi infantili e preadolescenziali ritorna... 18 \n", + "1 Un messaggio, quello dell'appassionato timonie... 63 \n", + "2 L'Ashmolean Museum d'altronde ha una lunga tra... 70 \n", + "3 Lui non se ne adonta, è orgoglioso del proprio... 125 \n", + "4 Come sia sia, non aveva visto male Monti quand... 212 \n", + "... ... ... \n", + "54924 Gian Michele Gambato non è (ancora) a questo l... 267 \n", + "54925 PADOVA - Sequestrato tre anni fa nell'ambito d... 73 \n", + "54926 Vanto de Il Falconiere è l'azienda agricola Ba... 122 \n", + "54927 «La nostra volontà – dice Devetag – è quella d... 120 \n", + "54928 Il governatore ha quindi ricordato un'altra de... 166 \n", + "\n", + " Original Char Count label \\\n", + "0 115 6 \n", + "1 411 26 \n", + "2 470 45 \n", + "3 702 87 \n", + "4 1431 75 \n", + "... ... ... \n", + "54924 1729 154 \n", + "54925 460 0 \n", + "54926 770 53 \n", + "54927 788 71 \n", + "54928 1068 63 \n", + "\n", + " text New Word Count \\\n", + "0 I giochi infantili e preadolescenziali ritorna... 108 \n", + "1 Un messaggio, quello dell'appassionato timonie... 122 \n", + "2 L'Ashmolean Museum d'altronde ha una lunga tra... 120 \n", + "3 Lui non se ne adonta, è orgoglioso del proprio... 134 \n", + "4 Come sia sia, non aveva visto male Monti quand... 147 \n", + "... ... ... \n", + "54924 Gian Michele Gambato non è (ancora) a questo l... 220 \n", + "54925 PADOVA - Aggiornamento sul caso Mustang Grif:... 74 \n", + "54926 Vanto de Il Falconiere è l'azienda agricola Ba... 124 \n", + "54927 «La nostra volontà – dice Devetag – è quella d... 126 \n", + "54928 Il governatore ha quindi ricordato un'altra de... 233 \n", + "\n", + " New Char Count id \n", + "0 673 ITA0 \n", + "1 807 ITA1 \n", + "2 782 ITA3 \n", + "3 738 ITA5 \n", + "4 971 ITA8 \n", + "... ... ... \n", + "54924 1487 ITA109804 \n", + "54925 475 ITA109817 \n", + "54926 841 ITA109823 \n", + "54927 794 ITA109829 \n", + "54928 1485 ITA109846 \n", + "\n", + "[54929 rows x 12 columns]" + ], + "text/html": [ + "\n", + "
\n", + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ISOLLM usedTypeData SplitOriginal textOriginal Word CountOriginal Char CountlabeltextNew Word CountNew Char Countid
0ITAGemini-Flash-1.5PartialTrainI giochi infantili e preadolescenziali ritorna...181156I giochi infantili e preadolescenziali ritorna...108673ITA0
1ITAGPT-o1PartialTrainUn messaggio, quello dell'appassionato timonie...6341126Un messaggio, quello dell'appassionato timonie...122807ITA1
2ITAMistral-Large-2411PartialTrainL'Ashmolean Museum d'altronde ha una lunga tra...7047045L'Ashmolean Museum d'altronde ha una lunga tra...120782ITA3
3ITAAya-23PartialTrainLui non se ne adonta, è orgoglioso del proprio...12570287Lui non se ne adonta, è orgoglioso del proprio...134738ITA5
4ITAMistral-Large-2411PartialTrainCome sia sia, non aveva visto male Monti quand...212143175Come sia sia, non aveva visto male Monti quand...147971ITA8
.......................................
54924ITAMistral-Large-2411PartialDevGian Michele Gambato non è (ancora) a questo l...2671729154Gian Michele Gambato non è (ancora) a questo l...2201487ITA109804
54925ITAGemini-Flash-1.5RewrittenDevPADOVA - Sequestrato tre anni fa nell'ambito d...734600PADOVA - Aggiornamento sul caso Mustang Grif:...74475ITA109817
54926ITAMistral-Large-2411PartialDevVanto de Il Falconiere è l'azienda agricola Ba...12277053Vanto de Il Falconiere è l'azienda agricola Ba...124841ITA109823
54927ITAGPT-4oPartialDev«La nostra volontà – dice Devetag – è quella d...12078871«La nostra volontà – dice Devetag – è quella d...126794ITA109829
54928ITAAmazon-Nova-Lite-1.0PartialDevIl governatore ha quindi ricordato un'altra de...166106863Il governatore ha quindi ricordato un'altra de...2331485ITA109846
\n", + "

54929 rows × 12 columns

\n", + "
\n", + "
\n", + "\n", + "
\n", + " \n", + "\n", + " \n", + "\n", + " \n", + "
\n", + "\n", + "\n", + "
\n", + " \n", + "\n", + "\n", + "\n", + " \n", + "
\n", + "\n", + "
\n", + " \n", + " \n", + " \n", + "
\n", + "\n", + "
\n", + "
\n" + ], + "application/vnd.google.colaboratory.intrinsic+json": { + "type": "dataframe", + "variable_name": "df_train", + "summary": "{\n \"name\": \"df_train\",\n \"rows\": 54929,\n \"fields\": [\n {\n \"column\": \"ISO\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 1,\n \"samples\": [\n \"ITA\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"LLM used\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 11,\n \"samples\": [\n \"Amazon-Nova-Lite-1.0\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Type\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 3,\n \"samples\": [\n \"Partial\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Data Split\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 2,\n \"samples\": [\n \"Dev\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Original text\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 54921,\n \"samples\": [\n \"Per il mercato dell'usato il 2012 si apre con il segno negativo. I passaggi di propriet\\u00e0 delle quattro ruote depurati delle minivolture, (i trasferimenti temporanei a nome del concessionario in attesa della rivendita al cliente finale), hanno fatto registrare -6,7%, rispetto allo stesso periodo dello scorso anno, le due ruote -0,6%. Per ogni 100 auto nuove ne sono state vendute 163 usate a gennaio.\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Original Word Count\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 59,\n \"min\": 11,\n \"max\": 1335,\n \"num_unique_values\": 509,\n \"samples\": [\n 29\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Original Char Count\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 379,\n \"min\": 46,\n \"max\": 8461,\n \"num_unique_values\": 2269,\n \"samples\": [\n 606\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"label\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 43,\n \"min\": 0,\n \"max\": 1211,\n \"num_unique_values\": 369,\n \"samples\": [\n 382\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"text\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 54929,\n \"samples\": [\n \"Bologna, 6 febbraio 2012 - \\u00abNON SI possono chiudere le scuole quando viene gi\\u00f9 una spolverata di neve, \\u00e8 ovvio, Bologna, 6 febbraio 2012 - \\u00abNON SI possono chiudere le scuole quando viene gi\\u00f9 una spolverata di neve, \\u00e8 ovvio, **ma qui si tratta di qualcosa di diverso. La neve \\u00e8 abbondante, le strade sono ghiacciate e pericolose, e la sicurezza degli studenti \\u00e8 la priorit\\u00e0 assoluta. Non si pu\\u00f2 pretendere che i bambini, e nemmeno gli insegnanti, affrontino un percorso cos\\u00ec rischioso per arrivare a scuola. La chiusura delle scuole, in questo caso specifico, \\u00e8 una misura necessaria e giustificata.**\\u00bb\\n\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"New Word Count\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 54,\n \"min\": 1,\n \"max\": 2334,\n \"num_unique_values\": 461,\n \"samples\": [\n 277\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"New Char Count\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 360,\n \"min\": 6,\n \"max\": 15966,\n \"num_unique_values\": 2234,\n \"samples\": [\n 1384\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"id\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 54929,\n \"samples\": [\n \"ITA27134\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}" + } + }, + "metadata": {}, + "execution_count": 10 + } + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "oevZxGzUw9ow", + "outputId": "fd1cdf69-df25-4604-c670-7aa7e33408f9" + }, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Requirement already satisfied: torch in /usr/local/lib/python3.11/dist-packages (2.5.1+cu124)\n", + "Requirement already satisfied: filelock in /usr/local/lib/python3.11/dist-packages (from torch) (3.17.0)\n", + "Requirement already satisfied: typing-extensions>=4.8.0 in /usr/local/lib/python3.11/dist-packages (from torch) (4.12.2)\n", + "Requirement already satisfied: networkx in /usr/local/lib/python3.11/dist-packages (from torch) (3.4.2)\n", + "Requirement already satisfied: jinja2 in /usr/local/lib/python3.11/dist-packages (from torch) (3.1.5)\n", + "Requirement already satisfied: fsspec in /usr/local/lib/python3.11/dist-packages (from torch) (2024.10.0)\n", + "Collecting nvidia-cuda-nvrtc-cu12==12.4.127 (from torch)\n", + " Downloading nvidia_cuda_nvrtc_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n", + "Collecting nvidia-cuda-runtime-cu12==12.4.127 (from torch)\n", + " Downloading nvidia_cuda_runtime_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n", + "Collecting nvidia-cuda-cupti-cu12==12.4.127 (from torch)\n", + " Downloading nvidia_cuda_cupti_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.6 kB)\n", + "Collecting nvidia-cudnn-cu12==9.1.0.70 (from torch)\n", + " Downloading nvidia_cudnn_cu12-9.1.0.70-py3-none-manylinux2014_x86_64.whl.metadata (1.6 kB)\n", + "Collecting nvidia-cublas-cu12==12.4.5.8 (from torch)\n", + " Downloading nvidia_cublas_cu12-12.4.5.8-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n", + "Collecting nvidia-cufft-cu12==11.2.1.3 (from torch)\n", + " Downloading nvidia_cufft_cu12-11.2.1.3-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n", + "Collecting nvidia-curand-cu12==10.3.5.147 (from torch)\n", + " Downloading nvidia_curand_cu12-10.3.5.147-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n", + "Collecting nvidia-cusolver-cu12==11.6.1.9 (from torch)\n", + " Downloading nvidia_cusolver_cu12-11.6.1.9-py3-none-manylinux2014_x86_64.whl.metadata (1.6 kB)\n", + "Collecting nvidia-cusparse-cu12==12.3.1.170 (from torch)\n", + " Downloading nvidia_cusparse_cu12-12.3.1.170-py3-none-manylinux2014_x86_64.whl.metadata (1.6 kB)\n", + "Requirement already satisfied: nvidia-nccl-cu12==2.21.5 in /usr/local/lib/python3.11/dist-packages (from torch) (2.21.5)\n", + "Requirement already satisfied: nvidia-nvtx-cu12==12.4.127 in /usr/local/lib/python3.11/dist-packages (from torch) (12.4.127)\n", + "Collecting nvidia-nvjitlink-cu12==12.4.127 (from torch)\n", + " Downloading nvidia_nvjitlink_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n", + "Requirement already satisfied: triton==3.1.0 in /usr/local/lib/python3.11/dist-packages (from torch) (3.1.0)\n", + "Requirement already satisfied: sympy==1.13.1 in /usr/local/lib/python3.11/dist-packages (from torch) (1.13.1)\n", + "Requirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.11/dist-packages (from sympy==1.13.1->torch) (1.3.0)\n", + "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.11/dist-packages (from jinja2->torch) (3.0.2)\n", + "Downloading nvidia_cublas_cu12-12.4.5.8-py3-none-manylinux2014_x86_64.whl (363.4 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m363.4/363.4 MB\u001b[0m \u001b[31m2.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading nvidia_cuda_cupti_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl (13.8 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m13.8/13.8 MB\u001b[0m \u001b[31m111.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading nvidia_cuda_nvrtc_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl (24.6 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m24.6/24.6 MB\u001b[0m \u001b[31m87.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading nvidia_cuda_runtime_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl (883 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m883.7/883.7 kB\u001b[0m \u001b[31m56.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading nvidia_cudnn_cu12-9.1.0.70-py3-none-manylinux2014_x86_64.whl (664.8 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m664.8/664.8 MB\u001b[0m \u001b[31m1.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading nvidia_cufft_cu12-11.2.1.3-py3-none-manylinux2014_x86_64.whl (211.5 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m211.5/211.5 MB\u001b[0m \u001b[31m11.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading nvidia_curand_cu12-10.3.5.147-py3-none-manylinux2014_x86_64.whl (56.3 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m56.3/56.3 MB\u001b[0m \u001b[31m41.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading nvidia_cusolver_cu12-11.6.1.9-py3-none-manylinux2014_x86_64.whl (127.9 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m127.9/127.9 MB\u001b[0m \u001b[31m18.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading nvidia_cusparse_cu12-12.3.1.170-py3-none-manylinux2014_x86_64.whl (207.5 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m207.5/207.5 MB\u001b[0m \u001b[31m5.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading nvidia_nvjitlink_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl (21.1 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m21.1/21.1 MB\u001b[0m \u001b[31m98.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hInstalling collected packages: nvidia-nvjitlink-cu12, nvidia-curand-cu12, nvidia-cufft-cu12, nvidia-cuda-runtime-cu12, nvidia-cuda-nvrtc-cu12, nvidia-cuda-cupti-cu12, nvidia-cublas-cu12, nvidia-cusparse-cu12, nvidia-cudnn-cu12, nvidia-cusolver-cu12\n", + " Attempting uninstall: nvidia-nvjitlink-cu12\n", + " Found existing installation: nvidia-nvjitlink-cu12 12.5.82\n", + " Uninstalling nvidia-nvjitlink-cu12-12.5.82:\n", + " Successfully uninstalled nvidia-nvjitlink-cu12-12.5.82\n", + " Attempting uninstall: nvidia-curand-cu12\n", + " Found existing installation: nvidia-curand-cu12 10.3.6.82\n", + " Uninstalling nvidia-curand-cu12-10.3.6.82:\n", + " Successfully uninstalled nvidia-curand-cu12-10.3.6.82\n", + " Attempting uninstall: nvidia-cufft-cu12\n", + " Found existing installation: nvidia-cufft-cu12 11.2.3.61\n", + " Uninstalling nvidia-cufft-cu12-11.2.3.61:\n", + " Successfully uninstalled nvidia-cufft-cu12-11.2.3.61\n", + " Attempting uninstall: nvidia-cuda-runtime-cu12\n", + " Found existing installation: nvidia-cuda-runtime-cu12 12.5.82\n", + " Uninstalling nvidia-cuda-runtime-cu12-12.5.82:\n", + " Successfully uninstalled nvidia-cuda-runtime-cu12-12.5.82\n", + " Attempting uninstall: nvidia-cuda-nvrtc-cu12\n", + " Found existing installation: nvidia-cuda-nvrtc-cu12 12.5.82\n", + " Uninstalling nvidia-cuda-nvrtc-cu12-12.5.82:\n", + " Successfully uninstalled nvidia-cuda-nvrtc-cu12-12.5.82\n", + " Attempting uninstall: nvidia-cuda-cupti-cu12\n", + " Found existing installation: nvidia-cuda-cupti-cu12 12.5.82\n", + " Uninstalling nvidia-cuda-cupti-cu12-12.5.82:\n", + " Successfully uninstalled nvidia-cuda-cupti-cu12-12.5.82\n", + " Attempting uninstall: nvidia-cublas-cu12\n", + " Found existing installation: nvidia-cublas-cu12 12.5.3.2\n", + " Uninstalling nvidia-cublas-cu12-12.5.3.2:\n", + " Successfully uninstalled nvidia-cublas-cu12-12.5.3.2\n", + " Attempting uninstall: nvidia-cusparse-cu12\n", + " Found existing installation: nvidia-cusparse-cu12 12.5.1.3\n", + " Uninstalling nvidia-cusparse-cu12-12.5.1.3:\n", + " Successfully uninstalled nvidia-cusparse-cu12-12.5.1.3\n", + " Attempting uninstall: nvidia-cudnn-cu12\n", + " Found existing installation: nvidia-cudnn-cu12 9.3.0.75\n", + " Uninstalling nvidia-cudnn-cu12-9.3.0.75:\n", + " Successfully uninstalled nvidia-cudnn-cu12-9.3.0.75\n", + " Attempting uninstall: nvidia-cusolver-cu12\n", + " Found existing installation: nvidia-cusolver-cu12 11.6.3.83\n", + " Uninstalling nvidia-cusolver-cu12-11.6.3.83:\n", + " Successfully uninstalled nvidia-cusolver-cu12-11.6.3.83\n", + "Successfully installed nvidia-cublas-cu12-12.4.5.8 nvidia-cuda-cupti-cu12-12.4.127 nvidia-cuda-nvrtc-cu12-12.4.127 nvidia-cuda-runtime-cu12-12.4.127 nvidia-cudnn-cu12-9.1.0.70 nvidia-cufft-cu12-11.2.1.3 nvidia-curand-cu12-10.3.5.147 nvidia-cusolver-cu12-11.6.1.9 nvidia-cusparse-cu12-12.3.1.170 nvidia-nvjitlink-cu12-12.4.127\n", + "Requirement already satisfied: transformers in /usr/local/lib/python3.11/dist-packages (4.47.1)\n", + "Requirement already satisfied: filelock in /usr/local/lib/python3.11/dist-packages (from transformers) (3.17.0)\n", + "Requirement already satisfied: huggingface-hub<1.0,>=0.24.0 in /usr/local/lib/python3.11/dist-packages (from transformers) (0.27.1)\n", + "Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.11/dist-packages (from transformers) (1.26.4)\n", + "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.11/dist-packages (from transformers) (24.2)\n", + "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.11/dist-packages (from transformers) (6.0.2)\n", + "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.11/dist-packages (from transformers) (2024.11.6)\n", + "Requirement already satisfied: requests in /usr/local/lib/python3.11/dist-packages (from transformers) (2.32.3)\n", + "Requirement already satisfied: tokenizers<0.22,>=0.21 in /usr/local/lib/python3.11/dist-packages (from transformers) (0.21.0)\n", + "Requirement already satisfied: safetensors>=0.4.1 in /usr/local/lib/python3.11/dist-packages (from transformers) (0.5.2)\n", + "Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.11/dist-packages (from transformers) (4.67.1)\n", + "Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.11/dist-packages (from huggingface-hub<1.0,>=0.24.0->transformers) (2024.10.0)\n", + "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.11/dist-packages (from huggingface-hub<1.0,>=0.24.0->transformers) (4.12.2)\n", + "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.11/dist-packages (from requests->transformers) (3.4.1)\n", + "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.11/dist-packages (from requests->transformers) (3.10)\n", + "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.11/dist-packages (from requests->transformers) (2.3.0)\n", + "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.11/dist-packages (from requests->transformers) (2024.12.14)\n", + "Requirement already satisfied: accelerate in /usr/local/lib/python3.11/dist-packages (1.2.1)\n", + "Collecting accelerate\n", + " Downloading accelerate-1.3.0-py3-none-any.whl.metadata (19 kB)\n", + "Requirement already satisfied: numpy<3.0.0,>=1.17 in /usr/local/lib/python3.11/dist-packages (from accelerate) (1.26.4)\n", + "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.11/dist-packages (from accelerate) (24.2)\n", + "Requirement already satisfied: psutil in /usr/local/lib/python3.11/dist-packages (from accelerate) (5.9.5)\n", + "Requirement already satisfied: pyyaml in /usr/local/lib/python3.11/dist-packages (from accelerate) (6.0.2)\n", + "Requirement already satisfied: torch>=2.0.0 in /usr/local/lib/python3.11/dist-packages (from accelerate) (2.5.1+cu124)\n", + "Requirement already satisfied: huggingface-hub>=0.21.0 in /usr/local/lib/python3.11/dist-packages (from accelerate) (0.27.1)\n", + "Requirement already satisfied: safetensors>=0.4.3 in /usr/local/lib/python3.11/dist-packages (from accelerate) (0.5.2)\n", + "Requirement already satisfied: filelock in /usr/local/lib/python3.11/dist-packages (from huggingface-hub>=0.21.0->accelerate) (3.17.0)\n", + "Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.11/dist-packages (from huggingface-hub>=0.21.0->accelerate) (2024.10.0)\n", + "Requirement already satisfied: requests in /usr/local/lib/python3.11/dist-packages (from huggingface-hub>=0.21.0->accelerate) (2.32.3)\n", + "Requirement already satisfied: tqdm>=4.42.1 in /usr/local/lib/python3.11/dist-packages (from huggingface-hub>=0.21.0->accelerate) (4.67.1)\n", + "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.11/dist-packages (from huggingface-hub>=0.21.0->accelerate) (4.12.2)\n", + "Requirement already satisfied: networkx in /usr/local/lib/python3.11/dist-packages (from torch>=2.0.0->accelerate) (3.4.2)\n", + "Requirement already satisfied: jinja2 in /usr/local/lib/python3.11/dist-packages (from torch>=2.0.0->accelerate) (3.1.5)\n", + "Requirement already satisfied: nvidia-cuda-nvrtc-cu12==12.4.127 in /usr/local/lib/python3.11/dist-packages (from torch>=2.0.0->accelerate) (12.4.127)\n", + "Requirement already satisfied: nvidia-cuda-runtime-cu12==12.4.127 in /usr/local/lib/python3.11/dist-packages (from torch>=2.0.0->accelerate) (12.4.127)\n", + "Requirement already satisfied: nvidia-cuda-cupti-cu12==12.4.127 in /usr/local/lib/python3.11/dist-packages (from torch>=2.0.0->accelerate) (12.4.127)\n", + "Requirement already satisfied: nvidia-cudnn-cu12==9.1.0.70 in /usr/local/lib/python3.11/dist-packages (from torch>=2.0.0->accelerate) (9.1.0.70)\n", + "Requirement already satisfied: nvidia-cublas-cu12==12.4.5.8 in /usr/local/lib/python3.11/dist-packages (from torch>=2.0.0->accelerate) (12.4.5.8)\n", + "Requirement already satisfied: nvidia-cufft-cu12==11.2.1.3 in /usr/local/lib/python3.11/dist-packages (from torch>=2.0.0->accelerate) (11.2.1.3)\n", + "Requirement already satisfied: nvidia-curand-cu12==10.3.5.147 in /usr/local/lib/python3.11/dist-packages (from torch>=2.0.0->accelerate) (10.3.5.147)\n", + "Requirement already satisfied: nvidia-cusolver-cu12==11.6.1.9 in /usr/local/lib/python3.11/dist-packages (from torch>=2.0.0->accelerate) (11.6.1.9)\n", + "Requirement already satisfied: nvidia-cusparse-cu12==12.3.1.170 in /usr/local/lib/python3.11/dist-packages (from torch>=2.0.0->accelerate) (12.3.1.170)\n", + "Requirement already satisfied: nvidia-nccl-cu12==2.21.5 in /usr/local/lib/python3.11/dist-packages (from torch>=2.0.0->accelerate) (2.21.5)\n", + "Requirement already satisfied: nvidia-nvtx-cu12==12.4.127 in /usr/local/lib/python3.11/dist-packages (from torch>=2.0.0->accelerate) (12.4.127)\n", + "Requirement already satisfied: nvidia-nvjitlink-cu12==12.4.127 in /usr/local/lib/python3.11/dist-packages (from torch>=2.0.0->accelerate) (12.4.127)\n", + "Requirement already satisfied: triton==3.1.0 in /usr/local/lib/python3.11/dist-packages (from torch>=2.0.0->accelerate) (3.1.0)\n", + "Requirement already satisfied: sympy==1.13.1 in /usr/local/lib/python3.11/dist-packages (from torch>=2.0.0->accelerate) (1.13.1)\n", + "Requirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.11/dist-packages (from sympy==1.13.1->torch>=2.0.0->accelerate) (1.3.0)\n", + "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.11/dist-packages (from jinja2->torch>=2.0.0->accelerate) (3.0.2)\n", + "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.11/dist-packages (from requests->huggingface-hub>=0.21.0->accelerate) (3.4.1)\n", + "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.11/dist-packages (from requests->huggingface-hub>=0.21.0->accelerate) (3.10)\n", + "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.11/dist-packages (from requests->huggingface-hub>=0.21.0->accelerate) (2.3.0)\n", + "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.11/dist-packages (from requests->huggingface-hub>=0.21.0->accelerate) (2024.12.14)\n", + "Downloading accelerate-1.3.0-py3-none-any.whl (336 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m336.6/336.6 kB\u001b[0m \u001b[31m7.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hInstalling collected packages: accelerate\n", + " Attempting uninstall: accelerate\n", + " Found existing installation: accelerate 1.2.1\n", + " Uninstalling accelerate-1.2.1:\n", + " Successfully uninstalled accelerate-1.2.1\n", + "Successfully installed accelerate-1.3.0\n", + "Requirement already satisfied: tqdm in /usr/local/lib/python3.11/dist-packages (4.67.1)\n", + "Collecting pytorch-crf\n", + " Downloading pytorch_crf-0.7.2-py3-none-any.whl.metadata (2.4 kB)\n", + "Downloading pytorch_crf-0.7.2-py3-none-any.whl (9.5 kB)\n", + "Installing collected packages: pytorch-crf\n", + "Successfully installed pytorch-crf-0.7.2\n", + "Requirement already satisfied: sentencepiece in /usr/local/lib/python3.11/dist-packages (0.2.0)\n" + ] + } + ], + "source": [ + "!pip install torch\n", + "!pip install transformers\n", + "!pip install accelerate -U\n", + "!pip install tqdm\n", + "!pip install pytorch-crf\n", + "!pip install sentencepiece" + ] + }, + { + "cell_type": "code", + "source": [ + "import os\n", + "os.makedirs(\"./runs/exp_seed_1024\", exist_ok=True)\n", + "os.makedirs(\"./runs/exp_seed_1024/logs\", exist_ok=True)\n", + "os.makedirs(\"./runs/exp_seed_1024/xlmlongformer\", exist_ok=True)" + ], + "metadata": { + "id": "b4qi7xc1xCBn" + }, + "execution_count": 12, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "import torch\n", + "import json\n", + "from transformers import AutoTokenizer, AutoModelForTokenClassification\n", + "from transformers.trainer_callback import TrainerState\n", + "from torch.utils.data import Dataset, DataLoader\n", + "from torch.nn.utils.rnn import pad_sequence\n", + "import transformers\n", + "from torch import nn\n", + "from transformers import AutoModel, AutoConfig\n", + "from torchcrf import CRF\n", + "from torch.cuda.amp import autocast\n", + "from transformers import Trainer\n", + "from tqdm import tqdm\n", + "import numpy as np\n", + "import logging\n", + "import glob\n", + "from tqdm import tqdm\n", + "from dataclasses import dataclass, field\n", + "logging.basicConfig(level=logging.INFO)\n", + "logger = logging.getLogger()\n", + "@dataclass\n", + "class ModelConfig:\n", + " model_path = \"hyperonym/xlm-roberta-longformer-base-16384\"\n", + " model_checkpoint_dir = \"./runs/exp_1024/xlm-longformer\"\n", + "@dataclass\n", + "class DatasetConfig:\n", + " train_file = \"/content/ITA_train.jsonl\"\n", + " test_files = [\"/content/ITA_test.jsonl\"]\n", + "@dataclass\n", + "class TrainingArgsConfig:\n", + " do_train = True\n", + " do_predict = False\n", + " seed = 1024\n", + " output_dir = \"./runs/exp_seed_1024\"\n", + " logging_steps = 160\n", + " logging_dir = \"./runs/exp_seed_1024/logs\"\n", + " num_train_epochs = 30\n", + " per_device_train_batch_size = 20\n", + " per_device_eval_batch_size = 20\n", + " max_length = 1024\n", + "model_args = ModelConfig()\n", + "data_args = DatasetConfig()\n", + "training_args = TrainingArgsConfig()\n", + "class CRFTrainer(Trainer):\n", + " def __init__(self, *args, **kwargs):\n", + " super().__init__(*args, **kwargs)\n", + " def compute_loss(self, model, inputs, return_outputs=False):\n", + " print(inputs.keys())\n", + " labels = inputs.pop(\"labels\")\n", + " outputs = model(**inputs)\n", + " emissions = outputs[0]\n", + " mask = inputs[\"attention_mask\"]\n", + " crf_loss = -model.crf(emissions, labels, mask=mask)\n", + " return crf_loss\n", + " def training_step(self, model, inputs):\n", + " loss = self.compute_loss(model, inputs)\n", + " return {\"loss\": loss, \"inputs\": inputs}\n", + "class AutoModelCRF(nn.Module):\n", + " def __init__(self, model_name_or_path, dropout=0.075):\n", + " super(AutoModelCRF, self).__init__()\n", + " self.config = AutoConfig.from_pretrained(model_name_or_path)\n", + " self.num_labels = 2\n", + " self.encoder = AutoModel.from_pretrained(model_name_or_path, trust_remote_code=True, config=self.config, from_tf=True)\n", + " self.dropout = nn.Dropout(dropout)\n", + " self.linear = nn.Linear(self.config.hidden_size, self.num_labels)\n", + " self.crf = CRF(self.num_labels, batch_first=True)\n", + " def forward(self, input_ids, attention_mask, labels=None):\n", + " inputs = {'input_ids': input_ids, 'attention_mask': attention_mask}\n", + " outputs = self.encoder(**inputs)\n", + " seq_output = outputs[0]\n", + " seq_output = self.dropout(seq_output)\n", + " emission = self.linear(seq_output)\n", + " if labels is None:\n", + " tags = self.crf.decode(emission, attention_mask.byte())\n", + " tags_padded = []\n", + " for idx, sequence in enumerate(tags):\n", + " if len(attention_mask[idx]) > len(sequence):\n", + " tag_padded = sequence + [sequence[-1]]*(len(attention_mask[idx])-len(sequence))\n", + " else:\n", + " tag_padded = sequence\n", + " tags_padded.append(tag_padded)\n", + " out = np.array(tags_padded)\n", + " return out\n", + " else:\n", + " crf_loss = -self.crf(emission, labels, mask=attention_mask.byte())\n", + " return crf_loss\n", + "def evaluate_position_difference(actual_position, predicted_position):\n", + " return abs(actual_position - predicted_position)\n", + "def get_start_position(sequence, mapping=None, token_level=True):\n", + " if mapping is not None:\n", + " mask = mapping != -100\n", + " sequence = sequence[mask]\n", + " mapping = mapping[mask]\n", + " change_indices = np.where(np.diff(sequence) == 1)[0]\n", + " if len(change_indices) > 0:\n", + " value = change_indices[0] + 1\n", + " else:\n", + " value = 0 if sequence[0] == 1 else len(sequence) - 1\n", + " if not token_level:\n", + " value = mapping[value] if mapping is not None else value\n", + " return value\n", + "def evaluate_machine_start_position(labels, predictions, idx2word=None, token_level=False):\n", + " actual_starts = []\n", + " predicted_starts = []\n", + " if not token_level and idx2word is None:\n", + " raise ValueError(\"idx2word must be provided if evaluation is at word level (token_level=False)\")\n", + " for idx in range(labels.shape[0]):\n", + " predict, label, mapping = (predictions[idx][1:len(labels[idx])], labels[idx][1:len(labels[idx])], idx2word[idx][1:len(labels[idx])] if not token_level else None,)\n", + " predicted_value = get_start_position(predict, mapping, token_level)\n", + " actual_value = get_start_position(label, mapping, token_level)\n", + " predicted_starts.append(predicted_value)\n", + " actual_starts.append(actual_value)\n", + " position_differences = [ evaluate_position_difference(actual, predict) for actual, predict in zip(actual_starts, predicted_starts) ]\n", + " mean_position_difference = np.mean(position_differences)\n", + " return mean_position_difference\n", + "def compute_metrics(p):\n", + " pred, labels = p\n", + " mean_absolute_diff = evaluate_machine_start_position(labels, pred, token_level=True)\n", + " return {\"mean_absolute_diff\": mean_absolute_diff,}\n", + "def training_loop(model, optimizer, train_dataloader, device):\n", + " model.train()\n", + " total_loss = 0\n", + " for step, batch in enumerate(tqdm(train_dataloader)):\n", + " input_ids = batch[\"input_ids\"].to(device)\n", + " attention_mask = batch[\"attention_mask\"].to(device)\n", + " labels = batch[\"labels\"].to(device)\n", + " optimizer.zero_grad()\n", + " loss = model(input_ids, attention_mask, labels=labels)\n", + " loss.backward()\n", + " optimizer.step()\n", + " logger.info(f\"Step {step}: {loss.item():.4f}\")\n", + " total_loss += loss.item()\n", + " avg_loss = total_loss/len(train_dataloader)\n", + " print(f\"Training loss: {avg_loss:.4f}\")\n", + "def predict(model, test_dataloader, device):\n", + " all_preds = []\n", + " with torch.no_grad():\n", + " for batch in tqdm(test_dataloader):\n", + " input_ids = batch[\"input_ids\"].to(device)\n", + " attention_mask = batch[\"attention_mask\"].to(device)\n", + " preds = model(input_ids, attention_mask)\n", + " all_preds.extend(preds)\n", + " out = np.array(all_preds)\n", + " print(out.shape)\n", + " return out\n", + "def save_model(model_name, model, optimizer, epoch, output_dir): # train_mae, val_mae,\n", + " if not os.path.exists(output_dir):\n", + " os.makedirs(output_dir)\n", + " checkpoint = {'model_state_dict': model.state_dict(),'optimizer_state_dict': optimizer.state_dict()} # 'train_mae': train_mae,'val_mae': val_mae,\n", + " model_name = model_name.replace(\"/\", \"-\")\n", + " file_path = os.path.join(output_dir, f\"{model_name}-epoch-{epoch}.pt\")\n", + " print(file_path)\n", + " torch.save(checkpoint, file_path)\n", + " logger.info(f\"Model has been saved successfully to {file_path}\")\n", + "class Semeval_Data(torch.utils.data.Dataset):\n", + " def __init__(self, data_path, model_name, max_length=1024, inference=False, debug=False):\n", + " with open(data_path, \"r\") as f:\n", + " self.data = [json.loads(line) for line in f]\n", + " self.inference = inference\n", + " self.tokenizer = AutoTokenizer.from_pretrained(model_name)\n", + " self.max_length = max_length\n", + " self.debug = debug\n", + " def __len__(self):\n", + " return len(self.data)\n", + " def __getitem__(self, idx):\n", + " text = self.data[idx][\"text\"]\n", + " id = self.data[idx][\"id\"]\n", + " label = None\n", + " labels_available = \"label\" in self.data[idx]\n", + " if labels_available:\n", + " label = self.data[idx][\"label\"]\n", + " labels = []\n", + " corresponding_word = []\n", + " tokens = []\n", + " input_ids = []\n", + " attention_mask = []\n", + " for jdx, word in enumerate(text.split(\" \")):\n", + " word_encoded = self.tokenizer.tokenize(word)\n", + " sub_words = len(word_encoded)\n", + " if labels_available:\n", + " is_machine_text = 1 if jdx >= label else 0\n", + " labels.extend([is_machine_text] * sub_words)\n", + " corresponding_word.extend([jdx] * sub_words)\n", + " tokens.extend(word_encoded)\n", + " input_ids.extend(self.tokenizer.convert_tokens_to_ids(word_encoded))\n", + " attention_mask.extend([1] * sub_words)\n", + " if len(input_ids) < self.max_length - 2:\n", + " input_ids = ( [0] + input_ids + [2] + [1] * (self.max_length - len(input_ids) - 2) )\n", + " if labels_available:\n", + " labels = [0] + labels + [labels[-1]] * (self.max_length - len(labels) - 1)\n", + " attention_mask = ( [1] + attention_mask + [1] + [0] * (self.max_length - len(attention_mask) - 2) )\n", + " corresponding_word = ( [-100] + corresponding_word + [-100] * (self.max_length - len(corresponding_word) - 1) )\n", + " tokens = ( [\"\"] + tokens + [\"\"] + [\"\"] * (self.max_length - len(tokens) - 2) )\n", + " else:\n", + " input_ids = [0] + input_ids[: self.max_length - 2] + [2]\n", + " if labels_available:\n", + " labels = [0] + labels[: self.max_length - 2] + [labels[self.max_length - 3]]\n", + " corresponding_word = ( [-100] + corresponding_word[: self.max_length - 2] + [-100] )\n", + " attention_mask = [1] + attention_mask[: self.max_length - 2] + [1]\n", + " tokens = [\"\"] + tokens[: self.max_length - 2] + [\"\"]\n", + " encoded = {}\n", + " if labels_available:\n", + " encoded[\"labels\"] = torch.tensor(labels)\n", + " encoded[\"input_ids\"] = torch.tensor(input_ids)\n", + " encoded[\"attention_mask\"] = torch.tensor(attention_mask)\n", + " if labels_available:\n", + " assert encoded[\"input_ids\"].shape == encoded[\"labels\"].shape\n", + " if self.debug and not self.inference:\n", + " encoded[\"partial_human_review\"] = \" \".join(text.split(\" \")[:label])\n", + " if self.inference:\n", + " encoded[\"text\"] = text\n", + " encoded[\"id\"] = id\n", + " encoded[\"corresponding_word\"] = corresponding_word\n", + " return encoded\n", + "if __name__ == \"__main__\":\n", + " model_args = ModelConfig()\n", + " data_args = DatasetConfig()\n", + " training_args = TrainingArgsConfig()\n", + " transformers.set_seed(training_args.seed)\n", + " model_path = model_args.model_path\n", + " model_checkpoint_dir = model_args.model_checkpoint_dir\n", + " device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n", + " model = AutoModelCRF(model_path).to(device)\n", + " optimizer = torch.optim.AdamW(model.parameters(), lr=1e-5)\n", + " train_set = Semeval_Data(data_args.train_file, model_path, max_length=training_args.max_length)\n", + " train_dataloader = DataLoader(train_set, batch_size=training_args.per_device_train_batch_size, shuffle=True)\n", + " train_eval_dataloader = DataLoader(train_set, batch_size=training_args.per_device_eval_batch_size, shuffle=False)\n", + " if training_args.do_train:\n", + " logger.info(\"Training...\")\n", + " logger.info(\"*** Train Dataset ***\")\n", + " logger.info(f\"Number of samples: {len(train_set)}\")\n", + " num_train_epochs = training_args.num_train_epochs\n", + " for epoch in tqdm(range(num_train_epochs)):\n", + " training_loop(model, optimizer, train_dataloader, device)\n", + " save_model(model_path, model, optimizer, epoch, model_checkpoint_dir) # ,train_mse ,val_mse" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 1000, + "referenced_widgets": [ + "d21f5a4689504a7ca014a2d7aed04e2b", + "a34ae57d3b1f47fdb8fa2e78ea87353f", + "c71e120a2bd843829d10ccce7a73ce0c", + "b3abd92d47c64bd9abc34965240cc330", + "9df1021268a34b279d5c8cf688a368e2", + "8770fa6872d941589a1d3fa095112e99", + "62a253ec992642bdb2bf00063462098f", + "2b3f220f28ba4fc6b5ae6f4d19703d01", + "76339c1d38e840b1b730ef35d7b1d9ff", + "dd59db74d57448c793a0e04da22da6cc", + "783911e293d143f3907a0bbaca202713", + "6e1a91af884248f2bbfb78fabbe95e14", + "412b1a4e5f6f4e03bb297c66111f984f", + "9b55737674da45a3b023c02cf83abeb8", + "3bb2ee1ea8ff496c88f3f4844cfeceb4", + "baf90a1ec4814bd3b09a4ad15303a992", + "f7f5618808c542ba8aad476d96100ae5", + "cd35bde91abc46a39e4d96aafbab46c5", + "f71b3a42b3c844d3bffa7074beb776c6", + "de91e1cee5174f8e82ff9839a7185063", + "87540f9e929e43b3ac3961ab7ad8a82d", + "eb8b49129c294c8096d6ccc8c1069f82", + "04a02e49ebec4ea4a4891c14470d187d", + "456d6f0353e349f38bc164c812ddc97a", + "b67249ced0ba4e6298fc320020b21f75", + "495d5c07ca6242019a66da31f252d60c", + "bd6f16353a53417d8e45e9cdce8a2354", + "2d3ef84af7d442dc9542869d94b6bcdd", + "2fba0f1a144048ffb6c110c66674903c", + "25bd1432d1b84b07a2d448bc16b8103a", + "da98b612f9e84861a07f334ab06ae2bc", + "d4c4017cbbcb470dbe50f6578705f1b8", + "57bad45670f742918f398dcf46d84ba1" + ] + }, + "id": "29TaD8IaxKxU", + "outputId": "0c00b7db-5a12-42b0-b6fe-7df57dd8b60f" + }, + "execution_count": 14, + "outputs": [ + { + "metadata": { + "tags": null + }, + "name": "stderr", + "output_type": "stream", + "text": [ + "All TF 2.0 model weights were used when initializing LongformerModel.\n", + "\n", + "All the weights of LongformerModel were initialized from the TF 2.0 model.\n", + "If your task is similar to the task the model of the checkpoint was trained on, you can already use LongformerModel for predictions without further training.\n" + ] + }, + { + "data": { + "application/vnd.jupyter.widget-view+json": { + "model_id": "d21f5a4689504a7ca014a2d7aed04e2b", + "version_major": 2, + "version_minor": 0 + }, + "text/plain": [ + "tokenizer_config.json: 0%| | 0.00/453 [00:00\u001b[0m in \u001b[0;36m\u001b[0;34m()\u001b[0m\n\u001b[1;32m 232\u001b[0m \u001b[0mnum_train_epochs\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtraining_args\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mnum_train_epochs\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 233\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mepoch\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mtqdm\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mrange\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mnum_train_epochs\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[0m\n\u001b[0;32m--> 234\u001b[0;31m \u001b[0mtraining_loop\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmodel\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0moptimizer\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtrain_dataloader\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdevice\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 235\u001b[0m \u001b[0msave_model\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmodel_path\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmodel\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0moptimizer\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mepoch\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmodel_checkpoint_dir\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;31m# ,train_mse ,val_mse\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m\u001b[0m in \u001b[0;36mtraining_loop\u001b[0;34m(model, optimizer, train_dataloader, device)\u001b[0m\n\u001b[1;32m 126\u001b[0m \u001b[0mlabels\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mbatch\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m\"labels\"\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mto\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdevice\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 127\u001b[0m \u001b[0moptimizer\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mzero_grad\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 128\u001b[0;31m \u001b[0mloss\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mmodel\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0minput_ids\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mattention_mask\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mlabels\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mlabels\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 129\u001b[0m \u001b[0mloss\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mbackward\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 130\u001b[0m \u001b[0moptimizer\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstep\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.11/dist-packages/torch/nn/modules/module.py\u001b[0m in \u001b[0;36m_wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1734\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_compiled_call_impl\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;31m# type: ignore[misc]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1735\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1736\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_call_impl\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\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 1737\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1738\u001b[0m \u001b[0;31m# torchrec tests the code consistency with the following code\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.11/dist-packages/torch/nn/modules/module.py\u001b[0m in \u001b[0;36m_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1745\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0m_global_backward_pre_hooks\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0m_global_backward_hooks\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1746\u001b[0m or _global_forward_hooks or _global_forward_pre_hooks):\n\u001b[0;32m-> 1747\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mforward_call\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\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 1748\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1749\u001b[0m \u001b[0mresult\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m\u001b[0m in \u001b[0;36mforward\u001b[0;34m(self, input_ids, attention_mask, labels)\u001b[0m\n\u001b[1;32m 83\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mout\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 84\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 85\u001b[0;31m \u001b[0mcrf_loss\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m-\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcrf\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0memission\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mlabels\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmask\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mattention_mask\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mbyte\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[0m\n\u001b[0m\u001b[1;32m 86\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mcrf_loss\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 87\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0mevaluate_position_difference\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mactual_position\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mpredicted_position\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.11/dist-packages/torch/nn/modules/module.py\u001b[0m in \u001b[0;36m_wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1734\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_compiled_call_impl\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;31m# type: ignore[misc]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1735\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1736\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_call_impl\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\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 1737\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1738\u001b[0m \u001b[0;31m# torchrec tests the code consistency with the following code\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.11/dist-packages/torch/nn/modules/module.py\u001b[0m in \u001b[0;36m_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1745\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0m_global_backward_pre_hooks\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0m_global_backward_hooks\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1746\u001b[0m or _global_forward_hooks or _global_forward_pre_hooks):\n\u001b[0;32m-> 1747\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mforward_call\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\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 1748\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1749\u001b[0m \u001b[0mresult\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.11/dist-packages/torchcrf/__init__.py\u001b[0m in \u001b[0;36mforward\u001b[0;34m(self, emissions, tags, mask, reduction)\u001b[0m\n\u001b[1;32m 95\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 96\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mbatch_first\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 97\u001b[0;31m \u001b[0memissions\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0memissions\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtranspose\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m0\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 98\u001b[0m \u001b[0mtags\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtags\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtranspose\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m0\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[1;32m 99\u001b[0m \u001b[0mmask\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mmask\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtranspose\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m0\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[0;31mKeyboardInterrupt\u001b[0m: " + ] + } + ] + }, + { + "cell_type": "code", + "source": [ + "from huggingface_hub import HfApi, create_repo, upload_file\n", + "hf_username = \"DrishtiSharma\"\n", + "repo_name = \"xlm-longformer-mgtd-italian\"\n", + "model_file_path = \"./runs/exp_1024/xlm-longformer/hyperonym-xlm-roberta-longformer-base-16384-epoch-3.pt\"\n", + "target_path_in_repo = \"checkpoint/xlm-longformer-epoch-3.pt\"\n", + "api = HfApi()\n", + "if not api.repo_exists(f\"{hf_username}/{repo_name}\"):\n", + " create_repo(repo_name, private=False)\n", + "upload_file(\n", + " path_or_fileobj=model_file_path,\n", + " path_in_repo=target_path_in_repo,\n", + " repo_id=f\"{hf_username}/{repo_name}\",\n", + " repo_type=\"model\"\n", + ")" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 118, + "referenced_widgets": [ + "7e33ab5539484be887a33acf5815f7db", + "bde5ee4c9af7498da085fcfbc46aaa68", + "371c95e5795e4444bba017ec4c310e3c", + "7edc2bb25fb348068f93af986603d928", + "8184d3c404bb490cad6da3b46d117e75", + "d5c489f1273a40df93a1f56433024149", + "79a4538894814e08b0d2ecf9b6028c4a", + "59a557eb0de64d7f840cd4b66f2da4f5", + "72cbe7b1cf254500aaffe7788d56fc7a", + "54eb3d562f8b406b97170286dea123de", + "63374b1bb0b84393a3cbee7db283e411" + ] + }, + "id": "soeK1zglZQ0V", + "outputId": "db3c08c1-4bff-4116-fef6-ad9b7dbe067b" + }, + "execution_count": 15, + "outputs": [ + { + "output_type": "display_data", + "data": { + "text/plain": [ + "hyperonym-xlm-roberta-longformer-base-16384-epoch-3.pt: 0%| | 0.00/3.56G [00:00