Showing preview only (888K chars total). Download the full file or copy to clipboard to get everything.
Repository: patil-suraj/exploring-T5
Branch: master
Commit: ae128fb85c27
Files: 3
Total size: 863.5 KB
Directory structure:
gitextract_imbs4xu_/
├── README.md
├── T5_on_TPU.ipynb
└── t5_fine_tuning.ipynb
================================================
FILE CONTENTS
================================================
================================================
FILE: README.md
================================================
# exploring-T5
A repo to explore different NLP tasks which can be solved using T5
================================================
FILE: T5_on_TPU.ipynb
================================================
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"name": "T5 on TPU",
"provenance": [],
"collapsed_sections": [],
"machine_shape": "hm",
"authorship_tag": "ABX9TyNhznFJcPoY54Wwqs6aEdRJ",
"include_colab_link": true
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"accelerator": "TPU",
"widgets": {
"application/vnd.jupyter.widget-state+json": {
"44ca82b3bbc5432eadc4f6fa3b81f483": {
"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_9a58f575a463454aba3a52742abf00bf",
"_model_module": "@jupyter-widgets/controls",
"children": [
"IPY_MODEL_6217a8ed0c634a5bbcbb4070d61d2ce3",
"IPY_MODEL_9542805d664d451aa33a5bd7cc36d614"
]
}
},
"9a58f575a463454aba3a52742abf00bf": {
"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
}
},
"6217a8ed0c634a5bbcbb4070d61d2ce3": {
"model_module": "@jupyter-widgets/controls",
"model_name": "FloatProgressModel",
"state": {
"_view_name": "ProgressView",
"style": "IPY_MODEL_f90e54ee9dee42a99f38fdf2186cea62",
"_dom_classes": [],
"description": "Downloading: 100%",
"_model_name": "FloatProgressModel",
"bar_style": "success",
"max": 791656,
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"value": 791656,
"_view_count": null,
"_view_module_version": "1.5.0",
"orientation": "horizontal",
"min": 0,
"description_tooltip": null,
"_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_2085a86f64a04a1586fefa0fe1413406"
}
},
"9542805d664d451aa33a5bd7cc36d614": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HTMLModel",
"state": {
"_view_name": "HTMLView",
"style": "IPY_MODEL_8e0c79e36d8c4d1faab99cc565feeb17",
"_dom_classes": [],
"description": "",
"_model_name": "HTMLModel",
"placeholder": "",
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"value": " 792k/792k [00:06<00:00, 124kB/s]",
"_view_count": null,
"_view_module_version": "1.5.0",
"description_tooltip": null,
"_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_413ae83fdf9d4573b2c2dc053db83aa2"
}
},
"f90e54ee9dee42a99f38fdf2186cea62": {
"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"
}
},
"2085a86f64a04a1586fefa0fe1413406": {
"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
}
},
"8e0c79e36d8c4d1faab99cc565feeb17": {
"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"
}
},
"413ae83fdf9d4573b2c2dc053db83aa2": {
"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
}
},
"d7fa301d6f7d498bac466849f04321c5": {
"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_0f662bc0fa4444f386ec8975b4289f04",
"_model_module": "@jupyter-widgets/controls",
"children": [
"IPY_MODEL_a2b08cf2bb834808b02d20fbee2f00ab",
"IPY_MODEL_5efd16badcb64aa3a708975504feade1"
]
}
},
"0f662bc0fa4444f386ec8975b4289f04": {
"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
}
},
"a2b08cf2bb834808b02d20fbee2f00ab": {
"model_module": "@jupyter-widgets/controls",
"model_name": "FloatProgressModel",
"state": {
"_view_name": "ProgressView",
"style": "IPY_MODEL_a763d584af9147bcbe5430f95bf16925",
"_dom_classes": [],
"description": "Downloading: 100%",
"_model_name": "FloatProgressModel",
"bar_style": "success",
"max": 4997,
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"value": 4997,
"_view_count": null,
"_view_module_version": "1.5.0",
"orientation": "horizontal",
"min": 0,
"description_tooltip": null,
"_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_329f27a50bee452b8f5ee719929fb33b"
}
},
"5efd16badcb64aa3a708975504feade1": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HTMLModel",
"state": {
"_view_name": "HTMLView",
"style": "IPY_MODEL_0be03081b1324f79a99bdbe926c30e89",
"_dom_classes": [],
"description": "",
"_model_name": "HTMLModel",
"placeholder": "",
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"value": " 5.00k/5.00k [00:00<00:00, 11.7kB/s]",
"_view_count": null,
"_view_module_version": "1.5.0",
"description_tooltip": null,
"_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_dca7ff44a73a4c9f872cb2596c3c729e"
}
},
"a763d584af9147bcbe5430f95bf16925": {
"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"
}
},
"329f27a50bee452b8f5ee719929fb33b": {
"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
}
},
"0be03081b1324f79a99bdbe926c30e89": {
"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"
}
},
"dca7ff44a73a4c9f872cb2596c3c729e": {
"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
}
},
"d530b763a0e9415f9b8b1f1787a66619": {
"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_7b85b787b5d9490c994f9e406835813b",
"_model_module": "@jupyter-widgets/controls",
"children": [
"IPY_MODEL_f86c72c0da864856b9ddb55568fe4a2b",
"IPY_MODEL_a4e0f5b0b3cf4091a44bad74e5abb62e"
]
}
},
"7b85b787b5d9490c994f9e406835813b": {
"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
}
},
"f86c72c0da864856b9ddb55568fe4a2b": {
"model_module": "@jupyter-widgets/controls",
"model_name": "FloatProgressModel",
"state": {
"_view_name": "ProgressView",
"style": "IPY_MODEL_3ecc3e6a31db4835987c22b81a85c23f",
"_dom_classes": [],
"description": "Downloading: 100%",
"_model_name": "FloatProgressModel",
"bar_style": "success",
"max": 2240,
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"value": 2240,
"_view_count": null,
"_view_module_version": "1.5.0",
"orientation": "horizontal",
"min": 0,
"description_tooltip": null,
"_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_7c062b51acab4bb59eeb4269d5e6c2df"
}
},
"a4e0f5b0b3cf4091a44bad74e5abb62e": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HTMLModel",
"state": {
"_view_name": "HTMLView",
"style": "IPY_MODEL_7fbf906e11d24bfdb90e3f0ce46250c1",
"_dom_classes": [],
"description": "",
"_model_name": "HTMLModel",
"placeholder": "",
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"value": " 2.24k/2.24k [00:02<00:00, 1.02kB/s]",
"_view_count": null,
"_view_module_version": "1.5.0",
"description_tooltip": null,
"_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_43deb763aee24506a82dd795cd126f49"
}
},
"3ecc3e6a31db4835987c22b81a85c23f": {
"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"
}
},
"7c062b51acab4bb59eeb4269d5e6c2df": {
"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
}
},
"7fbf906e11d24bfdb90e3f0ce46250c1": {
"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"
}
},
"43deb763aee24506a82dd795cd126f49": {
"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
}
},
"6af39625f78e4e5989739eff7e8849f6": {
"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_d97ac4c36e7944fdb989cf7ee1851350",
"_model_module": "@jupyter-widgets/controls",
"children": [
"IPY_MODEL_2539f0244f0e468a993609fd562ff1f5",
"IPY_MODEL_17025b38dedb45a39a95ffe7b6117d87"
]
}
},
"d97ac4c36e7944fdb989cf7ee1851350": {
"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
}
},
"2539f0244f0e468a993609fd562ff1f5": {
"model_module": "@jupyter-widgets/controls",
"model_name": "FloatProgressModel",
"state": {
"_view_name": "ProgressView",
"style": "IPY_MODEL_b6dde636eb51433fb5be7af2cedc2774",
"_dom_classes": [],
"description": "Downloading: ",
"_model_name": "FloatProgressModel",
"bar_style": "success",
"max": 8116577,
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"value": 8116577,
"_view_count": null,
"_view_module_version": "1.5.0",
"orientation": "horizontal",
"min": 0,
"description_tooltip": null,
"_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_ff877f980dd34d2d9f3a4d3efb50af0c"
}
},
"17025b38dedb45a39a95ffe7b6117d87": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HTMLModel",
"state": {
"_view_name": "HTMLView",
"style": "IPY_MODEL_cde27b62215448be92d8c8fa2292438a",
"_dom_classes": [],
"description": "",
"_model_name": "HTMLModel",
"placeholder": "",
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"value": " 30.3M/? [00:00<00:00, 41.3MB/s]",
"_view_count": null,
"_view_module_version": "1.5.0",
"description_tooltip": null,
"_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_5b66084b700145d5903aa91bcd2920f7"
}
},
"b6dde636eb51433fb5be7af2cedc2774": {
"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"
}
},
"ff877f980dd34d2d9f3a4d3efb50af0c": {
"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
}
},
"cde27b62215448be92d8c8fa2292438a": {
"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"
}
},
"5b66084b700145d5903aa91bcd2920f7": {
"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
}
},
"741a693169b54851a4cb47369dd9bd1e": {
"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_eb0f02133b9140be92288fd6a8415deb",
"_model_module": "@jupyter-widgets/controls",
"children": [
"IPY_MODEL_03a75d6d64524d47a3df6457e1901cbd",
"IPY_MODEL_b4a2213a0a0b421d895269733344cc9d"
]
}
},
"eb0f02133b9140be92288fd6a8415deb": {
"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
}
},
"03a75d6d64524d47a3df6457e1901cbd": {
"model_module": "@jupyter-widgets/controls",
"model_name": "FloatProgressModel",
"state": {
"_view_name": "ProgressView",
"style": "IPY_MODEL_64e947e3d9e440cf9f3880cb2325e57a",
"_dom_classes": [],
"description": "Downloading: ",
"_model_name": "FloatProgressModel",
"bar_style": "success",
"max": 1054280,
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"value": 1054280,
"_view_count": null,
"_view_module_version": "1.5.0",
"orientation": "horizontal",
"min": 0,
"description_tooltip": null,
"_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_108bbc9991614357aae4469fc19b4859"
}
},
"b4a2213a0a0b421d895269733344cc9d": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HTMLModel",
"state": {
"_view_name": "HTMLView",
"style": "IPY_MODEL_6792931cb55944deb260f07d6bf87931",
"_dom_classes": [],
"description": "",
"_model_name": "HTMLModel",
"placeholder": "",
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"value": " 4.85M/? [00:00<00:00, 15.2MB/s]",
"_view_count": null,
"_view_module_version": "1.5.0",
"description_tooltip": null,
"_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_3cb18f41264740c9933f159a9820ad77"
}
},
"64e947e3d9e440cf9f3880cb2325e57a": {
"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"
}
},
"108bbc9991614357aae4469fc19b4859": {
"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
}
},
"6792931cb55944deb260f07d6bf87931": {
"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"
}
},
"3cb18f41264740c9933f159a9820ad77": {
"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
}
},
"004faf88da144ad2bd3e50b5b9766627": {
"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_f02e5f34ac414081ab2882b2ab7ff64d",
"_model_module": "@jupyter-widgets/controls",
"children": [
"IPY_MODEL_41c3aac64e424e1db59b723a11bb0fb0",
"IPY_MODEL_44540a280fb141979bdeff7f93d0cde2"
]
}
},
"f02e5f34ac414081ab2882b2ab7ff64d": {
"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
}
},
"41c3aac64e424e1db59b723a11bb0fb0": {
"model_module": "@jupyter-widgets/controls",
"model_name": "FloatProgressModel",
"state": {
"_view_name": "ProgressView",
"style": "IPY_MODEL_f9c604fa9a8642eaa218824b8ab651fe",
"_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_34e5dacca6fc4497abda0a2ad37996e0"
}
},
"44540a280fb141979bdeff7f93d0cde2": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HTMLModel",
"state": {
"_view_name": "HTMLView",
"style": "IPY_MODEL_8bd88e5bf56e45bbbc1d339b00eff57c",
"_dom_classes": [],
"description": "",
"_model_name": "HTMLModel",
"placeholder": "",
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"value": " 87599/0 [00:03<00:00, 5389.75 examples/s]",
"_view_count": null,
"_view_module_version": "1.5.0",
"description_tooltip": null,
"_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_93b33f1c33de44b4a1e57fb4133343c9"
}
},
"f9c604fa9a8642eaa218824b8ab651fe": {
"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"
}
},
"34e5dacca6fc4497abda0a2ad37996e0": {
"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
}
},
"8bd88e5bf56e45bbbc1d339b00eff57c": {
"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"
}
},
"93b33f1c33de44b4a1e57fb4133343c9": {
"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
}
},
"3ec93bdea33b40ba82e24b4a0e605bc0": {
"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_121c3099d6e04079a4f6bf5707e0c60d",
"_model_module": "@jupyter-widgets/controls",
"children": [
"IPY_MODEL_4f17790e2f594811bbfe55c9d883cf41",
"IPY_MODEL_602e1a740e8f41fb800dbb3af0ea04f9"
]
}
},
"121c3099d6e04079a4f6bf5707e0c60d": {
"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
}
},
"4f17790e2f594811bbfe55c9d883cf41": {
"model_module": "@jupyter-widgets/controls",
"model_name": "FloatProgressModel",
"state": {
"_view_name": "ProgressView",
"style": "IPY_MODEL_c1628c0657a44cf0873f2d64c9fb549c",
"_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_99f6bf35ae7f4e66b4d339fe93768c7c"
}
},
"602e1a740e8f41fb800dbb3af0ea04f9": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HTMLModel",
"state": {
"_view_name": "HTMLView",
"style": "IPY_MODEL_d73cf402af074a5481bf900e6abe2c63",
"_dom_classes": [],
"description": "",
"_model_name": "HTMLModel",
"placeholder": "",
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"value": " 10570/0 [00:00<00:00, 18381.93 examples/s]",
"_view_count": null,
"_view_module_version": "1.5.0",
"description_tooltip": null,
"_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_0b2c415901d8468fb3f9acb63dd2f4e3"
}
},
"c1628c0657a44cf0873f2d64c9fb549c": {
"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"
}
},
"99f6bf35ae7f4e66b4d339fe93768c7c": {
"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
}
},
"d73cf402af074a5481bf900e6abe2c63": {
"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"
}
},
"0b2c415901d8468fb3f9acb63dd2f4e3": {
"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
}
},
"1d197b0946534a91b2eb4595baade174": {
"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_55c18e9169ab44c981de4cb2ebaea578",
"_model_module": "@jupyter-widgets/controls",
"children": [
"IPY_MODEL_21065bd4f9fa4d97a20a25c9a35b7737",
"IPY_MODEL_88d28cee2f02428aa3c4c22a873d6385"
]
}
},
"55c18e9169ab44c981de4cb2ebaea578": {
"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
}
},
"21065bd4f9fa4d97a20a25c9a35b7737": {
"model_module": "@jupyter-widgets/controls",
"model_name": "FloatProgressModel",
"state": {
"_view_name": "ProgressView",
"style": "IPY_MODEL_12d2d5b9a3f54b25aa8fef6439625db6",
"_dom_classes": [],
"description": "Epoch: 100%",
"_model_name": "FloatProgressModel",
"bar_style": "success",
"max": 4,
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"value": 4,
"_view_count": null,
"_view_module_version": "1.5.0",
"orientation": "horizontal",
"min": 0,
"description_tooltip": null,
"_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_32f70451efa6473a8a00807dd22a3248"
}
},
"88d28cee2f02428aa3c4c22a873d6385": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HTMLModel",
"state": {
"_view_name": "HTMLView",
"style": "IPY_MODEL_17c358e37fc346a9ac8ce475599e495a",
"_dom_classes": [],
"description": "",
"_model_name": "HTMLModel",
"placeholder": "",
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"value": " 4/4 [20:24<00:00, 306.06s/it]",
"_view_count": null,
"_view_module_version": "1.5.0",
"description_tooltip": null,
"_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_947afd4c522443b38bc223114178c7ee"
}
},
"12d2d5b9a3f54b25aa8fef6439625db6": {
"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"
}
},
"32f70451efa6473a8a00807dd22a3248": {
"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
}
},
"17c358e37fc346a9ac8ce475599e495a": {
"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"
}
},
"947afd4c522443b38bc223114178c7ee": {
"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
}
},
"a558cfceca8b43568dfad2267a534a35": {
"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_7a5270ddb66447af9fba298e830fe8a4",
"_model_module": "@jupyter-widgets/controls",
"children": [
"IPY_MODEL_d961f9fa40a04ceda3e1962eef4d33cc",
"IPY_MODEL_d9363dcd670643e6ad2d0b65c4238b98"
]
}
},
"7a5270ddb66447af9fba298e830fe8a4": {
"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
}
},
"d961f9fa40a04ceda3e1962eef4d33cc": {
"model_module": "@jupyter-widgets/controls",
"model_name": "FloatProgressModel",
"state": {
"_view_name": "ProgressView",
"style": "IPY_MODEL_b25b3d9394be4ac786678181c800e926",
"_dom_classes": [],
"description": "Iteration: 100%",
"_model_name": "FloatProgressModel",
"bar_style": "success",
"max": 1369,
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"value": 1369,
"_view_count": null,
"_view_module_version": "1.5.0",
"orientation": "horizontal",
"min": 0,
"description_tooltip": null,
"_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_3fed14bdec8b4162887d77dea7a9f289"
}
},
"d9363dcd670643e6ad2d0b65c4238b98": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HTMLModel",
"state": {
"_view_name": "HTMLView",
"style": "IPY_MODEL_5051978cf84f4f8191c1e3ad4661776e",
"_dom_classes": [],
"description": "",
"_model_name": "HTMLModel",
"placeholder": "",
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"value": " 1369/1369 [20:23<00:00, 1.12it/s]",
"_view_count": null,
"_view_module_version": "1.5.0",
"description_tooltip": null,
"_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_f67b49a0d48f4714a124bc972e9afa0f"
}
},
"b25b3d9394be4ac786678181c800e926": {
"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"
}
},
"3fed14bdec8b4162887d77dea7a9f289": {
"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
}
},
"5051978cf84f4f8191c1e3ad4661776e": {
"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"
}
},
"f67b49a0d48f4714a124bc972e9afa0f": {
"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
}
},
"2c4d7bdf7f6c48f0825ef87a12399f39": {
"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_391fc0937c3b48f8b4c3b33a1c3849a0",
"_model_module": "@jupyter-widgets/controls",
"children": [
"IPY_MODEL_11c6ff7dfb19436c920c5114734c0ec9",
"IPY_MODEL_3b3722a55e3d43bc93c29a505895a25c"
]
}
},
"391fc0937c3b48f8b4c3b33a1c3849a0": {
"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
}
},
"11c6ff7dfb19436c920c5114734c0ec9": {
"model_module": "@jupyter-widgets/controls",
"model_name": "FloatProgressModel",
"state": {
"_view_name": "ProgressView",
"style": "IPY_MODEL_f46743ac2da84d6ca77180d8686ead6b",
"_dom_classes": [],
"description": "Iteration: 0%",
"_model_name": "FloatProgressModel",
"bar_style": "danger",
"max": 1369,
"_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_1b0e2b414d6843ae9c918db417ffff4d"
}
},
"3b3722a55e3d43bc93c29a505895a25c": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HTMLModel",
"state": {
"_view_name": "HTMLView",
"style": "IPY_MODEL_e7559a6907f7479db7764f80c4501993",
"_dom_classes": [],
"description": "",
"_model_name": "HTMLModel",
"placeholder": "",
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"value": " 0/1369 [00:00<?, ?it/s]",
"_view_count": null,
"_view_module_version": "1.5.0",
"description_tooltip": null,
"_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_5f89a141b34d478e861ea6bd4a17dcd2"
}
},
"f46743ac2da84d6ca77180d8686ead6b": {
"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"
}
},
"1b0e2b414d6843ae9c918db417ffff4d": {
"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
}
},
"e7559a6907f7479db7764f80c4501993": {
"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"
}
},
"5f89a141b34d478e861ea6bd4a17dcd2": {
"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
}
},
"a9a7aeae6fa74b67a349a69e845f8898": {
"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_0a9d6c739f984b91a0e17724707eb7e1",
"_model_module": "@jupyter-widgets/controls",
"children": [
"IPY_MODEL_1ed37d3716374294b072524937625965",
"IPY_MODEL_4b44de48aeeb4b8dbc9388fc7f7da227"
]
}
},
"0a9d6c739f984b91a0e17724707eb7e1": {
"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
}
},
"1ed37d3716374294b072524937625965": {
"model_module": "@jupyter-widgets/controls",
"model_name": "FloatProgressModel",
"state": {
"_view_name": "ProgressView",
"style": "IPY_MODEL_051052ef94d447a4b0233225d8f5ae81",
"_dom_classes": [],
"description": "Iteration: 0%",
"_model_name": "FloatProgressModel",
"bar_style": "danger",
"max": 1369,
"_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_3e43d0668e6f461c9cc461aa735a4437"
}
},
"4b44de48aeeb4b8dbc9388fc7f7da227": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HTMLModel",
"state": {
"_view_name": "HTMLView",
"style": "IPY_MODEL_43e265f386ca4dfd88e226a87f32775c",
"_dom_classes": [],
"description": "",
"_model_name": "HTMLModel",
"placeholder": "",
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"value": " 0/1369 [00:00<?, ?it/s]",
"_view_count": null,
"_view_module_version": "1.5.0",
"description_tooltip": null,
"_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_6568a6e42f734c29ad5c26f2397a5a69"
}
},
"051052ef94d447a4b0233225d8f5ae81": {
"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"
}
},
"3e43d0668e6f461c9cc461aa735a4437": {
"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
}
},
"43e265f386ca4dfd88e226a87f32775c": {
"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"
}
},
"6568a6e42f734c29ad5c26f2397a5a69": {
"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
}
},
"c227333162114432a38b1480ec837701": {
"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_71a3e5b846a74f409dfd029ea3bf5d61",
"_model_module": "@jupyter-widgets/controls",
"children": [
"IPY_MODEL_8a27b38cd17649b1bc720a33050dc520",
"IPY_MODEL_16497f2b4de443bb9bb14ccaf0c94803"
]
}
},
"71a3e5b846a74f409dfd029ea3bf5d61": {
"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
}
},
"8a27b38cd17649b1bc720a33050dc520": {
"model_module": "@jupyter-widgets/controls",
"model_name": "FloatProgressModel",
"state": {
"_view_name": "ProgressView",
"style": "IPY_MODEL_f93601a0c6d84d8b9324fa2380e14d25",
"_dom_classes": [],
"description": "Iteration: 0%",
"_model_name": "FloatProgressModel",
"bar_style": "danger",
"max": 1369,
"_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_f30f39adee694c55bcbaa850cf031b69"
}
},
"16497f2b4de443bb9bb14ccaf0c94803": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HTMLModel",
"state": {
"_view_name": "HTMLView",
"style": "IPY_MODEL_ea4e4964058945f287eb2a6271b5bae7",
"_dom_classes": [],
"description": "",
"_model_name": "HTMLModel",
"placeholder": "",
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"value": " 0/1369 [00:00<?, ?it/s]",
"_view_count": null,
"_view_module_version": "1.5.0",
"description_tooltip": null,
"_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_1e74937c1f304d15ad49230b2428590d"
}
},
"f93601a0c6d84d8b9324fa2380e14d25": {
"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"
}
},
"f30f39adee694c55bcbaa850cf031b69": {
"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
}
},
"ea4e4964058945f287eb2a6271b5bae7": {
"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"
}
},
"1e74937c1f304d15ad49230b2428590d": {
"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
}
},
"df609e7f302e48949a49fae1b0deeb54": {
"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_be907685a2b949d0a088a907a2cb2a90",
"_model_module": "@jupyter-widgets/controls",
"children": [
"IPY_MODEL_743bba68cbe943d78ce63a1efd70d929",
"IPY_MODEL_f3fffc31462b49e193b3c24d600b4ddb"
]
}
},
"be907685a2b949d0a088a907a2cb2a90": {
"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
}
},
"743bba68cbe943d78ce63a1efd70d929": {
"model_module": "@jupyter-widgets/controls",
"model_name": "FloatProgressModel",
"state": {
"_view_name": "ProgressView",
"style": "IPY_MODEL_87fa58101b24400da90e4b0f87c7cb1a",
"_dom_classes": [],
"description": "100%",
"_model_name": "FloatProgressModel",
"bar_style": "success",
"max": 331,
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"value": 331,
"_view_count": null,
"_view_module_version": "1.5.0",
"orientation": "horizontal",
"min": 0,
"description_tooltip": null,
"_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_3c39d97054ba47a3ad3d9bb9a882756e"
}
},
"f3fffc31462b49e193b3c24d600b4ddb": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HTMLModel",
"state": {
"_view_name": "HTMLView",
"style": "IPY_MODEL_20855b3cb56944cfb0d6aa13bd06429a",
"_dom_classes": [],
"description": "",
"_model_name": "HTMLModel",
"placeholder": "",
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"value": " 331/331 [1:31:09<00:00, 16.52s/it]",
"_view_count": null,
"_view_module_version": "1.5.0",
"description_tooltip": null,
"_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_779d80cc14104171ab40ff53170e4807"
}
},
"87fa58101b24400da90e4b0f87c7cb1a": {
"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"
}
},
"3c39d97054ba47a3ad3d9bb9a882756e": {
"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
}
},
"20855b3cb56944cfb0d6aa13bd06429a": {
"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"
}
},
"779d80cc14104171ab40ff53170e4807": {
"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": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
"<a href=\"https://colab.research.google.com/github/patil-suraj/exploring-T5/blob/master/T5_on_TPU.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "_6q2San5Xh5N",
"colab_type": "text"
},
"source": [
"# T5 on TPU 💥🚀"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "knpacarPX2AN",
"colab_type": "text"
},
"source": [
"In this notebook we will see how to train T5 model on TPU with Huggingface's awesome new [trainer](https://github.com/huggingface/transformers/blob/master/src/transformers/trainer.py). We will train T5 base model on SQUAD dataset for QA task. We will use the recently released amazing [nlp](https://github.com/huggingface/nlp) package to load and process the dataset in just few lines.\n",
"\n",
"First make sure you are connected to the high RAM instance. This will not work on 12 GB colab instance."
]
},
{
"cell_type": "code",
"metadata": {
"id": "QLGiFCDqvuil",
"colab_type": "code",
"colab": {}
},
"source": [
"# Crash on purpose to get more ram :\n",
"import torch\n",
"torch.tensor([10.]*10000000000)"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "40CJSrN9ZiIP",
"colab_type": "text"
},
"source": [
"Let's install [PyTorch/XLA](https://github.com/pytorch/xla) which enables PyTorch on TPU. Make sure you install the nightly version, as the trainer breaks on other versions."
]
},
{
"cell_type": "code",
"metadata": {
"id": "coOmS2s_xDBy",
"colab_type": "code",
"outputId": "6ed0947e-4061-4ba7-9eca-72e7ed935bd6",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 907
}
},
"source": [
"VERSION = \"nightly\" #@param [\"1.5\" , \"20200325\", \"nightly\"]\n",
"!curl https://raw.githubusercontent.com/pytorch/xla/master/contrib/scripts/env-setup.py -o pytorch-xla-env-setup.py\n",
"!python pytorch-xla-env-setup.py --version $VERSION"
],
"execution_count": 5,
"outputs": [
{
"output_type": "stream",
"text": [
" % Total % Received % Xferd Average Speed Time Time Time Current\n",
" Dload Upload Total Spent Left Speed\n",
"\r 0 0 0 0 0 0 0 0 --:--:-- --:--:-- --:--:-- 0\r100 4264 100 4264 0 0 60914 0 --:--:-- --:--:-- --:--:-- 60914\n",
"Updating TPU and VM. This may take around 2 minutes.\n",
"Updating TPU runtime to pytorch-nightly ...\n",
"Uninstalling torch-1.5.0+cu101:\n",
"Done updating TPU runtime: <Response [200]>\n",
" Successfully uninstalled torch-1.5.0+cu101\n",
"Uninstalling torchvision-0.6.0+cu101:\n",
" Successfully uninstalled torchvision-0.6.0+cu101\n",
"Copying gs://tpu-pytorch/wheels/torch-nightly-cp36-cp36m-linux_x86_64.whl...\n",
"- [1 files][ 91.1 MiB/ 91.1 MiB] \n",
"Operation completed over 1 objects/91.1 MiB. \n",
"Copying gs://tpu-pytorch/wheels/torch_xla-nightly-cp36-cp36m-linux_x86_64.whl...\n",
"- [1 files][119.8 MiB/119.8 MiB] \n",
"Operation completed over 1 objects/119.8 MiB. \n",
"Copying gs://tpu-pytorch/wheels/torchvision-nightly-cp36-cp36m-linux_x86_64.whl...\n",
"/ [1 files][ 2.3 MiB/ 2.3 MiB] \n",
"Operation completed over 1 objects/2.3 MiB. \n",
"Processing ./torch-nightly-cp36-cp36m-linux_x86_64.whl\n",
"Requirement already satisfied: numpy in /usr/local/lib/python3.6/dist-packages (from torch==nightly) (1.18.4)\n",
"Requirement already satisfied: future in /usr/local/lib/python3.6/dist-packages (from torch==nightly) (0.16.0)\n",
"\u001b[31mERROR: fastai 1.0.61 requires torchvision, which is not installed.\u001b[0m\n",
"Installing collected packages: torch\n",
"Successfully installed torch-1.6.0a0+83df3be\n",
"Processing ./torch_xla-nightly-cp36-cp36m-linux_x86_64.whl\n",
"Installing collected packages: torch-xla\n",
"Successfully installed torch-xla-1.6+2191422\n",
"Processing ./torchvision-nightly-cp36-cp36m-linux_x86_64.whl\n",
"Requirement already satisfied: pillow>=4.1.1 in /usr/local/lib/python3.6/dist-packages (from torchvision==nightly) (7.0.0)\n",
"Requirement already satisfied: torch in /usr/local/lib/python3.6/dist-packages (from torchvision==nightly) (1.6.0a0+83df3be)\n",
"Requirement already satisfied: numpy in /usr/local/lib/python3.6/dist-packages (from torchvision==nightly) (1.18.4)\n",
"Requirement already satisfied: future in /usr/local/lib/python3.6/dist-packages (from torch->torchvision==nightly) (0.16.0)\n",
"Installing collected packages: torchvision\n",
"Successfully installed torchvision-0.7.0a0+348dd5a\n",
"Reading package lists... Done\n",
"Building dependency tree \n",
"Reading state information... Done\n",
"The following NEW packages will be installed:\n",
" libomp5\n",
"0 upgraded, 1 newly installed, 0 to remove and 31 not upgraded.\n",
"Need to get 234 kB of archives.\n",
"After this operation, 774 kB of additional disk space will be used.\n",
"Get:1 http://archive.ubuntu.com/ubuntu bionic/universe amd64 libomp5 amd64 5.0.1-1 [234 kB]\n",
"Fetched 234 kB in 1s (371 kB/s)\n",
"Selecting previously unselected package libomp5:amd64.\n",
"(Reading database ... 144433 files and directories currently installed.)\n",
"Preparing to unpack .../libomp5_5.0.1-1_amd64.deb ...\n",
"Unpacking libomp5:amd64 (5.0.1-1) ...\n",
"Setting up libomp5:amd64 (5.0.1-1) ...\n",
"Processing triggers for libc-bin (2.27-3ubuntu1) ...\n",
"/sbin/ldconfig.real: /usr/local/lib/python3.6/dist-packages/ideep4py/lib/libmkldnn.so.0 is not a symbolic link\n",
"\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "6-p80vyFZ-S8",
"colab_type": "text"
},
"source": [
"Install transformers and the nlp package. Restart colab after this"
]
},
{
"cell_type": "code",
"metadata": {
"id": "ptPupnLsfkMH",
"colab_type": "code",
"outputId": "94ed3f2e-a762-4969-cc6f-34382fc779ec",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 1000
}
},
"source": [
"!git clone https://github.com/huggingface/transformers.git\n",
"!pip install ./transformers\n",
"!pip install -U nlp"
],
"execution_count": 6,
"outputs": [
{
"output_type": "stream",
"text": [
"Cloning into 'transformers'...\n",
"remote: Enumerating objects: 94, done.\u001b[K\n",
"remote: Counting objects: 1% (1/94)\u001b[K\rremote: Counting objects: 2% (2/94)\u001b[K\rremote: Counting objects: 3% (3/94)\u001b[K\rremote: Counting objects: 4% (4/94)\u001b[K\rremote: Counting objects: 5% (5/94)\u001b[K\rremote: Counting objects: 6% (6/94)\u001b[K\rremote: Counting objects: 7% (7/94)\u001b[K\rremote: Counting objects: 8% (8/94)\u001b[K\rremote: Counting objects: 9% (9/94)\u001b[K\rremote: Counting objects: 10% (10/94)\u001b[K\rremote: Counting objects: 11% (11/94)\u001b[K\rremote: Counting objects: 12% (12/94)\u001b[K\rremote: Counting objects: 13% (13/94)\u001b[K\rremote: Counting objects: 14% (14/94)\u001b[K\rremote: Counting objects: 15% (15/94)\u001b[K\rremote: Counting objects: 17% (16/94)\u001b[K\rremote: Counting objects: 18% (17/94)\u001b[K\rremote: Counting objects: 19% (18/94)\u001b[K\rremote: Counting objects: 20% (19/94)\u001b[K\rremote: Counting objects: 21% (20/94)\u001b[K\rremote: Counting objects: 22% (21/94)\u001b[K\rremote: Counting objects: 23% (22/94)\u001b[K\rremote: Counting objects: 24% (23/94)\u001b[K\rremote: Counting objects: 25% (24/94)\u001b[K\rremote: Counting objects: 26% (25/94)\u001b[K\rremote: Counting objects: 27% (26/94)\u001b[K\rremote: Counting objects: 28% (27/94)\u001b[K\rremote: Counting objects: 29% (28/94)\u001b[K\rremote: Counting objects: 30% (29/94)\u001b[K\rremote: Counting objects: 31% (30/94)\u001b[K\rremote: Counting objects: 32% (31/94)\u001b[K\rremote: Counting objects: 34% (32/94)\u001b[K\rremote: Counting objects: 35% (33/94)\u001b[K\rremote: Counting objects: 36% (34/94)\u001b[K\rremote: Counting objects: 37% (35/94)\u001b[K\rremote: Counting objects: 38% (36/94)\u001b[K\rremote: Counting objects: 39% (37/94)\u001b[K\rremote: Counting objects: 40% (38/94)\u001b[K\rremote: Counting objects: 41% (39/94)\u001b[K\rremote: Counting objects: 42% (40/94)\u001b[K\rremote: Counting objects: 43% (41/94)\u001b[K\rremote: Counting objects: 44% (42/94)\u001b[K\rremote: Counting objects: 45% (43/94)\u001b[K\rremote: Counting objects: 46% (44/94)\u001b[K\rremote: Counting objects: 47% (45/94)\u001b[K\rremote: Counting objects: 48% (46/94)\u001b[K\rremote: Counting objects: 50% (47/94)\u001b[K\rremote: Counting objects: 51% (48/94)\u001b[K\rremote: Counting objects: 52% (49/94)\u001b[K\rremote: Counting objects: 53% (50/94)\u001b[K\rremote: Counting objects: 54% (51/94)\u001b[K\rremote: Counting objects: 55% (52/94)\u001b[K\rremote: Counting objects: 56% (53/94)\u001b[K\rremote: Counting objects: 57% (54/94)\u001b[K\rremote: Counting objects: 58% (55/94)\u001b[K\rremote: Counting objects: 59% (56/94)\u001b[K\rremote: Counting objects: 60% (57/94)\u001b[K\rremote: Counting objects: 61% (58/94)\u001b[K\rremote: Counting objects: 62% (59/94)\u001b[K\rremote: Counting objects: 63% (60/94)\u001b[K\rremote: Counting objects: 64% (61/94)\u001b[K\rremote: Counting objects: 65% (62/94)\u001b[K\rremote: Counting objects: 67% (63/94)\u001b[K\rremote: Counting objects: 68% (64/94)\u001b[K\rremote: Counting objects: 69% (65/94)\u001b[K\rremote: Counting objects: 70% (66/94)\u001b[K\rremote: Counting objects: 71% (67/94)\u001b[K\rremote: Counting objects: 72% (68/94)\u001b[K\rremote: Counting objects: 73% (69/94)\u001b[K\rremote: Counting objects: 74% (70/94)\u001b[K\rremote: Counting objects: 75% (71/94)\u001b[K\rremote: Counting objects: 76% (72/94)\u001b[K\rremote: Counting objects: 77% (73/94)\u001b[K\rremote: Counting objects: 78% (74/94)\u001b[K\rremote: Counting objects: 79% (75/94)\u001b[K\rremote: Counting objects: 80% (76/94)\u001b[K\rremote: Counting objects: 81% (77/94)\u001b[K\rremote: Counting objects: 82% (78/94)\u001b[K\rremote: Counting objects: 84% (79/94)\u001b[K\rremote: Counting objects: 85% (80/94)\u001b[K\rremote: Counting objects: 86% (81/94)\u001b[K\rremote: Counting objects: 87% (82/94)\u001b[K\rremote: Counting objects: 88% (83/94)\u001b[K\rremote: Counting objects: 89% (84/94)\u001b[K\rremote: Counting objects: 90% (85/94)\u001b[K\rremote: Counting objects: 91% (86/94)\u001b[K\rremote: Counting objects: 92% (87/94)\u001b[K\rremote: Counting objects: 93% (88/94)\u001b[K\rremote: Counting objects: 94% (89/94)\u001b[K\rremote: Counting objects: 95% (90/94)\u001b[K\rremote: Counting objects: 96% (91/94)\u001b[K\rremote: Counting objects: 97% (92/94)\u001b[K\rremote: Counting objects: 98% (93/94)\u001b[K\rremote: Counting objects: 100% (94/94)\u001b[K\rremote: Counting objects: 100% (94/94), done.\u001b[K\n",
"remote: Compressing objects: 100% (46/46), done.\u001b[K\n",
"remote: Total 26447 (delta 52), reused 66 (delta 32), pack-reused 26353\u001b[K\n",
"Receiving objects: 100% (26447/26447), 15.95 MiB | 29.37 MiB/s, done.\n",
"Resolving deltas: 100% (18423/18423), done.\n",
"Processing ./transformers\n",
"Requirement already satisfied: numpy in /usr/local/lib/python3.6/dist-packages (from transformers==2.9.1) (1.18.4)\n",
"Collecting tokenizers==0.7.0\n",
"\u001b[?25l Downloading https://files.pythonhosted.org/packages/14/e5/a26eb4716523808bb0a799fcfdceb6ebf77a18169d9591b2f46a9adb87d9/tokenizers-0.7.0-cp36-cp36m-manylinux1_x86_64.whl (3.8MB)\n",
"\u001b[K |████████████████████████████████| 3.8MB 3.5MB/s \n",
"\u001b[?25hRequirement already satisfied: filelock in /usr/local/lib/python3.6/dist-packages (from transformers==2.9.1) (3.0.12)\n",
"Requirement already satisfied: requests in /usr/local/lib/python3.6/dist-packages (from transformers==2.9.1) (2.23.0)\n",
"Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.6/dist-packages (from transformers==2.9.1) (4.41.1)\n",
"Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.6/dist-packages (from transformers==2.9.1) (2019.12.20)\n",
"Collecting sentencepiece\n",
"\u001b[?25l Downloading https://files.pythonhosted.org/packages/3b/88/49e772d686088e1278766ad68a463513642a2a877487decbd691dec02955/sentencepiece-0.1.90-cp36-cp36m-manylinux1_x86_64.whl (1.1MB)\n",
"\u001b[K |████████████████████████████████| 1.1MB 32.5MB/s \n",
"\u001b[?25hCollecting sacremoses\n",
"\u001b[?25l Downloading https://files.pythonhosted.org/packages/7d/34/09d19aff26edcc8eb2a01bed8e98f13a1537005d31e95233fd48216eed10/sacremoses-0.0.43.tar.gz (883kB)\n",
"\u001b[K |████████████████████████████████| 890kB 46.5MB/s \n",
"\u001b[?25hRequirement already satisfied: dataclasses in /usr/local/lib/python3.6/dist-packages (from transformers==2.9.1) (0.7)\n",
"Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.6/dist-packages (from requests->transformers==2.9.1) (2020.4.5.1)\n",
"Requirement already satisfied: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in /usr/local/lib/python3.6/dist-packages (from requests->transformers==2.9.1) (1.24.3)\n",
"Requirement already satisfied: chardet<4,>=3.0.2 in /usr/local/lib/python3.6/dist-packages (from requests->transformers==2.9.1) (3.0.4)\n",
"Requirement already satisfied: idna<3,>=2.5 in /usr/local/lib/python3.6/dist-packages (from requests->transformers==2.9.1) (2.9)\n",
"Requirement already satisfied: six in /usr/local/lib/python3.6/dist-packages (from sacremoses->transformers==2.9.1) (1.12.0)\n",
"Requirement already satisfied: click in /usr/local/lib/python3.6/dist-packages (from sacremoses->transformers==2.9.1) (7.1.2)\n",
"Requirement already satisfied: joblib in /usr/local/lib/python3.6/dist-packages (from sacremoses->transformers==2.9.1) (0.14.1)\n",
"Building wheels for collected packages: transformers, sacremoses\n",
" Building wheel for transformers (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
" Created wheel for transformers: filename=transformers-2.9.1-cp36-none-any.whl size=637722 sha256=d72ddcc31cb33178d6e0190c642ac0d5fe63801c03375fcf7c85b379c12a2938\n",
" Stored in directory: /tmp/pip-ephem-wheel-cache-417x3jto/wheels/23/19/dd/2561a4e47240cf6b307729d58e56f8077dd0c698f5992216cf\n",
" Building wheel for sacremoses (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
" Created wheel for sacremoses: filename=sacremoses-0.0.43-cp36-none-any.whl size=893260 sha256=7d348f2205ae5ec3039f13604ba844a8aa8083f6b9a96382cb0b3ee487157340\n",
" Stored in directory: /root/.cache/pip/wheels/29/3c/fd/7ce5c3f0666dab31a50123635e6fb5e19ceb42ce38d4e58f45\n",
"Successfully built transformers sacremoses\n",
"Installing collected packages: tokenizers, sentencepiece, sacremoses, transformers\n",
"Successfully installed sacremoses-0.0.43 sentencepiece-0.1.90 tokenizers-0.7.0 transformers-2.9.1\n",
"Collecting nlp\n",
"\u001b[?25l Downloading https://files.pythonhosted.org/packages/21/17/0a408ac3403c71c978e7906146c69ed00b18712a4548e34d0ffb567c34cc/nlp-0.1.0-py3-none-any.whl (87kB)\n",
"\u001b[K |████████████████████████████████| 92kB 2.9MB/s \n",
"\u001b[?25hRequirement already satisfied, skipping upgrade: numpy in /usr/local/lib/python3.6/dist-packages (from nlp) (1.18.4)\n",
"Requirement already satisfied, skipping upgrade: tqdm>=4.27 in /usr/local/lib/python3.6/dist-packages (from nlp) (4.41.1)\n",
"Collecting pyarrow>=0.16.0\n",
"\u001b[?25l Downloading https://files.pythonhosted.org/packages/8c/d8/ff07b4cf88362ae4bebe5b7ffc357e2e6c773cdf2db8fec1bf9e973012dd/pyarrow-0.17.0-cp36-cp36m-manylinux2014_x86_64.whl (63.8MB)\n",
"\u001b[K |████████████████████████████████| 63.8MB 69kB/s \n",
"\u001b[?25hRequirement already satisfied, skipping upgrade: dataclasses; python_version < \"3.7\" in /usr/local/lib/python3.6/dist-packages (from nlp) (0.7)\n",
"Requirement already satisfied, skipping upgrade: filelock in /usr/local/lib/python3.6/dist-packages (from nlp) (3.0.12)\n",
"Requirement already satisfied, skipping upgrade: requests>=2.19.0 in /usr/local/lib/python3.6/dist-packages (from nlp) (2.23.0)\n",
"Requirement already satisfied, skipping upgrade: dill in /usr/local/lib/python3.6/dist-packages (from nlp) (0.3.1.1)\n",
"Requirement already satisfied, skipping upgrade: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in /usr/local/lib/python3.6/dist-packages (from requests>=2.19.0->nlp) (1.24.3)\n",
"Requirement already satisfied, skipping upgrade: idna<3,>=2.5 in /usr/local/lib/python3.6/dist-packages (from requests>=2.19.0->nlp) (2.9)\n",
"Requirement already satisfied, skipping upgrade: chardet<4,>=3.0.2 in /usr/local/lib/python3.6/dist-packages (from requests>=2.19.0->nlp) (3.0.4)\n",
"Requirement already satisfied, skipping upgrade: certifi>=2017.4.17 in /usr/local/lib/python3.6/dist-packages (from requests>=2.19.0->nlp) (2020.4.5.1)\n",
"Installing collected packages: pyarrow, nlp\n",
" Found existing installation: pyarrow 0.14.1\n",
" Uninstalling pyarrow-0.14.1:\n",
" Successfully uninstalled pyarrow-0.14.1\n",
"Successfully installed nlp-0.1.0 pyarrow-0.17.0\n"
],
"name": "stdout"
},
{
"output_type": "display_data",
"data": {
"application/vnd.colab-display-data+json": {
"pip_warning": {
"packages": [
"pyarrow"
]
}
}
},
"metadata": {
"tags": []
}
},
{
"output_type": "stream",
"text": [
"--2020-05-16 16:02:40-- https://raw.githubusercontent.com/huggingface/transformers/2d184cb553ee20943b03b253f44300e466357871/examples/xla_spawn.py\n",
"Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 151.101.0.133, 151.101.64.133, 151.101.128.133, ...\n",
"Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|151.101.0.133|:443... connected.\n",
"HTTP request sent, awaiting response... 200 OK\n",
"Length: 1913 (1.9K) [text/plain]\n",
"Saving to: ‘xla_spawn.py’\n",
"\n",
"\rxla_spawn.py 0%[ ] 0 --.-KB/s \rxla_spawn.py 100%[===================>] 1.87K --.-KB/s in 0s \n",
"\n",
"2020-05-16 16:02:41 (40.3 MB/s) - ‘xla_spawn.py’ saved [1913/1913]\n",
"\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "zFWlfEJllAcw",
"colab_type": "text"
},
"source": [
"## Load and process data"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "NVOz2QUtaKQb",
"colab_type": "text"
},
"source": [
"Let's load and process the dataset using the nlp library. We will process the examples in follwoing way to cast QA task in text-to-text setting\n",
"\n",
"**input**\n",
"question: question_text context: context \n",
"\n",
"**target**\n",
"answer_text"
]
},
{
"cell_type": "code",
"metadata": {
"id": "CaRw0ke1e1sF",
"colab_type": "code",
"colab": {}
},
"source": [
"import torch\n",
"import nlp\n",
"from transformers import T5Tokenizer"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "NaGYDvKUe8VS",
"colab_type": "code",
"outputId": "a8cba6aa-c83d-4efb-d5ee-9bc6831509af",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 66,
"referenced_widgets": [
"44ca82b3bbc5432eadc4f6fa3b81f483",
"9a58f575a463454aba3a52742abf00bf",
"6217a8ed0c634a5bbcbb4070d61d2ce3",
"9542805d664d451aa33a5bd7cc36d614",
"f90e54ee9dee42a99f38fdf2186cea62",
"2085a86f64a04a1586fefa0fe1413406",
"8e0c79e36d8c4d1faab99cc565feeb17",
"413ae83fdf9d4573b2c2dc053db83aa2"
]
}
},
"source": [
"tokenizer = T5Tokenizer.from_pretrained('t5-base')"
],
"execution_count": 2,
"outputs": [
{
"output_type": "display_data",
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "44ca82b3bbc5432eadc4f6fa3b81f483",
"version_minor": 0,
"version_major": 2
},
"text/plain": [
"HBox(children=(FloatProgress(value=0.0, description='Downloading', max=791656.0, style=ProgressStyle(descripti…"
]
},
"metadata": {
"tags": []
}
},
{
"output_type": "stream",
"text": [
"\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "-gJOEe0Ye0di",
"colab_type": "code",
"colab": {}
},
"source": [
"# process the examples in input and target text format and the eos token at the end \n",
"def add_eos_to_examples(example):\n",
" example['input_text'] = 'question: %s context: %s </s>' % (example['question'], example['context'])\n",
" example['target_text'] = '%s </s>' % example['answers']['text'][0]\n",
" return example\n",
"\n",
"# tokenize the examples\n",
"def convert_to_features(example_batch):\n",
" input_encodings = tokenizer.batch_encode_plus(example_batch['input_text'], pad_to_max_length=True, max_length=512)\n",
" target_encodings = tokenizer.batch_encode_plus(example_batch['target_text'], pad_to_max_length=True, max_length=16)\n",
"\n",
" encodings = {\n",
" 'input_ids': input_encodings['input_ids'], \n",
" 'attention_mask': input_encodings['attention_mask'],\n",
" 'target_ids': target_encodings['input_ids'],\n",
" 'target_attention_mask': target_encodings['attention_mask']\n",
" }\n",
"\n",
" return encodings"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "2ZWE4addfSmi",
"colab_type": "code",
"outputId": "aee10e16-998e-45cd-feaa-e05d1f42283b",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 333,
"referenced_widgets": [
"d7fa301d6f7d498bac466849f04321c5",
"0f662bc0fa4444f386ec8975b4289f04",
"a2b08cf2bb834808b02d20fbee2f00ab",
"5efd16badcb64aa3a708975504feade1",
"a763d584af9147bcbe5430f95bf16925",
"329f27a50bee452b8f5ee719929fb33b",
"0be03081b1324f79a99bdbe926c30e89",
"dca7ff44a73a4c9f872cb2596c3c729e",
"d530b763a0e9415f9b8b1f1787a66619",
"7b85b787b5d9490c994f9e406835813b",
"f86c72c0da864856b9ddb55568fe4a2b",
"a4e0f5b0b3cf4091a44bad74e5abb62e",
"3ecc3e6a31db4835987c22b81a85c23f",
"7c062b51acab4bb59eeb4269d5e6c2df",
"7fbf906e11d24bfdb90e3f0ce46250c1",
"43deb763aee24506a82dd795cd126f49",
"6af39625f78e4e5989739eff7e8849f6",
"d97ac4c36e7944fdb989cf7ee1851350",
"2539f0244f0e468a993609fd562ff1f5",
"17025b38dedb45a39a95ffe7b6117d87",
"b6dde636eb51433fb5be7af2cedc2774",
"ff877f980dd34d2d9f3a4d3efb50af0c",
"cde27b62215448be92d8c8fa2292438a",
"5b66084b700145d5903aa91bcd2920f7",
"741a693169b54851a4cb47369dd9bd1e",
"eb0f02133b9140be92288fd6a8415deb",
"03a75d6d64524d47a3df6457e1901cbd",
"b4a2213a0a0b421d895269733344cc9d",
"64e947e3d9e440cf9f3880cb2325e57a",
"108bbc9991614357aae4469fc19b4859",
"6792931cb55944deb260f07d6bf87931",
"3cb18f41264740c9933f159a9820ad77",
"004faf88da144ad2bd3e50b5b9766627",
"f02e5f34ac414081ab2882b2ab7ff64d",
"41c3aac64e424e1db59b723a11bb0fb0",
"44540a280fb141979bdeff7f93d0cde2",
"f9c604fa9a8642eaa218824b8ab651fe",
"34e5dacca6fc4497abda0a2ad37996e0",
"8bd88e5bf56e45bbbc1d339b00eff57c",
"93b33f1c33de44b4a1e57fb4133343c9",
"3ec93bdea33b40ba82e24b4a0e605bc0",
"121c3099d6e04079a4f6bf5707e0c60d",
"4f17790e2f594811bbfe55c9d883cf41",
"602e1a740e8f41fb800dbb3af0ea04f9",
"c1628c0657a44cf0873f2d64c9fb549c",
"99f6bf35ae7f4e66b4d339fe93768c7c",
"d73cf402af074a5481bf900e6abe2c63",
"0b2c415901d8468fb3f9acb63dd2f4e3"
]
}
},
"source": [
"# load train and validation split of squad\n",
"train_dataset = nlp.load_dataset('squad', split=nlp.Split.TRAIN)\n",
"valid_dataset = nlp.load_dataset('squad', split=nlp.Split.VALIDATION)\n",
"\n",
"# map add_eos_to_examples function to the dataset example wise \n",
"train_dataset = train_dataset.map(add_eos_to_examples)\n",
"# map convert_to_features batch wise\n",
"train_dataset = train_dataset.map(convert_to_features, batched=True)\n",
"\n",
"valid_dataset = valid_dataset.map(add_eos_to_examples, load_from_cache_file=False)\n",
"valid_dataset = valid_dataset.map(convert_to_features, batched=True, load_from_cache_file=False)\n",
"\n",
"\n",
"# set the tensor type and the columns which the dataset should return\n",
"columns = ['input_ids', 'target_ids', 'attention_mask', 'target_attention_mask']\n",
"train_dataset.set_format(type='torch', columns=columns)\n",
"valid_dataset.set_format(type='torch', columns=columns)"
],
"execution_count": 4,
"outputs": [
{
"output_type": "display_data",
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "d7fa301d6f7d498bac466849f04321c5",
"version_minor": 0,
"version_major": 2
},
"text/plain": [
"HBox(children=(FloatProgress(value=0.0, description='Downloading', max=4997.0, style=ProgressStyle(description…"
]
},
"metadata": {
"tags": []
}
},
{
"output_type": "stream",
"text": [
"\n"
],
"name": "stdout"
},
{
"output_type": "display_data",
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "d530b763a0e9415f9b8b1f1787a66619",
"version_minor": 0,
"version_major": 2
},
"text/plain": [
"HBox(children=(FloatProgress(value=0.0, description='Downloading', max=2240.0, style=ProgressStyle(description…"
]
},
"metadata": {
"tags": []
}
},
{
"output_type": "stream",
"text": [
"\n",
"Downloading and preparing dataset squad/plain_text (download: 33.51 MiB, generated: 85.75 MiB, total: 119.27 MiB) to /root/.cache/huggingface/datasets/squad/plain_text/1.0.0...\n"
],
"name": "stdout"
},
{
"output_type": "display_data",
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "6af39625f78e4e5989739eff7e8849f6",
"version_minor": 0,
"version_major": 2
},
"text/plain": [
"HBox(children=(FloatProgress(value=0.0, description='Downloading', max=8116577.0, style=ProgressStyle(descript…"
]
},
"metadata": {
"tags": []
}
},
{
"output_type": "stream",
"text": [
"\n"
],
"name": "stdout"
},
{
"output_type": "display_data",
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "741a693169b54851a4cb47369dd9bd1e",
"version_minor": 0,
"version_major": 2
},
"text/plain": [
"HBox(children=(FloatProgress(value=0.0, description='Downloading', max=1054280.0, style=ProgressStyle(descript…"
]
},
"metadata": {
"tags": []
}
},
{
"output_type": "stream",
"text": [
"\n"
],
"name": "stdout"
},
{
"output_type": "display_data",
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "004faf88da144ad2bd3e50b5b9766627",
"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": [
"\r"
],
"name": "stdout"
},
{
"output_type": "display_data",
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "3ec93bdea33b40ba82e24b4a0e605bc0",
"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": [
"\rDataset squad downloaded and prepared to /root/.cache/huggingface/datasets/squad/plain_text/1.0.0. Subsequent calls will reuse this data.\n"
],
"name": "stdout"
},
{
"output_type": "stream",
"text": [
"87599it [00:04, 19002.06it/s]\n",
"100%|██████████| 88/88 [00:50<00:00, 1.75it/s]\n",
"10570it [00:00, 18815.95it/s]\n",
"100%|██████████| 11/11 [00:06<00:00, 1.77it/s]\n"
],
"name": "stderr"
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "vXJ24xVmlMoN",
"colab_type": "code",
"outputId": "a12ce45b-09bc-462f-dae4-f2278c9442c5",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 34
}
},
"source": [
"len(train_dataset), len(valid_dataset)"
],
"execution_count": 5,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"(87599, 10570)"
]
},
"metadata": {
"tags": []
},
"execution_count": 5
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "UYOvGLdVgoxt",
"colab_type": "code",
"colab": {}
},
"source": [
"# cach the dataset, so we can load it directly for training\n",
"\n",
"torch.save(train_dataset, 'train_data.pt')\n",
"torch.save(valid_dataset, 'valid_data.pt')"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "NASBkGrtnbgj",
"colab_type": "text"
},
"source": [
"For more details on how to use the nlp library check out this [notebook](https://colab.research.google.com/github/huggingface/nlp/blob/master/notebooks/Overview.ipynb)."
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "tty8vuMBqI5L",
"colab_type": "text"
},
"source": [
"## Write training script"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "djKKcgN1cvAX",
"colab_type": "text"
},
"source": [
"Using the `Trainer` is pretty straightforward. Here are the 4 basic steps which are needed to use trainer.\n",
"\n",
"1. **Parse the arguments needed**. These are divided in 3 parts for clarity and seperation (TrainingArguments, ModelArguments and DataTrainingArguments).\n",
"\n",
" 1. **TrainingArguments**: These are basicaly the training hyperparameters such as learning rate, batch size, weight decay, gradient accumulation steps etc. See all possible arguments [here](https://github.com/huggingface/transformers/blob/master/src/transformers/training_args.py). These are used by the Trainer.\n",
"\n",
" 2. **ModelArguments**: These are the arguments for the model that you want to use such as the model_name_or_path, tokenizer_name etc. You'll need these to load the model and tokenizer.\n",
"\n",
" 3. **DataTrainingArguments**: These are as the name suggests arguments needed for the dataset. Such as the directory name where your files are stored etc. You'll need these to load/process the dataset.\n",
"\n",
" TrainingArguments are already defined in the `TrainingArguments` class, you'll need to define `ModelArguments` and `DataTrainingArguments` classes for your task.\n",
"\n",
"\n",
"\n",
"\n",
"2. Load train and eval datasets\n",
"3. Initialize the `Trainer`\n",
"\n",
" These are the mininum parameters which you'll for initializing `Trainer`. For full list check [here](https://github.com/huggingface/transformers/blob/master/src/transformers/trainer.py#L107)\n",
"\n",
" ```\n",
" model: PreTrainedModel\n",
" args: TrainingArguments\n",
" train_dataset: Optional[Dataset]\n",
" eval_dataset: Optional[Dataset]\n",
" ```\n",
"4. Start training with `trainer.train`\n",
"\n",
" Call `trainer.train` and let the magic begin!\n",
"\n",
"\n",
"There are lots of things which the trainer handles for you out of the box such as gradient_accumulation, fp16 training, setting up the optimizer and scheduler, logging with wandb etc. I didn't set-up wandb for this experiment, but will explore it for sure in future experiment."
]
},
{
"cell_type": "code",
"metadata": {
"id": "KdmKlMkfcLa0",
"colab_type": "code",
"colab": {}
},
"source": [
"import dataclasses\n",
"import logging\n",
"import os\n",
"import sys\n",
"from dataclasses import dataclass, field\n",
"from typing import Dict, List, Optional\n",
"\n",
"import numpy as np\n",
"import torch\n",
"\n",
"from transformers import T5ForConditionalGeneration, T5Tokenizer, EvalPrediction\n",
"from transformers import (\n",
" HfArgumentParser,\n",
" DataCollator,\n",
" Trainer,\n",
" TrainingArguments,\n",
" set_seed,\n",
")\n",
"\n",
"\n",
"logger = logging.getLogger(__name__)\n",
"\n",
"# prepares lm_labels from target_ids, returns examples with keys as expected by the forward method\n",
"# this is necessacry because the trainer directly passes this dict as arguments to the model\n",
"# so make sure the keys match the parameter names of the forward method\n",
"@dataclass\n",
"class T2TDataCollator(DataCollator):\n",
" def collate_batch(self, batch: List) -> Dict[str, torch.Tensor]:\n",
" \"\"\"\n",
" Take a list of samples from a Dataset and collate them into a batch.\n",
" Returns:\n",
" A dictionary of tensors\n",
" \"\"\"\n",
" input_ids = torch.stack([example['input_ids'] for example in batch])\n",
" lm_labels = torch.stack([example['target_ids'] for example in batch])\n",
" lm_labels[lm_labels[:, :] == 0] = -100\n",
" attention_mask = torch.stack([example['attention_mask'] for example in batch])\n",
" decoder_attention_mask = torch.stack([example['target_attention_mask'] for example in batch])\n",
" \n",
"\n",
" return {\n",
" 'input_ids': input_ids, \n",
" 'attention_mask': attention_mask,\n",
" 'lm_labels': lm_labels, \n",
" 'decoder_attention_mask': decoder_attention_mask\n",
" }\n",
"\n",
"\n",
"@dataclass\n",
"class ModelArguments:\n",
" \"\"\"\n",
" Arguments pertaining to which model/config/tokenizer we are going to fine-tune from.\n",
" \"\"\"\n",
"\n",
" model_name_or_path: str = field(\n",
" metadata={\"help\": \"Path to pretrained model or model identifier from huggingface.co/models\"}\n",
" )\n",
" tokenizer_name: Optional[str] = field(\n",
" default=None, metadata={\"help\": \"Pretrained tokenizer name or path if not the same as model_name\"}\n",
" )\n",
" cache_dir: Optional[str] = field(\n",
" default=None, metadata={\"help\": \"Where do you want to store the pretrained models downloaded from s3\"}\n",
" )\n",
"\n",
"@dataclass\n",
"class DataTrainingArguments:\n",
" \"\"\"\n",
" Arguments pertaining to what data we are going to input our model for training and eval.\n",
" \"\"\"\n",
" train_file_path: Optional[str] = field(\n",
" default='train_data.pt',\n",
" metadata={\"help\": \"Path for cached train dataset\"},\n",
" )\n",
" valid_file_path: Optional[str] = field(\n",
" default='valid_data.pt',\n",
" metadata={\"help\": \"Path for cached valid dataset\"},\n",
" )\n",
" max_len: Optional[int] = field(\n",
" default=512,\n",
" metadata={\"help\": \"Max input length for the source text\"},\n",
" )\n",
" target_max_len: Optional[int] = field(\n",
" default=32,\n",
" metadata={\"help\": \"Max input length for the target text\"},\n",
" )\n",
"\n",
"\n",
"def main():\n",
" # See all possible arguments in src/transformers/training_args.py\n",
" # or by passing the --help flag to this script.\n",
" # We now keep distinct sets of args, for a cleaner separation of concerns.\n",
"\n",
" parser = HfArgumentParser((ModelArguments, DataTrainingArguments, TrainingArguments))\n",
"\n",
" # we will load the arguments from a json file, \n",
" #make sure you save the arguments in at ./args.json\n",
" model_args, data_args, training_args = parser.parse_json_file(json_file=os.path.abspath('args.json'))\n",
"\n",
" if (\n",
" os.path.exists(training_args.output_dir)\n",
" and os.listdir(training_args.output_dir)\n",
" and training_args.do_train\n",
" and not training_args.overwrite_output_dir\n",
" ):\n",
" raise ValueError(\n",
" f\"Output directory ({training_args.output_dir}) already exists and is not empty. Use --overwrite_output_dir to overcome.\"\n",
" )\n",
"\n",
" # Setup logging\n",
" logging.basicConfig(\n",
" format=\"%(asctime)s - %(levelname)s - %(name)s - %(message)s\",\n",
" datefmt=\"%m/%d/%Y %H:%M:%S\",\n",
" level=logging.INFO if training_args.local_rank in [-1, 0] else logging.WARN,\n",
" )\n",
" logger.warning(\n",
" \"Process rank: %s, device: %s, n_gpu: %s, distributed training: %s, 16-bits training: %s\",\n",
" training_args.local_rank,\n",
" training_args.device,\n",
" training_args.n_gpu,\n",
" bool(training_args.local_rank != -1),\n",
" training_args.fp16,\n",
" )\n",
" logger.info(\"Training/evaluation parameters %s\", training_args)\n",
"\n",
" # Set seed\n",
" set_seed(training_args.seed)\n",
"\n",
" # Load pretrained model and tokenizer\n",
" #\n",
" # Distributed training:\n",
" # The .from_pretrained methods guarantee that only one local process can concurrently\n",
" # download model & vocab.\n",
"\n",
" tokenizer = T5Tokenizer.from_pretrained(\n",
" model_args.tokenizer_name if model_args.tokenizer_name else model_args.model_name_or_path,\n",
" cache_dir=model_args.cache_dir,\n",
" )\n",
" model = T5ForConditionalGeneration.from_pretrained(\n",
" model_args.model_name_or_path,\n",
" cache_dir=model_args.cache_dir,\n",
" )\n",
"\n",
" # Get datasets\n",
" print('loading data')\n",
" train_dataset = torch.load(data_args.train_file_path)\n",
" valid_dataset = torch.load(data_args.valid_file_path)\n",
" print('loading done')\n",
"\n",
" # Initialize our Trainer\n",
" trainer = Trainer(\n",
" model=model,\n",
" args=training_args,\n",
" train_dataset=train_dataset,\n",
" eval_dataset=valid_dataset,\n",
" data_collator=T2TDataCollator(),\n",
" prediction_loss_only=True\n",
" )\n",
"\n",
" # Training\n",
" if training_args.do_train:\n",
" trainer.train(\n",
" model_path=model_args.model_name_or_path if os.path.isdir(model_args.model_name_or_path) else None\n",
" )\n",
" trainer.save_model()\n",
" # For convenience, we also re-save the tokenizer to the same directory,\n",
" # so that you can share your model easily on huggingface.co/models =)\n",
" if trainer.is_world_master():\n",
" tokenizer.save_pretrained(training_args.output_dir)\n",
"\n",
" # Evaluation\n",
" results = {}\n",
" if training_args.do_eval and training_args.local_rank in [-1, 0]:\n",
" logger.info(\"*** Evaluate ***\")\n",
"\n",
" eval_output = trainer.evaluate()\n",
"\n",
" output_eval_file = os.path.join(training_args.output_dir, \"eval_results.txt\")\n",
" with open(output_eval_file, \"w\") as writer:\n",
" logger.info(\"***** Eval results *****\")\n",
" for key in sorted(eval_output.keys()):\n",
" logger.info(\" %s = %s\", key, str(eval_output[key]))\n",
" writer.write(\"%s = %s\\n\" % (key, str(eval_output[key])))\n",
" \n",
" results.update(eval_output)\n",
" \n",
" return results\n",
"\n",
"\n",
"def _mp_fn(index):\n",
" # For xla_spawn (TPUs)\n",
" main()"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "15duw24hqMBy",
"colab_type": "text"
},
"source": [
"## Train"
]
},
{
"cell_type": "code",
"metadata": {
"id": "n1I6IhBM1KV2",
"colab_type": "code",
"colab": {}
},
"source": [
"import json"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "zOvs9RUllLTw",
"colab_type": "text"
},
"source": [
"Let's write the arguments in a dict and store in a json file. The above code will load this file and parse the arguments."
]
},
{
"cell_type": "code",
"metadata": {
"id": "2ObtXlBVuJqv",
"colab_type": "code",
"colab": {}
},
"source": [
"args_dict = {\n",
" \"num_cores\": 8,\n",
" 'training_script': 'train_t5_squad.py',\n",
" \"model_name_or_path\": 't5-base',\n",
" \"max_len\": 512 ,\n",
" \"target_max_len\": 16,\n",
" \"output_dir\": './models/tpu',\n",
" \"overwrite_output_dir\": True,\n",
" \"per_gpu_train_batch_size\": 8,\n",
" \"per_gpu_eval_batch_size\": 8,\n",
" \"gradient_accumulation_steps\": 4,\n",
" \"learning_rate\": 1e-4,\n",
" \"tpu_num_cores\": 8,\n",
" \"num_train_epochs\": 4,\n",
" \"do_train\": True\n",
"}"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "xU5MI8ju1L3w",
"colab_type": "code",
"colab": {}
},
"source": [
"with open('args.json', 'w') as f:\n",
" json.dump(args_dict, f)"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "AsQB1Kpjlltp",
"colab_type": "text"
},
"source": [
"Start training!"
]
},
{
"cell_type": "code",
"metadata": {
"id": "UnGuDVPYuyo4",
"colab_type": "code",
"colab": {}
},
"source": [
"import torch_xla.distributed.xla_multiprocessing as xmp"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "X9_Go99fvW-z",
"colab_type": "code",
"outputId": "784c2b84-ecb2-4a2a-871b-dc63f63ccc74",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 1000,
"referenced_widgets": [
"1d197b0946534a91b2eb4595baade174",
"55c18e9169ab44c981de4cb2ebaea578",
"21065bd4f9fa4d97a20a25c9a35b7737",
"88d28cee2f02428aa3c4c22a873d6385",
"12d2d5b9a3f54b25aa8fef6439625db6",
"32f70451efa6473a8a00807dd22a3248",
"17c358e37fc346a9ac8ce475599e495a",
"947afd4c522443b38bc223114178c7ee",
"a558cfceca8b43568dfad2267a534a35",
"7a5270ddb66447af9fba298e830fe8a4",
"d961f9fa40a04ceda3e1962eef4d33cc",
"d9363dcd670643e6ad2d0b65c4238b98",
"b25b3d9394be4ac786678181c800e926",
"3fed14bdec8b4162887d77dea7a9f289",
"5051978cf84f4f8191c1e3ad4661776e",
"f67b49a0d48f4714a124bc972e9afa0f",
"2c4d7bdf7f6c48f0825ef87a12399f39",
"391fc0937c3b48f8b4c3b33a1c3849a0",
"11c6ff7dfb19436c920c5114734c0ec9",
"3b3722a55e3d43bc93c29a505895a25c",
"f46743ac2da84d6ca77180d8686ead6b",
"1b0e2b414d6843ae9c918db417ffff4d",
"e7559a6907f7479db7764f80c4501993",
"5f89a141b34d478e861ea6bd4a17dcd2",
"a9a7aeae6fa74b67a349a69e845f8898",
"0a9d6c739f984b91a0e17724707eb7e1",
"1ed37d3716374294b072524937625965",
"4b44de48aeeb4b8dbc9388fc7f7da227",
"051052ef94d447a4b0233225d8f5ae81",
"3e43d0668e6f461c9cc461aa735a4437",
"43e265f386ca4dfd88e226a87f32775c",
"6568a6e42f734c29ad5c26f2397a5a69",
"c227333162114432a38b1480ec837701",
"71a3e5b846a74f409dfd029ea3bf5d61",
"8a27b38cd17649b1bc720a33050dc520",
"16497f2b4de443bb9bb14ccaf0c94803",
"f93601a0c6d84d8b9324fa2380e14d25",
"f30f39adee694c55bcbaa850cf031b69",
"ea4e4964058945f287eb2a6271b5bae7",
"1e74937c1f304d15ad49230b2428590d"
]
}
},
"source": [
"xmp.spawn(_mp_fn, args=(), nprocs=8, start_method='fork')"
],
"execution_count": 0,
"outputs": [
{
"output_type": "stream",
"text": [
"05/16/2020 09:42:27 - INFO - transformers.training_args - PyTorch: setting up devices\n",
"05/16/2020 09:42:27 - WARNING - __main__ - Process rank: -1, device: xla:1, n_gpu: 0, distributed training: False, 16-bits training: False\n",
"05/16/2020 09:42:27 - INFO - __main__ - Training/evaluation parameters TrainingArguments(output_dir='./models/tpu', overwrite_output_dir=True, do_train=True, do_eval=False, do_predict=False, evaluate_during_training=False, per_gpu_train_batch_size=8, per_gpu_eval_batch_size=8, gradient_accumulation_steps=4, learning_rate=0.0001, weight_decay=0.0, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=4, max_steps=-1, warmup_steps=0, logging_dir=None, logging_first_step=False, logging_steps=500, save_steps=500, save_total_limit=None, no_cuda=False, seed=42, fp16=False, fp16_opt_level='O1', local_rank=-1, tpu_num_cores=8, tpu_metrics_debug=False)\n",
"05/16/2020 09:42:27 - INFO - transformers.tokenization_utils - loading file https://s3.amazonaws.com/models.huggingface.co/bert/t5-spiece.model from cache at /root/.cache/torch/transformers/68f1b8dbca4350743bb54b8c4169fd38cbabaad564f85a9239337a8d0342af9f.9995af32582a1a7062cb3173c118cb7b4636fa03feb967340f20fc37406f021f\n",
"05/16/2020 09:42:27 - INFO - transformers.configuration_utils - loading configuration file https://s3.amazonaws.com/models.huggingface.co/bert/t5-base-config.json from cache at /root/.cache/torch/transformers/40578967d1f029acb6162b36db9d8b4307063e885990ccd297c2c5be1cf1b3d7.2995d650f5eba18c8baa4146e210d32d56165e90d374281741fc78b872cd6c9b\n",
"05/16/2020 09:42:27 - INFO - transformers.configuration_utils - Model config T5Config {\n",
" \"architectures\": [\n",
" \"T5WithLMHeadModel\"\n",
" ],\n",
" \"d_ff\": 3072,\n",
" \"d_kv\": 64,\n",
" \"d_model\": 768,\n",
" \"decoder_start_token_id\": 0,\n",
" \"dropout_rate\": 0.1,\n",
" \"eos_token_id\": 1,\n",
" \"initializer_factor\": 1.0,\n",
" \"is_encoder_decoder\": true,\n",
" \"layer_norm_epsilon\": 1e-06,\n",
" \"model_type\": \"t5\",\n",
" \"n_positions\": 512,\n",
" \"num_heads\": 12,\n",
" \"num_layers\": 12,\n",
" \"output_past\": true,\n",
" \"pad_token_id\": 0,\n",
" \"relative_attention_num_buckets\": 32,\n",
" \"task_specific_params\": {\n",
" \"summarization\": {\n",
" \"early_stopping\": true,\n",
" \"length_penalty\": 2.0,\n",
" \"max_length\": 200,\n",
" \"min_length\": 30,\n",
" \"no_repeat_ngram_size\": 3,\n",
" \"num_beams\": 4,\n",
" \"prefix\": \"summarize: \"\n",
" },\n",
" \"translation_en_to_de\": {\n",
" \"early_stopping\": true,\n",
" \"max_length\": 300,\n",
" \"num_beams\": 4,\n",
" \"prefix\": \"translate English to German: \"\n",
" },\n",
" \"translation_en_to_fr\": {\n",
" \"early_stopping\": true,\n",
" \"max_length\": 300,\n",
" \"num_beams\": 4,\n",
" \"prefix\": \"translate English to French: \"\n",
" },\n",
" \"translation_en_to_ro\": {\n",
" \"early_stopping\": true,\n",
" \"max_length\": 300,\n",
" \"num_beams\": 4,\n",
" \"prefix\": \"translate English to Romanian: \"\n",
" }\n",
" },\n",
" \"vocab_size\": 32128\n",
"}\n",
"\n",
"05/16/2020 09:42:27 - INFO - transformers.modeling_utils - loading weights file https://cdn.huggingface.co/t5-base-pytorch_model.bin from cache at /root/.cache/torch/transformers/f6f2fde9fa7611f4eff74620de9cbe734e7a717b5b143bd283cae4c2d6022990.54f906ff53bd09195cfc183a29cadc81b7705f07fcdb796d24163cb632b6bdfa\n",
"05/16/2020 09:42:29 - INFO - transformers.training_args - PyTorch: setting up devices\n",
"05/16/2020 09:42:29 - WARNING - __main__ - Process rank: -1, device: xla:0, n_gpu: 0, distributed training: False, 16-bits training: False\n",
"05/16/2020 09:42:29 - INFO - __main__ - Training/evaluation parameters TrainingArguments(output_dir='./models/tpu', overwrite_output_dir=True, do_train=True, do_eval=False, do_predict=False, evaluate_during_training=False, per_gpu_train_batch_size=8, per_gpu_eval_batch_size=8, gradient_accumulation_steps=4, learning_rate=0.0001, weight_decay=0.0, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=4, max_steps=-1, warmup_steps=0, logging_dir=None, logging_first_step=False, logging_steps=500, save_steps=500, save_total_limit=None, no_cuda=False, seed=42, fp16=False, fp16_opt_level='O1', local_rank=-1, tpu_num_cores=8, tpu_metrics_debug=False)\n",
"05/16/2020 09:42:29 - INFO - transformers.training_args - PyTorch: setting up devices\n",
"05/16/2020 09:42:29 - WARNING - __main__ - Process rank: -1, device: xla:0, n_gpu: 0, distributed training: False, 16-bits training: False\n",
"05/16/2020 09:42:29 - INFO - __main__ - Training/evaluation parameters TrainingArguments(output_dir='./models/tpu', overwrite_output_dir=True, do_train=True, do_eval=False, do_predict=False, evaluate_during_training=False, per_gpu_train_batch_size=8, per_gpu_eval_batch_size=8, gradient_accumulation_steps=4, learning_rate=0.0001, weight_decay=0.0, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=4, max_steps=-1, warmup_steps=0, logging_dir=None, logging_first_step=False, logging_steps=500, save_steps=500, save_total_limit=None, no_cuda=False, seed=42, fp16=False, fp16_opt_level='O1', local_rank=-1, tpu_num_cores=8, tpu_metrics_debug=False)\n",
"05/16/2020 09:42:29 - INFO - transformers.tokenization_utils - loading file https://s3.amazonaws.com/models.huggingface.co/bert/t5-spiece.model from cache at /root/.cache/torch/transformers/68f1b8dbca4350743bb54b8c4169fd38cbabaad564f85a9239337a8d0342af9f.9995af32582a1a7062cb3173c118cb7b4636fa03feb967340f20fc37406f021f\n",
"05/16/2020 09:42:29 - INFO - transformers.tokenization_utils - loading file https://s3.amazonaws.com/models.huggingface.co/bert/t5-spiece.model from cache at /root/.cache/torch/transformers/68f1b8dbca4350743bb54b8c4169fd38cbabaad564f85a9239337a8d0342af9f.9995af32582a1a7062cb3173c118cb7b4636fa03feb967340f20fc37406f021f\n",
"05/16/2020 09:42:29 - INFO - transformers.configuration_utils - loading configuration file https://s3.amazonaws.com/models.huggingface.co/bert/t5-base-config.json from cache at /root/.cache/torch/transformers/40578967d1f029acb6162b36db9d8b4307063e885990ccd297c2c5be1cf1b3d7.2995d650f5eba18c8baa4146e210d32d56165e90d374281741fc78b872cd6c9b\n",
"05/16/2020 09:42:29 - INFO - transformers.configuration_utils - Model config T5Config {\n",
" \"architectures\": [\n",
" \"T5WithLMHeadModel\"\n",
" ],\n",
" \"d_ff\": 3072,\n",
" \"d_kv\": 64,\n",
" \"d_model\": 768,\n",
" \"decoder_start_token_id\": 0,\n",
" \"dropout_rate\": 0.1,\n",
" \"eos_token_id\": 1,\n",
" \"initializer_factor\": 1.0,\n",
" \"is_encoder_decoder\": true,\n",
" \"layer_norm_epsilon\": 1e-06,\n",
" \"model_type\": \"t5\",\n",
" \"n_positions\": 512,\n",
" \"num_heads\": 12,\n",
" \"num_layers\": 12,\n",
" \"output_past\": true,\n",
" \"pad_token_id\": 0,\n",
" \"relative_attention_num_buckets\": 32,\n",
" \"task_specific_params\": {\n",
" \"summarization\": {\n",
" \"early_stopping\": true,\n",
" \"length_penalty\": 2.0,\n",
" \"max_length\": 200,\n",
" \"min_length\": 30,\n",
" \"no_repeat_ngram_size\": 3,\n",
" \"num_beams\": 4,\n",
" \"prefix\": \"summarize: \"\n",
" },\n",
" \"translation_en_to_de\": {\n",
" \"early_stopping\": true,\n",
" \"max_length\": 300,\n",
" \"num_beams\": 4,\n",
" \"prefix\": \"translate English to German: \"\n",
" },\n",
" \"translation_en_to_fr\": {\n",
" \"early_stopping\": true,\n",
" \"max_length\": 300,\n",
" \"num_beams\": 4,\n",
" \"prefix\": \"translate English to French: \"\n",
" },\n",
" \"translation_en_to_ro\": {\n",
" \"early_stopping\": true,\n",
" \"max_length\": 300,\n",
" \"num_beams\": 4,\n",
" \"prefix\": \"translate English to Romanian: \"\n",
" }\n",
" },\n",
" \"vocab_size\": 32128\n",
"}\n",
"\n",
"05/16/2020 09:42:29 - INFO - transformers.training_args - PyTorch: setting up devices\n",
"05/16/2020 09:42:29 - WARNING - __main__ - Process rank: -1, device: xla:0, n_gpu: 0, distributed training: False, 16-bits training: False\n",
"05/16/2020 09:42:29 - INFO - __main__ - Training/evaluation parameters TrainingArguments(output_dir='./models/tpu', overwrite_output_dir=True, do_train=True, do_eval=False, do_predict=False, evaluate_during_training=False, per_gpu_train_batch_size=8, per_gpu_eval_batch_size=8, gradient_accumulation_steps=4, learning_rate=0.0001, weight_decay=0.0, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=4, max_steps=-1, warmup_steps=0, logging_dir=None, logging_first_step=False, logging_steps=500, save_steps=500, save_total_limit=None, no_cuda=False, seed=42, fp16=False, fp16_opt_level='O1', local_rank=-1, tpu_num_cores=8, tpu_metrics_debug=False)\n",
"05/16/2020 09:42:29 - INFO - transformers.configuration_utils - loading configuration file https://s3.amazonaws.com/models.huggingface.co/bert/t5-base-config.json from cache at /root/.cache/torch/transformers/40578967d1f029acb6162b36db9d8b4307063e885990ccd297c2c5be1cf1b3d7.2995d650f5eba18c8baa4146e210d32d56165e90d374281741fc78b872cd6c9b\n",
"05/16/2020 09:42:29 - INFO - transformers.configuration_utils - Model config T5Config {\n",
" \"architectures\": [\n",
" \"T5WithLMHeadModel\"\n",
" ],\n",
" \"d_ff\": 3072,\n",
" \"d_kv\": 64,\n",
" \"d_model\": 768,\n",
" \"decoder_start_token_id\": 0,\n",
" \"dropout_rate\": 0.1,\n",
" \"eos_token_id\": 1,\n",
" \"initializer_factor\": 1.0,\n",
" \"is_encoder_decoder\": true,\n",
" \"layer_norm_epsilon\": 1e-06,\n",
" \"model_type\": \"t5\",\n",
" \"n_positions\": 512,\n",
" \"num_heads\": 12,\n",
" \"num_layers\": 12,\n",
" \"output_past\": true,\n",
" \"pad_token_id\": 0,\n",
" \"relative_attention_num_buckets\": 32,\n",
" \"task_specific_params\": {\n",
" \"summarization\": {\n",
" \"early_stopping\": true,\n",
" \"length_penalty\": 2.0,\n",
" \"max_length\": 200,\n",
" \"min_length\": 30,\n",
" \"no_repeat_ngram_size\": 3,\n",
" \"num_beams\": 4,\n",
" \"prefix\": \"summarize: \"\n",
" },\n",
" \"translation_en_to_de\": {\n",
" \"early_stopping\": true,\n",
" \"max_length\": 300,\n",
" \"num_beams\": 4,\n",
" \"prefix\": \"translate English to German: \"\n",
" },\n",
" \"translation_en_to_fr\": {\n",
" \"early_stopping\": true,\n",
" \"max_length\": 300,\n",
" \"num_beams\": 4,\n",
" \"prefix\": \"translate English to French: \"\n",
" },\n",
" \"translation_en_to_ro\": {\n",
" \"early_stopping\": true,\n",
" \"max_length\": 300,\n",
" \"num_beams\": 4,\n",
" \"prefix\": \"translate English to Romanian: \"\n",
" }\n",
" },\n",
" \"vocab_size\": 32128\n",
"}\n",
"\n",
"05/16/2020 09:42:29 - INFO - transformers.training_args - PyTorch: setting up devices\n",
"05/16/2020 09:42:29 - WARNING - __main__ - Process rank: -1, device: xla:0, n_gpu: 0, distributed training: False, 16-bits training: False\n",
"05/16/2020 09:42:29 - INFO - transformers.tokenization_utils - loading file https://s3.amazonaws.com/models.huggingface.co/bert/t5-spiece.model from cache at /root/.cache/torch/transformers/68f1b8dbca4350743bb54b8c4169fd38cbabaad564f85a9239337a8d0342af9f.9995af32582a1a7062cb3173c118cb7b4636fa03feb967340f20fc37406f021f\n",
"05/16/2020 09:42:29 - INFO - __main__ - Training/evaluation parameters TrainingArguments(output_dir='./models/tpu', overwrite_output_dir=True, do_train=True, do_eval=False, do_predict=False, evaluate_during_training=False, per_gpu_train_batch_size=8, per_gpu_eval_batch_size=8, gradient_accumulation_steps=4, learning_rate=0.0001, weight_decay=0.0, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=4, max_steps=-1, warmup_steps=0, logging_dir=None, logging_first_step=False, logging_steps=500, save_steps=500, save_total_limit=None, no_cuda=False, seed=42, fp16=False, fp16_opt_level='O1', local_rank=-1, tpu_num_cores=8, tpu_metrics_debug=False)\n",
"05/16/2020 09:42:29 - INFO - transformers.modeling_utils - loading weights file https://cdn.huggingface.co/t5-base-pytorch_model.bin from cache at /root/.cache/torch/transformers/f6f2fde9fa7611f4eff74620de9cbe734e7a717b5b143bd283cae4c2d6022990.54f906ff53bd09195cfc183a29cadc81b7705f07fcdb796d24163cb632b6bdfa\n",
"05/16/2020 09:42:29 - INFO - transformers.modeling_utils - loading weights file https://cdn.huggingface.co/t5-base-pytorch_model.bin from cache at /root/.cache/torch/transformers/f6f2fde9fa7611f4eff74620de9cbe734e7a717b5b143bd283cae4c2d6022990.54f906ff53bd09195cfc183a29cadc81b7705f07fcdb796d24163cb632b6bdfa\n",
"05/16/2020 09:42:29 - INFO - transformers.tokenization_utils - loading file https://s3.amazonaws.com/models.huggingface.co/bert/t5-spiece.model from cache at /root/.cache/torch/transformers/68f1b8dbca4350743bb54b8c4169fd38cbabaad564f85a9239337a8d0342af9f.9995af32582a1a7062cb3173c118cb7b4636fa03feb967340f20fc37406f021f\n",
"05/16/2020 09:42:30 - INFO - transformers.configuration_utils - loading configuration file https://s3.amazonaws.com/models.huggingface.co/bert/t5-base-config.json from cache at /root/.cache/torch/transformers/40578967d1f029acb6162b36db9d8b4307063e885990ccd297c2c5be1cf1b3d7.2995d650f5eba18c8baa4146e210d32d56165e90d374281741fc78b872cd6c9b\n",
"05/16/2020 09:42:30 - INFO - transformers.configuration_utils - Model config T5Config {\n",
" \"architectures\": [\n",
" \"T5WithLMHeadModel\"\n",
" ],\n",
" \"d_ff\": 3072,\n",
" \"d_kv\": 64,\n",
" \"d_model\": 768,\n",
" \"decoder_start_token_id\": 0,\n",
" \"dropout_rate\": 0.1,\n",
" \"eos_token_id\": 1,\n",
" \"initializer_factor\": 1.0,\n",
" \"is_encoder_decoder\": true,\n",
" \"layer_norm_epsilon\": 1e-06,\n",
" \"model_type\": \"t5\",\n",
" \"n_positions\": 512,\n",
" \"num_heads\": 12,\n",
" \"num_layers\": 12,\n",
" \"output_past\": true,\n",
" \"pad_token_id\": 0,\n",
" \"relative_attention_num_buckets\": 32,\n",
" \"task_specific_params\": {\n",
" \"summarization\": {\n",
" \"early_stopping\": true,\n",
" \"length_penalty\": 2.0,\n",
" \"max_length\": 200,\n",
" \"min_length\": 30,\n",
" \"no_repeat_ngram_size\": 3,\n",
" \"num_beams\": 4,\n",
" \"prefix\": \"summarize: \"\n",
" },\n",
" \"translation_en_to_de\": {\n",
" \"early_stopping\": true,\n",
" \"max_length\": 300,\n",
" \"num_beams\": 4,\n",
" \"prefix\": \"translate English to German: \"\n",
" },\n",
" \"translation_en_to_fr\": {\n",
" \"early_stopping\": true,\n",
" \"max_length\": 300,\n",
" \"num_beams\": 4,\n",
" \"prefix\": \"translate English to French: \"\n",
" },\n",
" \"translation_en_to_ro\": {\n",
" \"early_stopping\": true,\n",
" \"max_length\": 300,\n",
" \"num_beams\": 4,\n",
" \"prefix\": \"translate English to Romanian: \"\n",
" }\n",
" },\n",
" \"vocab_size\": 32128\n",
"}\n",
"\n",
"05/16/2020 09:42:30 - INFO - transformers.training_args - PyTorch: setting up devices\n",
"05/16/2020 09:42:30 - WARNING - __main__ - Process rank: -1, device: xla:0, n_gpu: 0, distributed training: False, 16-bits training: False\n",
"05/16/2020 09:42:30 - INFO - __main__ - Training/evaluation parameters TrainingArguments(output_dir='./models/tpu', overwrite_output_dir=True, do_train=True, do_eval=False, do_predict=False, evaluate_during_training=False, per_gpu_train_batch_size=8, per_gpu_eval_batch_size=8, gradient_accumulation_steps=4, learning_rate=0.0001, weight_decay=0.0, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=4, max_steps=-1, warmup_steps=0, logging_dir=None, logging_first_step=False, logging_steps=500, save_steps=500, save_total_limit=None, no_cuda=False, seed=42, fp16=False, fp16_opt_level='O1', local_rank=-1, tpu_num_cores=8, tpu_metrics_debug=False)\n",
"05/16/2020 09:42:30 - INFO - transformers.training_args - PyTorch: setting up devices\n",
"05/16/2020 09:42:30 - WARNING - __main__ - Process rank: -1, device: xla:0, n_gpu: 0, distributed training: False, 16-bits training: False\n",
"05/16/2020 09:42:30 - INFO - __main__ - Training/evaluation parameters TrainingArguments(output_dir='./models/tpu', overwrite_output_dir=True, do_train=True, do_eval=False, do_predict=False, evaluate_during_training=False, per_gpu_train_batch_size=8, per_gpu_eval_batch_size=8, gradient_accumulation_steps=4, learning_rate=0.0001, weight_decay=0.0, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=4, max_steps=-1, warmup_steps=0, logging_dir=None, logging_first_step=False, logging_steps=500, save_steps=500, save_total_limit=None, no_cuda=False, seed=42, fp16=False, fp16_opt_level='O1', local_rank=-1, tpu_num_cores=8, tpu_metrics_debug=False)\n",
"05/16/2020 09:42:30 - INFO - transformers.configuration_utils - loading configuration file https://s3.amazonaws.com/models.huggingface.co/bert/t5-base-config.json from cache at /root/.cache/torch/transformers/40578967d1f029acb6162b36db9d8b4307063e885990ccd297c2c5be1cf1b3d7.2995d650f5eba18c8baa4146e210d32d56165e90d374281741fc78b872cd6c9b\n",
"05/16/2020 09:42:30 - INFO - transformers.configuration_utils - Model config T5Config {\n",
" \"architectures\": [\n",
" \"T5WithLMHeadModel\"\n",
" ],\n",
" \"d_ff\": 3072,\n",
" \"d_kv\": 64,\n",
" \"d_model\": 768,\n",
" \"decoder_start_token_id\": 0,\n",
" \"dropout_rate\": 0.1,\n",
" \"eos_token_id\": 1,\n",
" \"initializer_factor\": 1.0,\n",
" \"is_encoder_decoder\": true,\n",
" \"layer_norm_epsilon\": 1e-06,\n",
" \"model_type\": \"t5\",\n",
" \"n_positions\": 512,\n",
" \"num_heads\": 12,\n",
" \"num_layers\": 12,\n",
" \"output_past\": true,\n",
" \"pad_token_id\": 0,\n",
" \"relative_attention_num_buckets\": 32,\n",
" \"task_specific_params\": {\n",
" \"summarization\": {\n",
" \"early_stopping\": true,\n",
" \"length_penalty\": 2.0,\n",
" \"max_length\": 200,\n",
" \"min_length\": 30,\n",
" \"no_repeat_ngram_size\": 3,\n",
" \"num_beams\": 4,\n",
" \"prefix\": \"summarize: \"\n",
" },\n",
" \"translation_en_to_de\": {\n",
" \"early_stopping\": true,\n",
" \"max_length\": 300,\n",
" \"num_beams\": 4,\n",
" \"prefix\": \"translate English to German: \"\n",
" },\n",
" \"translation_en_to_fr\": {\n",
" \"early_stopping\": true,\n",
" \"max_length\": 300,\n",
" \"num_beams\": 4,\n",
" \"prefix\": \"translate English to French: \"\n",
" },\n",
" \"translation_en_to_ro\": {\n",
" \"early_stopping\": true,\n",
" \"max_length\": 300,\n",
" \"num_beams\": 4,\n",
" \"prefix\": \"translate English to Romanian: \"\n",
" }\n",
" },\n",
" \"vocab_size\": 32128\n",
"}\n",
"\n",
"05/16/2020 09:42:30 - INFO - transformers.modeling_utils - loading weights file https://cdn.huggingface.co/t5-base-pytorch_model.bin from cache at /root/.cache/torch/transformers/f6f2fde9fa7611f4eff74620de9cbe734e7a717b5b143bd283cae4c2d6022990.54f906ff53bd09195cfc183a29cadc81b7705f07fcdb796d24163cb632b6bdfa\n",
"05/16/2020 09:42:30 - INFO - transformers.modeling_utils - loading weights file https://cdn.huggingface.co/t5-base-pytorch_model.bin from cache at /root/.cache/torch/transformers/f6f2fde9fa7611f4eff74620de9cbe734e7a717b5b143bd283cae4c2d6022990.54f906ff53bd09195cfc183a29cadc81b7705f07fcdb796d24163cb632b6bdfa\n",
"05/16/2020 09:42:30 - INFO - transformers.training_args - PyTorch: setting up devices\n",
"05/16/2020 09:42:30 - WARNING - __main__ - Process rank: -1, device: xla:0, n_gpu: 0, distributed training: False, 16-bits training: False\n",
"05/16/2020 09:42:30 - INFO - __main__ - Training/evaluation parameters TrainingArguments(output_dir='./models/tpu', overwrite_output_dir=True, do_train=True, do_eval=False, do_predict=False, evaluate_during_training=False, per_gpu_train_batch_size=8, per_gpu_eval_batch_size=8, gradient_accumulation_steps=4, learning_rate=0.0001, weight_decay=0.0, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=4, max_steps=-1, warmup_steps=0, logging_dir=None, logging_first_step=False, logging_steps=500, save_steps=500, save_total_limit=None, no_cuda=False, seed=42, fp16=False, fp16_opt_level='O1', local_rank=-1, tpu_num_cores=8, tpu_metrics_debug=False)\n",
"05/16/2020 09:42:30 - INFO - transformers.tokenization_utils - loading file https://s3.amazonaws.com/models.huggingface.co/bert/t5-spiece.model from cache at /root/.cache/torch/transformers/68f1b8dbca4350743bb54b8c4169fd38cbabaad564f85a9239337a8d0342af9f.9995af32582a1a7062cb3173c118cb7b4636fa03feb967340f20fc37406f021f\n",
"05/16/2020 09:42:30 - INFO - transformers.tokenization_utils - loading file https://s3.amazonaws.com/models.huggingface.co/bert/t5-spiece.model from cache at /root/.cache/torch/transformers/68f1b8dbca4350743bb54b8c4169fd38cbabaad564f85a9239337a8d0342af9f.9995af32582a1a7062cb3173c118cb7b4636fa03feb967340f20fc37406f021f\n",
"05/16/2020 09:42:30 - INFO - transformers.tokenization_utils - loading file https://s3.amazonaws.com/models.huggingface.co/bert/t5-spiece.model from cache at /root/.cache/torch/transformers/68f1b8dbca4350743bb54b8c4169fd38cbabaad564f85a9239337a8d0342af9f.9995af32582a1a7062cb3173c118cb7b4636fa03feb967340f20fc37406f021f\n",
"05/16/2020 09:42:30 - INFO - transformers.configuration_utils - loading configuration file https://s3.amazonaws.com/models.huggingface.co/bert/t5-base-config.json from cache at /root/.cache/torch/transformers/40578967d1f029acb6162b36db9d8b4307063e885990ccd297c2c5be1cf1b3d7.2995d650f5eba18c8baa4146e210d32d56165e90d374281741fc78b872cd6c9b\n",
"05/16/2020 09:42:30 - INFO - transformers.configuration_utils - Model config T5Config {\n",
" \"architectures\": [\n",
" \"T5WithLMHeadModel\"\n",
" ],\n",
" \"d_ff\": 3072,\n",
" \"d_kv\": 64,\n",
" \"d_model\": 768,\n",
" \"decoder_start_token_id\": 0,\n",
" \"dropout_rate\": 0.1,\n",
" \"eos_token_id\": 1,\n",
" \"initializer_factor\": 1.0,\n",
" \"is_encoder_decoder\": true,\n",
" \"layer_norm_epsilon\": 1e-06,\n",
" \"model_type\": \"t5\",\n",
" \"n_positions\": 512,\n",
" \"num_heads\": 12,\n",
" \"num_layers\": 12,\n",
" \"output_past\": true,\n",
" \"pad_token_id\": 0,\n",
" \"relative_attention_num_buckets\": 32,\n",
" \"task_specific_params\": {\n",
" \"summarization\": {\n",
" \"early_stopping\": true,\n",
" \"length_penalty\": 2.0,\n",
" \"max_length\": 200,\n",
" \"min_length\": 30,\n",
" \"no_repeat_ngram_size\": 3,\n",
" \"num_beams\": 4,\n",
" \"prefix\": \"summarize: \"\n",
" },\n",
" \"translation_en_to_de\": {\n",
" \"early_stopping\": true,\n",
" \"max_length\": 300,\n",
" \"num_beams\": 4,\n",
" \"prefix\": \"translate English to German: \"\n",
" },\n",
" \"translation_en_to_fr\": {\n",
" \"early_stopping\": true,\n",
" \"max_length\": 300,\n",
" \"num_beams\": 4,\n",
" \"prefix\": \"translate English to French: \"\n",
" },\n",
" \"translation_en_to_ro\": {\n",
" \"early_stopping\": true,\n",
" \"max_length\": 300,\n",
" \"num_beams\": 4,\n",
" \"prefix\": \"translate English to Romanian: \"\n",
" }\n",
" },\n",
" \"vocab_size\": 32128\n",
"}\n",
"\n",
"05/16/2020 09:42:30 - INFO - transformers.configuration_utils - loading configuration file https://s3.amazonaws.com/models.huggingface.co/bert/t5-base-config.json from cache at /root/.cache/torch/transformers/40578967d1f029acb6162b36db9d8b4307063e885990ccd297c2c5be1cf1b3d7.2995d650f5eba18c8baa4146e210d32d56165e90d374281741fc78b872cd6c9b\n",
"05/16/2020 09:42:30 - INFO - transformers.configuration_utils - Model config T5Config {\n",
" \"architectures\": [\n",
" \"T5WithLMHeadModel\"\n",
" ],\n",
" \"d_ff\": 3072,\n",
" \"d_kv\": 64,\n",
" \"d_model\": 768,\n",
" \"decoder_start_token_id\": 0,\n",
" \"dropout_rate\": 0.1,\n",
" \"eos_token_id\": 1,\n",
" \"initializer_factor\": 1.0,\n",
" \"is_encoder_decoder\": true,\n",
" \"layer_norm_epsilon\": 1e-06,\n",
" \"model_type\": \"t5\",\n",
" \"n_positions\": 512,\n",
" \"num_heads\": 12,\n",
" \"num_layers\": 12,\n",
" \"output_past\": true,\n",
" \"pad_token_id\": 0,\n",
" \"relative_attention_num_buckets\": 32,\n",
" \"task_specific_params\": {\n",
" \"summarization\": {\n",
" \"early_stopping\": true,\n",
" \"length_penalty\": 2.0,\n",
" \"max_length\": 200,\n",
" \"min_length\": 30,\n",
" \"no_repeat_ngram_size\": 3,\n",
" \"num_beams\": 4,\n",
" \"prefix\": \"summarize: \"\n",
" },\n",
" \"translation_en_to_de\": {\n",
" \"early_stopping\": true,\n",
" \"max_length\": 300,\n",
" \"num_beams\": 4,\n",
" \"prefix\": \"translate English to German: \"\n",
" },\n",
" \"translation_en_to_fr\": {\n",
" \"early_stopping\": true,\n",
" \"max_length\": 300,\n",
" \"num_beams\": 4,\n",
" \"prefix\": \"translate English to French: \"\n",
" },\n",
" \"translation_en_to_ro\": {\n",
" \"early_stopping\": true,\n",
" \"max_length\": 300,\n",
" \"num_beams\": 4,\n",
" \"prefix\": \"translate English to Romanian: \"\n",
" }\n",
" },\n",
" \"vocab_size\": 32128\n",
"}\n",
"05/16/2020 09:42:30 - INFO - transformers.modeling_utils - loading weights file https://cdn.huggingface.co/t5-base-pytorch_model.bin from cache at /root/.cache/torch/transformers/f6f2fde9fa7611f4eff74620de9cbe734e7a717b5b143bd283cae4c2d6022990.54f906ff53bd09195cfc183a29cadc81b7705f07fcdb796d24163cb632b6bdfa\n",
"\n",
"05/16/2020 09:42:30 - INFO - transformers.modeling_utils - loading weights file https://cdn.huggingface.co/t5-base-pytorch_model.bin from cache at /root/.cache/torch/transformers/f6f2fde9fa7611f4eff74620de9cbe734e7a717b5b143bd283cae4c2d6022990.54f906ff53bd09195cfc183a29cadc81b7705f07fcdb796d24163cb632b6bdfa\n",
"05/16/2020 09:42:30 - INFO - transformers.configuration_utils - loading configuration file https://s3.amazonaws.com/models.huggingface.co/bert/t5-base-config.json from cache at /root/.cache/torch/transformers/40578967d1f029acb6162b36db9d8b4307063e885990ccd297c2c5be1cf1b3d7.2995d650f5eba18c8baa4146e210d32d56165e90d374281741fc78b872cd6c9b\n",
"05/16/2020 09:42:30 - INFO - transformers.configuration_utils - Model config T5Config {\n",
" \"architectures\": [\n",
" \"T5WithLMHeadModel\"\n",
" ],\n",
" \"d_ff\": 3072,\n",
" \"d_kv\": 64,\n",
" \"d_model\": 768,\n",
" \"decoder_start_token_id\": 0,\n",
" \"dropout_rate\": 0.1,\n",
" \"eos_token_id\": 1,\n",
" \"initializer_factor\": 1.0,\n",
" \"is_encoder_decoder\": true,\n",
" \"layer_norm_epsilon\": 1e-06,\n",
" \"model_type\": \"t5\",\n",
" \"n_positions\": 512,\n",
" \"num_heads\": 12,\n",
" \"num_layers\": 12,\n",
" \"output_past\": true,\n",
" \"pad_token_id\": 0,\n",
" \"relative_attention_num_buckets\": 32,\n",
" \"task_specific_params\": {\n",
" \"summarization\": {\n",
" \"early_stopping\": true,\n",
" \"length_penalty\": 2.0,\n",
" \"max_length\": 200,\n",
" \"min_length\": 30,\n",
" \"no_repeat_ngram_size\": 3,\n",
" \"num_beams\": 4,\n",
" \"prefix\": \"summarize: \"\n",
" },\n",
" \"translation_en_to_de\": {\n",
" \"early_stopping\": true,\n",
" \"max_length\": 300,\n",
" \"num_beams\": 4,\n",
" \"prefix\": \"translate English to German: \"\n",
" },\n",
" \"translation_en_to_fr\": {\n",
" \"early_stopping\": true,\n",
" \"max_length\": 300,\n",
" \"num_beams\": 4,\n",
" \"prefix\": \"translate English to French: \"\n",
" },\n",
" \"translation_en_to_ro\": {\n",
" \"early_stopping\": true,\n",
" \"max_length\": 300,\n",
" \"num_beams\": 4,\n",
" \"prefix\": \"translate English to Romanian: \"\n",
" }\n",
" },\n",
" \"vocab_size\": 32128\n",
"}\n",
"\n",
"05/16/2020 09:42:30 - INFO - transformers.modeling_
gitextract_imbs4xu_/ ├── README.md ├── T5_on_TPU.ipynb └── t5_fine_tuning.ipynb
Condensed preview — 3 files, each showing path, character count, and a content snippet. Download the .json file or copy for the full structured content (952K chars).
[
{
"path": "README.md",
"chars": 82,
"preview": "# exploring-T5\nA repo to explore different NLP tasks which can be solved using T5\n"
},
{
"path": "T5_on_TPU.ipynb",
"chars": 232085,
"preview": "{\n \"nbformat\": 4,\n \"nbformat_minor\": 0,\n \"metadata\": {\n \"colab\": {\n \"name\": \"T5 on TPU\",\n \"provenance\": "
},
{
"path": "t5_fine_tuning.ipynb",
"chars": 652096,
"preview": "{\n \"nbformat\": 4,\n \"nbformat_minor\": 0,\n \"metadata\": {\n \"colab\": {\n \"name\": \"t5_fine-tuning\",\n \"provenan"
}
]
About this extraction
This page contains the full source code of the patil-suraj/exploring-T5 GitHub repository, extracted and formatted as plain text for AI agents and large language models (LLMs). The extraction includes 3 files (863.5 KB), approximately 235.8k tokens. Use this with OpenClaw, Claude, ChatGPT, Cursor, Windsurf, or any other AI tool that accepts text input. You can copy the full output to your clipboard or download it as a .txt file.
Extracted by GitExtract — free GitHub repo to text converter for AI. Built by Nikandr Surkov.