Skip to content

Instantly share code, notes, and snippets.

@Danysan1

Danysan1/bertmap_match_16.ipynb

Created July 16, 2023 15:39
Download ZIP
BERTMap Wikidata <-> Polifonia error
Raw
bertmap_match_16.ipynb
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"provenance": [],
"gpuType": "T4"
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"language_info": {
"name": "python"
},
"widgets": {
"application/vnd.jupyter.widget-state+json": {
"a29dcfabbb884079bebc65ca721d4286": {
"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_ad93707468d0443b8b2a29068ff6d348",
"IPY_MODEL_2b3c6737381742c1935b7f0c9d0c58d0",
"IPY_MODEL_7c41f46338c1409abd10e6e8741c80ae"
],
"layout": "IPY_MODEL_de2f3004fbdf4dc59cea10ca15801690"
}
},
"ad93707468d0443b8b2a29068ff6d348": {
"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_180de3b408a74992b2c7bc6a8882cbab",
"placeholder": "​",
"style": "IPY_MODEL_8940f8264c5847839605374237c85484",
"value": "Downloading (…)lve/main/config.json: 100%"
}
},
"2b3c6737381742c1935b7f0c9d0c58d0": {
"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_6d269f4f86344545b94f9bb1f8323a8b",
"max": 570,
"min": 0,
"orientation": "horizontal",
"style": "IPY_MODEL_a6a284e8b0434285a2c852fe7a4cddae",
"value": 570
}
},
"7c41f46338c1409abd10e6e8741c80ae": {
"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_f2511ce7ee4e4b238549c5817b141971",
"placeholder": "​",
"style": "IPY_MODEL_0f60a68d43ae4e0592a4a79bfbcc1e34",
"value": " 570/570 [00:00&lt;00:00, 28.8kB/s]"
}
},
"de2f3004fbdf4dc59cea10ca15801690": {
"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
}
},
"180de3b408a74992b2c7bc6a8882cbab": {
"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
}
},
"8940f8264c5847839605374237c85484": {
"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": ""
}
},
"6d269f4f86344545b94f9bb1f8323a8b": {
"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
}
},
"a6a284e8b0434285a2c852fe7a4cddae": {
"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": ""
}
},
"f2511ce7ee4e4b238549c5817b141971": {
"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
}
},
"0f60a68d43ae4e0592a4a79bfbcc1e34": {
"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": ""
}
},
"9b909f5d386a43429f8f621604e364dd": {
"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_e29d8bf7b5b9420282833f3605807e17",
"IPY_MODEL_6724e4e64e9a4b8ea6ed31945ccbce16",
"IPY_MODEL_4cc95c84e5204f438cb465b4e3ebabbb"
],
"layout": "IPY_MODEL_99a8c002aa424c2491761c82d69b4606"
}
},
"e29d8bf7b5b9420282833f3605807e17": {
"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_d96495cbe6ac4a43a5b40aa625247710",
"placeholder": "​",
"style": "IPY_MODEL_f596c7e167de46c5a9eac1c23685e27e",
"value": "Downloading model.safetensors: 100%"
}
},
"6724e4e64e9a4b8ea6ed31945ccbce16": {
"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_7197a59c5e1741abac4fa45b9b09c286",
"max": 440449768,
"min": 0,
"orientation": "horizontal",
"style": "IPY_MODEL_665734b57c0e4fc0a0aa2a385c571719",
"value": 440449768
}
},
"4cc95c84e5204f438cb465b4e3ebabbb": {
"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_e69863265e07488ba4844615fa40913a",
"placeholder": "​",
"style": "IPY_MODEL_6ec1575e585d4574a9d5269d6d18cddf",
"value": " 440M/440M [00:02&lt;00:00, 205MB/s]"
}
},
"99a8c002aa424c2491761c82d69b4606": {
"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
}
},
"d96495cbe6ac4a43a5b40aa625247710": {
"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
}
},
"f596c7e167de46c5a9eac1c23685e27e": {
"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": ""
}
},
"7197a59c5e1741abac4fa45b9b09c286": {
"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
}
},
"665734b57c0e4fc0a0aa2a385c571719": {
"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": ""
}
},
"e69863265e07488ba4844615fa40913a": {
"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
}
},
"6ec1575e585d4574a9d5269d6d18cddf": {
"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": ""
}
},
"e6ae8828daa1436dacfb684e9e54351a": {
"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_77f13cc16db94cb3b86b17bda215f163",
"IPY_MODEL_45e44f58ea9c4be7b2999ec22f4126c7",
"IPY_MODEL_db6e0666b6bf475cb75cffc8902c6eb5"
],
"layout": "IPY_MODEL_ec322b6b100545adaa1c043581abdd28"
}
},
"77f13cc16db94cb3b86b17bda215f163": {
"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_10adebeb500549c39fb18eb69ff13666",
"placeholder": "​",
"style": "IPY_MODEL_30a5adbfa30e4fd89ad8c4520f173513",
"value": "Downloading (…)okenizer_config.json: 100%"
}
},
"45e44f58ea9c4be7b2999ec22f4126c7": {
"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_ffb7bd37186f4c9685bf1475153f96a2",
"max": 28,
"min": 0,
"orientation": "horizontal",
"style": "IPY_MODEL_5c3943eb8cd642cb9b46f3f5babf7f98",
"value": 28
}
},
"db6e0666b6bf475cb75cffc8902c6eb5": {
"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_69d31656ecc54eb9a65a65960ce68b0b",
"placeholder": "​",
"style": "IPY_MODEL_c8c3c64e45324c8683787fa61d323b22",
"value": " 28.0/28.0 [00:00&lt;00:00, 1.02kB/s]"
}
},
"ec322b6b100545adaa1c043581abdd28": {
"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
}
},
"10adebeb500549c39fb18eb69ff13666": {
"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
}
},
"30a5adbfa30e4fd89ad8c4520f173513": {
"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": ""
}
},
"ffb7bd37186f4c9685bf1475153f96a2": {
"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
}
},
"5c3943eb8cd642cb9b46f3f5babf7f98": {
"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": ""
}
},
"69d31656ecc54eb9a65a65960ce68b0b": {
"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
}
},
"c8c3c64e45324c8683787fa61d323b22": {
"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": ""
}
},
"0bc03a786641441c8c1618de4429a790": {
"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_7c86cb8e88e540d88ca2cf8a4014a48f",
"IPY_MODEL_2662955f108245ddbf038587949777ab",
"IPY_MODEL_87aa519f6b6548d58a6f93aee326f82a"
],
"layout": "IPY_MODEL_21cd77cf52d74ebcbed39810c2c8f5cb"
}
},
"7c86cb8e88e540d88ca2cf8a4014a48f": {
"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_48d2927025c64fbbaab881598368b1e4",
"placeholder": "​",
"style": "IPY_MODEL_ad4294a0c8eb4be783f64ef455050b43",
"value": "Downloading (…)solve/main/vocab.txt: 100%"
}
},
"2662955f108245ddbf038587949777ab": {
"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_9bf38875dc074681b9e64ad5ba245e87",
"max": 231508,
"min": 0,
"orientation": "horizontal",
"style": "IPY_MODEL_3e4fbd6406b647ed927d21aae61ab8e4",
"value": 231508
}
},
"87aa519f6b6548d58a6f93aee326f82a": {
"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_0438de07f35c45e8a253ef91f9420bb5",
"placeholder": "​",
"style": "IPY_MODEL_64d7186bae2e4963bd820f6c2c6ba1c7",
"value": " 232k/232k [00:00&lt;00:00, 4.26MB/s]"
}
},
"21cd77cf52d74ebcbed39810c2c8f5cb": {
"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
}
},
"48d2927025c64fbbaab881598368b1e4": {
"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
}
},
"ad4294a0c8eb4be783f64ef455050b43": {
"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": ""
}
},
"9bf38875dc074681b9e64ad5ba245e87": {
"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
}
},
"3e4fbd6406b647ed927d21aae61ab8e4": {
"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": ""
}
},
"0438de07f35c45e8a253ef91f9420bb5": {
"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
}
},
"64d7186bae2e4963bd820f6c2c6ba1c7": {
"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": ""
}
},
"63b46e70fe7745309221a9eaf62ae23e": {
"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_98f4b080721e4beda8a4cad23170422d",
"IPY_MODEL_03bdf7cedd874f78a6a2457dd4e31920",
"IPY_MODEL_2d5f7590dcdf47c4af6e12dff0c43848"
],
"layout": "IPY_MODEL_13ff05d1452e441ba7fa3417521e5b6e"
}
},
"98f4b080721e4beda8a4cad23170422d": {
"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_5bd9f796c34745239378edad591f898e",
"placeholder": "​",
"style": "IPY_MODEL_de57ab7f05ec4239a93ca18c9b55fbd7",
"value": "Downloading (…)/main/tokenizer.json: 100%"
}
},
"03bdf7cedd874f78a6a2457dd4e31920": {
"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_d36726787a2d4581934a48ca3970d79d",
"max": 466062,
"min": 0,
"orientation": "horizontal",
"style": "IPY_MODEL_cca0e64b85664113ace2be425ee08240",
"value": 466062
}
},
"2d5f7590dcdf47c4af6e12dff0c43848": {
"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_cd434830b0c6476f8f1459ea4ce304b8",
"placeholder": "​",
"style": "IPY_MODEL_d4330d558fd147278166b78b2ff4d776",
"value": " 466k/466k [00:00&lt;00:00, 1.53MB/s]"
}
},
"13ff05d1452e441ba7fa3417521e5b6e": {
"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
}
},
"5bd9f796c34745239378edad591f898e": {
"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
}
},
"de57ab7f05ec4239a93ca18c9b55fbd7": {
"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": ""
}
},
"d36726787a2d4581934a48ca3970d79d": {
"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
}
},
"cca0e64b85664113ace2be425ee08240": {
"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": ""
}
},
"cd434830b0c6476f8f1459ea4ce304b8": {
"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
}
},
"d4330d558fd147278166b78b2ff4d776": {
"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": ""
}
},
"21418af9617d40afa23267a0ae5b81fe": {
"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_752dbf2931754d919db58b2d2d4f83ef",
"IPY_MODEL_d14f8e5dd7dc4a58b773097b95f7896d",
"IPY_MODEL_774230ac4753412a9d7103e4a58b2435"
],
"layout": "IPY_MODEL_a68966cd4eea419e9bfb553f4d566818"
}
},
"752dbf2931754d919db58b2d2d4f83ef": {
"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_b5b8f58ebbb74a4dafcc1109e757f55c",
"placeholder": "​",
"style": "IPY_MODEL_5653bc295f544976a0b5e5e9b5c43bf8",
"value": "Generating train split: "
}
},
"d14f8e5dd7dc4a58b773097b95f7896d": {
"model_module": "@jupyter-widgets/controls",
"model_name": "FloatProgressModel",
"model_module_version": "1.5.0",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "FloatProgressModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "ProgressView",
"bar_style": "info",
"description": "",
"description_tooltip": null,
"layout": "IPY_MODEL_dcb8bdbe7b8946789ff022d75a7e8367",
"max": 1,
"min": 0,
"orientation": "horizontal",
"style": "IPY_MODEL_c104adb32c92442fb2fff9acd4b983e8",
"value": 1
}
},
"774230ac4753412a9d7103e4a58b2435": {
"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_7da66e8266ab4747ba877ba06d4dd5f4",
"placeholder": "​",
"style": "IPY_MODEL_e115eb6d774e4ff2b99b3d32d5fb4e98",
"value": " 77000/0 [00:00&lt;00:00, 195029.41 examples/s]"
}
},
"a68966cd4eea419e9bfb553f4d566818": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": "hidden",
"width": null
}
},
"b5b8f58ebbb74a4dafcc1109e757f55c": {
"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
}
},
"5653bc295f544976a0b5e5e9b5c43bf8": {
"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": ""
}
},
"dcb8bdbe7b8946789ff022d75a7e8367": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": "20px"
}
},
"c104adb32c92442fb2fff9acd4b983e8": {
"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": ""
}
},
"7da66e8266ab4747ba877ba06d4dd5f4": {
"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
}
},
"e115eb6d774e4ff2b99b3d32d5fb4e98": {
"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": ""
}
},
"e6140b2e1ef349c4a756ae2674c5b6c9": {
"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_fd391f0488944ce9aea083d0f94119f4",
"IPY_MODEL_b1cdc5cf4d544736ae133bbb36eb8c6e",
"IPY_MODEL_ad1c5f8837aa4d4e94692ae2f9f101a8"
],
"layout": "IPY_MODEL_d6fc9d469fa742a8a8b5fb859a71c371"
}
},
"fd391f0488944ce9aea083d0f94119f4": {
"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_4c0f9aae81724863b05fdbf76039dbcc",
"placeholder": "​",
"style": "IPY_MODEL_751e24d59ed44d538ab1d1706f54aa34",
"value": "Load training data:: 99%"
}
},
"b1cdc5cf4d544736ae133bbb36eb8c6e": {
"model_module": "@jupyter-widgets/controls",
"model_name": "FloatProgressModel",
"model_module_version": "1.5.0",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "FloatProgressModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "ProgressView",
"bar_style": "",
"description": "",
"description_tooltip": null,
"layout": "IPY_MODEL_2d9b4f1e83ec4eeea3e785c411bc1999",
"max": 79121,
"min": 0,
"orientation": "horizontal",
"style": "IPY_MODEL_84ea0b8f912d41f7b4e41b8a637664d2",
"value": 79121
}
},
"ad1c5f8837aa4d4e94692ae2f9f101a8": {
"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_3175637cbd2f43d79d29c097d7914220",
"placeholder": "​",
"style": "IPY_MODEL_9dca6d06f18042c98efa6bd733b40f34",
"value": " 78000/79121 [00:05&lt;00:00, 11638.74 examples/s]"
}
},
"d6fc9d469fa742a8a8b5fb859a71c371": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": "hidden",
"width": null
}
},
"4c0f9aae81724863b05fdbf76039dbcc": {
"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
}
},
"751e24d59ed44d538ab1d1706f54aa34": {
"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": ""
}
},
"2d9b4f1e83ec4eeea3e785c411bc1999": {
"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
}
},
"84ea0b8f912d41f7b4e41b8a637664d2": {
"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": ""
}
},
"3175637cbd2f43d79d29c097d7914220": {
"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
}
},
"9dca6d06f18042c98efa6bd733b40f34": {
"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": ""
}
},
"e0f58fb57b5347c88a748abe27df0f79": {
"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_cf5123787bf04f178a84279146cb38c0",
"IPY_MODEL_f3e87f0658334207a93a3c057b258339",
"IPY_MODEL_365d00af29d54195a93054d1fca53d36"
],
"layout": "IPY_MODEL_367d5a1e487249f0b164567da6581464"
}
},
"cf5123787bf04f178a84279146cb38c0": {
"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_c9dad15028d74daa92f3b7f0efdd16be",
"placeholder": "​",
"style": "IPY_MODEL_c88b3c2aad204a5a9358359d501f2eaa",
"value": "Generating train split: "
}
},
"f3e87f0658334207a93a3c057b258339": {
"model_module": "@jupyter-widgets/controls",
"model_name": "FloatProgressModel",
"model_module_version": "1.5.0",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "FloatProgressModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "ProgressView",
"bar_style": "info",
"description": "",
"description_tooltip": null,
"layout": "IPY_MODEL_075a603b3b354cec8825cb93feabb1ea",
"max": 1,
"min": 0,
"orientation": "horizontal",
"style": "IPY_MODEL_9ab12b0d13b54a7494a33761884e4c2a",
"value": 1
}
},
"365d00af29d54195a93054d1fca53d36": {
"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_515679d44eba4748838968f28528b368",
"placeholder": "​",
"style": "IPY_MODEL_d0367dda678a428fbfc411cebd8f2bfe",
"value": " 8792/0 [00:00&lt;00:00, 71379.97 examples/s]"
}
},
"367d5a1e487249f0b164567da6581464": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": "hidden",
"width": null
}
},
"c9dad15028d74daa92f3b7f0efdd16be": {
"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
}
},
"c88b3c2aad204a5a9358359d501f2eaa": {
"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": ""
}
},
"075a603b3b354cec8825cb93feabb1ea": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": "20px"
}
},
"9ab12b0d13b54a7494a33761884e4c2a": {
"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": ""
}
},
"515679d44eba4748838968f28528b368": {
"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
}
},
"d0367dda678a428fbfc411cebd8f2bfe": {
"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": ""
}
},
"59ea58dcc0044afe95f1e2a9b34f73ae": {
"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_b5681c0cf9434135a053adff4967d7d5",
"IPY_MODEL_1b5a51751e924cfab0c066f89c5bb49d",
"IPY_MODEL_1918ef7e644f4fc5ab840eefea6d9943"
],
"layout": "IPY_MODEL_9c94103393e54102a2db1d5b158deeb3"
}
},
"b5681c0cf9434135a053adff4967d7d5": {
"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_81b0942bf8ee4f4c99e22672b74d8174",
"placeholder": "​",
"style": "IPY_MODEL_c160f248b20541d289b009649d4f4209",
"value": "Load validation data:: 100%"
}
},
"1b5a51751e924cfab0c066f89c5bb49d": {
"model_module": "@jupyter-widgets/controls",
"model_name": "FloatProgressModel",
"model_module_version": "1.5.0",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "FloatProgressModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "ProgressView",
"bar_style": "",
"description": "",
"description_tooltip": null,
"layout": "IPY_MODEL_c620153094ad41b8bfe76dbb45110e85",
"max": 8792,
"min": 0,
"orientation": "horizontal",
"style": "IPY_MODEL_650b44de04fe47e6b1a8f7e44a3dc26d",
"value": 8792
}
},
"1918ef7e644f4fc5ab840eefea6d9943": {
"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_d27c038bf4c3442a8198d8202bd75738",
"placeholder": "​",
"style": "IPY_MODEL_44f5a7f896014af5823bdb2df1506648",
"value": " 8792/8792 [00:00&lt;00:00, 20381.65 examples/s]"
}
},
"9c94103393e54102a2db1d5b158deeb3": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": "hidden",
"width": null
}
},
"81b0942bf8ee4f4c99e22672b74d8174": {
"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
}
},
"c160f248b20541d289b009649d4f4209": {
"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": ""
}
},
"c620153094ad41b8bfe76dbb45110e85": {
"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
}
},
"650b44de04fe47e6b1a8f7e44a3dc26d": {
"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": ""
}
},
"d27c038bf4c3442a8198d8202bd75738": {
"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
}
},
"44f5a7f896014af5823bdb2df1506648": {
"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": ""
}
}
}
},
"accelerator": "GPU"
},
"cells": [
{
"cell_type": "markdown",
"source": [
"[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Danysan1/unibo-ke-matching-ontologies/blob/main/wikidata/bertmap_match.ipynb)\n",
"[![Open in Kaggle](https://kaggle.com/static/images/open-in-kaggle.svg)](https://kaggle.com/kernels/welcome?src=https://github.com/Danysan1/unibo-ke-matching-ontologies/blob/main/wikidata/bertmap_match.ipynb)\n",
"[![Open in SageMaker Studio Lab](https://studiolab.sagemaker.aws/studiolab.svg)](https://studiolab.sagemaker.aws/import/github/Danysan1/unibo-ke-matching-ontologies/tree/main/wikidata/bertmap_match.ipynb)"
],
"metadata": {
"id": "0DalYOass6Xx"
}
},
{
"cell_type": "markdown",
"source": [
"# Polifonia - Wikidata alignment with BERTMap"
],
"metadata": {
"id": "hdxJwQbCspQ-"
}
},
{
"cell_type": "code",
"source": [
"!pip3 install torch torchvision torchaudio deeponto"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "qQOfMpEDgd5M",
"outputId": "1c679710-275c-499b-ae0c-ad5adb32e56b"
},
"execution_count": 1,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Requirement already satisfied: torch in /usr/local/lib/python3.10/dist-packages (2.0.1+cu118)\n",
"Requirement already satisfied: torchvision in /usr/local/lib/python3.10/dist-packages (0.15.2+cu118)\n",
"Requirement already satisfied: torchaudio in /usr/local/lib/python3.10/dist-packages (2.0.2+cu118)\n",
"Collecting deeponto\n",
" Downloading deeponto-0.8.3-py3-none-any.whl (92.3 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m92.3/92.3 MB\u001b[0m \u001b[31m11.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from torch) (3.12.2)\n",
"Requirement already satisfied: typing-extensions in /usr/local/lib/python3.10/dist-packages (from torch) (4.7.1)\n",
"Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch) (1.11.1)\n",
"Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch) (3.1)\n",
"Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch) (3.1.2)\n",
"Requirement already satisfied: triton==2.0.0 in /usr/local/lib/python3.10/dist-packages (from torch) (2.0.0)\n",
"Requirement already satisfied: cmake in /usr/local/lib/python3.10/dist-packages (from triton==2.0.0->torch) (3.25.2)\n",
"Requirement already satisfied: lit in /usr/local/lib/python3.10/dist-packages (from triton==2.0.0->torch) (16.0.6)\n",
"Requirement already satisfied: numpy in /usr/local/lib/python3.10/dist-packages (from torchvision) (1.22.4)\n",
"Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from torchvision) (2.27.1)\n",
"Requirement already satisfied: pillow!=8.3.*,>=5.3.0 in /usr/local/lib/python3.10/dist-packages (from torchvision) (8.4.0)\n",
"Collecting JPype1==1.3.0 (from deeponto)\n",
" Downloading JPype1-1.3.0.tar.gz (820 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m820.3/820.3 kB\u001b[0m \u001b[31m66.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25h Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
"Collecting yacs (from deeponto)\n",
" Downloading yacs-0.1.8-py3-none-any.whl (14 kB)\n",
"Collecting anytree==2.8.0 (from deeponto)\n",
" Downloading anytree-2.8.0-py2.py3-none-any.whl (41 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m41.7/41.7 kB\u001b[0m \u001b[31m5.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: click in /usr/local/lib/python3.10/dist-packages (from deeponto) (8.1.4)\n",
"Collecting dill (from deeponto)\n",
" Downloading dill-0.3.6-py3-none-any.whl (110 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m110.5/110.5 kB\u001b[0m \u001b[31m16.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (from deeponto) (1.5.3)\n",
"Requirement already satisfied: scikit-learn in /usr/local/lib/python3.10/dist-packages (from deeponto) (1.2.2)\n",
"Collecting openprompt==1.0.0 (from deeponto)\n",
" Downloading openprompt-1.0.0-py3-none-any.whl (146 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m146.1/146.1 kB\u001b[0m \u001b[31m19.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting transformers[torch] (from deeponto)\n",
" Downloading transformers-4.30.2-py3-none-any.whl (7.2 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m7.2/7.2 MB\u001b[0m \u001b[31m98.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting datasets (from deeponto)\n",
" Downloading datasets-2.13.1-py3-none-any.whl (486 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m486.2/486.2 kB\u001b[0m \u001b[31m51.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: spacy in /usr/local/lib/python3.10/dist-packages (from deeponto) (3.5.4)\n",
"Collecting pprintpp (from deeponto)\n",
" Downloading pprintpp-0.4.0-py2.py3-none-any.whl (16 kB)\n",
"Requirement already satisfied: lxml in /usr/local/lib/python3.10/dist-packages (from deeponto) (4.9.3)\n",
"Collecting textdistance (from deeponto)\n",
" Downloading textdistance-4.5.0-py3-none-any.whl (31 kB)\n",
"Requirement already satisfied: ipywidgets==7.7.1 in /usr/local/lib/python3.10/dist-packages (from deeponto) (7.7.1)\n",
"Requirement already satisfied: ipykernel in /usr/local/lib/python3.10/dist-packages (from deeponto) (5.5.6)\n",
"Collecting enlighten (from deeponto)\n",
" Downloading enlighten-1.11.2-py2.py3-none-any.whl (53 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m53.7/53.7 kB\u001b[0m \u001b[31m7.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: six>=1.9.0 in /usr/local/lib/python3.10/dist-packages (from anytree==2.8.0->deeponto) (1.16.0)\n",
"Requirement already satisfied: ipython-genutils~=0.2.0 in /usr/local/lib/python3.10/dist-packages (from ipywidgets==7.7.1->deeponto) (0.2.0)\n",
"Requirement already satisfied: traitlets>=4.3.1 in /usr/local/lib/python3.10/dist-packages (from ipywidgets==7.7.1->deeponto) (5.7.1)\n",
"Requirement already satisfied: widgetsnbextension~=3.6.0 in /usr/local/lib/python3.10/dist-packages (from ipywidgets==7.7.1->deeponto) (3.6.4)\n",
"Requirement already satisfied: ipython>=4.0.0 in /usr/local/lib/python3.10/dist-packages (from ipywidgets==7.7.1->deeponto) (7.34.0)\n",
"Requirement already satisfied: jupyterlab-widgets>=1.0.0 in /usr/local/lib/python3.10/dist-packages (from ipywidgets==7.7.1->deeponto) (3.0.8)\n",
"Collecting sentencepiece==0.1.96 (from openprompt==1.0.0->deeponto)\n",
" Downloading sentencepiece-0.1.96-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.2 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.2/1.2 MB\u001b[0m \u001b[31m73.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: tqdm>=4.62.2 in /usr/local/lib/python3.10/dist-packages (from openprompt==1.0.0->deeponto) (4.65.0)\n",
"Collecting tensorboardX (from openprompt==1.0.0->deeponto)\n",
" Downloading tensorboardX-2.6.1-py2.py3-none-any.whl (101 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m101.6/101.6 kB\u001b[0m \u001b[31m11.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: nltk in /usr/local/lib/python3.10/dist-packages (from openprompt==1.0.0->deeponto) (3.8.1)\n",
"Collecting rouge==1.0.0 (from openprompt==1.0.0->deeponto)\n",
" Downloading rouge-1.0.0-py3-none-any.whl (14 kB)\n",
"Requirement already satisfied: pyarrow in /usr/local/lib/python3.10/dist-packages (from openprompt==1.0.0->deeponto) (9.0.0)\n",
"Requirement already satisfied: scipy in /usr/local/lib/python3.10/dist-packages (from openprompt==1.0.0->deeponto) (1.10.1)\n",
"Requirement already satisfied: jupyter-client in /usr/local/lib/python3.10/dist-packages (from ipykernel->deeponto) (6.1.12)\n",
"Requirement already satisfied: tornado>=4.2 in /usr/local/lib/python3.10/dist-packages (from ipykernel->deeponto) (6.3.1)\n",
"Collecting xxhash (from datasets->deeponto)\n",
" Downloading xxhash-3.2.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (212 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m212.5/212.5 kB\u001b[0m \u001b[31m25.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting multiprocess (from datasets->deeponto)\n",
" Downloading multiprocess-0.70.14-py310-none-any.whl (134 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m134.3/134.3 kB\u001b[0m \u001b[31m19.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: fsspec[http]>=2021.11.1 in /usr/local/lib/python3.10/dist-packages (from datasets->deeponto) (2023.6.0)\n",
"Requirement already satisfied: aiohttp in /usr/local/lib/python3.10/dist-packages (from datasets->deeponto) (3.8.4)\n",
"Collecting huggingface-hub<1.0.0,>=0.11.0 (from datasets->deeponto)\n",
" Downloading huggingface_hub-0.16.4-py3-none-any.whl (268 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m268.8/268.8 kB\u001b[0m \u001b[31m33.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: packaging in /usr/local/lib/python3.10/dist-packages (from datasets->deeponto) (23.1)\n",
"Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from datasets->deeponto) (6.0)\n",
"Requirement already satisfied: urllib3<1.27,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->torchvision) (1.26.16)\n",
"Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->torchvision) (2023.5.7)\n",
"Requirement already satisfied: charset-normalizer~=2.0.0 in /usr/local/lib/python3.10/dist-packages (from requests->torchvision) (2.0.12)\n",
"Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->torchvision) (3.4)\n",
"Collecting blessed>=1.17.7 (from enlighten->deeponto)\n",
" Downloading blessed-1.20.0-py2.py3-none-any.whl (58 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m58.4/58.4 kB\u001b[0m \u001b[31m8.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting prefixed>=0.3.2 (from enlighten->deeponto)\n",
" Downloading prefixed-0.7.0-py2.py3-none-any.whl (13 kB)\n",
"Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->torch) (2.1.3)\n",
"Requirement already satisfied: python-dateutil>=2.8.1 in /usr/local/lib/python3.10/dist-packages (from pandas->deeponto) (2.8.2)\n",
"Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas->deeponto) (2022.7.1)\n",
"Requirement already satisfied: joblib>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from scikit-learn->deeponto) (1.3.1)\n",
"Requirement already satisfied: threadpoolctl>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from scikit-learn->deeponto) (3.1.0)\n",
"Requirement already satisfied: spacy-legacy<3.1.0,>=3.0.11 in /usr/local/lib/python3.10/dist-packages (from spacy->deeponto) (3.0.12)\n",
"Requirement already satisfied: spacy-loggers<2.0.0,>=1.0.0 in /usr/local/lib/python3.10/dist-packages (from spacy->deeponto) (1.0.4)\n",
"Requirement already satisfied: murmurhash<1.1.0,>=0.28.0 in /usr/local/lib/python3.10/dist-packages (from spacy->deeponto) (1.0.9)\n",
"Requirement already satisfied: cymem<2.1.0,>=2.0.2 in /usr/local/lib/python3.10/dist-packages (from spacy->deeponto) (2.0.7)\n",
"Requirement already satisfied: preshed<3.1.0,>=3.0.2 in /usr/local/lib/python3.10/dist-packages (from spacy->deeponto) (3.0.8)\n",
"Requirement already satisfied: thinc<8.2.0,>=8.1.8 in /usr/local/lib/python3.10/dist-packages (from spacy->deeponto) (8.1.10)\n",
"Requirement already satisfied: wasabi<1.2.0,>=0.9.1 in /usr/local/lib/python3.10/dist-packages (from spacy->deeponto) (1.1.2)\n",
"Requirement already satisfied: srsly<3.0.0,>=2.4.3 in /usr/local/lib/python3.10/dist-packages (from spacy->deeponto) (2.4.6)\n",
"Requirement already satisfied: catalogue<2.1.0,>=2.0.6 in /usr/local/lib/python3.10/dist-packages (from spacy->deeponto) (2.0.8)\n",
"Requirement already satisfied: typer<0.10.0,>=0.3.0 in /usr/local/lib/python3.10/dist-packages (from spacy->deeponto) (0.9.0)\n",
"Requirement already satisfied: pathy>=0.10.0 in /usr/local/lib/python3.10/dist-packages (from spacy->deeponto) (0.10.2)\n",
"Requirement already satisfied: smart-open<7.0.0,>=5.2.1 in /usr/local/lib/python3.10/dist-packages (from spacy->deeponto) (6.3.0)\n",
"Requirement already satisfied: pydantic!=1.8,!=1.8.1,<1.11.0,>=1.7.4 in /usr/local/lib/python3.10/dist-packages (from spacy->deeponto) (1.10.11)\n",
"Requirement already satisfied: setuptools in /usr/local/lib/python3.10/dist-packages (from spacy->deeponto) (67.7.2)\n",
"Requirement already satisfied: langcodes<4.0.0,>=3.2.0 in /usr/local/lib/python3.10/dist-packages (from spacy->deeponto) (3.3.0)\n",
"Requirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/dist-packages (from sympy->torch) (1.3.0)\n",
"Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers[torch]->deeponto) (2022.10.31)\n",
"Collecting tokenizers!=0.11.3,<0.14,>=0.11.1 (from transformers[torch]->deeponto)\n",
" Downloading tokenizers-0.13.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (7.8 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m7.8/7.8 MB\u001b[0m \u001b[31m54.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting safetensors>=0.3.1 (from transformers[torch]->deeponto)\n",
" Downloading safetensors-0.3.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.3 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.3/1.3 MB\u001b[0m \u001b[31m64.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting accelerate>=0.20.2 (from transformers[torch]->deeponto)\n",
" Downloading accelerate-0.21.0-py3-none-any.whl (244 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m244.2/244.2 kB\u001b[0m \u001b[31m29.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: psutil in /usr/local/lib/python3.10/dist-packages (from accelerate>=0.20.2->transformers[torch]->deeponto) (5.9.5)\n",
"Requirement already satisfied: wcwidth>=0.1.4 in /usr/local/lib/python3.10/dist-packages (from blessed>=1.17.7->enlighten->deeponto) (0.2.6)\n",
"Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets->deeponto) (23.1.0)\n",
"Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets->deeponto) (6.0.4)\n",
"Requirement already satisfied: async-timeout<5.0,>=4.0.0a3 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets->deeponto) (4.0.2)\n",
"Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets->deeponto) (1.9.2)\n",
"Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets->deeponto) (1.3.3)\n",
"Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets->deeponto) (1.3.1)\n",
"Collecting jedi>=0.16 (from ipython>=4.0.0->ipywidgets==7.7.1->deeponto)\n",
" Downloading jedi-0.18.2-py2.py3-none-any.whl (1.6 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.6/1.6 MB\u001b[0m \u001b[31m98.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: decorator in /usr/local/lib/python3.10/dist-packages (from ipython>=4.0.0->ipywidgets==7.7.1->deeponto) (4.4.2)\n",
"Requirement already satisfied: pickleshare in /usr/local/lib/python3.10/dist-packages (from ipython>=4.0.0->ipywidgets==7.7.1->deeponto) (0.7.5)\n",
"Requirement already satisfied: prompt-toolkit!=3.0.0,!=3.0.1,<3.1.0,>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from ipython>=4.0.0->ipywidgets==7.7.1->deeponto) (3.0.39)\n",
"Requirement already satisfied: pygments in /usr/local/lib/python3.10/dist-packages (from ipython>=4.0.0->ipywidgets==7.7.1->deeponto) (2.14.0)\n",
"Requirement already satisfied: backcall in /usr/local/lib/python3.10/dist-packages (from ipython>=4.0.0->ipywidgets==7.7.1->deeponto) (0.2.0)\n",
"Requirement already satisfied: matplotlib-inline in /usr/local/lib/python3.10/dist-packages (from ipython>=4.0.0->ipywidgets==7.7.1->deeponto) (0.1.6)\n",
"Requirement already satisfied: pexpect>4.3 in /usr/local/lib/python3.10/dist-packages (from ipython>=4.0.0->ipywidgets==7.7.1->deeponto) (4.8.0)\n",
"Requirement already satisfied: blis<0.8.0,>=0.7.8 in /usr/local/lib/python3.10/dist-packages (from thinc<8.2.0,>=8.1.8->spacy->deeponto) (0.7.9)\n",
"Requirement already satisfied: confection<1.0.0,>=0.0.1 in /usr/local/lib/python3.10/dist-packages (from thinc<8.2.0,>=8.1.8->spacy->deeponto) (0.1.0)\n",
"Requirement already satisfied: notebook>=4.4.1 in /usr/local/lib/python3.10/dist-packages (from widgetsnbextension~=3.6.0->ipywidgets==7.7.1->deeponto) (6.4.8)\n",
"Requirement already satisfied: jupyter-core>=4.6.0 in /usr/local/lib/python3.10/dist-packages (from jupyter-client->ipykernel->deeponto) (5.3.1)\n",
"Requirement already satisfied: pyzmq>=13 in /usr/local/lib/python3.10/dist-packages (from jupyter-client->ipykernel->deeponto) (23.2.1)\n",
"Collecting protobuf>=4.22.3 (from tensorboardX->openprompt==1.0.0->deeponto)\n",
" Downloading protobuf-4.23.4-cp37-abi3-manylinux2014_x86_64.whl (304 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m304.5/304.5 kB\u001b[0m \u001b[31m37.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: parso<0.9.0,>=0.8.0 in /usr/local/lib/python3.10/dist-packages (from jedi>=0.16->ipython>=4.0.0->ipywidgets==7.7.1->deeponto) (0.8.3)\n",
"Requirement already satisfied: platformdirs>=2.5 in /usr/local/lib/python3.10/dist-packages (from jupyter-core>=4.6.0->jupyter-client->ipykernel->deeponto) (3.8.1)\n",
"Requirement already satisfied: argon2-cffi in /usr/local/lib/python3.10/dist-packages (from notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1->deeponto) (21.3.0)\n",
"Requirement already satisfied: nbformat in /usr/local/lib/python3.10/dist-packages (from notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1->deeponto) (5.9.1)\n",
"Requirement already satisfied: nbconvert in /usr/local/lib/python3.10/dist-packages (from notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1->deeponto) (6.5.4)\n",
"Requirement already satisfied: nest-asyncio>=1.5 in /usr/local/lib/python3.10/dist-packages (from notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1->deeponto) (1.5.6)\n",
"Requirement already satisfied: Send2Trash>=1.8.0 in /usr/local/lib/python3.10/dist-packages (from notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1->deeponto) (1.8.2)\n",
"Requirement already satisfied: terminado>=0.8.3 in /usr/local/lib/python3.10/dist-packages (from notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1->deeponto) (0.17.1)\n",
"Requirement already satisfied: prometheus-client in /usr/local/lib/python3.10/dist-packages (from notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1->deeponto) (0.17.1)\n",
"Requirement already satisfied: ptyprocess>=0.5 in /usr/local/lib/python3.10/dist-packages (from pexpect>4.3->ipython>=4.0.0->ipywidgets==7.7.1->deeponto) (0.7.0)\n",
"Requirement already satisfied: argon2-cffi-bindings in /usr/local/lib/python3.10/dist-packages (from argon2-cffi->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1->deeponto) (21.2.0)\n",
"Requirement already satisfied: beautifulsoup4 in /usr/local/lib/python3.10/dist-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1->deeponto) (4.11.2)\n",
"Requirement already satisfied: bleach in /usr/local/lib/python3.10/dist-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1->deeponto) (6.0.0)\n",
"Requirement already satisfied: defusedxml in /usr/local/lib/python3.10/dist-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1->deeponto) (0.7.1)\n",
"Requirement already satisfied: entrypoints>=0.2.2 in /usr/local/lib/python3.10/dist-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1->deeponto) (0.4)\n",
"Requirement already satisfied: jupyterlab-pygments in /usr/local/lib/python3.10/dist-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1->deeponto) (0.2.2)\n",
"Requirement already satisfied: mistune<2,>=0.8.1 in /usr/local/lib/python3.10/dist-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1->deeponto) (0.8.4)\n",
"Requirement already satisfied: nbclient>=0.5.0 in /usr/local/lib/python3.10/dist-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1->deeponto) (0.8.0)\n",
"Requirement already satisfied: pandocfilters>=1.4.1 in /usr/local/lib/python3.10/dist-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1->deeponto) (1.5.0)\n",
"Requirement already satisfied: tinycss2 in /usr/local/lib/python3.10/dist-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1->deeponto) (1.2.1)\n",
"Requirement already satisfied: fastjsonschema in /usr/local/lib/python3.10/dist-packages (from nbformat->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1->deeponto) (2.17.1)\n",
"Requirement already satisfied: jsonschema>=2.6 in /usr/local/lib/python3.10/dist-packages (from nbformat->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1->deeponto) (4.3.3)\n",
"Requirement already satisfied: pyrsistent!=0.17.0,!=0.17.1,!=0.17.2,>=0.14.0 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=2.6->nbformat->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1->deeponto) (0.19.3)\n",
"Requirement already satisfied: cffi>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from argon2-cffi-bindings->argon2-cffi->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1->deeponto) (1.15.1)\n",
"Requirement already satisfied: soupsieve>1.2 in /usr/local/lib/python3.10/dist-packages (from beautifulsoup4->nbconvert->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1->deeponto) (2.4.1)\n",
"Requirement already satisfied: webencodings in /usr/local/lib/python3.10/dist-packages (from bleach->nbconvert->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1->deeponto) (0.5.1)\n",
"Requirement already satisfied: pycparser in /usr/local/lib/python3.10/dist-packages (from cffi>=1.0.1->argon2-cffi-bindings->argon2-cffi->notebook>=4.4.1->widgetsnbextension~=3.6.0->ipywidgets==7.7.1->deeponto) (2.21)\n",
"Building wheels for collected packages: JPype1\n",
" Building wheel for JPype1 (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
" Created wheel for JPype1: filename=JPype1-1.3.0-cp310-cp310-linux_x86_64.whl size=452719 sha256=2bacf30d7eb46048918e7c6363edcee2c36082f9c4edd932ca31ed6e91b86c68\n",
" Stored in directory: /root/.cache/pip/wheels/f5/c7/8f/c97c6c9868c256c8d17dabb772a2ca9002dcff2912fa8d7d58\n",
"Successfully built JPype1\n",
"Installing collected packages: tokenizers, sentencepiece, safetensors, prefixed, pprintpp, JPype1, yacs, xxhash, textdistance, rouge, protobuf, jedi, dill, blessed, anytree, tensorboardX, multiprocess, huggingface-hub, enlighten, transformers, datasets, openprompt, accelerate, deeponto\n",
" Attempting uninstall: protobuf\n",
" Found existing installation: protobuf 3.20.3\n",
" Uninstalling protobuf-3.20.3:\n",
" Successfully uninstalled protobuf-3.20.3\n",
"Successfully installed JPype1-1.3.0 accelerate-0.21.0 anytree-2.8.0 blessed-1.20.0 datasets-2.13.1 deeponto-0.8.3 dill-0.3.6 enlighten-1.11.2 huggingface-hub-0.16.4 jedi-0.18.2 multiprocess-0.70.14 openprompt-1.0.0 pprintpp-0.4.0 prefixed-0.7.0 protobuf-4.23.4 rouge-1.0.0 safetensors-0.3.1 sentencepiece-0.1.96 tensorboardX-2.6.1 textdistance-4.5.0 tokenizers-0.13.3 transformers-4.30.2 xxhash-3.2.0 yacs-0.1.8\n"
]
}
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "DfcY0cL6gZvT",
"outputId": "fc794641-ad69-49c3-a783-34bd37cd3527"
},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Please enter the maximum memory located to JVM [8g]: \n",
"\n",
"8g maximum memory allocated to JVM.\n",
"JVM started successfully.\n"
]
}
],
"source": [
"from deeponto.onto import Ontology\n",
"from deeponto.align.bertmap import BERTMapPipeline, DEFAULT_CONFIG_FILE"
]
},
{
"cell_type": "code",
"source": [
"config_file = \"bertmap.yaml\"\n",
"#config_file = DEFAULT_CONFIG_FILE\n",
"src_onto_file = \"music-representation.owl\"\n",
"tgt_onto_file = \"musicClasses.owl\"\n"
],
"metadata": {
"id": "9t-qx1QBgebN"
},
"execution_count": 8,
"outputs": []
},
{
"cell_type": "code",
"source": [
"config = BERTMapPipeline.load_bertmap_config(config_file)\n",
"#BERTMapPipeline.save_bertmap_config(config, \"bertmap.yaml\")"
],
"metadata": {
"id": "XZ4NorrMo7XN"
},
"execution_count": 4,
"outputs": []
},
{
"cell_type": "code",
"source": [
"src_onto = Ontology(src_onto_file)"
],
"metadata": {
"id": "9p4c3DmuhHI9"
},
"execution_count": 9,
"outputs": []
},
{
"cell_type": "code",
"source": [
"tgt_onto = Ontology(tgt_onto_file)"
],
"metadata": {
"id": "m2uAE1HUkULV"
},
"execution_count": 11,
"outputs": []
},
{
"cell_type": "code",
"source": [
"bertmap = BERTMapPipeline(src_onto, tgt_onto, config)"
],
"metadata": {
"id": "--jY5HGakY1t",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 1000,
"referenced_widgets": [
"a29dcfabbb884079bebc65ca721d4286",
"ad93707468d0443b8b2a29068ff6d348",
"2b3c6737381742c1935b7f0c9d0c58d0",
"7c41f46338c1409abd10e6e8741c80ae",
"de2f3004fbdf4dc59cea10ca15801690",
"180de3b408a74992b2c7bc6a8882cbab",
"8940f8264c5847839605374237c85484",
"6d269f4f86344545b94f9bb1f8323a8b",
"a6a284e8b0434285a2c852fe7a4cddae",
"f2511ce7ee4e4b238549c5817b141971",
"0f60a68d43ae4e0592a4a79bfbcc1e34",
"9b909f5d386a43429f8f621604e364dd",
"e29d8bf7b5b9420282833f3605807e17",
"6724e4e64e9a4b8ea6ed31945ccbce16",
"4cc95c84e5204f438cb465b4e3ebabbb",
"99a8c002aa424c2491761c82d69b4606",
"d96495cbe6ac4a43a5b40aa625247710",
"f596c7e167de46c5a9eac1c23685e27e",
"7197a59c5e1741abac4fa45b9b09c286",
"665734b57c0e4fc0a0aa2a385c571719",
"e69863265e07488ba4844615fa40913a",
"6ec1575e585d4574a9d5269d6d18cddf",
"e6ae8828daa1436dacfb684e9e54351a",
"77f13cc16db94cb3b86b17bda215f163",
"45e44f58ea9c4be7b2999ec22f4126c7",
"db6e0666b6bf475cb75cffc8902c6eb5",
"ec322b6b100545adaa1c043581abdd28",
"10adebeb500549c39fb18eb69ff13666",
"30a5adbfa30e4fd89ad8c4520f173513",
"ffb7bd37186f4c9685bf1475153f96a2",
"5c3943eb8cd642cb9b46f3f5babf7f98",
"69d31656ecc54eb9a65a65960ce68b0b",
"c8c3c64e45324c8683787fa61d323b22",
"0bc03a786641441c8c1618de4429a790",
"7c86cb8e88e540d88ca2cf8a4014a48f",
"2662955f108245ddbf038587949777ab",
"87aa519f6b6548d58a6f93aee326f82a",
"21cd77cf52d74ebcbed39810c2c8f5cb",
"48d2927025c64fbbaab881598368b1e4",
"ad4294a0c8eb4be783f64ef455050b43",
"9bf38875dc074681b9e64ad5ba245e87",
"3e4fbd6406b647ed927d21aae61ab8e4",
"0438de07f35c45e8a253ef91f9420bb5",
"64d7186bae2e4963bd820f6c2c6ba1c7",
"63b46e70fe7745309221a9eaf62ae23e",
"98f4b080721e4beda8a4cad23170422d",
"03bdf7cedd874f78a6a2457dd4e31920",
"2d5f7590dcdf47c4af6e12dff0c43848",
"13ff05d1452e441ba7fa3417521e5b6e",
"5bd9f796c34745239378edad591f898e",
"de57ab7f05ec4239a93ca18c9b55fbd7",
"d36726787a2d4581934a48ca3970d79d",
"cca0e64b85664113ace2be425ee08240",
"cd434830b0c6476f8f1459ea4ce304b8",
"d4330d558fd147278166b78b2ff4d776",
"21418af9617d40afa23267a0ae5b81fe",
"752dbf2931754d919db58b2d2d4f83ef",
"d14f8e5dd7dc4a58b773097b95f7896d",
"774230ac4753412a9d7103e4a58b2435",
"a68966cd4eea419e9bfb553f4d566818",
"b5b8f58ebbb74a4dafcc1109e757f55c",
"5653bc295f544976a0b5e5e9b5c43bf8",
"dcb8bdbe7b8946789ff022d75a7e8367",
"c104adb32c92442fb2fff9acd4b983e8",
"7da66e8266ab4747ba877ba06d4dd5f4",
"e115eb6d774e4ff2b99b3d32d5fb4e98",
"e6140b2e1ef349c4a756ae2674c5b6c9",
"fd391f0488944ce9aea083d0f94119f4",
"b1cdc5cf4d544736ae133bbb36eb8c6e",
"ad1c5f8837aa4d4e94692ae2f9f101a8",
"d6fc9d469fa742a8a8b5fb859a71c371",
"4c0f9aae81724863b05fdbf76039dbcc",
"751e24d59ed44d538ab1d1706f54aa34",
"2d9b4f1e83ec4eeea3e785c411bc1999",
"84ea0b8f912d41f7b4e41b8a637664d2",
"3175637cbd2f43d79d29c097d7914220",
"9dca6d06f18042c98efa6bd733b40f34",
"e0f58fb57b5347c88a748abe27df0f79",
"cf5123787bf04f178a84279146cb38c0",
"f3e87f0658334207a93a3c057b258339",
"365d00af29d54195a93054d1fca53d36",
"367d5a1e487249f0b164567da6581464",
"c9dad15028d74daa92f3b7f0efdd16be",
"c88b3c2aad204a5a9358359d501f2eaa",
"075a603b3b354cec8825cb93feabb1ea",
"9ab12b0d13b54a7494a33761884e4c2a",
"515679d44eba4748838968f28528b368",
"d0367dda678a428fbfc411cebd8f2bfe",
"59ea58dcc0044afe95f1e2a9b34f73ae",
"b5681c0cf9434135a053adff4967d7d5",
"1b5a51751e924cfab0c066f89c5bb49d",
"1918ef7e644f4fc5ab840eefea6d9943",
"9c94103393e54102a2db1d5b158deeb3",
"81b0942bf8ee4f4c99e22672b74d8174",
"c160f248b20541d289b009649d4f4209",
"c620153094ad41b8bfe76dbb45110e85",
"650b44de04fe47e6b1a8f7e44a3dc26d",
"d27c038bf4c3442a8198d8202bd75738",
"44f5a7f896014af5823bdb2df1506648"
]
},
"outputId": "860d7563-8562-4caa-976e-12546daa3a6e"
},
"execution_count": 12,
"outputs": [
{
"output_type": "stream",
"name": "stderr",
"text": [
"[Time: 00:00:00] - [PID: 194] - [Model: bertmap] \n",
"Load the following configurations:\n",
"{\n",
" \"model\": \"bertmap\",\n",
" \"output_path\": \"/content\",\n",
" \"annotation_property_iris\": [\n",
" \"http://www.w3.org/2000/01/rdf-schema#label\",\n",
" \"http://www.geneontology.org/formats/oboInOwl#hasSynonym\",\n",
" \"http://www.geneontology.org/formats/oboInOwl#hasExactSynonym\",\n",
" \"http://www.w3.org/2004/02/skos/core#exactMatch\",\n",
" \"http://www.ebi.ac.uk/efo/alternative_term\",\n",
" \"http://www.orpha.net/ORDO/Orphanet_#symbol\",\n",
" \"http://purl.org/sig/ont/fma/synonym\",\n",
" \"http://www.w3.org/2004/02/skos/core#prefLabel\",\n",
" \"http://www.w3.org/2004/02/skos/core#altLabel\",\n",
" \"http://ncicb.nci.nih.gov/xml/owl/EVS/Thesaurus.owl#P108\",\n",
" \"http://ncicb.nci.nih.gov/xml/owl/EVS/Thesaurus.owl#P90\"\n",
" ],\n",
" \"known_mappings\": null,\n",
" \"auxiliary_ontos\": [],\n",
" \"bert\": {\n",
" \"pretrained_path\": \"bert-base-uncased\",\n",
" \"max_length_for_input\": 256,\n",
" \"num_epochs_for_training\": 3.0,\n",
" \"batch_size_for_training\": 16,\n",
" \"batch_size_for_prediction\": 128,\n",
" \"resume_training\": null\n",
" },\n",
" \"global_matching\": {\n",
" \"enabled\": true,\n",
" \"num_raw_candidates\": 200,\n",
" \"num_best_predictions\": 10,\n",
" \"mapping_extension_threshold\": 0.8,\n",
" \"mapping_filtered_threshold\": 0.9\n",
" }\n",
"}\n",
"INFO:bertmap:Load the following configurations:\n",
"{\n",
" \"model\": \"bertmap\",\n",
" \"output_path\": \"/content\",\n",
" \"annotation_property_iris\": [\n",
" \"http://www.w3.org/2000/01/rdf-schema#label\",\n",
" \"http://www.geneontology.org/formats/oboInOwl#hasSynonym\",\n",
" \"http://www.geneontology.org/formats/oboInOwl#hasExactSynonym\",\n",
" \"http://www.w3.org/2004/02/skos/core#exactMatch\",\n",
" \"http://www.ebi.ac.uk/efo/alternative_term\",\n",
" \"http://www.orpha.net/ORDO/Orphanet_#symbol\",\n",
" \"http://purl.org/sig/ont/fma/synonym\",\n",
" \"http://www.w3.org/2004/02/skos/core#prefLabel\",\n",
" \"http://www.w3.org/2004/02/skos/core#altLabel\",\n",
" \"http://ncicb.nci.nih.gov/xml/owl/EVS/Thesaurus.owl#P108\",\n",
" \"http://ncicb.nci.nih.gov/xml/owl/EVS/Thesaurus.owl#P90\"\n",
" ],\n",
" \"known_mappings\": null,\n",
" \"auxiliary_ontos\": [],\n",
" \"bert\": {\n",
" \"pretrained_path\": \"bert-base-uncased\",\n",
" \"max_length_for_input\": 256,\n",
" \"num_epochs_for_training\": 3.0,\n",
" \"batch_size_for_training\": 16,\n",
" \"batch_size_for_prediction\": 128,\n",
" \"resume_training\": null\n",
" },\n",
" \"global_matching\": {\n",
" \"enabled\": true,\n",
" \"num_raw_candidates\": 200,\n",
" \"num_best_predictions\": 10,\n",
" \"mapping_extension_threshold\": 0.8,\n",
" \"mapping_filtered_threshold\": 0.9\n",
" }\n",
"}\n",
"[Time: 00:00:00] - [PID: 194] - [Model: bertmap] \n",
"Save the configuration file at /content/bertmap/config.yaml.\n",
"INFO:bertmap:Save the configuration file at /content/bertmap/config.yaml.\n",
"[Time: 00:00:00] - [PID: 194] - [Model: bertmap] \n",
"Construct new text semantics corpora and save at /content/bertmap/data/text-semantics.corpora.json.\n",
"INFO:bertmap:Construct new text semantics corpora and save at /content/bertmap/data/text-semantics.corpora.json.\n",
"[Time: 00:00:02] - [PID: 194] - [Model: bertmap] \n",
"{\n",
" \"TextSemanticsCorpora\": {\n",
" \"num_synonyms\": 17587,\n",
" \"num_nonsynonyms\": 70326,\n",
" \"intra_src_onto_corpus\": {\n",
" \"num_synonyms\": 11,\n",
" \"num_nonsynonyms\": 43,\n",
" \"num_soft_nonsynonyms\": 43,\n",
" \"num_hard_nonsynonyms\": 0,\n",
" \"annotation_thesaurus\": {\n",
" \"ontology\": {\n",
" \"loaded_from\": \"music-representation.owl\",\n",
" \"num_classes\": 29,\n",
" \"num_object_properties\": 44,\n",
" \"num_data_properties\": 2,\n",
" \"num_annotation_properties\": 7\n",
" },\n",
" \"average_number_of_annotations_per_class\": 0.379,\n",
" \"number_of_synonym_groups\": 29\n",
" }\n",
" },\n",
" \"intra_tgt_onto_corpus\": {\n",
" \"num_synonyms\": 17576,\n",
" \"num_nonsynonyms\": 70304,\n",
" \"num_soft_nonsynonyms\": 35225,\n",
" \"num_hard_nonsynonyms\": 35079,\n",
" \"annotation_thesaurus\": {\n",
" \"ontology\": {\n",
" \"loaded_from\": \"musicClasses.owl\",\n",
" \"num_classes\": 10942,\n",
" \"num_object_properties\": 0,\n",
" \"num_data_properties\": 0,\n",
" \"num_annotation_properties\": 4\n",
" },\n",
" \"average_number_of_annotations_per_class\": 1.144,\n",
" \"number_of_synonym_groups\": 10942\n",
" }\n",
" },\n",
" \"cross_onto_corpus\": null,\n",
" \"auxiliary_onto_corpora\": []\n",
" }\n",
"}\n",
"INFO:bertmap:{\n",
" \"TextSemanticsCorpora\": {\n",
" \"num_synonyms\": 17587,\n",
" \"num_nonsynonyms\": 70326,\n",
" \"intra_src_onto_corpus\": {\n",
" \"num_synonyms\": 11,\n",
" \"num_nonsynonyms\": 43,\n",
" \"num_soft_nonsynonyms\": 43,\n",
" \"num_hard_nonsynonyms\": 0,\n",
" \"annotation_thesaurus\": {\n",
" \"ontology\": {\n",
" \"loaded_from\": \"music-representation.owl\",\n",
" \"num_classes\": 29,\n",
" \"num_object_properties\": 44,\n",
" \"num_data_properties\": 2,\n",
" \"num_annotation_properties\": 7\n",
" },\n",
" \"average_number_of_annotations_per_class\": 0.379,\n",
" \"number_of_synonym_groups\": 29\n",
" }\n",
" },\n",
" \"intra_tgt_onto_corpus\": {\n",
" \"num_synonyms\": 17576,\n",
" \"num_nonsynonyms\": 70304,\n",
" \"num_soft_nonsynonyms\": 35225,\n",
" \"num_hard_nonsynonyms\": 35079,\n",
" \"annotation_thesaurus\": {\n",
" \"ontology\": {\n",
" \"loaded_from\": \"musicClasses.owl\",\n",
" \"num_classes\": 10942,\n",
" \"num_object_properties\": 0,\n",
" \"num_data_properties\": 0,\n",
" \"num_annotation_properties\": 4\n",
" },\n",
" \"average_number_of_annotations_per_class\": 1.144,\n",
" \"number_of_synonym_groups\": 10942\n",
" }\n",
" },\n",
" \"cross_onto_corpus\": null,\n",
" \"auxiliary_onto_corpora\": []\n",
" }\n",
"}\n",
"[Time: 00:00:02] - [PID: 194] - [Model: bertmap] \n",
"Construct new fine-tuning data and save at /content/bertmap/data/fine-tune.data.json.\n",
"INFO:bertmap:Construct new fine-tuning data and save at /content/bertmap/data/fine-tune.data.json.\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"Loading a BERT model from: bert-base-uncased.\n"
]
},
{
"output_type": "display_data",
"data": {
"text/plain": [
"Downloading (…)lve/main/config.json: 0%| | 0.00/570 [00:00<?, ?B/s]"
],
"application/vnd.jupyter.widget-view+json": {
"version_major": 2,
"version_minor": 0,
"model_id": "a29dcfabbb884079bebc65ca721d4286"
}
},
"metadata": {}
},
{
"output_type": "display_data",
"data": {
"text/plain": [
"Downloading model.safetensors: 0%| | 0.00/440M [00:00<?, ?B/s]"
],
"application/vnd.jupyter.widget-view+json": {
"version_major": 2,
"version_minor": 0,
"model_id": "9b909f5d386a43429f8f621604e364dd"
}
},
"metadata": {}
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"Some weights of the model checkpoint at bert-base-uncased were not used when initializing BertForSequenceClassification: ['cls.predictions.bias', 'cls.seq_relationship.bias', 'cls.predictions.transform.LayerNorm.weight', 'cls.predictions.transform.dense.weight', 'cls.predictions.transform.LayerNorm.bias', 'cls.predictions.transform.dense.bias', 'cls.seq_relationship.weight']\n",
"- This IS expected if you are initializing BertForSequenceClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).\n",
"- This IS NOT expected if you are initializing BertForSequenceClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).\n",
"Some weights of BertForSequenceClassification were not initialized from the model checkpoint at bert-base-uncased and are newly initialized: ['classifier.bias', 'classifier.weight']\n",
"You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
]
},
{
"output_type": "display_data",
"data": {
"text/plain": [
"Downloading (…)okenizer_config.json: 0%| | 0.00/28.0 [00:00<?, ?B/s]"
],
"application/vnd.jupyter.widget-view+json": {
"version_major": 2,
"version_minor": 0,
"model_id": "e6ae8828daa1436dacfb684e9e54351a"
}
},
"metadata": {}
},
{
"output_type": "display_data",
"data": {
"text/plain": [
"Downloading (…)solve/main/vocab.txt: 0%| | 0.00/232k [00:00<?, ?B/s]"
],
"application/vnd.jupyter.widget-view+json": {
"version_major": 2,
"version_minor": 0,
"model_id": "0bc03a786641441c8c1618de4429a790"
}
},
"metadata": {}
},
{
"output_type": "display_data",
"data": {
"text/plain": [
"Downloading (…)/main/tokenizer.json: 0%| | 0.00/466k [00:00<?, ?B/s]"
],
"application/vnd.jupyter.widget-view+json": {
"version_major": 2,
"version_minor": 0,
"model_id": "63b46e70fe7745309221a9eaf62ae23e"
}
},
"metadata": {}
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"Downloading and preparing dataset generator/default to /root/.cache/huggingface/datasets/generator/default-dd661ad551fb9b15/0.0.0...\n"
]
},
{
"output_type": "display_data",
"data": {
"text/plain": [
"Generating train split: 0 examples [00:00, ? examples/s]"
],
"application/vnd.jupyter.widget-view+json": {
"version_major": 2,
"version_minor": 0,
"model_id": "21418af9617d40afa23267a0ae5b81fe"
}
},
"metadata": {}
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"Dataset generator downloaded and prepared to /root/.cache/huggingface/datasets/generator/default-dd661ad551fb9b15/0.0.0. Subsequent calls will reuse this data.\n"
]
},
{
"output_type": "display_data",
"data": {
"text/plain": [
"Load training data:: 0%| | 0/79121 [00:00<?, ? examples/s]"
],
"application/vnd.jupyter.widget-view+json": {
"version_major": 2,
"version_minor": 0,
"model_id": "e6140b2e1ef349c4a756ae2674c5b6c9"
}
},
"metadata": {}
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"Downloading and preparing dataset generator/default to /root/.cache/huggingface/datasets/generator/default-3e8c36597523434f/0.0.0...\n"
]
},
{
"output_type": "display_data",
"data": {
"text/plain": [
"Generating train split: 0 examples [00:00, ? examples/s]"
],
"application/vnd.jupyter.widget-view+json": {
"version_major": 2,
"version_minor": 0,
"model_id": "e0f58fb57b5347c88a748abe27df0f79"
}
},
"metadata": {}
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"Dataset generator downloaded and prepared to /root/.cache/huggingface/datasets/generator/default-3e8c36597523434f/0.0.0. Subsequent calls will reuse this data.\n"
]
},
{
"output_type": "display_data",
"data": {
"text/plain": [
"Load validation data:: 0%| | 0/8792 [00:00<?, ? examples/s]"
],
"application/vnd.jupyter.widget-view+json": {
"version_major": 2,
"version_minor": 0,
"model_id": "59ea58dcc0044afe95f1e2a9b34f73ae"
}
},
"metadata": {}
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"[Time: 00:00:38] - [PID: 194] - [Model: bertmap] \n",
"Data statistics:\n",
" {\n",
" \"num_training\": 79121,\n",
" \"num_validation\": 8792\n",
"}\n",
"INFO:bertmap:Data statistics:\n",
" {\n",
" \"num_training\": 79121,\n",
" \"num_validation\": 8792\n",
"}\n",
"/usr/local/lib/python3.10/dist-packages/transformers/optimization.py:411: FutureWarning: This implementation of AdamW is deprecated and will be removed in a future version. Use the PyTorch implementation torch.optim.AdamW instead, or set `no_deprecation_warning=True` to disable this warning\n",
" warnings.warn(\n",
"You're using a BertTokenizerFast tokenizer. Please note that with a fast tokenizer, using the `__call__` method is faster than using a method to encode the text followed by a call to the `pad` method to get a padded encoding.\n"
]
},
{
"output_type": "display_data",
"data": {
"text/plain": [
"<IPython.core.display.HTML object>"
],
"text/html": [
"\n",
" <div>\n",
" \n",
" <progress value='14838' max='14838' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
" [14838/14838 30:32, Epoch 3/3]\n",
" </div>\n",
" <table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: left;\">\n",
" <th>Step</th>\n",
" <th>Training Loss</th>\n",
" <th>Validation Loss</th>\n",
" <th>Accuracy</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <td>980</td>\n",
" <td>0.125800</td>\n",
" <td>0.109794</td>\n",
" <td>0.973499</td>\n",
" </tr>\n",
" <tr>\n",
" <td>1960</td>\n",
" <td>0.120100</td>\n",
" <td>0.109092</td>\n",
" <td>0.974295</td>\n",
" </tr>\n",
" <tr>\n",
" <td>2940</td>\n",
" <td>0.113100</td>\n",
" <td>0.131368</td>\n",
" <td>0.974067</td>\n",
" </tr>\n",
" <tr>\n",
" <td>3920</td>\n",
" <td>0.112100</td>\n",
" <td>0.097271</td>\n",
" <td>0.978617</td>\n",
" </tr>\n",
" <tr>\n",
" <td>4900</td>\n",
" <td>0.117000</td>\n",
" <td>0.094326</td>\n",
" <td>0.976342</td>\n",
" </tr>\n",
" <tr>\n",
" <td>5880</td>\n",
" <td>0.060200</td>\n",
" <td>0.090819</td>\n",
" <td>0.977934</td>\n",
" </tr>\n",
" <tr>\n",
" <td>6860</td>\n",
" <td>0.057100</td>\n",
" <td>0.114139</td>\n",
" <td>0.979186</td>\n",
" </tr>\n",
" <tr>\n",
" <td>7840</td>\n",
" <td>0.070900</td>\n",
" <td>0.097529</td>\n",
" <td>0.979641</td>\n",
" </tr>\n",
" <tr>\n",
" <td>8820</td>\n",
" <td>0.076200</td>\n",
" <td>0.082380</td>\n",
" <td>0.982370</td>\n",
" </tr>\n",
" <tr>\n",
" <td>9800</td>\n",
" <td>0.059000</td>\n",
" <td>0.071074</td>\n",
" <td>0.983849</td>\n",
" </tr>\n",
" <tr>\n",
" <td>10780</td>\n",
" <td>0.035400</td>\n",
" <td>0.086666</td>\n",
" <td>0.982598</td>\n",
" </tr>\n",
" <tr>\n",
" <td>11760</td>\n",
" <td>0.034000</td>\n",
" <td>0.083171</td>\n",
" <td>0.983963</td>\n",
" </tr>\n",
" <tr>\n",
" <td>12740</td>\n",
" <td>0.039100</td>\n",
" <td>0.081670</td>\n",
" <td>0.984190</td>\n",
" </tr>\n",
" <tr>\n",
" <td>13720</td>\n",
" <td>0.035600</td>\n",
" <td>0.073470</td>\n",
" <td>0.984986</td>\n",
" </tr>\n",
" <tr>\n",
" <td>14700</td>\n",
" <td>0.031200</td>\n",
" <td>0.075684</td>\n",
" <td>0.985328</td>\n",
" </tr>\n",
" </tbody>\n",
"</table><p>"
]
},
"metadata": {}
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"[Time: 00:31:15] - [PID: 194] - [Model: bertmap] \n",
"Fine-tuning finished, found best checkpoint at /content/bertmap/bert/checkpoint-9800.\n",
"INFO:bertmap:Fine-tuning finished, found best checkpoint at /content/bertmap/bert/checkpoint-9800.\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"The BERT model is set to eval mode for making predictions.\n",
"There are 1 GPU(s) available.\n",
"We will use the GPU: Tesla T4\n"
]
},
{
"output_type": "display_data",
"data": {
"text/plain": [
"<IPython.core.display.HTML object>"
],
"text/html": [
"<style>\n",
".enlighten-bold {\n",
" font-weight: bold;\n",
"}\n",
".enlighten-underline {\n",
" text-decoration: underline;\n",
"}\n",
".enlighten-fg-bright-white {\n",
" color: #ffffff;\n",
"}\n",
".enlighten-bg-lightslategray {\n",
" background-color: #778899;\n",
"}\n",
"</style>\n",
"<div class=\"enlighten\">\n",
" <div class=\"enlighten-bar\">\n",
" <pre><span class=\"enlighten-bold enlighten-underline enlighten-fg-bright-white enlighten-bg-lightslategray\">Global Matching Stage: Mapping Extension 00:03</span></pre>\n",
" </div>\n",
" <div class=\"enlighten-bar\">\n",
" <pre>Mapping Prediction 100%|████████████████████████████████| 29/29 [00:02&lt;00:00, 12.02 per src class/s]</pre>\n",
" </div>\n",
" <div class=\"enlighten-bar\">\n",
" <pre>Mapping Extension [Iteration #0] 0 mapping [00:00, 0.00 mapping/s] </pre>\n",
" </div>\n",
" <div class=\"enlighten-bar\">\n",
" <pre></pre>\n",
" </div>\n",
"</div>\n"
]
},
"metadata": {}
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"[Time: 00:31:15] - [PID: 194] - [Model: bertmap] \n",
"Build inverted annotation index for candidate selection.\n",
"INFO:bertmap:Build inverted annotation index for candidate selection.\n",
"[Time: 00:31:16] - [PID: 194] - [Model: bertmap] \n",
"Start global matching for each class in the source ontology.\n",
"INFO:bertmap:Start global matching for each class in the source ontology.\n",
"[Time: 00:31:16] - [PID: 194] - [Model: bertmap] \n",
"The best scored class mappings for http://cedric.cnam.fr/isid/ontologies/MusicNote.owl#Part are\n",
"[]\n",
"INFO:bertmap:The best scored class mappings for http://cedric.cnam.fr/isid/ontologies/MusicNote.owl#Part are\n",
"[]\n",
"[Time: 00:31:16] - [PID: 194] - [Model: bertmap] \n",
"Save currently computed mappings to prevent undesirable loss.\n",
"INFO:bertmap:Save currently computed mappings to prevent undesirable loss.\n",
"[Time: 00:31:16] - [PID: 194] - [Model: bertmap] \n",
"The best scored class mappings for http://cedric.cnam.fr/isid/ontologies/MusicNote.owl#Score are\n",
"[]\n",
"INFO:bertmap:The best scored class mappings for http://cedric.cnam.fr/isid/ontologies/MusicNote.owl#Score are\n",
"[]\n",
"[Time: 00:31:16] - [PID: 194] - [Model: bertmap] \n",
"The best scored class mappings for http://cedric.cnam.fr/isid/ontologies/MusicNote.owl#Voice are\n",
"[]\n",
"INFO:bertmap:The best scored class mappings for http://cedric.cnam.fr/isid/ontologies/MusicNote.owl#Voice are\n",
"[]\n",
"[Time: 00:31:16] - [PID: 194] - [Model: bertmap] \n",
"The best scored class mappings for http://linkeddata.uni-muenster.de/ontology/musicscore#Instant are\n",
"[]\n",
"INFO:bertmap:The best scored class mappings for http://linkeddata.uni-muenster.de/ontology/musicscore#Instant are\n",
"[]\n",
"[Time: 00:31:16] - [PID: 194] - [Model: bertmap] \n",
"The best scored class mappings for http://purl.org/andreapoltronieri/music-annotation-pattern/MusicTimeInterval are\n",
"[]\n",
"INFO:bertmap:The best scored class mappings for http://purl.org/andreapoltronieri/music-annotation-pattern/MusicTimeInterval are\n",
"[]\n",
"[Time: 00:31:16] - [PID: 194] - [Model: bertmap] \n",
"The best scored class mappings for http://w3id.org/polifonia/ontology/jams/AnnotationType are\n",
"[]\n",
"INFO:bertmap:The best scored class mappings for http://w3id.org/polifonia/ontology/jams/AnnotationType are\n",
"[]\n",
"[Time: 00:31:16] - [PID: 194] - [Model: bertmap] \n",
"The best scored class mappings for http://w3id.org/polifonia/ontology/jams/AnnotatorType are\n",
"[]\n",
"INFO:bertmap:The best scored class mappings for http://w3id.org/polifonia/ontology/jams/AnnotatorType are\n",
"[]\n",
"[Time: 00:31:16] - [PID: 194] - [Model: bertmap] \n",
"The best scored class mappings for http://w3id.org/polifonia/ontology/jams/JAMSAnnotation are\n",
"[]\n",
"INFO:bertmap:The best scored class mappings for http://w3id.org/polifonia/ontology/jams/JAMSAnnotation are\n",
"[]\n",
"[Time: 00:31:16] - [PID: 194] - [Model: bertmap] \n",
"The best scored class mappings for http://w3id.org/polifonia/ontology/jams/JAMSObservation are\n",
"[]\n",
"INFO:bertmap:The best scored class mappings for http://w3id.org/polifonia/ontology/jams/JAMSObservation are\n",
"[]\n",
"[Time: 00:31:16] - [PID: 194] - [Model: bertmap] \n",
"The best scored class mappings for https://purl.org/andreapoltronieri/notepattern/Position are\n",
"[]\n",
"INFO:bertmap:The best scored class mappings for https://purl.org/andreapoltronieri/notepattern/Position are\n",
"[]\n",
"[Time: 00:31:16] - [PID: 194] - [Model: bertmap] \n",
"The best scored class mappings for https://w3id.org/polifonia/ontology/core/Agent are\n",
"[]\n",
"INFO:bertmap:The best scored class mappings for https://w3id.org/polifonia/ontology/core/Agent are\n",
"[]\n",
"[Time: 00:31:16] - [PID: 194] - [Model: bertmap] \n",
"The best scored class mappings for https://w3id.org/polifonia/ontology/core/Explanation are\n",
"[]\n",
"INFO:bertmap:The best scored class mappings for https://w3id.org/polifonia/ontology/core/Explanation are\n",
"[]\n",
"[Time: 00:31:16] - [PID: 194] - [Model: bertmap] \n",
"The best scored class mappings for https://w3id.org/polifonia/ontology/core/MusicTimeInterval are\n",
"[]\n",
"INFO:bertmap:The best scored class mappings for https://w3id.org/polifonia/ontology/core/MusicTimeInterval are\n",
"[]\n",
"[Time: 00:31:16] - [PID: 194] - [Model: bertmap] \n",
"The best scored class mappings for https://w3id.org/polifonia/ontology/core/Role are\n",
"[]\n",
"INFO:bertmap:The best scored class mappings for https://w3id.org/polifonia/ontology/core/Role are\n",
"[]\n",
"[Time: 00:31:16] - [PID: 194] - [Model: bertmap] \n",
"The best scored class mappings for https://w3id.org/polifonia/ontology/core/Theory are\n",
"[]\n",
"INFO:bertmap:The best scored class mappings for https://w3id.org/polifonia/ontology/core/Theory are\n",
"[]\n",
"[Time: 00:31:16] - [PID: 194] - [Model: bertmap] \n",
"The best scored class mappings for https://w3id.org/polifonia/ontology/music-meta/AbstractScore are\n",
"[]\n",
"INFO:bertmap:The best scored class mappings for https://w3id.org/polifonia/ontology/music-meta/AbstractScore are\n",
"[]\n",
"[Time: 00:31:16] - [PID: 194] - [Model: bertmap] \n",
"The best scored class mappings for https://w3id.org/polifonia/ontology/music-meta/Recording are\n",
"[]\n",
"INFO:bertmap:The best scored class mappings for https://w3id.org/polifonia/ontology/music-meta/Recording are\n",
"[]\n",
"[Time: 00:31:16] - [PID: 194] - [Model: bertmap] \n",
"The best scored class mappings for https://w3id.org/polifonia/ontology/music-meta/Score are\n",
"[]\n",
"INFO:bertmap:The best scored class mappings for https://w3id.org/polifonia/ontology/music-meta/Score are\n",
"[]\n",
"[Time: 00:31:16] - [PID: 194] - [Model: bertmap] \n",
"The best scored class mappings for https://w3id.org/polifonia/ontology/music-representation/Analysis are\n",
"[]\n",
"INFO:bertmap:The best scored class mappings for https://w3id.org/polifonia/ontology/music-representation/Analysis are\n",
"[]\n",
"[Time: 00:31:16] - [PID: 194] - [Model: bertmap] \n",
"The best scored class mappings for https://w3id.org/polifonia/ontology/music-representation/Analyst are\n",
"[]\n",
"INFO:bertmap:The best scored class mappings for https://w3id.org/polifonia/ontology/music-representation/Analyst are\n",
"[]\n",
"[Time: 00:31:16] - [PID: 194] - [Model: bertmap] \n",
"The best scored class mappings for https://w3id.org/polifonia/ontology/music-representation/AnalyticalReference are\n",
"[]\n",
"INFO:bertmap:The best scored class mappings for https://w3id.org/polifonia/ontology/music-representation/AnalyticalReference are\n",
"[]\n",
"[Time: 00:31:16] - [PID: 194] - [Model: bertmap] \n",
"The best scored class mappings for https://w3id.org/polifonia/ontology/music-representation/Annotation are\n",
"[EntityMapping(https://w3id.org/polifonia/ontology/music-representation/Annotation <EquivalentTo> http://www.wikidata.org/entity/Q4289658, 0.925591)]\n",
"INFO:bertmap:The best scored class mappings for https://w3id.org/polifonia/ontology/music-representation/Annotation are\n",
"[EntityMapping(https://w3id.org/polifonia/ontology/music-representation/Annotation <EquivalentTo> http://www.wikidata.org/entity/Q4289658, 0.925591)]\n",
"[Time: 00:31:16] - [PID: 194] - [Model: bertmap] \n",
"The best scored class mappings for https://w3id.org/polifonia/ontology/music-representation/AnnotationType are\n",
"[]\n",
"INFO:bertmap:The best scored class mappings for https://w3id.org/polifonia/ontology/music-representation/AnnotationType are\n",
"[]\n",
"[Time: 00:31:16] - [PID: 194] - [Model: bertmap] \n",
"The best scored class mappings for https://w3id.org/polifonia/ontology/music-representation/Annotator are\n",
"[EntityMapping(https://w3id.org/polifonia/ontology/music-representation/Annotator <EquivalentTo> http://www.wikidata.org/entity/Q1790046, 0.937481), EntityMapping(https://w3id.org/polifonia/ontology/music-representation/Annotator <EquivalentTo> http://www.wikidata.org/entity/Q1141589, 0.931599)]\n",
"INFO:bertmap:The best scored class mappings for https://w3id.org/polifonia/ontology/music-representation/Annotator are\n",
"[EntityMapping(https://w3id.org/polifonia/ontology/music-representation/Annotator <EquivalentTo> http://www.wikidata.org/entity/Q1790046, 0.937481), EntityMapping(https://w3id.org/polifonia/ontology/music-representation/Annotator <EquivalentTo> http://www.wikidata.org/entity/Q1141589, 0.931599)]\n",
"[Time: 00:31:16] - [PID: 194] - [Model: bertmap] \n",
"The best scored class mappings for https://w3id.org/polifonia/ontology/music-representation/AnnotatorType are\n",
"[EntityMapping(https://w3id.org/polifonia/ontology/music-representation/AnnotatorType <EquivalentTo> http://www.wikidata.org/entity/Q105303913, 0.964318)]\n",
"INFO:bertmap:The best scored class mappings for https://w3id.org/polifonia/ontology/music-representation/AnnotatorType are\n",
"[EntityMapping(https://w3id.org/polifonia/ontology/music-representation/AnnotatorType <EquivalentTo> http://www.wikidata.org/entity/Q105303913, 0.964318)]\n",
"[Time: 00:31:16] - [PID: 194] - [Model: bertmap] \n",
"The best scored class mappings for https://w3id.org/polifonia/ontology/music-representation/Fragment are\n",
"[]\n",
"INFO:bertmap:The best scored class mappings for https://w3id.org/polifonia/ontology/music-representation/Fragment are\n",
"[]\n",
"[Time: 00:31:17] - [PID: 194] - [Model: bertmap] \n",
"The best scored class mappings for https://w3id.org/polifonia/ontology/music-representation/MusicContent are\n",
"[]\n",
"INFO:bertmap:The best scored class mappings for https://w3id.org/polifonia/ontology/music-representation/MusicContent are\n",
"[]\n",
"[Time: 00:31:18] - [PID: 194] - [Model: bertmap] \n",
"The best scored class mappings for https://w3id.org/polifonia/ontology/music-representation/MusicProjection are\n",
"[]\n",
"INFO:bertmap:The best scored class mappings for https://w3id.org/polifonia/ontology/music-representation/MusicProjection are\n",
"[]\n",
"[Time: 00:31:18] - [PID: 194] - [Model: bertmap] \n",
"The best scored class mappings for https://w3id.org/polifonia/ontology/music-representation/Observation are\n",
"[]\n",
"INFO:bertmap:The best scored class mappings for https://w3id.org/polifonia/ontology/music-representation/Observation are\n",
"[]\n",
"[Time: 00:31:18] - [PID: 194] - [Model: bertmap] \n",
"Save currently computed mappings to prevent undesirable loss.\n",
"INFO:bertmap:Save currently computed mappings to prevent undesirable loss.\n",
"[Time: 00:31:18] - [PID: 194] - [Model: bertmap] \n",
"Finished mapping prediction for each class in the source ontology.\n",
"INFO:bertmap:Finished mapping prediction for each class in the source ontology.\n",
"[Time: 00:31:18] - [PID: 194] - [Model: bertmap] \n",
"Start mapping extension for each class pair with score >= 0.8.\n",
"INFO:bertmap:Start mapping extension for each class pair with score >= 0.8.\n"
]
},
{
"output_type": "error",
"ename": "IndexError",
"evalue": "ignored",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mIndexError\u001b[0m Traceback (most recent call last)",
"\u001b[0;32m<ipython-input-12-a888744a31b2>\u001b[0m in \u001b[0;36m<cell line: 1>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mbertmap\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mBERTMapPipeline\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0msrc_onto\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtgt_onto\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mconfig\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
"\u001b[0;32m/usr/local/lib/python3.10/dist-packages/deeponto/align/bertmap/pipeline.py\u001b[0m in \u001b[0;36m__init__\u001b[0;34m(self, src_onto, tgt_onto, config)\u001b[0m\n\u001b[1;32m 191\u001b[0m \u001b[0menlighten_status\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0menlighten_status\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 192\u001b[0m )\n\u001b[0;32m--> 193\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmapping_refiner\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmapping_extension\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;31m# mapping extension\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 194\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmapping_refiner\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmapping_repair\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;31m# mapping repair\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 195\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0menlighten_status\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mupdate\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdemo\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m\"Finished\"\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/python3.10/dist-packages/deeponto/align/bertmap/mapping_refinement.py\u001b[0m in \u001b[0;36mmapping_extension\u001b[0;34m(self, max_iter)\u001b[0m\n\u001b[1;32m 163\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0msrc_class_iri\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtgt_class_iri\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mfrontier\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 164\u001b[0m \u001b[0;31m# one hop extension makes sure new mappings are really \"new\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 165\u001b[0;31m \u001b[0mcur_new_mappings\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mone_hop_extend\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0msrc_class_iri\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtgt_class_iri\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 166\u001b[0m \u001b[0mextension_progress_bar\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mupdate\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcur_new_mappings\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 167\u001b[0m \u001b[0mnew_mappings\u001b[0m \u001b[0;34m+=\u001b[0m \u001b[0mcur_new_mappings\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.10/dist-packages/deeponto/align/bertmap/mapping_refinement.py\u001b[0m in \u001b[0;36mone_hop_extend\u001b[0;34m(self, src_class_iri, tgt_class_iri, pool_size)\u001b[0m\n\u001b[1;32m 251\u001b[0m \u001b[0msrc_candidate_annotations\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmapping_predictor\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msrc_annotation_index\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0msrc_candidate_iri\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 252\u001b[0m \u001b[0mtgt_candidate_annotations\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmapping_predictor\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtgt_annotation_index\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mtgt_candidate_iri\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 253\u001b[0;31m \u001b[0mscore\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmapping_predictor\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mbert_mapping_score\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0msrc_candidate_annotations\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtgt_candidate_annotations\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 254\u001b[0m \u001b[0;31m# add to already scored collection\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 255\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmapping_score_dict\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0msrc_candidate_iri\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtgt_candidate_iri\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mscore\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.10/dist-packages/deeponto/align/bertmap/mapping_prediction.py\u001b[0m in \u001b[0;36mbert_mapping_score\u001b[0;34m(self, src_class_annotations, tgt_class_annotations)\u001b[0m\n\u001b[1;32m 107\u001b[0m \u001b[0;31m# apply BERT classifier and define mapping score := Average(SynonymScores)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 108\u001b[0m \u001b[0mclass_annotation_pairs\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mlist\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mitertools\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mproduct\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0msrc_class_annotations\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtgt_class_annotations\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--> 109\u001b[0;31m \u001b[0msynonym_scores\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mbert_synonym_classifier\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpredict\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mclass_annotation_pairs\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 110\u001b[0m \u001b[0;31m# only one element tensor is able to be extracted as a scalar by .item()\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 111\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mfloat\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtorch\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmean\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0msynonym_scores\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mitem\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/usr/local/lib/python3.10/dist-packages/deeponto/align/bertmap/bert_classifier.py\u001b[0m in \u001b[0;36mpredict\u001b[0;34m(self, sent_pairs)\u001b[0m\n\u001b[1;32m 155\u001b[0m \u001b[0mReturn\u001b[0m \u001b[0mthe\u001b[0m\u001b[0;31m \u001b[0m\u001b[0;31m`\u001b[0m\u001b[0msoftmax\u001b[0m\u001b[0;31m`\u001b[0m \u001b[0mprobailities\u001b[0m \u001b[0mof\u001b[0m \u001b[0mpredicting\u001b[0m \u001b[0mpairs\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0msynonyms\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0;31m`\u001b[0m\u001b[0mindex\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;31m`\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 156\u001b[0m \"\"\"\n\u001b[0;32m--> 157\u001b[0;31m \u001b[0minputs\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mprocess_inputs\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0msent_pairs\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 158\u001b[0m \u001b[0;32mwith\u001b[0m \u001b[0mtorch\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mno_grad\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[1;32m 159\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msoftmax\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmodel\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m**\u001b[0m\u001b[0minputs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mlogits\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;36m1\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.10/dist-packages/deeponto/align/bertmap/bert_classifier.py\u001b[0m in \u001b[0;36mprocess_inputs\u001b[0;34m(self, sent_pairs)\u001b[0m\n\u001b[1;32m 183\u001b[0m \u001b[0mThis\u001b[0m \u001b[0mfunction\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0mcalled\u001b[0m \u001b[0monly\u001b[0m \u001b[0mwhen\u001b[0m \u001b[0mthe\u001b[0m \u001b[0mBERT\u001b[0m \u001b[0mmodel\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0mabout\u001b[0m \u001b[0mto\u001b[0m \u001b[0mmake\u001b[0m \u001b[0mpredictions\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0;31m`\u001b[0m\u001b[0meval\u001b[0m\u001b[0;31m`\u001b[0m \u001b[0mmode\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 184\u001b[0m \"\"\"\n\u001b[0;32m--> 185\u001b[0;31m return self.tokenizer._tokenizer(\n\u001b[0m\u001b[1;32m 186\u001b[0m \u001b[0msent_pairs\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 187\u001b[0m \u001b[0mreturn_tensors\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m\"pt\"\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/python3.10/dist-packages/transformers/tokenization_utils_base.py\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self, text, text_pair, text_target, text_pair_target, add_special_tokens, padding, truncation, max_length, stride, is_split_into_words, pad_to_multiple_of, return_tensors, return_token_type_ids, return_attention_mask, return_overflowing_tokens, return_special_tokens_mask, return_offsets_mapping, return_length, verbose, **kwargs)\u001b[0m\n\u001b[1;32m 2559\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_in_target_context_manager\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2560\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_switch_to_input_mode\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-> 2561\u001b[0;31m \u001b[0mencodings\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_call_one\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtext\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mtext\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtext_pair\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mtext_pair\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mall_kwargs\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 2562\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mtext_target\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2563\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_switch_to_target_mode\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/python3.10/dist-packages/transformers/tokenization_utils_base.py\u001b[0m in \u001b[0;36m_call_one\u001b[0;34m(self, text, text_pair, add_special_tokens, padding, truncation, max_length, stride, is_split_into_words, pad_to_multiple_of, return_tensors, return_token_type_ids, return_attention_mask, return_overflowing_tokens, return_special_tokens_mask, return_offsets_mapping, return_length, verbose, **kwargs)\u001b[0m\n\u001b[1;32m 2645\u001b[0m )\n\u001b[1;32m 2646\u001b[0m \u001b[0mbatch_text_or_text_pairs\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mlist\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mzip\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtext\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtext_pair\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mtext_pair\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32mNone\u001b[0m \u001b[0;32melse\u001b[0m \u001b[0mtext\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2647\u001b[0;31m return self.batch_encode_plus(\n\u001b[0m\u001b[1;32m 2648\u001b[0m \u001b[0mbatch_text_or_text_pairs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mbatch_text_or_text_pairs\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2649\u001b[0m \u001b[0madd_special_tokens\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0madd_special_tokens\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/python3.10/dist-packages/transformers/tokenization_utils_base.py\u001b[0m in \u001b[0;36mbatch_encode_plus\u001b[0;34m(self, batch_text_or_text_pairs, add_special_tokens, padding, truncation, max_length, stride, is_split_into_words, pad_to_multiple_of, return_tensors, return_token_type_ids, return_attention_mask, return_overflowing_tokens, return_special_tokens_mask, return_offsets_mapping, return_length, verbose, **kwargs)\u001b[0m\n\u001b[1;32m 2836\u001b[0m )\n\u001b[1;32m 2837\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2838\u001b[0;31m return self._batch_encode_plus(\n\u001b[0m\u001b[1;32m 2839\u001b[0m \u001b[0mbatch_text_or_text_pairs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mbatch_text_or_text_pairs\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2840\u001b[0m \u001b[0madd_special_tokens\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0madd_special_tokens\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/python3.10/dist-packages/transformers/tokenization_utils_fast.py\u001b[0m in \u001b[0;36m_batch_encode_plus\u001b[0;34m(self, batch_text_or_text_pairs, add_special_tokens, padding_strategy, truncation_strategy, max_length, stride, is_split_into_words, pad_to_multiple_of, return_tensors, return_token_type_ids, return_attention_mask, return_overflowing_tokens, return_special_tokens_mask, return_offsets_mapping, return_length, verbose)\u001b[0m\n\u001b[1;32m 456\u001b[0m \u001b[0;31m# we add an overflow_to_sample_mapping array (see below)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 457\u001b[0m \u001b[0msanitized_tokens\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--> 458\u001b[0;31m \u001b[0;32mfor\u001b[0m \u001b[0mkey\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mtokens_and_encodings\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mkeys\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 459\u001b[0m \u001b[0mstack\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0me\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mitem\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0m_\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mtokens_and_encodings\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0me\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mitem\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mkey\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 460\u001b[0m \u001b[0msanitized_tokens\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mstack\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;31mIndexError\u001b[0m: list index out of range"
]
}
]
},
{
"cell_type": "code",
"source": [
"!zip -r /content/bertmap-output.zip /content/bertmap/match"
],
"metadata": {
"id": "NnZ6PZPte4SI"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"!rm -rf /content/bertmap"
],
"metadata": {
"id": "NKyshVXEiVKk"
},
"execution_count": 10,
"outputs": []
}
]
}
Raw
bertmap_match_8.ipynb
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment