Skip to content

GitLab

Commit cd3c6c57 authored by Chen Chen's avatar Chen Chen Committed by A. Unique TensorFlower
Browse files

Internal change 

PiperOrigin-RevId: 314556957
parent daa1408c
Hide whitespace changes
Inline Side-by-side
Showing with 264 additions and 2600 deletions
official/colab/fine_tuning_bert.ipynb
View file @ cd3c6c57
{ {
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"name": "How-to Guide: Using a PIP package for fine-tuning a BERT model.ipynb",
"provenance": [],
"collapsed_sections": [],
"toc_visible": true
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"accelerator": "GPU",
"widgets": {
"application/vnd.jupyter.widget-state+json": {
"2a9e31a9fb264e86b4ee0a1c81cceaa5": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HBoxModel",
"state": {
"_view_name": "HBoxView",
"_dom_classes": [],
"_model_name": "HBoxModel",
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_view_count": null,
"_view_module_version": "1.5.0",
"box_style": "",
"layout": "IPY_MODEL_23cc9ef1a4ab49a4a4434cd99cdb388f",
"_model_module": "@jupyter-widgets/controls",
"children": [
"IPY_MODEL_e13997eeb02641fabf42e1014c28fb0e",
"IPY_MODEL_870d3b6641c74a1f9166171317a9879a"
]
}
},
"23cc9ef1a4ab49a4a4434cd99cdb388f": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"state": {
"_view_name": "LayoutView",
"grid_template_rows": null,
"right": null,
"justify_content": null,
"_view_module": "@jupyter-widgets/base",
"overflow": null,
"_model_module_version": "1.2.0",
"_view_count": null,
"flex_flow": null,
"width": null,
"min_width": null,
"border": null,
"align_items": null,
"bottom": null,
"_model_module": "@jupyter-widgets/base",
"top": null,
"grid_column": null,
"overflow_y": null,
"overflow_x": null,
"grid_auto_flow": null,
"grid_area": null,
"grid_template_columns": null,
"flex": null,
"_model_name": "LayoutModel",
"justify_items": null,
"grid_row": null,
"max_height": null,
"align_content": null,
"visibility": null,
"align_self": null,
"height": null,
"min_height": null,
"padding": null,
"grid_auto_rows": null,
"grid_gap": null,
"max_width": null,
"order": null,
"_view_module_version": "1.2.0",
"grid_template_areas": null,
"object_position": null,
"object_fit": null,
"grid_auto_columns": null,
"margin": null,
"display": null,
"left": null
}
},
"e13997eeb02641fabf42e1014c28fb0e": {
"model_module": "@jupyter-widgets/controls",
"model_name": "FloatProgressModel",
"state": {
"_view_name": "ProgressView",
"style": "IPY_MODEL_2e597e06a7e84f29a231c9391dc41f2d",
"_dom_classes": [],
"description": "Dl Completed...: 100%",
"_model_name": "FloatProgressModel",
"bar_style": "success",
"max": 1,
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"value": 1,
"_view_count": null,
"_view_module_version": "1.5.0",
"orientation": "horizontal",
"min": 0,
"description_tooltip": null,
"_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_c1b7fcefc445437faddef2b892eb120f"
}
},
"870d3b6641c74a1f9166171317a9879a": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HTMLModel",
"state": {
"_view_name": "HTMLView",
"style": "IPY_MODEL_66d48af99af441b387be35044558625f",
"_dom_classes": [],
"description": "",
"_model_name": "HTMLModel",
"placeholder": "​",
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"value": " 3/3 [00:00<00:00, 5.29 url/s]",
"_view_count": null,
"_view_module_version": "1.5.0",
"description_tooltip": null,
"_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_f210578a032f4743a926d331d4db4135"
}
},
"2e597e06a7e84f29a231c9391dc41f2d": {
"model_module": "@jupyter-widgets/controls",
"model_name": "ProgressStyleModel",
"state": {
"_view_name": "StyleView",
"_model_name": "ProgressStyleModel",
"description_width": "initial",
"_view_module": "@jupyter-widgets/base",
"_model_module_version": "1.5.0",
"_view_count": null,
"_view_module_version": "1.2.0",
"bar_color": null,
"_model_module": "@jupyter-widgets/controls"
}
},
"c1b7fcefc445437faddef2b892eb120f": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"state": {
"_view_name": "LayoutView",
"grid_template_rows": null,
"right": null,
"justify_content": null,
"_view_module": "@jupyter-widgets/base",
"overflow": null,
"_model_module_version": "1.2.0",
"_view_count": null,
"flex_flow": null,
"width": null,
"min_width": null,
"border": null,
"align_items": null,
"bottom": null,
"_model_module": "@jupyter-widgets/base",
"top": null,
"grid_column": null,
"overflow_y": null,
"overflow_x": null,
"grid_auto_flow": null,
"grid_area": null,
"grid_template_columns": null,
"flex": null,
"_model_name": "LayoutModel",
"justify_items": null,
"grid_row": null,
"max_height": null,
"align_content": null,
"visibility": null,
"align_self": null,
"height": null,
"min_height": null,
"padding": null,
"grid_auto_rows": null,
"grid_gap": null,
"max_width": null,
"order": null,
"_view_module_version": "1.2.0",
"grid_template_areas": null,
"object_position": null,
"object_fit": null,
"grid_auto_columns": null,
"margin": null,
"display": null,
"left": null
}
},
"66d48af99af441b387be35044558625f": {
"model_module": "@jupyter-widgets/controls",
"model_name": "DescriptionStyleModel",
"state": {
"_view_name": "StyleView",
"_model_name": "DescriptionStyleModel",
"description_width": "",
"_view_module": "@jupyter-widgets/base",
"_model_module_version": "1.5.0",
"_view_count": null,
"_view_module_version": "1.2.0",
"_model_module": "@jupyter-widgets/controls"
}
},
"f210578a032f4743a926d331d4db4135": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"state": {
"_view_name": "LayoutView",
"grid_template_rows": null,
"right": null,
"justify_content": null,
"_view_module": "@jupyter-widgets/base",
"overflow": null,
"_model_module_version": "1.2.0",
"_view_count": null,
"flex_flow": null,
"width": null,
"min_width": null,
"border": null,
"align_items": null,
"bottom": null,
"_model_module": "@jupyter-widgets/base",
"top": null,
"grid_column": null,
"overflow_y": null,
"overflow_x": null,
"grid_auto_flow": null,
"grid_area": null,
"grid_template_columns": null,
"flex": null,
"_model_name": "LayoutModel",
"justify_items": null,
"grid_row": null,
"max_height": null,
"align_content": null,
"visibility": null,
"align_self": null,
"height": null,
"min_height": null,
"padding": null,
"grid_auto_rows": null,
"grid_gap": null,
"max_width": null,
"order": null,
"_view_module_version": "1.2.0",
"grid_template_areas": null,
"object_position": null,
"object_fit": null,
"grid_auto_columns": null,
"margin": null,
"display": null,
"left": null
}
},
"6f3e0af4934d4b6885336c79a46055af": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HBoxModel",
"state": {
"_view_name": "HBoxView",
"_dom_classes": [],
"_model_name": "HBoxModel",
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_view_count": null,
"_view_module_version": "1.5.0",
"box_style": "",
"layout": "IPY_MODEL_8f059203cbcc457dadc9171ae8bf9745",
"_model_module": "@jupyter-widgets/controls",
"children": [
"IPY_MODEL_badd950dde44435293e5622d5b0e396d",
"IPY_MODEL_06756d263dd544278bbfeb886c7796cd"
]
}
},
"8f059203cbcc457dadc9171ae8bf9745": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"state": {
"_view_name": "LayoutView",
"grid_template_rows": null,
"right": null,
"justify_content": null,
"_view_module": "@jupyter-widgets/base",
"overflow": null,
"_model_module_version": "1.2.0",
"_view_count": null,
"flex_flow": null,
"width": null,
"min_width": null,
"border": null,
"align_items": null,
"bottom": null,
"_model_module": "@jupyter-widgets/base",
"top": null,
"grid_column": null,
"overflow_y": null,
"overflow_x": null,
"grid_auto_flow": null,
"grid_area": null,
"grid_template_columns": null,
"flex": null,
"_model_name": "LayoutModel",
"justify_items": null,
"grid_row": null,
"max_height": null,
"align_content": null,
"visibility": null,
"align_self": null,
"height": null,
"min_height": null,
"padding": null,
"grid_auto_rows": null,
"grid_gap": null,
"max_width": null,
"order": null,
"_view_module_version": "1.2.0",
"grid_template_areas": null,
"object_position": null,
"object_fit": null,
"grid_auto_columns": null,
"margin": null,
"display": null,
"left": null
}
},
"badd950dde44435293e5622d5b0e396d": {
"model_module": "@jupyter-widgets/controls",
"model_name": "FloatProgressModel",
"state": {
"_view_name": "ProgressView",
"style": "IPY_MODEL_c89906e177ad4f6583409b7a88043cbc",
"_dom_classes": [],
"description": "Dl Size...: ",
"_model_name": "FloatProgressModel",
"bar_style": "success",
"max": 1,
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"value": 0,
"_view_count": null,
"_view_module_version": "1.5.0",
"orientation": "horizontal",
"min": 0,
"description_tooltip": null,
"_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_715c78d08b124e02933be04ecaca07d7"
}
},
"06756d263dd544278bbfeb886c7796cd": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HTMLModel",
"state": {
"_view_name": "HTMLView",
"style": "IPY_MODEL_287df5b08de848fe916c1ea8617aa93f",
"_dom_classes": [],
"description": "",
"_model_name": "HTMLModel",
"placeholder": "​",
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"value": " 0/0 [00:00<?, ? MiB/s]",
"_view_count": null,
"_view_module_version": "1.5.0",
"description_tooltip": null,
"_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_761e1a4b02b245cd9a5128a0dbc7d7f7"
}
},
"c89906e177ad4f6583409b7a88043cbc": {
"model_module": "@jupyter-widgets/controls",
"model_name": "ProgressStyleModel",
"state": {
"_view_name": "StyleView",
"_model_name": "ProgressStyleModel",
"description_width": "initial",
"_view_module": "@jupyter-widgets/base",
"_model_module_version": "1.5.0",
"_view_count": null,
"_view_module_version": "1.2.0",
"bar_color": null,
"_model_module": "@jupyter-widgets/controls"
}
},
"715c78d08b124e02933be04ecaca07d7": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"state": {
"_view_name": "LayoutView",
"grid_template_rows": null,
"right": null,
"justify_content": null,
"_view_module": "@jupyter-widgets/base",
"overflow": null,
"_model_module_version": "1.2.0",
"_view_count": null,
"flex_flow": null,
"width": null,
"min_width": null,
"border": null,
"align_items": null,
"bottom": null,
"_model_module": "@jupyter-widgets/base",
"top": null,
"grid_column": null,
"overflow_y": null,
"overflow_x": null,
"grid_auto_flow": null,
"grid_area": null,
"grid_template_columns": null,
"flex": null,
"_model_name": "LayoutModel",
"justify_items": null,
"grid_row": null,
"max_height": null,
"align_content": null,
"visibility": null,
"align_self": null,
"height": null,
"min_height": null,
"padding": null,
"grid_auto_rows": null,
"grid_gap": null,
"max_width": null,
"order": null,
"_view_module_version": "1.2.0",
"grid_template_areas": null,
"object_position": null,
"object_fit": null,
"grid_auto_columns": null,
"margin": null,
"display": null,
"left": null
}
},
"287df5b08de848fe916c1ea8617aa93f": {
"model_module": "@jupyter-widgets/controls",
"model_name": "DescriptionStyleModel",
"state": {
"_view_name": "StyleView",
"_model_name": "DescriptionStyleModel",
"description_width": "",
"_view_module": "@jupyter-widgets/base",
"_model_module_version": "1.5.0",
"_view_count": null,
"_view_module_version": "1.2.0",
"_model_module": "@jupyter-widgets/controls"
}
},
"761e1a4b02b245cd9a5128a0dbc7d7f7": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"state": {
"_view_name": "LayoutView",
"grid_template_rows": null,
"right": null,
"justify_content": null,
"_view_module": "@jupyter-widgets/base",
"overflow": null,
"_model_module_version": "1.2.0",
"_view_count": null,
"flex_flow": null,
"width": null,
"min_width": null,
"border": null,
"align_items": null,
"bottom": null,
"_model_module": "@jupyter-widgets/base",
"top": null,
"grid_column": null,
"overflow_y": null,
"overflow_x": null,
"grid_auto_flow": null,
"grid_area": null,
"grid_template_columns": null,
"flex": null,
"_model_name": "LayoutModel",
"justify_items": null,
"grid_row": null,
"max_height": null,
"align_content": null,
"visibility": null,
"align_self": null,
"height": null,
"min_height": null,
"padding": null,
"grid_auto_rows": null,
"grid_gap": null,
"max_width": null,
"order": null,
"_view_module_version": "1.2.0",
"grid_template_areas": null,
"object_position": null,
"object_fit": null,
"grid_auto_columns": null,
"margin": null,
"display": null,
"left": null
}
},
"707d210e5505474b9994ddb2aa3e4b65": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HBoxModel",
"state": {
"_view_name": "HBoxView",
"_dom_classes": [],
"_model_name": "HBoxModel",
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_view_count": null,
"_view_module_version": "1.5.0",
"box_style": "",
"layout": "IPY_MODEL_a1e7697a216d49efaee31b0b626262c2",
"_model_module": "@jupyter-widgets/controls",
"children": [
"IPY_MODEL_731be0cbeabc405db6b9ff1bf4042da0",
"IPY_MODEL_11b1d290abdc4a8daf55ad061b442eb7"
]
}
},
"a1e7697a216d49efaee31b0b626262c2": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"state": {
"_view_name": "LayoutView",
"grid_template_rows": null,
"right": null,
"justify_content": null,
"_view_module": "@jupyter-widgets/base",
"overflow": null,
"_model_module_version": "1.2.0",
"_view_count": null,
"flex_flow": null,
"width": null,
"min_width": null,
"border": null,
"align_items": null,
"bottom": null,
"_model_module": "@jupyter-widgets/base",
"top": null,
"grid_column": null,
"overflow_y": null,
"overflow_x": null,
"grid_auto_flow": null,
"grid_area": null,
"grid_template_columns": null,
"flex": null,
"_model_name": "LayoutModel",
"justify_items": null,
"grid_row": null,
"max_height": null,
"align_content": null,
"visibility": null,
"align_self": null,
"height": null,
"min_height": null,
"padding": null,
"grid_auto_rows": null,
"grid_gap": null,
"max_width": null,
"order": null,
"_view_module_version": "1.2.0",
"grid_template_areas": null,
"object_position": null,
"object_fit": null,
"grid_auto_columns": null,
"margin": null,
"display": null,
"left": null
}
},
"731be0cbeabc405db6b9ff1bf4042da0": {
"model_module": "@jupyter-widgets/controls",
"model_name": "FloatProgressModel",
"state": {
"_view_name": "ProgressView",
"style": "IPY_MODEL_8d8f14ed642a42dfaa5e087dd72dff01",
"_dom_classes": [],
"description": "",
"_model_name": "FloatProgressModel",
"bar_style": "info",
"max": 1,
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"value": 1,
"_view_count": null,
"_view_module_version": "1.5.0",
"orientation": "horizontal",
"min": 0,
"description_tooltip": null,
"_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_dd615ea054cc457eac995f5bf4a749c5"
}
},
"11b1d290abdc4a8daf55ad061b442eb7": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HTMLModel",
"state": {
"_view_name": "HTMLView",
"style": "IPY_MODEL_70867a9731a34f33a04e0cea29bf31f2",
"_dom_classes": [],
"description": "",
"_model_name": "HTMLModel",
"placeholder": "​",
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"value": " 3668/0 [00:01<00:00, 2686.17 examples/s]",
"_view_count": null,
"_view_module_version": "1.5.0",
"description_tooltip": null,
"_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_49ea6178eb75448a9d92d664c7207150"
}
},
"8d8f14ed642a42dfaa5e087dd72dff01": {
"model_module": "@jupyter-widgets/controls",
"model_name": "ProgressStyleModel",
"state": {
"_view_name": "StyleView",
"_model_name": "ProgressStyleModel",
"description_width": "initial",
"_view_module": "@jupyter-widgets/base",
"_model_module_version": "1.5.0",
"_view_count": null,
"_view_module_version": "1.2.0",
"bar_color": null,
"_model_module": "@jupyter-widgets/controls"
}
},
"dd615ea054cc457eac995f5bf4a749c5": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"state": {
"_view_name": "LayoutView",
"grid_template_rows": null,
"right": null,
"justify_content": null,
"_view_module": "@jupyter-widgets/base",
"overflow": null,
"_model_module_version": "1.2.0",
"_view_count": null,
"flex_flow": null,
"width": null,
"min_width": null,
"border": null,
"align_items": null,
"bottom": null,
"_model_module": "@jupyter-widgets/base",
"top": null,
"grid_column": null,
"overflow_y": null,
"overflow_x": null,
"grid_auto_flow": null,
"grid_area": null,
"grid_template_columns": null,
"flex": null,
"_model_name": "LayoutModel",
"justify_items": null,
"grid_row": null,
"max_height": null,
"align_content": null,
"visibility": null,
"align_self": null,
"height": null,
"min_height": null,
"padding": null,
"grid_auto_rows": null,
"grid_gap": null,
"max_width": null,
"order": null,
"_view_module_version": "1.2.0",
"grid_template_areas": null,
"object_position": null,
"object_fit": null,
"grid_auto_columns": null,
"margin": null,
"display": null,
"left": null
}
},
"70867a9731a34f33a04e0cea29bf31f2": {
"model_module": "@jupyter-widgets/controls",
"model_name": "DescriptionStyleModel",
"state": {
"_view_name": "StyleView",
"_model_name": "DescriptionStyleModel",
"description_width": "",
"_view_module": "@jupyter-widgets/base",
"_model_module_version": "1.5.0",
"_view_count": null,
"_view_module_version": "1.2.0",
"_model_module": "@jupyter-widgets/controls"
}
},
"49ea6178eb75448a9d92d664c7207150": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"state": {
"_view_name": "LayoutView",
"grid_template_rows": null,
"right": null,
"justify_content": null,
"_view_module": "@jupyter-widgets/base",
"overflow": null,
"_model_module_version": "1.2.0",
"_view_count": null,
"flex_flow": null,
"width": null,
"min_width": null,
"border": null,
"align_items": null,
"bottom": null,
"_model_module": "@jupyter-widgets/base",
"top": null,
"grid_column": null,
"overflow_y": null,
"overflow_x": null,
"grid_auto_flow": null,
"grid_area": null,
"grid_template_columns": null,
"flex": null,
"_model_name": "LayoutModel",
"justify_items": null,
"grid_row": null,
"max_height": null,
"align_content": null,
"visibility": null,
"align_self": null,
"height": null,
"min_height": null,
"padding": null,
"grid_auto_rows": null,
"grid_gap": null,
"max_width": null,
"order": null,
"_view_module_version": "1.2.0",
"grid_template_areas": null,
"object_position": null,
"object_fit": null,
"grid_auto_columns": null,
"margin": null,
"display": null,
"left": null
}
},
"0d210dc6092a42fabff575536a383941": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HBoxModel",
"state": {
"_view_name": "HBoxView",
"_dom_classes": [],
"_model_name": "HBoxModel",
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_view_count": null,
"_view_module_version": "1.5.0",
"box_style": "",
"layout": "IPY_MODEL_207c6b19d87e41e2a3e4f6f4341884c1",
"_model_module": "@jupyter-widgets/controls",
"children": [
"IPY_MODEL_f202dabd4b384625ac5ea838bf964179",
"IPY_MODEL_861900417e0d48dca0bf35348ecfac71"
]
}
},
"207c6b19d87e41e2a3e4f6f4341884c1": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"state": {
"_view_name": "LayoutView",
"grid_template_rows": null,
"right": null,
"justify_content": null,
"_view_module": "@jupyter-widgets/base",
"overflow": null,
"_model_module_version": "1.2.0",
"_view_count": null,
"flex_flow": null,
"width": null,
"min_width": null,
"border": null,
"align_items": null,
"bottom": null,
"_model_module": "@jupyter-widgets/base",
"top": null,
"grid_column": null,
"overflow_y": null,
"overflow_x": null,
"grid_auto_flow": null,
"grid_area": null,
"grid_template_columns": null,
"flex": null,
"_model_name": "LayoutModel",
"justify_items": null,
"grid_row": null,
"max_height": null,
"align_content": null,
"visibility": null,
"align_self": null,
"height": null,
"min_height": null,
"padding": null,
"grid_auto_rows": null,
"grid_gap": null,
"max_width": null,
"order": null,
"_view_module_version": "1.2.0",
"grid_template_areas": null,
"object_position": null,
"object_fit": null,
"grid_auto_columns": null,
"margin": null,
"display": null,
"left": null
}
},
"f202dabd4b384625ac5ea838bf964179": {
"model_module": "@jupyter-widgets/controls",
"model_name": "FloatProgressModel",
"state": {
"_view_name": "ProgressView",
"style": "IPY_MODEL_162ab1fd123a45f585deb18a769e8c3e",
"_dom_classes": [],
"description": " 0%",
"_model_name": "FloatProgressModel",
"bar_style": "danger",
"max": 3668,
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"value": 0,
"_view_count": null,
"_view_module_version": "1.5.0",
"orientation": "horizontal",
"min": 0,
"description_tooltip": null,
"_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_77df42d116674420872e77d7a03b1bda"
}
},
"861900417e0d48dca0bf35348ecfac71": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HTMLModel",
"state": {
"_view_name": "HTMLView",
"style": "IPY_MODEL_50ba1095c78b401cbc37f2905842dba8",
"_dom_classes": [],
"description": "",
"_model_name": "HTMLModel",
"placeholder": "​",
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"value": " 0/3668 [00:00<?, ? examples/s]",
"_view_count": null,
"_view_module_version": "1.5.0",
"description_tooltip": null,
"_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_ea12c48a45de425bbeb9593bd194e274"
}
},
"162ab1fd123a45f585deb18a769e8c3e": {
"model_module": "@jupyter-widgets/controls",
"model_name": "ProgressStyleModel",
"state": {
"_view_name": "StyleView",
"_model_name": "ProgressStyleModel",
"description_width": "initial",
"_view_module": "@jupyter-widgets/base",
"_model_module_version": "1.5.0",
"_view_count": null,
"_view_module_version": "1.2.0",
"bar_color": null,
"_model_module": "@jupyter-widgets/controls"
}
},
"77df42d116674420872e77d7a03b1bda": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"state": {
"_view_name": "LayoutView",
"grid_template_rows": null,
"right": null,
"justify_content": null,
"_view_module": "@jupyter-widgets/base",
"overflow": null,
"_model_module_version": "1.2.0",
"_view_count": null,
"flex_flow": null,
"width": null,
"min_width": null,
"border": null,
"align_items": null,
"bottom": null,
"_model_module": "@jupyter-widgets/base",
"top": null,
"grid_column": null,
"overflow_y": null,
"overflow_x": null,
"grid_auto_flow": null,
"grid_area": null,
"grid_template_columns": null,
"flex": null,
"_model_name": "LayoutModel",
"justify_items": null,
"grid_row": null,
"max_height": null,
"align_content": null,
"visibility": null,
"align_self": null,
"height": null,
"min_height": null,
"padding": null,
"grid_auto_rows": null,
"grid_gap": null,
"max_width": null,
"order": null,
"_view_module_version": "1.2.0",
"grid_template_areas": null,
"object_position": null,
"object_fit": null,
"grid_auto_columns": null,
"margin": null,
"display": null,
"left": null
}
},
"50ba1095c78b401cbc37f2905842dba8": {
"model_module": "@jupyter-widgets/controls",
"model_name": "DescriptionStyleModel",
"state": {
"_view_name": "StyleView",
"_model_name": "DescriptionStyleModel",
"description_width": "",
"_view_module": "@jupyter-widgets/base",
"_model_module_version": "1.5.0",
"_view_count": null,
"_view_module_version": "1.2.0",
"_model_module": "@jupyter-widgets/controls"
}
},
"ea12c48a45de425bbeb9593bd194e274": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"state": {
"_view_name": "LayoutView",
"grid_template_rows": null,
"right": null,
"justify_content": null,
"_view_module": "@jupyter-widgets/base",
"overflow": null,
"_model_module_version": "1.2.0",
"_view_count": null,
"flex_flow": null,
"width": null,
"min_width": null,
"border": null,
"align_items": null,
"bottom": null,
"_model_module": "@jupyter-widgets/base",
"top": null,
"grid_column": null,
"overflow_y": null,
"overflow_x": null,
"grid_auto_flow": null,
"grid_area": null,
"grid_template_columns": null,
"flex": null,
"_model_name": "LayoutModel",
"justify_items": null,
"grid_row": null,
"max_height": null,
"align_content": null,
"visibility": null,
"align_self": null,
"height": null,
"min_height": null,
"padding": null,
"grid_auto_rows": null,
"grid_gap": null,
"max_width": null,
"order": null,
"_view_module_version": "1.2.0",
"grid_template_areas": null,
"object_position": null,
"object_fit": null,
"grid_auto_columns": null,
"margin": null,
"display": null,
"left": null
}
},
"dcdb5006adc5492eab470930b6335d47": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HBoxModel",
"state": {
"_view_name": "HBoxView",
"_dom_classes": [],
"_model_name": "HBoxModel",
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_view_count": null,
"_view_module_version": "1.5.0",
"box_style": "",
"layout": "IPY_MODEL_348b5f70c320488f962c46be9022613d",
"_model_module": "@jupyter-widgets/controls",
"children": [
"IPY_MODEL_427a293f14eb4f3f9288eead101725ac",
"IPY_MODEL_ef1ad9afff504fa1ace8ad5f7b979235"
]
}
},
"348b5f70c320488f962c46be9022613d": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"state": {
"_view_name": "LayoutView",
"grid_template_rows": null,
"right": null,
"justify_content": null,
"_view_module": "@jupyter-widgets/base",
"overflow": null,
"_model_module_version": "1.2.0",
"_view_count": null,
"flex_flow": null,
"width": null,
"min_width": null,
"border": null,
"align_items": null,
"bottom": null,
"_model_module": "@jupyter-widgets/base",
"top": null,
"grid_column": null,
"overflow_y": null,
"overflow_x": null,
"grid_auto_flow": null,
"grid_area": null,
"grid_template_columns": null,
"flex": null,
"_model_name": "LayoutModel",
"justify_items": null,
"grid_row": null,
"max_height": null,
"align_content": null,
"visibility": null,
"align_self": null,
"height": null,
"min_height": null,
"padding": null,
"grid_auto_rows": null,
"grid_gap": null,
"max_width": null,
"order": null,
"_view_module_version": "1.2.0",
"grid_template_areas": null,
"object_position": null,
"object_fit": null,
"grid_auto_columns": null,
"margin": null,
"display": null,
"left": null
}
},
"427a293f14eb4f3f9288eead101725ac": {
"model_module": "@jupyter-widgets/controls",
"model_name": "FloatProgressModel",
"state": {
"_view_name": "ProgressView",
"style": "IPY_MODEL_a5b85dc847ad448589b0b4516aba6c8e",
"_dom_classes": [],
"description": "",
"_model_name": "FloatProgressModel",
"bar_style": "info",
"max": 1,
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"value": 1,
"_view_count": null,
"_view_module_version": "1.5.0",
"orientation": "horizontal",
"min": 0,
"description_tooltip": null,
"_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_6ccc0bc5da8b46e9a685b7dd8e818af9"
}
},
"ef1ad9afff504fa1ace8ad5f7b979235": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HTMLModel",
"state": {
"_view_name": "HTMLView",
"style": "IPY_MODEL_8fef9f4c593d4a92b80849d9a3750abf",
"_dom_classes": [],
"description": "",
"_model_name": "HTMLModel",
"placeholder": "​",
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"value": " 408/0 [00:00<00:00, 1241.75 examples/s]",
"_view_count": null,
"_view_module_version": "1.5.0",
"description_tooltip": null,
"_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_09dd4f7d4ca540368b875f8dba8d2c53"
}
},
"a5b85dc847ad448589b0b4516aba6c8e": {
"model_module": "@jupyter-widgets/controls",
"model_name": "ProgressStyleModel",
"state": {
"_view_name": "StyleView",
"_model_name": "ProgressStyleModel",
"description_width": "initial",
"_view_module": "@jupyter-widgets/base",
"_model_module_version": "1.5.0",
"_view_count": null,
"_view_module_version": "1.2.0",
"bar_color": null,
"_model_module": "@jupyter-widgets/controls"
}
},
"6ccc0bc5da8b46e9a685b7dd8e818af9": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"state": {
"_view_name": "LayoutView",
"grid_template_rows": null,
"right": null,
"justify_content": null,
"_view_module": "@jupyter-widgets/base",
"overflow": null,
"_model_module_version": "1.2.0",
"_view_count": null,
"flex_flow": null,
"width": null,
"min_width": null,
"border": null,
"align_items": null,
"bottom": null,
"_model_module": "@jupyter-widgets/base",
"top": null,
"grid_column": null,
"overflow_y": null,
"overflow_x": null,
"grid_auto_flow": null,
"grid_area": null,
"grid_template_columns": null,
"flex": null,
"_model_name": "LayoutModel",
"justify_items": null,
"grid_row": null,
"max_height": null,
"align_content": null,
"visibility": null,
"align_self": null,
"height": null,
"min_height": null,
"padding": null,
"grid_auto_rows": null,
"grid_gap": null,
"max_width": null,
"order": null,
"_view_module_version": "1.2.0",
"grid_template_areas": null,
"object_position": null,
"object_fit": null,
"grid_auto_columns": null,
"margin": null,
"display": null,
"left": null
}
},
"8fef9f4c593d4a92b80849d9a3750abf": {
"model_module": "@jupyter-widgets/controls",
"model_name": "DescriptionStyleModel",
"state": {
"_view_name": "StyleView",
"_model_name": "DescriptionStyleModel",
"description_width": "",
"_view_module": "@jupyter-widgets/base",
"_model_module_version": "1.5.0",
"_view_count": null,
"_view_module_version": "1.2.0",
"_model_module": "@jupyter-widgets/controls"
}
},
"09dd4f7d4ca540368b875f8dba8d2c53": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"state": {
"_view_name": "LayoutView",
"grid_template_rows": null,
"right": null,
"justify_content": null,
"_view_module": "@jupyter-widgets/base",
"overflow": null,
"_model_module_version": "1.2.0",
"_view_count": null,
"flex_flow": null,
"width": null,
"min_width": null,
"border": null,
"align_items": null,
"bottom": null,
"_model_module": "@jupyter-widgets/base",
"top": null,
"grid_column": null,
"overflow_y": null,
"overflow_x": null,
"grid_auto_flow": null,
"grid_area": null,
"grid_template_columns": null,
"flex": null,
"_model_name": "LayoutModel",
"justify_items": null,
"grid_row": null,
"max_height": null,
"align_content": null,
"visibility": null,
"align_self": null,
"height": null,
"min_height": null,
"padding": null,
"grid_auto_rows": null,
"grid_gap": null,
"max_width": null,
"order": null,
"_view_module_version": "1.2.0",
"grid_template_areas": null,
"object_position": null,
"object_fit": null,
"grid_auto_columns": null,
"margin": null,
"display": null,
"left": null
}
},
"99b14b614f204e85a3d681bcec8c45e0": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HBoxModel",
"state": {
"_view_name": "HBoxView",
"_dom_classes": [],
"_model_name": "HBoxModel",
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_view_count": null,
"_view_module_version": "1.5.0",
"box_style": "",
"layout": "IPY_MODEL_bb0e8493062d4196820ef3dc8769083f",
"_model_module": "@jupyter-widgets/controls",
"children": [
"IPY_MODEL_8e2ebc2036934f9a9182dec1caddfc19",
"IPY_MODEL_ab15b7ff1edd433c895b608f5447a49b"
]
}
},
"bb0e8493062d4196820ef3dc8769083f": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"state": {
"_view_name": "LayoutView",
"grid_template_rows": null,
"right": null,
"justify_content": null,
"_view_module": "@jupyter-widgets/base",
"overflow": null,
"_model_module_version": "1.2.0",
"_view_count": null,
"flex_flow": null,
"width": null,
"min_width": null,
"border": null,
"align_items": null,
"bottom": null,
"_model_module": "@jupyter-widgets/base",
"top": null,
"grid_column": null,
"overflow_y": null,
"overflow_x": null,
"grid_auto_flow": null,
"grid_area": null,
"grid_template_columns": null,
"flex": null,
"_model_name": "LayoutModel",
"justify_items": null,
"grid_row": null,
"max_height": null,
"align_content": null,
"visibility": null,
"align_self": null,
"height": null,
"min_height": null,
"padding": null,
"grid_auto_rows": null,
"grid_gap": null,
"max_width": null,
"order": null,
"_view_module_version": "1.2.0",
"grid_template_areas": null,
"object_position": null,
"object_fit": null,
"grid_auto_columns": null,
"margin": null,
"display": null,
"left": null
}
},
"8e2ebc2036934f9a9182dec1caddfc19": {
"model_module": "@jupyter-widgets/controls",
"model_name": "FloatProgressModel",
"state": {
"_view_name": "ProgressView",
"style": "IPY_MODEL_5c6967e75c92456fa566e13880a084d0",
"_dom_classes": [],
"description": " 0%",
"_model_name": "FloatProgressModel",
"bar_style": "danger",
"max": 408,
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"value": 0,
"_view_count": null,
"_view_module_version": "1.5.0",
"orientation": "horizontal",
"min": 0,
"description_tooltip": null,
"_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_66ee871010784e6391d4bca3f5acb2dd"
}
},
"ab15b7ff1edd433c895b608f5447a49b": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HTMLModel",
"state": {
"_view_name": "HTMLView",
"style": "IPY_MODEL_128807925cdd47f6b39c6578666d93a8",
"_dom_classes": [],
"description": "",
"_model_name": "HTMLModel",
"placeholder": "​",
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"value": " 0/408 [00:00<?, ? examples/s]",
"_view_count": null,
"_view_module_version": "1.5.0",
"description_tooltip": null,
"_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_130678ed546441338166dc934e88e1f7"
}
},
"5c6967e75c92456fa566e13880a084d0": {
"model_module": "@jupyter-widgets/controls",
"model_name": "ProgressStyleModel",
"state": {
"_view_name": "StyleView",
"_model_name": "ProgressStyleModel",
"description_width": "initial",
"_view_module": "@jupyter-widgets/base",
"_model_module_version": "1.5.0",
"_view_count": null,
"_view_module_version": "1.2.0",
"bar_color": null,
"_model_module": "@jupyter-widgets/controls"
}
},
"66ee871010784e6391d4bca3f5acb2dd": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"state": {
"_view_name": "LayoutView",
"grid_template_rows": null,
"right": null,
"justify_content": null,
"_view_module": "@jupyter-widgets/base",
"overflow": null,
"_model_module_version": "1.2.0",
"_view_count": null,
"flex_flow": null,
"width": null,
"min_width": null,
"border": null,
"align_items": null,
"bottom": null,
"_model_module": "@jupyter-widgets/base",
"top": null,
"grid_column": null,
"overflow_y": null,
"overflow_x": null,
"grid_auto_flow": null,
"grid_area": null,
"grid_template_columns": null,
"flex": null,
"_model_name": "LayoutModel",
"justify_items": null,
"grid_row": null,
"max_height": null,
"align_content": null,
"visibility": null,
"align_self": null,
"height": null,
"min_height": null,
"padding": null,
"grid_auto_rows": null,
"grid_gap": null,
"max_width": null,
"order": null,
"_view_module_version": "1.2.0",
"grid_template_areas": null,
"object_position": null,
"object_fit": null,
"grid_auto_columns": null,
"margin": null,
"display": null,
"left": null
}
},
"128807925cdd47f6b39c6578666d93a8": {
"model_module": "@jupyter-widgets/controls",
"model_name": "DescriptionStyleModel",
"state": {
"_view_name": "StyleView",
"_model_name": "DescriptionStyleModel",
"description_width": "",
"_view_module": "@jupyter-widgets/base",
"_model_module_version": "1.5.0",
"_view_count": null,
"_view_module_version": "1.2.0",
"_model_module": "@jupyter-widgets/controls"
}
},
"130678ed546441338166dc934e88e1f7": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"state": {
"_view_name": "LayoutView",
"grid_template_rows": null,
"right": null,
"justify_content": null,
"_view_module": "@jupyter-widgets/base",
"overflow": null,
"_model_module_version": "1.2.0",
"_view_count": null,
"flex_flow": null,
"width": null,
"min_width": null,
"border": null,
"align_items": null,
"bottom": null,
"_model_module": "@jupyter-widgets/base",
"top": null,
"grid_column": null,
"overflow_y": null,
"overflow_x": null,
"grid_auto_flow": null,
"grid_area": null,
"grid_template_columns": null,
"flex": null,
"_model_name": "LayoutModel",
"justify_items": null,
"grid_row": null,
"max_height": null,
"align_content": null,
"visibility": null,
"align_self": null,
"height": null,
"min_height": null,
"padding": null,
"grid_auto_rows": null,
"grid_gap": null,
"max_width": null,
"order": null,
"_view_module_version": "1.2.0",
"grid_template_areas": null,
"object_position": null,
"object_fit": null,
"grid_auto_columns": null,
"margin": null,
"display": null,
"left": null
}
},
"43d3c73f5c9c4614a81603ec7323bd85": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HBoxModel",
"state": {
"_view_name": "HBoxView",
"_dom_classes": [],
"_model_name": "HBoxModel",
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_view_count": null,
"_view_module_version": "1.5.0",
"box_style": "",
"layout": "IPY_MODEL_69fc9fb8ceb24c8a97b45b9503bf4434",
"_model_module": "@jupyter-widgets/controls",
"children": [
"IPY_MODEL_d5cf0e1256d242eca09f81eed933a8dd",
"IPY_MODEL_2c3922e6ec73417389af92c37fabf608"
]
}
},
"69fc9fb8ceb24c8a97b45b9503bf4434": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"state": {
"_view_name": "LayoutView",
"grid_template_rows": null,
"right": null,
"justify_content": null,
"_view_module": "@jupyter-widgets/base",
"overflow": null,
"_model_module_version": "1.2.0",
"_view_count": null,
"flex_flow": null,
"width": null,
"min_width": null,
"border": null,
"align_items": null,
"bottom": null,
"_model_module": "@jupyter-widgets/base",
"top": null,
"grid_column": null,
"overflow_y": null,
"overflow_x": null,
"grid_auto_flow": null,
"grid_area": null,
"grid_template_columns": null,
"flex": null,
"_model_name": "LayoutModel",
"justify_items": null,
"grid_row": null,
"max_height": null,
"align_content": null,
"visibility": null,
"align_self": null,
"height": null,
"min_height": null,
"padding": null,
"grid_auto_rows": null,
"grid_gap": null,
"max_width": null,
"order": null,
"_view_module_version": "1.2.0",
"grid_template_areas": null,
"object_position": null,
"object_fit": null,
"grid_auto_columns": null,
"margin": null,
"display": null,
"left": null
}
},
"d5cf0e1256d242eca09f81eed933a8dd": {
"model_module": "@jupyter-widgets/controls",
"model_name": "FloatProgressModel",
"state": {
"_view_name": "ProgressView",
"style": "IPY_MODEL_ee09284a5627447faaf6492b0b00762b",
"_dom_classes": [],
"description": "",
"_model_name": "FloatProgressModel",
"bar_style": "info",
"max": 1,
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"value": 1,
"_view_count": null,
"_view_module_version": "1.5.0",
"orientation": "horizontal",
"min": 0,
"description_tooltip": null,
"_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_9e83f236d6384645957b24808c62e605"
}
},
"2c3922e6ec73417389af92c37fabf608": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HTMLModel",
"state": {
"_view_name": "HTMLView",
"style": "IPY_MODEL_d4d3949283b34f7da5e481979d6c1cc2",
"_dom_classes": [],
"description": "",
"_model_name": "HTMLModel",
"placeholder": "​",
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"value": " 1725/0 [00:00<00:00, 2361.88 examples/s]",
"_view_count": null,
"_view_module_version": "1.5.0",
"description_tooltip": null,
"_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_e6e159a79a444ec68b5379254735b94a"
}
},
"ee09284a5627447faaf6492b0b00762b": {
"model_module": "@jupyter-widgets/controls",
"model_name": "ProgressStyleModel",
"state": {
"_view_name": "StyleView",
"_model_name": "ProgressStyleModel",
"description_width": "initial",
"_view_module": "@jupyter-widgets/base",
"_model_module_version": "1.5.0",
"_view_count": null,
"_view_module_version": "1.2.0",
"bar_color": null,
"_model_module": "@jupyter-widgets/controls"
}
},
"9e83f236d6384645957b24808c62e605": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"state": {
"_view_name": "LayoutView",
"grid_template_rows": null,
"right": null,
"justify_content": null,
"_view_module": "@jupyter-widgets/base",
"overflow": null,
"_model_module_version": "1.2.0",
"_view_count": null,
"flex_flow": null,
"width": null,
"min_width": null,
"border": null,
"align_items": null,
"bottom": null,
"_model_module": "@jupyter-widgets/base",
"top": null,
"grid_column": null,
"overflow_y": null,
"overflow_x": null,
"grid_auto_flow": null,
"grid_area": null,
"grid_template_columns": null,
"flex": null,
"_model_name": "LayoutModel",
"justify_items": null,
"grid_row": null,
"max_height": null,
"align_content": null,
"visibility": null,
"align_self": null,
"height": null,
"min_height": null,
"padding": null,
"grid_auto_rows": null,
"grid_gap": null,
"max_width": null,
"order": null,
"_view_module_version": "1.2.0",
"grid_template_areas": null,
"object_position": null,
"object_fit": null,
"grid_auto_columns": null,
"margin": null,
"display": null,
"left": null
}
},
"d4d3949283b34f7da5e481979d6c1cc2": {
"model_module": "@jupyter-widgets/controls",
"model_name": "DescriptionStyleModel",
"state": {
"_view_name": "StyleView",
"_model_name": "DescriptionStyleModel",
"description_width": "",
"_view_module": "@jupyter-widgets/base",
"_model_module_version": "1.5.0",
"_view_count": null,
"_view_module_version": "1.2.0",
"_model_module": "@jupyter-widgets/controls"
}
},
"e6e159a79a444ec68b5379254735b94a": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"state": {
"_view_name": "LayoutView",
"grid_template_rows": null,
"right": null,
"justify_content": null,
"_view_module": "@jupyter-widgets/base",
"overflow": null,
"_model_module_version": "1.2.0",
"_view_count": null,
"flex_flow": null,
"width": null,
"min_width": null,
"border": null,
"align_items": null,
"bottom": null,
"_model_module": "@jupyter-widgets/base",
"top": null,
"grid_column": null,
"overflow_y": null,
"overflow_x": null,
"grid_auto_flow": null,
"grid_area": null,
"grid_template_columns": null,
"flex": null,
"_model_name": "LayoutModel",
"justify_items": null,
"grid_row": null,
"max_height": null,
"align_content": null,
"visibility": null,
"align_self": null,
"height": null,
"min_height": null,
"padding": null,
"grid_auto_rows": null,
"grid_gap": null,
"max_width": null,
"order": null,
"_view_module_version": "1.2.0",
"grid_template_areas": null,
"object_position": null,
"object_fit": null,
"grid_auto_columns": null,
"margin": null,
"display": null,
"left": null
}
},
"7758bd45630e4eae88bf47c34055de38": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HBoxModel",
"state": {
"_view_name": "HBoxView",
"_dom_classes": [],
"_model_name": "HBoxModel",
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_view_count": null,
"_view_module_version": "1.5.0",
"box_style": "",
"layout": "IPY_MODEL_eb0be74ff1074bf4ada0e5dcd84702b5",
"_model_module": "@jupyter-widgets/controls",
"children": [
"IPY_MODEL_121bb541fc7c428dada37201862d47ce",
"IPY_MODEL_98582bcc3b3c494798e1a0e500c2e9d1"
]
}
},
"eb0be74ff1074bf4ada0e5dcd84702b5": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"state": {
"_view_name": "LayoutView",
"grid_template_rows": null,
"right": null,
"justify_content": null,
"_view_module": "@jupyter-widgets/base",
"overflow": null,
"_model_module_version": "1.2.0",
"_view_count": null,
"flex_flow": null,
"width": null,
"min_width": null,
"border": null,
"align_items": null,
"bottom": null,
"_model_module": "@jupyter-widgets/base",
"top": null,
"grid_column": null,
"overflow_y": null,
"overflow_x": null,
"grid_auto_flow": null,
"grid_area": null,
"grid_template_columns": null,
"flex": null,
"_model_name": "LayoutModel",
"justify_items": null,
"grid_row": null,
"max_height": null,
"align_content": null,
"visibility": null,
"align_self": null,
"height": null,
"min_height": null,
"padding": null,
"grid_auto_rows": null,
"grid_gap": null,
"max_width": null,
"order": null,
"_view_module_version": "1.2.0",
"grid_template_areas": null,
"object_position": null,
"object_fit": null,
"grid_auto_columns": null,
"margin": null,
"display": null,
"left": null
}
},
"121bb541fc7c428dada37201862d47ce": {
"model_module": "@jupyter-widgets/controls",
"model_name": "FloatProgressModel",
"state": {
"_view_name": "ProgressView",
"style": "IPY_MODEL_d8dd89c4e7704104b314898991c84ce7",
"_dom_classes": [],
"description": " 0%",
"_model_name": "FloatProgressModel",
"bar_style": "danger",
"max": 1725,
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"value": 0,
"_view_count": null,
"_view_module_version": "1.5.0",
"orientation": "horizontal",
"min": 0,
"description_tooltip": null,
"_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_f05d20bfb0fd474ab2683d3f3e52e1af"
}
},
"98582bcc3b3c494798e1a0e500c2e9d1": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HTMLModel",
"state": {
"_view_name": "HTMLView",
"style": "IPY_MODEL_0f83922a7c55458dbc083cc527bb2015",
"_dom_classes": [],
"description": "",
"_model_name": "HTMLModel",
"placeholder": "​",
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"value": " 0/1725 [00:02<?, ? examples/s]",
"_view_count": null,
"_view_module_version": "1.5.0",
"description_tooltip": null,
"_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_33a7d10888a8433dad7b64621bf0e5b1"
}
},
"d8dd89c4e7704104b314898991c84ce7": {
"model_module": "@jupyter-widgets/controls",
"model_name": "ProgressStyleModel",
"state": {
"_view_name": "StyleView",
"_model_name": "ProgressStyleModel",
"description_width": "initial",
"_view_module": "@jupyter-widgets/base",
"_model_module_version": "1.5.0",
"_view_count": null,
"_view_module_version": "1.2.0",
"bar_color": null,
"_model_module": "@jupyter-widgets/controls"
}
},
"f05d20bfb0fd474ab2683d3f3e52e1af": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"state": {
"_view_name": "LayoutView",
"grid_template_rows": null,
"right": null,
"justify_content": null,
"_view_module": "@jupyter-widgets/base",
"overflow": null,
"_model_module_version": "1.2.0",
"_view_count": null,
"flex_flow": null,
"width": null,
"min_width": null,
"border": null,
"align_items": null,
"bottom": null,
"_model_module": "@jupyter-widgets/base",
"top": null,
"grid_column": null,
"overflow_y": null,
"overflow_x": null,
"grid_auto_flow": null,
"grid_area": null,
"grid_template_columns": null,
"flex": null,
"_model_name": "LayoutModel",
"justify_items": null,
"grid_row": null,
"max_height": null,
"align_content": null,
"visibility": null,
"align_self": null,
"height": null,
"min_height": null,
"padding": null,
"grid_auto_rows": null,
"grid_gap": null,
"max_width": null,
"order": null,
"_view_module_version": "1.2.0",
"grid_template_areas": null,
"object_position": null,
"object_fit": null,
"grid_auto_columns": null,
"margin": null,
"display": null,
"left": null
}
},
"0f83922a7c55458dbc083cc527bb2015": {
"model_module": "@jupyter-widgets/controls",
"model_name": "DescriptionStyleModel",
"state": {
"_view_name": "StyleView",
"_model_name": "DescriptionStyleModel",
"description_width": "",
"_view_module": "@jupyter-widgets/base",
"_model_module_version": "1.5.0",
"_view_count": null,
"_view_module_version": "1.2.0",
"_model_module": "@jupyter-widgets/controls"
}
},
"33a7d10888a8433dad7b64621bf0e5b1": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"state": {
"_view_name": "LayoutView",
"grid_template_rows": null,
"right": null,
"justify_content": null,
"_view_module": "@jupyter-widgets/base",
"overflow": null,
"_model_module_version": "1.2.0",
"_view_count": null,
"flex_flow": null,
"width": null,
"min_width": null,
"border": null,
"align_items": null,
"bottom": null,
"_model_module": "@jupyter-widgets/base",
"top": null,
"grid_column": null,
"overflow_y": null,
"overflow_x": null,
"grid_auto_flow": null,
"grid_area": null,
"grid_template_columns": null,
"flex": null,
"_model_name": "LayoutModel",
"justify_items": null,
"grid_row": null,
"max_height": null,
"align_content": null,
"visibility": null,
"align_self": null,
"height": null,
"min_height": null,
"padding": null,
"grid_auto_rows": null,
"grid_gap": null,
"max_width": null,
"order": null,
"_view_module_version": "1.2.0",
"grid_template_areas": null,
"object_position": null,
"object_fit": null,
"grid_auto_columns": null,
"margin": null,
"display": null,
"left": null
}
}
}
}
},
"cells": [ "cells": [
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": { "metadata": {
"id": "YN2ACivEPxgD", "colab_type": "text",
"colab_type": "text" "id": "YN2ACivEPxgD"
}, },
"source": [ "source": [
"## How-to Guide: Using a PIP package for fine-tuning a BERT model\n", "## How-to Guide: Using a PIP package for fine-tuning a BERT model\n",
...@@ -1996,8 +17,8 @@ ...@@ -1996,8 +17,8 @@
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": { "metadata": {
"id": "T7BBEc1-RNCQ", "colab_type": "text",
"colab_type": "text" "id": "T7BBEc1-RNCQ"
}, },
"source": [ "source": [
"## License\n", "## License\n",
...@@ -2020,8 +41,8 @@ ...@@ -2020,8 +41,8 @@
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": { "metadata": {
"id": "Pf6xzoKjywY_", "colab_type": "text",
"colab_type": "text" "id": "Pf6xzoKjywY_"
}, },
"source": [ "source": [
"## Learning objectives\n", "## Learning objectives\n",
...@@ -2032,8 +53,8 @@ ...@@ -2032,8 +53,8 @@
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": { "metadata": {
"id": "YHkmV89jRWkS", "colab_type": "text",
"colab_type": "text" "id": "YHkmV89jRWkS"
}, },
"source": [ "source": [
"## Enable the GPU acceleration\n", "## Enable the GPU acceleration\n",
...@@ -2046,8 +67,8 @@ ...@@ -2046,8 +67,8 @@
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": { "metadata": {
"id": "s2d9S2CSSO1z", "colab_type": "text",
"colab_type": "text" "id": "s2d9S2CSSO1z"
}, },
"source": [ "source": [
"##Install and import" "##Install and import"
...@@ -2056,149 +77,34 @@ ...@@ -2056,149 +77,34 @@
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": { "metadata": {
"id": "fsACVQpVSifi", "colab_type": "text",
"colab_type": "text" "id": "fsACVQpVSifi"
}, },
"source": [ "source": [
"### Install the TensorFlow Model Garden pip package\n", "### Install the TensorFlow Model Garden pip package\n",
"\n", "\n",
"* tf-models-nightly is the nightly Model Garden package created daily automatically. \n", "* tf-models-nightly is the nightly Model Garden package created daily automatically.\n",
"* pip will install all models and dependencies automatically." "* pip will install all models and dependencies automatically."
] ]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 0,
"metadata": { "metadata": {
"id": "NvNr2svBM-p3", "colab": {},
"colab_type": "code", "colab_type": "code",
"outputId": "f0be17be-2474-4f18-c87d-5b3f4237fab4", "id": "NvNr2svBM-p3"
"colab": {
"base_uri": "https://localhost:8080/",
"height": 1000
}
}, },
"outputs": [],
"source": [ "source": [
"pip install tf-models-nightly" "!pip install tf-models-nightly"
],
"execution_count": 0,
"outputs": [
{
"output_type": "stream",
"text": [
"Collecting tf-models-nightly\n",
" Using cached https://files.pythonhosted.org/packages/f5/08/c88a3d54959e037b3a1fd01929b57893f2bac640e3971a16dbd1640b1520/tf_models_nightly-2.2.0.dev20200508-py2.py3-none-any.whl\n",
"Requirement already satisfied: oauth2client>=4.1.2 in /usr/local/lib/python3.6/dist-packages (from tf-models-nightly) (4.1.3)\n",
"Requirement already satisfied: tensorflow-addons in /usr/local/lib/python3.6/dist-packages (from tf-models-nightly) (0.8.3)\n",
"Requirement already satisfied: numpy>=1.15.4 in /usr/local/lib/python3.6/dist-packages (from tf-models-nightly) (1.18.4)\n",
"Requirement already satisfied: pandas>=0.22.0 in /usr/local/lib/python3.6/dist-packages (from tf-models-nightly) (1.0.3)\n",
"Requirement already satisfied: tensorflow-datasets in /usr/local/lib/python3.6/dist-packages (from tf-models-nightly) (2.1.0)\n",
"Requirement already satisfied: pyyaml in /usr/local/lib/python3.6/dist-packages (from tf-models-nightly) (3.13)\n",
"Requirement already satisfied: scipy>=0.19.1 in /usr/local/lib/python3.6/dist-packages (from tf-models-nightly) (1.4.1)\n",
"Requirement already satisfied: Cython in /usr/local/lib/python3.6/dist-packages (from tf-models-nightly) (0.29.17)\n",
"Collecting mlperf-compliance==0.0.10\n",
" Downloading https://files.pythonhosted.org/packages/f4/08/f2febd8cbd5c9371f7dab311e90400d83238447ba7609b3bf0145b4cb2a2/mlperf_compliance-0.0.10-py3-none-any.whl\n",
"Requirement already satisfied: Pillow in /usr/local/lib/python3.6/dist-packages (from tf-models-nightly) (7.0.0)\n",
"Requirement already satisfied: dataclasses in /usr/local/lib/python3.6/dist-packages (from tf-models-nightly) (0.7)\n",
"Requirement already satisfied: google-api-python-client>=1.6.7 in /usr/local/lib/python3.6/dist-packages (from tf-models-nightly) (1.7.12)\n",
"Requirement already satisfied: kaggle>=1.3.9 in /usr/local/lib/python3.6/dist-packages (from tf-models-nightly) (1.5.6)\n",
"Collecting sentencepiece\n",
"\u001b[?25l Downloading https://files.pythonhosted.org/packages/98/2c/8df20f3ac6c22ac224fff307ebc102818206c53fc454ecd37d8ac2060df5/sentencepiece-0.1.86-cp36-cp36m-manylinux1_x86_64.whl (1.0MB)\n",
"\u001b[K |████████████████████████████████| 1.0MB 6.8MB/s \n",
"\u001b[?25hRequirement already satisfied: matplotlib in /usr/local/lib/python3.6/dist-packages (from tf-models-nightly) (3.2.1)\n",
"Collecting tensorflow-model-optimization>=0.2.1\n",
"\u001b[?25l Downloading https://files.pythonhosted.org/packages/09/7e/e94aa029999ec30951e8129fa992fecbbaffda66eba97c65d5a83f8ea96d/tensorflow_model_optimization-0.3.0-py2.py3-none-any.whl (165kB)\n",
"\u001b[K |████████████████████████████████| 174kB 23.0MB/s \n",
"\u001b[?25hCollecting opencv-python-headless\n",
"\u001b[?25l Downloading https://files.pythonhosted.org/packages/43/2c/909a04b07360516953beaf6f66480bb6b84b817c6b300c1235bfb2901ad8/opencv_python_headless-4.2.0.34-cp36-cp36m-manylinux1_x86_64.whl (21.6MB)\n",
"\u001b[K |████████████████████████████████| 21.6MB 1.5MB/s \n",
"\u001b[?25hCollecting tf-nightly\n",
"\u001b[?25l Downloading https://files.pythonhosted.org/packages/4e/55/c1c1e60bd269013bc0a136a150904a7f931b45ec0d9caa9ed032331491ba/tf_nightly-2.2.0.dev20200507-cp36-cp36m-manylinux2010_x86_64.whl (521.7MB)\n",
"\u001b[K |████████████████████████████████| 521.7MB 33kB/s \n",
"\u001b[?25hRequirement already satisfied: typing in /usr/local/lib/python3.6/dist-packages (from tf-models-nightly) (3.6.6)\n",
"Requirement already satisfied: google-cloud-bigquery>=0.31.0 in /usr/local/lib/python3.6/dist-packages (from tf-models-nightly) (1.21.0)\n",
"Requirement already satisfied: six in /usr/local/lib/python3.6/dist-packages (from tf-models-nightly) (1.12.0)\n",
"Collecting py-cpuinfo>=3.3.0\n",
"\u001b[?25l Downloading https://files.pythonhosted.org/packages/42/60/63f28a5401da733043abe7053e7d9591491b4784c4f87c339bf51215aa0a/py-cpuinfo-5.0.0.tar.gz (82kB)\n",
"\u001b[K |████████████████████████████████| 92kB 13.3MB/s \n",
"\u001b[?25hRequirement already satisfied: psutil>=5.4.3 in /usr/local/lib/python3.6/dist-packages (from tf-models-nightly) (5.4.8)\n",
"Requirement already satisfied: gin-config in /usr/local/lib/python3.6/dist-packages (from tf-models-nightly) (0.3.0)\n",
"Requirement already satisfied: tensorflow-hub>=0.6.0 in /usr/local/lib/python3.6/dist-packages (from tf-models-nightly) (0.8.0)\n",
"Requirement already satisfied: pyasn1-modules>=0.0.5 in /usr/local/lib/python3.6/dist-packages (from oauth2client>=4.1.2->tf-models-nightly) (0.2.8)\n",
"Requirement already satisfied: pyasn1>=0.1.7 in /usr/local/lib/python3.6/dist-packages (from oauth2client>=4.1.2->tf-models-nightly) (0.4.8)\n",
"Requirement already satisfied: rsa>=3.1.4 in /usr/local/lib/python3.6/dist-packages (from oauth2client>=4.1.2->tf-models-nightly) (4.0)\n",
"Requirement already satisfied: httplib2>=0.9.1 in /usr/local/lib/python3.6/dist-packages (from oauth2client>=4.1.2->tf-models-nightly) (0.17.3)\n",
"Requirement already satisfied: typeguard in /usr/local/lib/python3.6/dist-packages (from tensorflow-addons->tf-models-nightly) (2.7.1)\n",
"Requirement already satisfied: python-dateutil>=2.6.1 in /usr/local/lib/python3.6/dist-packages (from pandas>=0.22.0->tf-models-nightly) (2.8.1)\n",
"Requirement already satisfied: pytz>=2017.2 in /usr/local/lib/python3.6/dist-packages (from pandas>=0.22.0->tf-models-nightly) (2018.9)\n",
"Requirement already satisfied: requests>=2.19.0 in /usr/local/lib/python3.6/dist-packages (from tensorflow-datasets->tf-models-nightly) (2.23.0)\n",
"Requirement already satisfied: tensorflow-metadata in /usr/local/lib/python3.6/dist-packages (from tensorflow-datasets->tf-models-nightly) (0.21.2)\n",
"Requirement already satisfied: dill in /usr/local/lib/python3.6/dist-packages (from tensorflow-datasets->tf-models-nightly) (0.3.1.1)\n",
"Requirement already satisfied: promise in /usr/local/lib/python3.6/dist-packages (from tensorflow-datasets->tf-models-nightly) (2.3)\n",
"Requirement already satisfied: protobuf>=3.6.1 in /usr/local/lib/python3.6/dist-packages (from tensorflow-datasets->tf-models-nightly) (3.10.0)\n",
"Requirement already satisfied: tqdm in /usr/local/lib/python3.6/dist-packages (from tensorflow-datasets->tf-models-nightly) (4.41.1)\n",
"Requirement already satisfied: wrapt in /usr/local/lib/python3.6/dist-packages (from tensorflow-datasets->tf-models-nightly) (1.12.1)\n",
"Requirement already satisfied: termcolor in /usr/local/lib/python3.6/dist-packages (from tensorflow-datasets->tf-models-nightly) (1.1.0)\n",
"Requirement already satisfied: future in /usr/local/lib/python3.6/dist-packages (from tensorflow-datasets->tf-models-nightly) (0.16.0)\n",
"Requirement already satisfied: absl-py in /usr/local/lib/python3.6/dist-packages (from tensorflow-datasets->tf-models-nightly) (0.9.0)\n",
"Requirement already satisfied: attrs>=18.1.0 in /usr/local/lib/python3.6/dist-packages (from tensorflow-datasets->tf-models-nightly) (19.3.0)\n",
"Requirement already satisfied: google-auth>=1.4.1 in /usr/local/lib/python3.6/dist-packages (from google-api-python-client>=1.6.7->tf-models-nightly) (1.7.2)\n",
"Requirement already satisfied: uritemplate<4dev,>=3.0.0 in /usr/local/lib/python3.6/dist-packages (from google-api-python-client>=1.6.7->tf-models-nightly) (3.0.1)\n",
"Requirement already satisfied: google-auth-httplib2>=0.0.3 in /usr/local/lib/python3.6/dist-packages (from google-api-python-client>=1.6.7->tf-models-nightly) (0.0.3)\n",
"Requirement already satisfied: certifi in /usr/local/lib/python3.6/dist-packages (from kaggle>=1.3.9->tf-models-nightly) (2020.4.5.1)\n",
"Requirement already satisfied: python-slugify in /usr/local/lib/python3.6/dist-packages (from kaggle>=1.3.9->tf-models-nightly) (4.0.0)\n",
"Requirement already satisfied: urllib3<1.25,>=1.21.1 in /usr/local/lib/python3.6/dist-packages (from kaggle>=1.3.9->tf-models-nightly) (1.24.3)\n",
"Requirement already satisfied: pyparsing!=2.0.4,!=2.1.2,!=2.1.6,>=2.0.1 in /usr/local/lib/python3.6/dist-packages (from matplotlib->tf-models-nightly) (2.4.7)\n",
"Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.6/dist-packages (from matplotlib->tf-models-nightly) (0.10.0)\n",
"Requirement already satisfied: kiwisolver>=1.0.1 in /usr/local/lib/python3.6/dist-packages (from matplotlib->tf-models-nightly) (1.2.0)\n",
"Collecting dm-tree~=0.1.1\n",
"\u001b[?25l Downloading https://files.pythonhosted.org/packages/16/48/10fb721334810081b7e6eebeba0d12e12126c76993e8c243062d2f56a89f/dm_tree-0.1.5-cp36-cp36m-manylinux1_x86_64.whl (294kB)\n",
"\u001b[K |████████████████████████████████| 296kB 37.9MB/s \n",
"\u001b[?25hRequirement already satisfied: google-pasta>=0.1.8 in /usr/local/lib/python3.6/dist-packages (from tf-nightly->tf-models-nightly) (0.2.0)\n",
"Requirement already satisfied: keras-preprocessing>=1.1.0 in /usr/local/lib/python3.6/dist-packages (from tf-nightly->tf-models-nightly) (1.1.0)\n",
"Requirement already satisfied: opt-einsum>=2.3.2 in /usr/local/lib/python3.6/dist-packages (from tf-nightly->tf-models-nightly) (3.2.1)\n",
"Collecting tb-nightly<2.4.0a0,>=2.3.0a0\n",
"\u001b[?25l Downloading https://files.pythonhosted.org/packages/9c/9c/83fdd2823771661a188dd13df3a06d391cfaa87a8f9a8b541bc4da065886/tb_nightly-2.3.0a20200507-py3-none-any.whl (2.9MB)\n",
"\u001b[K |████████████████████████████████| 2.9MB 52.2MB/s \n",
"\u001b[?25hRequirement already satisfied: gast==0.3.3 in /usr/local/lib/python3.6/dist-packages (from tf-nightly->tf-models-nightly) (0.3.3)\n",
"Requirement already satisfied: grpcio>=1.8.6 in /usr/local/lib/python3.6/dist-packages (from tf-nightly->tf-models-nightly) (1.28.1)\n",
"Collecting tf-estimator-nightly\n",
"\u001b[?25l Downloading https://files.pythonhosted.org/packages/b3/ae/4ce63a0edaa72d5ddd622f968dfb5f6621c76b3656d5e1fb6057c09c1c12/tf_estimator_nightly-2.3.0.dev2020050801-py2.py3-none-any.whl (456kB)\n",
"\u001b[K |████████████████████████████████| 460kB 51.7MB/s \n",
"\u001b[?25hRequirement already satisfied: h5py<2.11.0,>=2.10.0 in /usr/local/lib/python3.6/dist-packages (from tf-nightly->tf-models-nightly) (2.10.0)\n",
"Requirement already satisfied: wheel>=0.26; python_version >= \"3\" in /usr/local/lib/python3.6/dist-packages (from tf-nightly->tf-models-nightly) (0.34.2)\n",
"Requirement already satisfied: astunparse==1.6.3 in /usr/local/lib/python3.6/dist-packages (from tf-nightly->tf-models-nightly) (1.6.3)\n",
"Requirement already satisfied: google-cloud-core<2.0dev,>=1.0.3 in /usr/local/lib/python3.6/dist-packages (from google-cloud-bigquery>=0.31.0->tf-models-nightly) (1.0.3)\n",
"Requirement already satisfied: google-resumable-media!=0.4.0,<0.5.0dev,>=0.3.1 in /usr/local/lib/python3.6/dist-packages (from google-cloud-bigquery>=0.31.0->tf-models-nightly) (0.4.1)\n",
"Requirement already satisfied: idna<3,>=2.5 in /usr/local/lib/python3.6/dist-packages (from requests>=2.19.0->tensorflow-datasets->tf-models-nightly) (2.9)\n",
"Requirement already satisfied: chardet<4,>=3.0.2 in /usr/local/lib/python3.6/dist-packages (from requests>=2.19.0->tensorflow-datasets->tf-models-nightly) (3.0.4)\n",
"Requirement already satisfied: googleapis-common-protos in /usr/local/lib/python3.6/dist-packages (from tensorflow-metadata->tensorflow-datasets->tf-models-nightly) (1.51.0)\n",
"Requirement already satisfied: setuptools in /usr/local/lib/python3.6/dist-packages (from protobuf>=3.6.1->tensorflow-datasets->tf-models-nightly) (46.1.3)\n",
"Requirement already satisfied: cachetools<3.2,>=2.0.0 in /usr/local/lib/python3.6/dist-packages (from google-auth>=1.4.1->google-api-python-client>=1.6.7->tf-models-nightly) (3.1.1)\n",
"Requirement already satisfied: text-unidecode>=1.3 in /usr/local/lib/python3.6/dist-packages (from python-slugify->kaggle>=1.3.9->tf-models-nightly) (1.3)\n",
"Requirement already satisfied: tensorboard-plugin-wit>=1.6.0 in /usr/local/lib/python3.6/dist-packages (from tb-nightly<2.4.0a0,>=2.3.0a0->tf-nightly->tf-models-nightly) (1.6.0.post3)\n",
"Requirement already satisfied: werkzeug>=0.11.15 in /usr/local/lib/python3.6/dist-packages (from tb-nightly<2.4.0a0,>=2.3.0a0->tf-nightly->tf-models-nightly) (1.0.1)\n",
"Requirement already satisfied: google-auth-oauthlib<0.5,>=0.4.1 in /usr/local/lib/python3.6/dist-packages (from tb-nightly<2.4.0a0,>=2.3.0a0->tf-nightly->tf-models-nightly) (0.4.1)\n",
"Requirement already satisfied: markdown>=2.6.8 in /usr/local/lib/python3.6/dist-packages (from tb-nightly<2.4.0a0,>=2.3.0a0->tf-nightly->tf-models-nightly) (3.2.1)\n",
"Requirement already satisfied: google-api-core<2.0.0dev,>=1.14.0 in /usr/local/lib/python3.6/dist-packages (from google-cloud-core<2.0dev,>=1.0.3->google-cloud-bigquery>=0.31.0->tf-models-nightly) (1.16.0)\n",
"Requirement already satisfied: requests-oauthlib>=0.7.0 in /usr/local/lib/python3.6/dist-packages (from google-auth-oauthlib<0.5,>=0.4.1->tb-nightly<2.4.0a0,>=2.3.0a0->tf-nightly->tf-models-nightly) (1.3.0)\n",
"Requirement already satisfied: oauthlib>=3.0.0 in /usr/local/lib/python3.6/dist-packages (from requests-oauthlib>=0.7.0->google-auth-oauthlib<0.5,>=0.4.1->tb-nightly<2.4.0a0,>=2.3.0a0->tf-nightly->tf-models-nightly) (3.1.0)\n",
"Building wheels for collected packages: py-cpuinfo\n",
" Building wheel for py-cpuinfo (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
" Created wheel for py-cpuinfo: filename=py_cpuinfo-5.0.0-cp36-none-any.whl size=18684 sha256=ea2e86de6a6c417388fb77cf43b197b5d7e9a66b5a3985330687e1a291b16b77\n",
" Stored in directory: /root/.cache/pip/wheels/01/7e/a9/b982d0fea22b7e4ae5619de949570cde5ad55420cec16e86a5\n",
"Successfully built py-cpuinfo\n",
"Installing collected packages: mlperf-compliance, sentencepiece, dm-tree, tensorflow-model-optimization, opencv-python-headless, tb-nightly, tf-estimator-nightly, tf-nightly, py-cpuinfo, tf-models-nightly\n",
"Successfully installed dm-tree-0.1.5 mlperf-compliance-0.0.10 opencv-python-headless-4.2.0.34 py-cpuinfo-5.0.0 sentencepiece-0.1.86 tb-nightly-2.3.0a20200507 tensorflow-model-optimization-0.3.0 tf-estimator-nightly-2.3.0.dev2020050801 tf-models-nightly-2.2.0.dev20200508 tf-nightly-2.2.0.dev20200507\n"
],
"name": "stdout"
}
] ]
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": { "metadata": {
"id": "U-7qPCjWUAyy", "colab_type": "text",
"colab_type": "text" "id": "U-7qPCjWUAyy"
}, },
"source": [ "source": [
"### Import Tensorflow and other libraries" "### Import Tensorflow and other libraries"
...@@ -2206,48 +112,49 @@ ...@@ -2206,48 +112,49 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 0,
"metadata": { "metadata": {
"id": "lXsXev5MNr20", "colab": {},
"colab_type": "code", "colab_type": "code",
"colab": {} "id": "lXsXev5MNr20"
}, },
"outputs": [],
"source": [ "source": [
"import json\n", "import os\n",
"import math\n",
"\n", "\n",
"import numpy as np\n",
"import tensorflow as tf\n",
"\n",
"from official.modeling import tf_utils\n",
"from official.nlp import optimization\n", "from official.nlp import optimization\n",
"from official.nlp.bert import bert_models\n",
"from official.nlp.bert import configs as bert_configs\n", "from official.nlp.bert import configs as bert_configs\n",
"from official.nlp.bert import run_classifier\n",
"from official.nlp.bert import tokenization\n", "from official.nlp.bert import tokenization\n",
"from official.nlp.data import classifier_data_lib\n", "from official.nlp.data import classifier_data_lib\n",
"from official.utils.misc import distribution_utils\n", "from official.nlp.modeling import losses\n",
"\n", "from official.nlp.modeling import models\n",
"import tensorflow as tf" "from official.nlp.modeling import networks"
], ]
"execution_count": 0,
"outputs": []
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": { "metadata": {
"id": "C2drjD7OVCmh", "colab_type": "text",
"colab_type": "text" "id": "C2drjD7OVCmh"
}, },
"source": [ "source": [
"## Get dataset" "## Preprocess the raw data and output tf.record files"
] ]
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": { "metadata": {
"id": "qfjcKj5FYQOp", "colab_type": "text",
"colab_type": "text" "id": "qfjcKj5FYQOp"
}, },
"source": [ "source": [
"### Introduction of dataset\n", "### Introduction of dataset\n",
"\n", "\n",
"The Microsoft Research Paraphrase Corpus (Dolan & Brockett, 2005) is a corpus of sentence pairs automatically extracted from online news sources, with human annotations for whether the sentences in the pair are semantically equivalent.\n", "The Microsoft Research Paraphrase Corpus (Dolan \u0026 Brockett, 2005) is a corpus of sentence pairs automatically extracted from online news sources, with human annotations for whether the sentences in the pair are semantically equivalent.\n",
"\n", "\n",
"* Number of labels: 2.\n", "* Number of labels: 2.\n",
"* Size of training dataset: 3668.\n", "* Size of training dataset: 3668.\n",
...@@ -2259,8 +166,8 @@ ...@@ -2259,8 +166,8 @@
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": { "metadata": {
"id": "28DvUhC1YUiB", "colab_type": "text",
"colab_type": "text" "id": "28DvUhC1YUiB"
}, },
"source": [ "source": [
"### Get dataset from TensorFlow Datasets (TFDS)\n", "### Get dataset from TensorFlow Datasets (TFDS)\n",
...@@ -2271,8 +178,8 @@ ...@@ -2271,8 +178,8 @@
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": { "metadata": {
"id": "4PhRLWh9jaXp", "colab_type": "text",
"colab_type": "text" "id": "4PhRLWh9jaXp"
}, },
"source": [ "source": [
"### Preprocess the data and write to TensorFlow record file\n", "### Preprocess the data and write to TensorFlow record file\n",
...@@ -2281,354 +188,116 @@ ...@@ -2281,354 +188,116 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 0,
"metadata": { "metadata": {
"id": "FhcMdzsrjWzG", "colab": {},
"colab_type": "code", "colab_type": "code",
"outputId": "f75ff71f-f05f-4cf3-e748-ca1949fcf5ec", "id": "FhcMdzsrjWzG"
"colab": {
"base_uri": "https://localhost:8080/",
"height": 449,
"referenced_widgets": [
"2a9e31a9fb264e86b4ee0a1c81cceaa5",
"23cc9ef1a4ab49a4a4434cd99cdb388f",
"e13997eeb02641fabf42e1014c28fb0e",
"870d3b6641c74a1f9166171317a9879a",
"2e597e06a7e84f29a231c9391dc41f2d",
"c1b7fcefc445437faddef2b892eb120f",
"66d48af99af441b387be35044558625f",
"f210578a032f4743a926d331d4db4135",
"6f3e0af4934d4b6885336c79a46055af",
"8f059203cbcc457dadc9171ae8bf9745",
"badd950dde44435293e5622d5b0e396d",
"06756d263dd544278bbfeb886c7796cd",
"c89906e177ad4f6583409b7a88043cbc",
"715c78d08b124e02933be04ecaca07d7",
"287df5b08de848fe916c1ea8617aa93f",
"761e1a4b02b245cd9a5128a0dbc7d7f7",
"707d210e5505474b9994ddb2aa3e4b65",
"a1e7697a216d49efaee31b0b626262c2",
"731be0cbeabc405db6b9ff1bf4042da0",
"11b1d290abdc4a8daf55ad061b442eb7",
"8d8f14ed642a42dfaa5e087dd72dff01",
"dd615ea054cc457eac995f5bf4a749c5",
"70867a9731a34f33a04e0cea29bf31f2",
"49ea6178eb75448a9d92d664c7207150",
"0d210dc6092a42fabff575536a383941",
"207c6b19d87e41e2a3e4f6f4341884c1",
"f202dabd4b384625ac5ea838bf964179",
"861900417e0d48dca0bf35348ecfac71",
"162ab1fd123a45f585deb18a769e8c3e",
"77df42d116674420872e77d7a03b1bda",
"50ba1095c78b401cbc37f2905842dba8",
"ea12c48a45de425bbeb9593bd194e274",
"dcdb5006adc5492eab470930b6335d47",
"348b5f70c320488f962c46be9022613d",
"427a293f14eb4f3f9288eead101725ac",
"ef1ad9afff504fa1ace8ad5f7b979235",
"a5b85dc847ad448589b0b4516aba6c8e",
"6ccc0bc5da8b46e9a685b7dd8e818af9",
"8fef9f4c593d4a92b80849d9a3750abf",
"09dd4f7d4ca540368b875f8dba8d2c53",
"99b14b614f204e85a3d681bcec8c45e0",
"bb0e8493062d4196820ef3dc8769083f",
"8e2ebc2036934f9a9182dec1caddfc19",
"ab15b7ff1edd433c895b608f5447a49b",
"5c6967e75c92456fa566e13880a084d0",
"66ee871010784e6391d4bca3f5acb2dd",
"128807925cdd47f6b39c6578666d93a8",
"130678ed546441338166dc934e88e1f7",
"43d3c73f5c9c4614a81603ec7323bd85",
"69fc9fb8ceb24c8a97b45b9503bf4434",
"d5cf0e1256d242eca09f81eed933a8dd",
"2c3922e6ec73417389af92c37fabf608",
"ee09284a5627447faaf6492b0b00762b",
"9e83f236d6384645957b24808c62e605",
"d4d3949283b34f7da5e481979d6c1cc2",
"e6e159a79a444ec68b5379254735b94a",
"7758bd45630e4eae88bf47c34055de38",
"eb0be74ff1074bf4ada0e5dcd84702b5",
"121bb541fc7c428dada37201862d47ce",
"98582bcc3b3c494798e1a0e500c2e9d1",
"d8dd89c4e7704104b314898991c84ce7",
"f05d20bfb0fd474ab2683d3f3e52e1af",
"0f83922a7c55458dbc083cc527bb2015",
"33a7d10888a8433dad7b64621bf0e5b1"
]
}
}, },
"outputs": [],
"source": [ "source": [
"gs_folder_bert = \"gs://cloud-tpu-checkpoints/bert/keras_bert/uncased_L-12_H-768_A-12\"\n", "gs_folder_bert = \"gs://cloud-tpu-checkpoints/bert/keras_bert/uncased_L-12_H-768_A-12\"\n",
"\n", "\n",
"# Get vocabulary file\n",
"vocab_file = gs_folder_bert + \"/vocab.txt\"\n",
"\n",
"# Set up output of training and evaluation Tensorflow dataset\n",
"train_data_output_path=\"./mrpc_train.tf_record\"\n",
"eval_data_output_path=\"./mrpc_eval.tf_record\"\n",
"\n",
"# Set up tokenizer to generate Tensorflow dataset\n", "# Set up tokenizer to generate Tensorflow dataset\n",
"tokenizer = tokenization.FullTokenizer(\n", "tokenizer = tokenization.FullTokenizer(\n",
" vocab_file=vocab_file, do_lower_case=True)\n", " vocab_file=os.path.join(gs_folder_bert, \"vocab.txt\"), do_lower_case=True)\n",
"\n", "\n",
"# Set up processor to generate Tensorflow dataset\n", "# Set up processor to generate Tensorflow dataset\n",
"processor_text_fn = tokenization.convert_to_unicode\n",
"processor = classifier_data_lib.TfdsProcessor(\n", "processor = classifier_data_lib.TfdsProcessor(\n",
" tfds_params=\"dataset=glue/mrpc,text_key=sentence1,text_b_key=sentence2\",\n", " tfds_params=\"dataset=glue/mrpc,text_key=sentence1,text_b_key=sentence2\",\n",
" process_text_fn=processor_text_fn)\n", " process_text_fn=tokenization.convert_to_unicode)\n",
"\n",
"# Set up output of training and evaluation Tensorflow dataset\n",
"train_data_output_path=\"./mrpc_train.tf_record\"\n",
"eval_data_output_path=\"./mrpc_eval.tf_record\"\n",
"\n", "\n",
"# Generate and save training data into a tf record file\n", "# Generate and save training data into a tf record file\n",
"input_meta_data = classifier_data_lib.generate_tf_record_from_data_file(\n", "input_meta_data = classifier_data_lib.generate_tf_record_from_data_file(\n",
" processor,\n", " processor=processor,\n",
" None,\n", " data_dir=None, # It is `None` because data is from tfds, not local dir.\n",
" tokenizer,\n", " tokenizer=tokenizer,\n",
" train_data_output_path=\"./mrpc_train.tf_record\",\n", " train_data_output_path=train_data_output_path,\n",
" eval_data_output_path=\"./mrpc_eval.tf_record\",\n", " eval_data_output_path=eval_data_output_path,\n",
" max_seq_length=128)" " max_seq_length=128)"
],
"execution_count": 0,
"outputs": [
{
"output_type": "stream",
"text": [
"\u001b[1mDownloading and preparing dataset glue/mrpc/1.0.0 (download: 1.43 MiB, generated: Unknown size, total: 1.43 MiB) to /root/tensorflow_datasets/glue/mrpc/1.0.0...\u001b[0m\n"
],
"name": "stdout"
},
{
"output_type": "display_data",
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "2a9e31a9fb264e86b4ee0a1c81cceaa5",
"version_minor": 0,
"version_major": 2
},
"text/plain": [
"HBox(children=(FloatProgress(value=1.0, bar_style='info', description='Dl Completed...', max=1.0, style=Progre…"
]
},
"metadata": {
"tags": []
}
},
{
"output_type": "display_data",
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "6f3e0af4934d4b6885336c79a46055af",
"version_minor": 0,
"version_major": 2
},
"text/plain": [
"HBox(children=(FloatProgress(value=1.0, bar_style='info', description='Dl Size...', max=1.0, style=ProgressSty…"
]
},
"metadata": {
"tags": []
}
},
{
"output_type": "stream",
"text": [
"/usr/local/lib/python3.6/dist-packages/urllib3/connectionpool.py:847: InsecureRequestWarning: Unverified HTTPS request is being made. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#ssl-warnings\n",
" InsecureRequestWarning)\n",
"/usr/local/lib/python3.6/dist-packages/urllib3/connectionpool.py:847: InsecureRequestWarning: Unverified HTTPS request is being made. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#ssl-warnings\n",
" InsecureRequestWarning)\n",
"/usr/local/lib/python3.6/dist-packages/urllib3/connectionpool.py:847: InsecureRequestWarning: Unverified HTTPS request is being made. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#ssl-warnings\n",
" InsecureRequestWarning)\n"
],
"name": "stderr"
},
{
"output_type": "stream",
"text": [
"\n",
"\n",
"\n",
"\n"
],
"name": "stdout"
},
{
"output_type": "display_data",
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "707d210e5505474b9994ddb2aa3e4b65",
"version_minor": 0,
"version_major": 2
},
"text/plain": [
"HBox(children=(FloatProgress(value=1.0, bar_style='info', max=1.0), HTML(value='')))"
]
},
"metadata": {
"tags": []
}
},
{
"output_type": "stream",
"text": [
"\rShuffling and writing examples to /root/tensorflow_datasets/glue/mrpc/1.0.0.incompleteC1ZQ3K/glue-train.tfrecord\n"
],
"name": "stdout"
},
{
"output_type": "display_data",
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "0d210dc6092a42fabff575536a383941",
"version_minor": 0,
"version_major": 2
},
"text/plain": [
"HBox(children=(FloatProgress(value=0.0, max=3668.0), HTML(value='')))"
]
},
"metadata": {
"tags": []
}
},
{
"output_type": "stream",
"text": [
"\r"
],
"name": "stdout"
},
{
"output_type": "display_data",
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "dcdb5006adc5492eab470930b6335d47",
"version_minor": 0,
"version_major": 2
},
"text/plain": [
"HBox(children=(FloatProgress(value=1.0, bar_style='info', max=1.0), HTML(value='')))"
]
},
"metadata": {
"tags": []
}
},
{
"output_type": "stream",
"text": [
"\rShuffling and writing examples to /root/tensorflow_datasets/glue/mrpc/1.0.0.incompleteC1ZQ3K/glue-validation.tfrecord\n"
],
"name": "stdout"
},
{
"output_type": "display_data",
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "99b14b614f204e85a3d681bcec8c45e0",
"version_minor": 0,
"version_major": 2
},
"text/plain": [
"HBox(children=(FloatProgress(value=0.0, max=408.0), HTML(value='')))"
]
},
"metadata": {
"tags": []
}
},
{
"output_type": "stream",
"text": [
"\r"
],
"name": "stdout"
},
{
"output_type": "display_data",
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "43d3c73f5c9c4614a81603ec7323bd85",
"version_minor": 0,
"version_major": 2
},
"text/plain": [
"HBox(children=(FloatProgress(value=1.0, bar_style='info', max=1.0), HTML(value='')))"
]
},
"metadata": {
"tags": []
}
},
{
"output_type": "stream",
"text": [
"\rShuffling and writing examples to /root/tensorflow_datasets/glue/mrpc/1.0.0.incompleteC1ZQ3K/glue-test.tfrecord\n"
],
"name": "stdout"
},
{
"output_type": "display_data",
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "7758bd45630e4eae88bf47c34055de38",
"version_minor": 0,
"version_major": 2
},
"text/plain": [
"HBox(children=(FloatProgress(value=0.0, max=1725.0), HTML(value='')))"
]
},
"metadata": {
"tags": []
}
},
{
"output_type": "stream",
"text": [
"\u001b[1mDataset glue downloaded and prepared to /root/tensorflow_datasets/glue/mrpc/1.0.0. Subsequent calls will reuse this data.\u001b[0m\n"
],
"name": "stdout"
}
] ]
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": { "metadata": {
"id": "dbJ76vSJj77j", "colab_type": "text",
"colab_type": "text" "id": "dbJ76vSJj77j"
}, },
"source": [ "source": [
"### Get Tensorflow dataset\n", "### Create tf.dataset for training and evaluation\n"
"\n"
] ]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 0,
"metadata": { "metadata": {
"id": "gCvaLLAxPuMc", "colab": {},
"colab_type": "code", "colab_type": "code",
"colab": {} "id": "gCvaLLAxPuMc"
}, },
"outputs": [],
"source": [ "source": [
"# Get dataset information from meta data\n", "def create_classifier_dataset(file_path, seq_length, batch_size, is_training):\n",
"max_seq_length = input_meta_data['max_seq_length']\n", " \"\"\"Creates input dataset from (tf)records files for train/eval.\"\"\"\n",
"num_classes = input_meta_data['num_labels']\n", " dataset = tf.data.TFRecordDataset(file_path)\n",
" if is_training:\n",
" dataset = dataset.shuffle(100)\n",
" dataset = dataset.repeat()\n",
"\n",
" def decode_record(record):\n",
" name_to_features = {\n",
" 'input_ids': tf.io.FixedLenFeature([seq_length], tf.int64),\n",
" 'input_mask': tf.io.FixedLenFeature([seq_length], tf.int64),\n",
" 'segment_ids': tf.io.FixedLenFeature([seq_length], tf.int64),\n",
" 'label_ids': tf.io.FixedLenFeature([], tf.int64),\n",
" }\n",
" return tf.io.parse_single_example(record, name_to_features)\n",
"\n",
" def _select_data_from_record(record):\n",
" x = {\n",
" 'input_word_ids': record['input_ids'],\n",
" 'input_mask': record['input_mask'],\n",
" 'input_type_ids': record['segment_ids']\n",
" }\n",
" y = record['label_ids']\n",
" return (x, y)\n",
"\n",
" dataset = dataset.map(decode_record,\n",
" num_parallel_calls=tf.data.experimental.AUTOTUNE)\n",
" dataset = dataset.map(\n",
" _select_data_from_record,\n",
" num_parallel_calls=tf.data.experimental.AUTOTUNE)\n",
" dataset = dataset.batch(batch_size, drop_remainder=is_training)\n",
" dataset = dataset.prefetch(tf.data.experimental.AUTOTUNE)\n",
" return dataset\n",
"\n", "\n",
"# Set up batch sizes\n", "# Set up batch sizes\n",
"batch_size = 32\n", "batch_size = 32\n",
"eval_batch_size = 32\n", "eval_batch_size = 32\n",
"\n", "\n",
"# Return Tensorflow dataset\n", "# Return Tensorflow dataset\n",
"train_input_fn = run_classifier.get_dataset_fn(train_data_output_path, max_seq_length, batch_size, is_training=True)\n", "training_dataset = create_classifier_dataset(\n",
"eval_input_fn = run_classifier.get_dataset_fn(eval_data_output_path, max_seq_length, eval_batch_size, is_training=False)\n", " train_data_output_path,\n",
"training_dataset = train_input_fn()\n", " input_meta_data['max_seq_length'],\n",
"evaluation_dataset = eval_input_fn()" " batch_size,\n",
], " is_training=True)\n",
"execution_count": 0, "\n",
"outputs": [] "evaluation_dataset = create_classifier_dataset(\n",
" eval_data_output_path,\n",
" input_meta_data['max_seq_length'],\n",
" eval_batch_size,\n",
" is_training=False)\n"
]
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": { "metadata": {
"id": "Efrj3Cn1kLAp", "colab_type": "text",
"colab_type": "text" "id": "Efrj3Cn1kLAp"
}, },
"source": [ "source": [
"## Create, compile and train the model" "## Create, compile and train the model"
...@@ -2637,8 +306,8 @@ ...@@ -2637,8 +306,8 @@
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": { "metadata": {
"id": "96ldxDSwkVkj", "colab_type": "text",
"colab_type": "text" "id": "96ldxDSwkVkj"
}, },
"source": [ "source": [
"### Construct a Bert Model\n", "### Construct a Bert Model\n",
...@@ -2648,37 +317,87 @@ ...@@ -2648,37 +317,87 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 0,
"metadata": { "metadata": {
"id": "Qgajw8WPYzJZ", "colab": {},
"colab_type": "code", "colab_type": "code",
"colab": {} "id": "Qgajw8WPYzJZ"
}, },
"outputs": [],
"source": [ "source": [
"bert_config_file = gs_folder_bert + \"/bert_config.json\"\n", "bert_config_file = os.path.join(gs_folder_bert, \"bert_config.json\")\n",
"bert_config = bert_configs.BertConfig.from_json_file(bert_config_file)\n", "bert_config = bert_configs.BertConfig.from_json_file(bert_config_file)\n",
"classifier_model, encoder = bert_models.classifier_model(\n", "\n",
" bert_config, num_classes, max_seq_length)" "bert_encoder = networks.TransformerEncoder(vocab_size=bert_config.vocab_size,\n",
], " hidden_size=bert_config.hidden_size,\n",
" num_layers=bert_config.num_hidden_layers,\n",
" num_attention_heads=bert_config.num_attention_heads,\n",
" intermediate_size=bert_config.intermediate_size,\n",
" activation=tf_utils.get_activation(bert_config.hidden_act),\n",
" dropout_rate=bert_config.hidden_dropout_prob,\n",
" attention_dropout_rate=bert_config.attention_probs_dropout_prob,\n",
" sequence_length=input_meta_data['max_seq_length'],\n",
" max_sequence_length=bert_config.max_position_embeddings,\n",
" type_vocab_size=bert_config.type_vocab_size,\n",
" embedding_width=bert_config.embedding_size,\n",
" initializer=tf.keras.initializers.TruncatedNormal(\n",
" stddev=bert_config.initializer_range))\n",
"\n",
"classifier_model = models.BertClassifier(\n",
" bert_encoder,\n",
" num_classes=input_meta_data['num_labels'],\n",
" dropout_rate=bert_config.hidden_dropout_prob,\n",
" initializer=tf.keras.initializers.TruncatedNormal(\n",
" stddev=bert_config.initializer_range))"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text",
"id": "pkSq1wbNXBaa"
},
"source": [
"### Initialize the encoder from a pretrained model"
]
},
{
"cell_type": "code",
"execution_count": 0, "execution_count": 0,
"outputs": [] "metadata": {
"colab": {},
"colab_type": "code",
"id": "X6N9NEqfXJCx"
},
"outputs": [],
"source": [
"checkpoint = tf.train.Checkpoint(model=bert_encoder)\n",
"checkpoint.restore(\n",
" os.path.join(gs_folder_bert, 'bert_model.ckpt')).assert_consumed()"
]
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": { "metadata": {
"id": "115caFLMk-_l", "colab_type": "text",
"colab_type": "text" "id": "115caFLMk-_l"
}, },
"source": [ "source": [
"### Set up an optimizer for the model" "### Set up an optimizer for the model\n",
"\n",
"BERT model adopts the Adam optimizer with weight decay.\n",
"It also employs a learning rate schedule that firstly warms up from 0 and then decays to 0."
] ]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 0,
"metadata": { "metadata": {
"id": "2Hf2rpRXk89N", "colab": {},
"colab_type": "code", "colab_type": "code",
"colab": {} "id": "2Hf2rpRXk89N"
}, },
"outputs": [],
"source": [ "source": [
"# Set up epochs and steps\n", "# Set up epochs and steps\n",
"epochs = 3\n", "epochs = 3\n",
...@@ -2687,104 +406,91 @@ ...@@ -2687,104 +406,91 @@
"num_train_steps = steps_per_epoch * epochs\n", "num_train_steps = steps_per_epoch * epochs\n",
"warmup_steps = int(epochs * train_data_size * 0.1 / batch_size)\n", "warmup_steps = int(epochs * train_data_size * 0.1 / batch_size)\n",
"\n", "\n",
"# Set up evaluation batch size and steps\n", "# Create learning rate schedule that firstly warms up from 0 and they decy to 0.\n",
"eval_batch_size = 32\n", "lr_schedule = tf.keras.optimizers.schedules.PolynomialDecay(\n",
"eval_data_size = input_meta_data['eval_data_size']\n", " initial_learning_rate=2e-5,\n",
"eval_steps = int(eval_data_size / eval_batch_size)\n", " decay_steps=num_train_steps,\n",
"\n", " end_learning_rate=0)\n",
"# creates an optimizer with learning rate schedule\n", "lr_schedule = optimization.WarmUp(\n",
"optimizer = optimization.create_optimizer(\n", " initial_learning_rate=2e-5,\n",
" 2e-5, num_train_steps=num_train_steps, num_warmup_steps=warmup_steps)" " decay_schedule_fn=lr_schedule,\n",
], " warmup_steps=warmup_steps)\n",
"execution_count": 0, "optimizer = optimization.AdamWeightDecay(\n",
"outputs": [] " learning_rate=lr_schedule,\n",
" weight_decay_rate=0.01,\n",
" beta_1=0.9,\n",
" beta_2=0.999,\n",
" epsilon=1e-6,\n",
" exclude_from_weight_decay=['LayerNorm', 'layer_norm', 'bias'])"
]
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": { "metadata": {
"id": "78FEUOOEkoP0", "colab_type": "text",
"colab_type": "text" "id": "OTNcA0O0nSq9"
}, },
"source": [ "source": [
"### Compile and train the model" "### Define metric_fn and loss_fn\n",
"\n",
"The metric is accuracy and we use sparse categorical cross-entropy as loss."
] ]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 0,
"metadata": { "metadata": {
"id": "nzi8hjeTQTRs", "colab": {},
"colab_type": "code", "colab_type": "code",
"outputId": "0738882c-1522-4cc4-d9ba-a6234cc82a0e", "id": "ELHjRp87nVNH"
"colab": {
"base_uri": "https://localhost:8080/",
"height": 188
}
}, },
"outputs": [],
"source": [ "source": [
"# Function: calculates how often predictions matches integer labels.\n",
"def metric_fn():\n", "def metric_fn():\n",
" return tf.keras.metrics.SparseCategoricalAccuracy(\n", " return tf.keras.metrics.SparseCategoricalAccuracy(\n",
" 'test_accuracy', dtype=tf.float32)\n", " 'accuracy', dtype=tf.float32)\n",
"\n", "\n",
"# Compile and train the model\n", "def classification_loss_fn(labels, logits):\n",
" return losses.weighted_sparse_categorical_crossentropy_loss(\n",
" labels=labels, predictions=tf.nn.log_softmax(logits, axis=-1))\n"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text",
"id": "78FEUOOEkoP0"
},
"source": [
"### Compile and train the model"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab": {},
"colab_type": "code",
"id": "nzi8hjeTQTRs"
},
"outputs": [],
"source": [
"classifier_model.compile(optimizer=optimizer,\n", "classifier_model.compile(optimizer=optimizer,\n",
" loss=run_classifier.get_loss_fn(num_classes=2),\n", " loss=classification_loss_fn,\n",
" metrics=[metric_fn()])\n", " metrics=[metric_fn()])\n",
"\n",
"classifier_model.fit(\n", "classifier_model.fit(\n",
" x=training_dataset,\n", " x=training_dataset,\n",
" validation_data=evaluation_dataset,\n", " validation_data=evaluation_dataset,\n",
" steps_per_epoch=steps_per_epoch,\n", " steps_per_epoch=steps_per_epoch,\n",
" epochs=epochs,\n", " epochs=epochs,\n",
" validation_steps=int(eval_data_size / eval_batch_size))" " validation_steps=int(input_meta_data['eval_data_size'] / eval_batch_size))"
],
"execution_count": 0,
"outputs": [
{
"output_type": "stream",
"text": [
"Epoch 1/3\n",
" 2/114 [..............................] - ETA: 57s - loss: 0.7512 - test_accuracy: 0.2500WARNING:tensorflow:Callbacks method `on_train_batch_end` is slow compared to the batch time. Check your callbacks.\n"
],
"name": "stdout"
},
{
"output_type": "stream",
"text": [
"WARNING:tensorflow:Callbacks method `on_train_batch_end` is slow compared to the batch time. Check your callbacks.\n"
],
"name": "stderr"
},
{
"output_type": "stream",
"text": [
"114/114 [==============================] - 90s 785ms/step - loss: 0.6498 - test_accuracy: 0.6595 - val_loss: 0.6397 - val_test_accuracy: 0.6797\n",
"Epoch 2/3\n",
"114/114 [==============================] - 97s 848ms/step - loss: 0.6334 - test_accuracy: 0.6743 - val_loss: 0.6215 - val_test_accuracy: 0.6797\n",
"Epoch 3/3\n",
"114/114 [==============================] - 96s 842ms/step - loss: 0.6179 - test_accuracy: 0.6763 - val_loss: 0.6106 - val_test_accuracy: 0.6797\n"
],
"name": "stdout"
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<tensorflow.python.keras.callbacks.History at 0x7febe2eed128>"
]
},
"metadata": {
"tags": []
},
"execution_count": 8
}
] ]
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": { "metadata": {
"id": "fVo_AnT0l26j", "colab_type": "text",
"colab_type": "text" "id": "fVo_AnT0l26j"
}, },
"source": [ "source": [
"### Save the model" "### Save the model"
...@@ -2792,97 +498,55 @@ ...@@ -2792,97 +498,55 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 0,
"metadata": { "metadata": {
"id": "Nl5x6nElZqkP", "colab": {},
"colab_type": "code", "colab_type": "code",
"outputId": "197a1ebe-02cc-46ec-eeb7-f83158795d91", "id": "Nl5x6nElZqkP"
"colab": {
"base_uri": "https://localhost:8080/",
"height": 171
}
}, },
"outputs": [],
"source": [ "source": [
"classifier_model.save('/tmp/saved_model', include_optimizer=False, save_format='tf')" "classifier_model.save('./saved_model', include_optimizer=False, save_format='tf')"
],
"execution_count": 0,
"outputs": [
{
"output_type": "stream",
"text": [
"WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/tensorflow/python/training/tracking/tracking.py:105: Network.state_updates (from tensorflow.python.keras.engine.network) is deprecated and will be removed in a future version.\n",
"Instructions for updating:\n",
"This property should not be used in TensorFlow 2.0, as updates are applied automatically.\n"
],
"name": "stdout"
},
{
"output_type": "stream",
"text": [
"WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/tensorflow/python/training/tracking/tracking.py:105: Network.state_updates (from tensorflow.python.keras.engine.network) is deprecated and will be removed in a future version.\n",
"Instructions for updating:\n",
"This property should not be used in TensorFlow 2.0, as updates are applied automatically.\n"
],
"name": "stderr"
},
{
"output_type": "stream",
"text": [
"INFO:tensorflow:Assets written to: /tmp/saved_model/assets\n"
],
"name": "stdout"
},
{
"output_type": "stream",
"text": [
"INFO:tensorflow:Assets written to: /tmp/saved_model/assets\n"
],
"name": "stderr"
}
] ]
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": { "metadata": {
"id": "nWsE6yeyfW00", "colab_type": "text",
"colab_type": "text" "id": "nWsE6yeyfW00"
}, },
"source": [ "source": [
"## Use the trained model\n" "## Use the trained model to predict\n"
] ]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 0,
"metadata": { "metadata": {
"id": "vz7YJY2QYAjP", "colab": {},
"colab_type": "code", "colab_type": "code",
"outputId": "49d82b71-1473-45d3-e2e8-f517b83b4d21", "id": "vz7YJY2QYAjP"
"colab": {
"base_uri": "https://localhost:8080/",
"height": 70
}
}, },
"outputs": [],
"source": [ "source": [
"# Set up distribution strategy\n", "eval_predictions = classifier_model.predict(evaluation_dataset)\n",
"strategy = distribution_utils.get_distribution_strategy(\n", "for prediction in eval_predictions:\n",
" distribution_strategy='one_device', num_gpus=1)\n", " print(\"Predicted label id: %s\" % np.argmax(prediction))"
"\n",
"# Get predictiona and labels for evaluation dataset\n",
"eval_predictions, eval_labels = run_classifier.get_predictions_and_labels(strategy, classifier_model, eval_input_fn,\n",
" eval_steps)\n",
"print(eval_predictions)\n",
"print(eval_labels)"
],
"execution_count": 0,
"outputs": [
{
"output_type": "stream",
"text": [
"[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]\n",
"[1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 0, 0, 0, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 0, 0, 1, 1, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 1, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 1, 0, 1, 1, 1, 1, 0, 1, 1, 0, 1, 1, 1, 0, 0, 1, 1, 0, 1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 1, 0, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 1, 0, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 0, 1, 0, 1, 1, 1, 1, 0, 1, 1, 0, 1, 0, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0, 1, 0, 1, 0, 1, 1, 0, 0, 0, 0, 1, 0, 1, 1, 0, 0, 1, 0, 1, 0, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 0, 1, 0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 1, 1, 0, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 0, 0, 0, 1, 1, 0, 0, 0, 1, 1, 0, 0, 0, 1, 1, 1, 0, 0, 1, 1, 0, 0, 1, 0, 0, 1, 1, 1, 0, 1, 1, 0, 1, 0, 1, 1, 1, 0, 1, 1, 1, 1, 0, 0, 1, 1, 0, 0, 1, 0, 0, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 0, 1, 1, 0, 0, 1, 1, 1, 1, 1, 0, 1, 0, 0, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 0, 1, 1, 1, 1, 0, 1, 0, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 1, 0, 1, 1, 1, 0, 1, 1, 0, 0, 1, 1, 1, 1, 0, 1, 0, 1, 1, 0]\n"
],
"name": "stdout"
}
] ]
} }
] ],
} "metadata": {
\ No newline at end of file "accelerator": "GPU",
"colab": {
"collapsed_sections": [],
"name": "How-to Guide: Using a PIP package for fine-tuning a BERT model",
"provenance": []
},
"kernelspec": {
"display_name": "Python 3",
"name": "python3"
}
},
"nbformat": 4,
"nbformat_minor": 0
}
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment