SimaoQuintela commited on
Commit
1f7fe70
·
verified ·
1 Parent(s): e0e53cc

Feat: LayoutLMv3 trained on the FUNSD dataset

Browse files

This notebook trains the LayoutLMv3 layout model (on kagggle to take advantage of the GPU accelerators) on the FUNSD dataset.
It also provides an inference phase where you can store your results on google drive

Files changed (1) hide show
  1. LayoutLMv3-FUNSD.ipynb +1 -0
LayoutLMv3-FUNSD.ipynb ADDED
@@ -0,0 +1 @@
 
 
1
+ {"nbformat":4,"nbformat_minor":0,"metadata":{"colab":{"provenance":[],"mount_file_id":"18dgmMnyLKC5ZQNtPVzQioDagmg-ylkWY","authorship_tag":"ABX9TyPy6fb4bWrfZbmSQgFDiEvk"},"kernelspec":{"name":"python3","display_name":"Python 3"},"language_info":{"name":"python"},"widgets":{"application/vnd.jupyter.widget-state+json":{"00ba0d7300e6417aa4350a22af12b5ad":{"model_module":"@jupyter-widgets/controls","model_name":"HBoxModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_06ad3707e73a4f9086f5705a369c87e8","IPY_MODEL_948b79e1f45247c7af98ca3642f3e566","IPY_MODEL_fd37f64801484c1f8e429d3fd4dbe548"],"layout":"IPY_MODEL_32332b27299b42afa686a6c6969b29ed"}},"06ad3707e73a4f9086f5705a369c87e8":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_91591dcb0d6f4151a0c4b47aea80c22c","placeholder":"​","style":"IPY_MODEL_4a74c348e7ca4271b6d9f267fdeaba9c","value":"funsd.py: 100%"}},"948b79e1f45247c7af98ca3642f3e566":{"model_module":"@jupyter-widgets/controls","model_name":"FloatProgressModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ProgressView","bar_style":"success","description":"","description_tooltip":null,"layout":"IPY_MODEL_8f38c2eb73a44a658282f21ec532ce7f","max":4536,"min":0,"orientation":"horizontal","style":"IPY_MODEL_7d7351eb3e224346bb8681a792cc5ae7","value":4536}},"fd37f64801484c1f8e429d3fd4dbe548":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_b5f026b7c6e448bebb72c7a9c0484d90","placeholder":"​","style":"IPY_MODEL_d004e1ea81524734a2393772ac5683d7","value":" 4.54k/4.54k [00:00&lt;00:00, 519kB/s]"}},"32332b27299b42afa686a6c6969b29ed":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"91591dcb0d6f4151a0c4b47aea80c22c":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"4a74c348e7ca4271b6d9f267fdeaba9c":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"8f38c2eb73a44a658282f21ec532ce7f":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"7d7351eb3e224346bb8681a792cc5ae7":{"model_module":"@jupyter-widgets/controls","model_name":"ProgressStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"b5f026b7c6e448bebb72c7a9c0484d90":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"d004e1ea81524734a2393772ac5683d7":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"e5eff9cfe1c04527b10fd7a13eee5f13":{"model_module":"@jupyter-widgets/controls","model_name":"HBoxModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_4328e6656bc34727bca16f849ea0b7e1","IPY_MODEL_20ead82bc5e74ebaabc64c9a382eb5a0","IPY_MODEL_78fd95b671ed49a7b2c7c9f3ec8cce18"],"layout":"IPY_MODEL_0316fa51cbca4e75a81d5a34768dabb9"}},"4328e6656bc34727bca16f849ea0b7e1":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_36de2a0aa32b4885a8eb29501381f4bf","placeholder":"​","style":"IPY_MODEL_95bb9927e66e432b886b7f9da69df885","value":"Downloading data: 100%"}},"20ead82bc5e74ebaabc64c9a382eb5a0":{"model_module":"@jupyter-widgets/controls","model_name":"FloatProgressModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ProgressView","bar_style":"success","description":"","description_tooltip":null,"layout":"IPY_MODEL_87d5ed49387948adb0ac63c44bd1f067","max":16838830,"min":0,"orientation":"horizontal","style":"IPY_MODEL_2d396af9570c44fcbb9d98b6b2dae03d","value":16838830}},"78fd95b671ed49a7b2c7c9f3ec8cce18":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_db13024b11444a62984d99b53dcd2801","placeholder":"​","style":"IPY_MODEL_3ac6424d85f545bcbec371e7bcc4e0c9","value":" 16.8M/16.8M [00:00&lt;00:00, 170MB/s]"}},"0316fa51cbca4e75a81d5a34768dabb9":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"36de2a0aa32b4885a8eb29501381f4bf":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"95bb9927e66e432b886b7f9da69df885":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"87d5ed49387948adb0ac63c44bd1f067":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"2d396af9570c44fcbb9d98b6b2dae03d":{"model_module":"@jupyter-widgets/controls","model_name":"ProgressStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"db13024b11444a62984d99b53dcd2801":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"3ac6424d85f545bcbec371e7bcc4e0c9":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"52c9a5ad220a4e9ab902391ce560d635":{"model_module":"@jupyter-widgets/controls","model_name":"HBoxModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_f0893cf8f81c43c6a89c9d22b633f82f","IPY_MODEL_3de5b6203d6f42d18c957050cf804b86","IPY_MODEL_63398d2907fc4fbba6732d00e5e6cb4c"],"layout":"IPY_MODEL_d05e18efcc814b83bad62ca2da21cd22"}},"f0893cf8f81c43c6a89c9d22b633f82f":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_e65d1b68f5ed46ee9554a875420bc93c","placeholder":"​","style":"IPY_MODEL_c3d85e8cd4784a73aaaa74043f4f38eb","value":"Generating train split: "}},"3de5b6203d6f42d18c957050cf804b86":{"model_module":"@jupyter-widgets/controls","model_name":"FloatProgressModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ProgressView","bar_style":"success","description":"","description_tooltip":null,"layout":"IPY_MODEL_a85fe3a65ca14dbea1fd994b3447da4c","max":1,"min":0,"orientation":"horizontal","style":"IPY_MODEL_c94c9de83f5c48edb8656543e50ec481","value":1}},"63398d2907fc4fbba6732d00e5e6cb4c":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_35e7a858fe2344e692bd98b9a7cc5271","placeholder":"​","style":"IPY_MODEL_8a6a8beeb73743ff9b294b10f039c300","value":" 149/0 [00:01&lt;00:00, 154.50 examples/s]"}},"d05e18efcc814b83bad62ca2da21cd22":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"e65d1b68f5ed46ee9554a875420bc93c":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"c3d85e8cd4784a73aaaa74043f4f38eb":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"a85fe3a65ca14dbea1fd994b3447da4c":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":"20px"}},"c94c9de83f5c48edb8656543e50ec481":{"model_module":"@jupyter-widgets/controls","model_name":"ProgressStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"35e7a858fe2344e692bd98b9a7cc5271":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"8a6a8beeb73743ff9b294b10f039c300":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"59c1be8d68834c7bb6d9c619b1600d87":{"model_module":"@jupyter-widgets/controls","model_name":"HBoxModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_22d681db15b244b2b5df1183d80c0e50","IPY_MODEL_2e096f49905648bc8502cc3bc9e9dc58","IPY_MODEL_4c3837188a70491b89d667434f678d29"],"layout":"IPY_MODEL_1bafa89ad5a44fe8b4262b462c1135e9"}},"22d681db15b244b2b5df1183d80c0e50":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_1f198aee8a11462ab41cf8f7b1b2b830","placeholder":"​","style":"IPY_MODEL_c44f34b40b694472a29cbcd612301dcf","value":"Generating test split: "}},"2e096f49905648bc8502cc3bc9e9dc58":{"model_module":"@jupyter-widgets/controls","model_name":"FloatProgressModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ProgressView","bar_style":"success","description":"","description_tooltip":null,"layout":"IPY_MODEL_8fc55f57c7e84d4daa38e144560504ab","max":1,"min":0,"orientation":"horizontal","style":"IPY_MODEL_d9e27c356d6b4bf082e267b1a6dca601","value":1}},"4c3837188a70491b89d667434f678d29":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_587654adb3a84e2490b8690ecb230ecc","placeholder":"​","style":"IPY_MODEL_d71dada534d947b292a075d47c823b12","value":" 50/0 [00:00&lt;00:00, 153.55 examples/s]"}},"1bafa89ad5a44fe8b4262b462c1135e9":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"1f198aee8a11462ab41cf8f7b1b2b830":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"c44f34b40b694472a29cbcd612301dcf":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"8fc55f57c7e84d4daa38e144560504ab":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":"20px"}},"d9e27c356d6b4bf082e267b1a6dca601":{"model_module":"@jupyter-widgets/controls","model_name":"ProgressStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"587654adb3a84e2490b8690ecb230ecc":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"d71dada534d947b292a075d47c823b12":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"add91e2650f14a3ca81156aea71d861e":{"model_module":"@jupyter-widgets/controls","model_name":"HBoxModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_09b1e833c8ff4603b9a8dd13a8fe6796","IPY_MODEL_f79a49d991724e6698cbb4ec9eab8e0e","IPY_MODEL_45eff6094e5a40ef952c6ec318341720"],"layout":"IPY_MODEL_073d225e234c411f8725a30bf8745cc2"}},"09b1e833c8ff4603b9a8dd13a8fe6796":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_c24a82a9f790491594107fc31bb28db4","placeholder":"​","style":"IPY_MODEL_e8989c5562494e509dff9312883ebd48","value":"tokenizer_config.json: 100%"}},"f79a49d991724e6698cbb4ec9eab8e0e":{"model_module":"@jupyter-widgets/controls","model_name":"FloatProgressModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ProgressView","bar_style":"success","description":"","description_tooltip":null,"layout":"IPY_MODEL_3823367257854f489e0540614c6b7149","max":1144,"min":0,"orientation":"horizontal","style":"IPY_MODEL_0bca305d55f4406484e1baf435a76532","value":1144}},"45eff6094e5a40ef952c6ec318341720":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_7e4d76dea0174e428ac534e3836be531","placeholder":"​","style":"IPY_MODEL_eff9fd977c8c4886b3ad8f16462f2c1e","value":" 1.14k/1.14k [00:00&lt;00:00, 17.7kB/s]"}},"073d225e234c411f8725a30bf8745cc2":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"c24a82a9f790491594107fc31bb28db4":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"e8989c5562494e509dff9312883ebd48":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"3823367257854f489e0540614c6b7149":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"0bca305d55f4406484e1baf435a76532":{"model_module":"@jupyter-widgets/controls","model_name":"ProgressStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"7e4d76dea0174e428ac534e3836be531":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"eff9fd977c8c4886b3ad8f16462f2c1e":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"8e3b23940bca43a5bd25fd9a2cf677a7":{"model_module":"@jupyter-widgets/controls","model_name":"HBoxModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_6dde07f8479e441aa9f7f60a654a271c","IPY_MODEL_43c7e7e92dfe4db5b05c5b8678c2a168","IPY_MODEL_1d8680e25a854f3e9e19efc8e1321c29"],"layout":"IPY_MODEL_9ed2c2aaf9f1443aa0464fbbf1a85e2a"}},"6dde07f8479e441aa9f7f60a654a271c":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_bd248ee9d16b476b985ce19f51c7c7e3","placeholder":"​","style":"IPY_MODEL_d34f1544a5b24a359b9c5a0db52c0ec6","value":"vocab.json: 100%"}},"43c7e7e92dfe4db5b05c5b8678c2a168":{"model_module":"@jupyter-widgets/controls","model_name":"FloatProgressModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ProgressView","bar_style":"success","description":"","description_tooltip":null,"layout":"IPY_MODEL_3c03fbb415b446f1a0e0185ab0ef0c15","max":898822,"min":0,"orientation":"horizontal","style":"IPY_MODEL_e491a1db6f14427c9ba93f148b2f8db6","value":898822}},"1d8680e25a854f3e9e19efc8e1321c29":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_365b80a8f39e417ca24b7758237ae856","placeholder":"​","style":"IPY_MODEL_ae837f8fae6d467dae865fc63a47b93c","value":" 899k/899k [00:00&lt;00:00, 11.5MB/s]"}},"9ed2c2aaf9f1443aa0464fbbf1a85e2a":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"bd248ee9d16b476b985ce19f51c7c7e3":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"d34f1544a5b24a359b9c5a0db52c0ec6":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"3c03fbb415b446f1a0e0185ab0ef0c15":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"e491a1db6f14427c9ba93f148b2f8db6":{"model_module":"@jupyter-widgets/controls","model_name":"ProgressStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"365b80a8f39e417ca24b7758237ae856":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"ae837f8fae6d467dae865fc63a47b93c":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"38fb4fd17e5b4bdead971850673ca247":{"model_module":"@jupyter-widgets/controls","model_name":"HBoxModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_0e139fa3ce1c436b899e9282ad02f542","IPY_MODEL_389c8a27e6e74cd283585b36c7ae20ac","IPY_MODEL_948a5155aaa24f4c92f7468617a7cae1"],"layout":"IPY_MODEL_afddba665dfd40fcbffaed723e82849a"}},"0e139fa3ce1c436b899e9282ad02f542":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_28f12040b42a40ef84366b174bae01cf","placeholder":"​","style":"IPY_MODEL_d1b1596c6f8c4ab4aace17e3f5c3d856","value":"merges.txt: 100%"}},"389c8a27e6e74cd283585b36c7ae20ac":{"model_module":"@jupyter-widgets/controls","model_name":"FloatProgressModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ProgressView","bar_style":"success","description":"","description_tooltip":null,"layout":"IPY_MODEL_a21427de566842ab94bd8e2190ec1869","max":456318,"min":0,"orientation":"horizontal","style":"IPY_MODEL_e7503f9bde2941a99659b7257ac95cdb","value":456318}},"948a5155aaa24f4c92f7468617a7cae1":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_0f6e623197b449d9b98a7bda6a16d33e","placeholder":"​","style":"IPY_MODEL_136f84bfc8b44e509b471b793ad2ee49","value":" 456k/456k [00:00&lt;00:00, 21.7MB/s]"}},"afddba665dfd40fcbffaed723e82849a":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"28f12040b42a40ef84366b174bae01cf":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"d1b1596c6f8c4ab4aace17e3f5c3d856":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"a21427de566842ab94bd8e2190ec1869":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"e7503f9bde2941a99659b7257ac95cdb":{"model_module":"@jupyter-widgets/controls","model_name":"ProgressStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"0f6e623197b449d9b98a7bda6a16d33e":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"136f84bfc8b44e509b471b793ad2ee49":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"95ccbcf2180d4bb7ae24634dbfe2af13":{"model_module":"@jupyter-widgets/controls","model_name":"HBoxModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_134b31acfc0d4e37952a5f9bf7bb05b0","IPY_MODEL_cb4fb059f54844f58e3f9ff7bbe267e9","IPY_MODEL_4fc63f8517064b14ae52cd2ee21e430c"],"layout":"IPY_MODEL_c408161098a44f7ca30a1c21e05a217e"}},"134b31acfc0d4e37952a5f9bf7bb05b0":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_cfe54473555e4b18a96f34ffdb202f69","placeholder":"​","style":"IPY_MODEL_b066466e85f3418281d3a80f838f99a8","value":"config.json: 100%"}},"cb4fb059f54844f58e3f9ff7bbe267e9":{"model_module":"@jupyter-widgets/controls","model_name":"FloatProgressModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ProgressView","bar_style":"success","description":"","description_tooltip":null,"layout":"IPY_MODEL_a76e59b5987148f385b36ecbd2c5b0b9","max":856,"min":0,"orientation":"horizontal","style":"IPY_MODEL_05304f88942e46d087bf3c8a604e07ea","value":856}},"4fc63f8517064b14ae52cd2ee21e430c":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_95550ab008af4324b92d80318d2e7ac3","placeholder":"​","style":"IPY_MODEL_a2c7b850a49942bbb69ef966c8877594","value":" 856/856 [00:00&lt;00:00, 15.8kB/s]"}},"c408161098a44f7ca30a1c21e05a217e":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"cfe54473555e4b18a96f34ffdb202f69":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"b066466e85f3418281d3a80f838f99a8":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"a76e59b5987148f385b36ecbd2c5b0b9":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"05304f88942e46d087bf3c8a604e07ea":{"model_module":"@jupyter-widgets/controls","model_name":"ProgressStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"95550ab008af4324b92d80318d2e7ac3":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"a2c7b850a49942bbb69ef966c8877594":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"1da5ab56c33846d7b48123fb847e013e":{"model_module":"@jupyter-widgets/controls","model_name":"HBoxModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_89d60ab1ba8a4cf1b1ffe729a6f7683a","IPY_MODEL_6d6fbf757a76464782dc05b75f105995","IPY_MODEL_2fcffd859f994190862853155c07ec10"],"layout":"IPY_MODEL_b727f17253574b1497a181314d287073"}},"89d60ab1ba8a4cf1b1ffe729a6f7683a":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_61ad8c45cd7b46c4be5fc038391aeb6d","placeholder":"​","style":"IPY_MODEL_1697325176c849fe85caaa3d6c81dc9d","value":"model.safetensors: 100%"}},"6d6fbf757a76464782dc05b75f105995":{"model_module":"@jupyter-widgets/controls","model_name":"FloatProgressModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ProgressView","bar_style":"success","description":"","description_tooltip":null,"layout":"IPY_MODEL_ae4c9adefaff4ffba6008aa7f27c00ca","max":501338056,"min":0,"orientation":"horizontal","style":"IPY_MODEL_c97cbfc717d04379b59df38149bb7d14","value":501338056}},"2fcffd859f994190862853155c07ec10":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_94c22dee94684f149e74b92cf5090acb","placeholder":"​","style":"IPY_MODEL_1633d2801472443090c5b959874fea55","value":" 501M/501M [00:04&lt;00:00, 164MB/s]"}},"b727f17253574b1497a181314d287073":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"61ad8c45cd7b46c4be5fc038391aeb6d":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"1697325176c849fe85caaa3d6c81dc9d":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"ae4c9adefaff4ffba6008aa7f27c00ca":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"c97cbfc717d04379b59df38149bb7d14":{"model_module":"@jupyter-widgets/controls","model_name":"ProgressStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"94c22dee94684f149e74b92cf5090acb":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"1633d2801472443090c5b959874fea55":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}}}}},"cells":[{"cell_type":"code","source":["!pip install Pillow\n","!pip install pytesseract\n","!pip install datasets\n","!sudo apt-get install libtesseract-dev python3-pil tesseract-ocr-eng tesseract-ocr-script-latn\n"],"metadata":{"id":"HA_83Izr8Ay6","collapsed":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["from google.colab import drive\n","drive.mount('/content/drive')"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"NBckcUj7Lyal","executionInfo":{"status":"ok","timestamp":1741029947610,"user_tz":0,"elapsed":8937,"user":{"displayName":"Simão Quintela","userId":"13164910078562325200"}},"outputId":"3a5002cd-79df-4bba-f64a-d83e472bf29d"},"execution_count":3,"outputs":[{"output_type":"stream","name":"stdout","text":["Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount(\"/content/drive\", force_remount=True).\n"]}]},{"cell_type":"code","execution_count":4,"metadata":{"id":"I-ppmx1a05gY","collapsed":true,"executionInfo":{"status":"ok","timestamp":1741029949225,"user_tz":0,"elapsed":5,"user":{"displayName":"Simão Quintela","userId":"13164910078562325200"}}},"outputs":[],"source":["import os\n","\n","os.chdir('drive/MyDrive/Colab Notebooks')"]},{"cell_type":"markdown","source":["### References\n","Apply classes to this model like in here: https://medium.com/@tejpal.abhyuday/information-extraction-part-3-9c2487ec4930"],"metadata":{"id":"-qvDPH-qlj33"}},{"cell_type":"code","source":["import numpy as np\n","from transformers import LayoutLMv3Processor, LayoutLMv3Tokenizer, LayoutLMv3ForTokenClassification, AdamW, LayoutLMv3ImageProcessor\n","from datasets import load_dataset, Dataset, Features, Sequence, ClassLabel, Value, Array2D, Array3D\n","import torch\n","from PIL import Image, ImageDraw, ImageFont\n","from tqdm.notebook import tqdm"],"metadata":{"id":"ovjLqOlFCZ1e","executionInfo":{"status":"ok","timestamp":1741029968791,"user_tz":0,"elapsed":16955,"user":{"displayName":"Simão Quintela","userId":"13164910078562325200"}}},"execution_count":5,"outputs":[]},{"cell_type":"code","source":["# Load our dataset\n","funsd_dataset = load_dataset(\"nielsr/funsd\")\n","id2label = [\"O\", \"B-HEADER\", \"I-HEADER\", \"B-QUESTION\", \"I-QUESTION\", \"B-ANSWER\", \"I-ANSWER\"]\n","label2id = {l:i for i, l in enumerate(id2label)}\n"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":460,"referenced_widgets":["00ba0d7300e6417aa4350a22af12b5ad","06ad3707e73a4f9086f5705a369c87e8","948b79e1f45247c7af98ca3642f3e566","fd37f64801484c1f8e429d3fd4dbe548","32332b27299b42afa686a6c6969b29ed","91591dcb0d6f4151a0c4b47aea80c22c","4a74c348e7ca4271b6d9f267fdeaba9c","8f38c2eb73a44a658282f21ec532ce7f","7d7351eb3e224346bb8681a792cc5ae7","b5f026b7c6e448bebb72c7a9c0484d90","d004e1ea81524734a2393772ac5683d7","e5eff9cfe1c04527b10fd7a13eee5f13","4328e6656bc34727bca16f849ea0b7e1","20ead82bc5e74ebaabc64c9a382eb5a0","78fd95b671ed49a7b2c7c9f3ec8cce18","0316fa51cbca4e75a81d5a34768dabb9","36de2a0aa32b4885a8eb29501381f4bf","95bb9927e66e432b886b7f9da69df885","87d5ed49387948adb0ac63c44bd1f067","2d396af9570c44fcbb9d98b6b2dae03d","db13024b11444a62984d99b53dcd2801","3ac6424d85f545bcbec371e7bcc4e0c9","52c9a5ad220a4e9ab902391ce560d635","f0893cf8f81c43c6a89c9d22b633f82f","3de5b6203d6f42d18c957050cf804b86","63398d2907fc4fbba6732d00e5e6cb4c","d05e18efcc814b83bad62ca2da21cd22","e65d1b68f5ed46ee9554a875420bc93c","c3d85e8cd4784a73aaaa74043f4f38eb","a85fe3a65ca14dbea1fd994b3447da4c","c94c9de83f5c48edb8656543e50ec481","35e7a858fe2344e692bd98b9a7cc5271","8a6a8beeb73743ff9b294b10f039c300","59c1be8d68834c7bb6d9c619b1600d87","22d681db15b244b2b5df1183d80c0e50","2e096f49905648bc8502cc3bc9e9dc58","4c3837188a70491b89d667434f678d29","1bafa89ad5a44fe8b4262b462c1135e9","1f198aee8a11462ab41cf8f7b1b2b830","c44f34b40b694472a29cbcd612301dcf","8fc55f57c7e84d4daa38e144560504ab","d9e27c356d6b4bf082e267b1a6dca601","587654adb3a84e2490b8690ecb230ecc","d71dada534d947b292a075d47c823b12"]},"id":"3IHHKf0aCb8n","executionInfo":{"status":"ok","timestamp":1741029999486,"user_tz":0,"elapsed":30689,"user":{"displayName":"Simão Quintela","userId":"13164910078562325200"}},"outputId":"07795595-53f5-4916-918c-d08bfbbe2915"},"execution_count":6,"outputs":[{"output_type":"stream","name":"stderr","text":["/usr/local/lib/python3.11/dist-packages/huggingface_hub/utils/_auth.py:94: UserWarning: \n","The secret `HF_TOKEN` does not exist in your Colab secrets.\n","To authenticate with the Hugging Face Hub, create a token in your settings tab (https://huggingface.co/settings/tokens), set it as secret in your Google Colab and restart your session.\n","You will be able to reuse this secret in all of your notebooks.\n","Please note that authentication is recommended but still optional to access public models or datasets.\n"," warnings.warn(\n"]},{"output_type":"display_data","data":{"text/plain":["funsd.py: 0%| | 0.00/4.54k [00:00<?, ?B/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"00ba0d7300e6417aa4350a22af12b5ad"}},"metadata":{}},{"name":"stdout","output_type":"stream","text":["The repository for nielsr/funsd contains custom code which must be executed to correctly load the dataset. You can inspect the repository content at https://hf.co/datasets/nielsr/funsd.\n","You can avoid this prompt in future by passing the argument `trust_remote_code=True`.\n","\n","Do you wish to run the custom code? [y/N] y\n"]},{"output_type":"display_data","data":{"text/plain":["Downloading data: 0%| | 0.00/16.8M [00:00<?, ?B/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"e5eff9cfe1c04527b10fd7a13eee5f13"}},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["Generating train split: 0 examples [00:00, ? examples/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"52c9a5ad220a4e9ab902391ce560d635"}},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["Generating test split: 0 examples [00:00, ? examples/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"59c1be8d68834c7bb6d9c619b1600d87"}},"metadata":{}},{"output_type":"execute_result","data":{"text/plain":["{'O': 0,\n"," 'B-HEADER': 1,\n"," 'I-HEADER': 2,\n"," 'B-QUESTION': 3,\n"," 'I-QUESTION': 4,\n"," 'B-ANSWER': 5,\n"," 'I-ANSWER': 6}"]},"metadata":{},"execution_count":6}]},{"cell_type":"code","source":["# Processor and model\n","device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n","processor = LayoutLMv3Processor(\n"," image_processor=LayoutLMv3ImageProcessor(apply_ocr=True),\n"," tokenizer=LayoutLMv3Tokenizer.from_pretrained(\"microsoft/layoutlmv3-base\"),\n",")\n","model = LayoutLMv3ForTokenClassification.from_pretrained(\n"," \"microsoft/layoutlmv3-base\", num_labels=len(id2label)\n",")\n","model.to(device);"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":232,"referenced_widgets":["add91e2650f14a3ca81156aea71d861e","09b1e833c8ff4603b9a8dd13a8fe6796","f79a49d991724e6698cbb4ec9eab8e0e","45eff6094e5a40ef952c6ec318341720","073d225e234c411f8725a30bf8745cc2","c24a82a9f790491594107fc31bb28db4","e8989c5562494e509dff9312883ebd48","3823367257854f489e0540614c6b7149","0bca305d55f4406484e1baf435a76532","7e4d76dea0174e428ac534e3836be531","eff9fd977c8c4886b3ad8f16462f2c1e","8e3b23940bca43a5bd25fd9a2cf677a7","6dde07f8479e441aa9f7f60a654a271c","43c7e7e92dfe4db5b05c5b8678c2a168","1d8680e25a854f3e9e19efc8e1321c29","9ed2c2aaf9f1443aa0464fbbf1a85e2a","bd248ee9d16b476b985ce19f51c7c7e3","d34f1544a5b24a359b9c5a0db52c0ec6","3c03fbb415b446f1a0e0185ab0ef0c15","e491a1db6f14427c9ba93f148b2f8db6","365b80a8f39e417ca24b7758237ae856","ae837f8fae6d467dae865fc63a47b93c","38fb4fd17e5b4bdead971850673ca247","0e139fa3ce1c436b899e9282ad02f542","389c8a27e6e74cd283585b36c7ae20ac","948a5155aaa24f4c92f7468617a7cae1","afddba665dfd40fcbffaed723e82849a","28f12040b42a40ef84366b174bae01cf","d1b1596c6f8c4ab4aace17e3f5c3d856","a21427de566842ab94bd8e2190ec1869","e7503f9bde2941a99659b7257ac95cdb","0f6e623197b449d9b98a7bda6a16d33e","136f84bfc8b44e509b471b793ad2ee49","95ccbcf2180d4bb7ae24634dbfe2af13","134b31acfc0d4e37952a5f9bf7bb05b0","cb4fb059f54844f58e3f9ff7bbe267e9","4fc63f8517064b14ae52cd2ee21e430c","c408161098a44f7ca30a1c21e05a217e","cfe54473555e4b18a96f34ffdb202f69","b066466e85f3418281d3a80f838f99a8","a76e59b5987148f385b36ecbd2c5b0b9","05304f88942e46d087bf3c8a604e07ea","95550ab008af4324b92d80318d2e7ac3","a2c7b850a49942bbb69ef966c8877594","1da5ab56c33846d7b48123fb847e013e","89d60ab1ba8a4cf1b1ffe729a6f7683a","6d6fbf757a76464782dc05b75f105995","2fcffd859f994190862853155c07ec10","b727f17253574b1497a181314d287073","61ad8c45cd7b46c4be5fc038391aeb6d","1697325176c849fe85caaa3d6c81dc9d","ae4c9adefaff4ffba6008aa7f27c00ca","c97cbfc717d04379b59df38149bb7d14","94c22dee94684f149e74b92cf5090acb","1633d2801472443090c5b959874fea55"]},"id":"5QoQUskfCkM9","executionInfo":{"status":"ok","timestamp":1741030017165,"user_tz":0,"elapsed":7041,"user":{"displayName":"Simão Quintela","userId":"13164910078562325200"}},"outputId":"309f6802-884a-4887-b3cb-3a1d8af57f48"},"execution_count":7,"outputs":[{"output_type":"display_data","data":{"text/plain":["tokenizer_config.json: 0%| | 0.00/1.14k [00:00<?, ?B/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"add91e2650f14a3ca81156aea71d861e"}},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["vocab.json: 0%| | 0.00/899k [00:00<?, ?B/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"8e3b23940bca43a5bd25fd9a2cf677a7"}},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["merges.txt: 0%| | 0.00/456k [00:00<?, ?B/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"38fb4fd17e5b4bdead971850673ca247"}},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["config.json: 0%| | 0.00/856 [00:00<?, ?B/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"95ccbcf2180d4bb7ae24634dbfe2af13"}},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["model.safetensors: 0%| | 0.00/501M [00:00<?, ?B/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"1da5ab56c33846d7b48123fb847e013e"}},"metadata":{}},{"output_type":"stream","name":"stderr","text":["Some weights of LayoutLMv3ForTokenClassification were not initialized from the model checkpoint at microsoft/layoutlmv3-base and are newly initialized: ['classifier.bias', 'classifier.weight']\n","You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"]}]},{"cell_type":"code","source":["def encode_training_example(examples):\n"," images = [Image.open(path).convert(\"RGB\") for path in examples['image_path']]\n","\n"," words = examples['words']\n"," boxes = examples['bboxes']\n"," word_labels = examples['ner_tags']\n","\n"," encoded_inputs = processor(\n"," images, words, boxes=boxes, word_labels=word_labels, padding=\"max_length\", truncation=True\n"," )\n","\n"," print(\"encoded inputs\", encoded_inputs.keys())\n","\n"," return encoded_inputs\n","\n","training_features = Features({\n"," 'pixel_values': Array3D(dtype=\"float32\", shape=(3, 224, 224)),\n"," 'input_ids': Sequence(feature=Value(dtype='int64')),\n"," 'attention_mask': Sequence(Value(dtype='int64')),\n"," 'bbox': Array2D(dtype=\"int64\", shape=(512, 4)),\n"," 'labels': Sequence(ClassLabel(names=id2label)),\n","})\n","\n","def training_dataloader_from_dataset(dataset):\n"," encoded_data = dataset.map(\n"," encode_training_example, batched=True, remove_columns=funsd_dataset['train'].column_names,\n"," features=training_features\n"," )\n"," encoded_data.set_format(type='torch', device=device)\n"," dataloader = torch.utils.data.DataLoader(encoded_data, batch_size=4, shuffle=True)\n"," batch = next(iter(dataloader))\n","\n"," return dataloader\n","train_dataloader = training_dataloader_from_dataset(funsd_dataset['train'])\n","valid_dataloader = training_dataloader_from_dataset(funsd_dataset['test'])"],"metadata":{"id":"rbrQAvShCmTA"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["# Training the model\n","optimizer = AdamW(model.parameters(), lr=5e-5)\n","num_epochs = 200\n","\n","training_loss_history = []\n","validation_loss_history = []\n","\n","saved_models = 0\n","\n","for epoch in range(num_epochs):\n"," print(\"Epoch: \", epoch)\n"," training_loss = 0.0\n"," model.train()\n"," for batch in tqdm(train_dataloader):\n"," outputs = model(**batch)\n"," loss = outputs.loss\n","\n"," training_loss += loss.item()\n","\n"," loss.backward()\n"," optimizer.step()\n"," optimizer.zero_grad()\n"," # Save the model and optimizer state after each epoch\n"," if ((training_loss / batch[\"input_ids\"].shape[0]) < 5) and saved_models < 8:\n"," save_path = f\"/kaggle/working/model_checkpoint_epoch_{epoch}.pt\"\n"," torch.save({\n"," 'epoch': epoch,\n"," 'model_state_dict': model.state_dict(),\n"," 'optimizer_state_dict': optimizer.state_dict(),\n"," 'training_loss': training_loss,\n"," }, save_path)\n"," print(f\"Checkpoint saved: {save_path}\")\n"," saved_models+=1\n","\n"," training_loss_history.append(training_loss)\n"," print(\"Training Loss: \", training_loss / batch[\"input_ids\"].shape[0])\n"," validation_loss = 0.0\n"," for batch in tqdm(valid_dataloader):\n"," outputs = model(**batch)\n"," loss = outputs.loss\n"," validation_loss += loss.item()\n","\n"," print(\"Validation Loss: \", validation_loss)\n"," validation_loss_history.append(validation_loss)\n"],"metadata":{"id":"05_xdowfCoeg"},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":["## Inference phase"],"metadata":{"id":"the6M-xJCtAl"}},{"cell_type":"code","source":["import torch\n","torch.cuda.empty_cache()\n","device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n","\n","model = LayoutLMv3ForTokenClassification.from_pretrained('../Tese/LayoutLMv3_0/')\n","model.to(device)"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"collapsed":true,"id":"2cciCSgNCuQT","executionInfo":{"status":"ok","timestamp":1741030033862,"user_tz":0,"elapsed":8031,"user":{"displayName":"Simão Quintela","userId":"13164910078562325200"}},"outputId":"5f90aded-801c-403b-933c-565c89c81c89"},"execution_count":8,"outputs":[{"output_type":"execute_result","data":{"text/plain":["LayoutLMv3ForTokenClassification(\n"," (layoutlmv3): LayoutLMv3Model(\n"," (embeddings): LayoutLMv3TextEmbeddings(\n"," (word_embeddings): Embedding(50265, 768, padding_idx=1)\n"," (token_type_embeddings): Embedding(1, 768)\n"," (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n"," (dropout): Dropout(p=0.1, inplace=False)\n"," (position_embeddings): Embedding(514, 768, padding_idx=1)\n"," (x_position_embeddings): Embedding(1024, 128)\n"," (y_position_embeddings): Embedding(1024, 128)\n"," (h_position_embeddings): Embedding(1024, 128)\n"," (w_position_embeddings): Embedding(1024, 128)\n"," )\n"," (patch_embed): LayoutLMv3PatchEmbeddings(\n"," (proj): Conv2d(3, 768, kernel_size=(16, 16), stride=(16, 16))\n"," )\n"," (pos_drop): Dropout(p=0.0, inplace=False)\n"," (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n"," (dropout): Dropout(p=0.1, inplace=False)\n"," (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True)\n"," (encoder): LayoutLMv3Encoder(\n"," (layer): ModuleList(\n"," (0-11): 12 x LayoutLMv3Layer(\n"," (attention): LayoutLMv3Attention(\n"," (self): LayoutLMv3SelfAttention(\n"," (query): Linear(in_features=768, out_features=768, bias=True)\n"," (key): Linear(in_features=768, out_features=768, bias=True)\n"," (value): Linear(in_features=768, out_features=768, bias=True)\n"," (dropout): Dropout(p=0.1, inplace=False)\n"," )\n"," (output): LayoutLMv3SelfOutput(\n"," (dense): Linear(in_features=768, out_features=768, bias=True)\n"," (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n"," (dropout): Dropout(p=0.1, inplace=False)\n"," )\n"," )\n"," (intermediate): LayoutLMv3Intermediate(\n"," (dense): Linear(in_features=768, out_features=3072, bias=True)\n"," (intermediate_act_fn): GELUActivation()\n"," )\n"," (output): LayoutLMv3Output(\n"," (dense): Linear(in_features=3072, out_features=768, bias=True)\n"," (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n"," (dropout): Dropout(p=0.1, inplace=False)\n"," )\n"," )\n"," )\n"," (rel_pos_bias): Linear(in_features=32, out_features=12, bias=False)\n"," (rel_pos_x_bias): Linear(in_features=64, out_features=12, bias=False)\n"," (rel_pos_y_bias): Linear(in_features=64, out_features=12, bias=False)\n"," )\n"," )\n"," (dropout): Dropout(p=0.1, inplace=False)\n"," (classifier): Linear(in_features=768, out_features=7, bias=True)\n",")"]},"metadata":{},"execution_count":8}]},{"cell_type":"code","source":["\n","from pprint import pprint\n","def unnormalize_box(bbox, width, height):\n"," return [\n"," width * (bbox[0] / 1000),\n"," height * (bbox[1] / 1000),\n"," width * (bbox[2] / 1000),\n"," height * (bbox[3] / 1000),\n"," ]\n","\n","def iob_to_label(label):\n"," label = label[2:]\n"," if not label:\n"," return 'other'\n"," return label\n","\n","def inference(apply_ocr=False, save=False):\n"," for i, image_ocr in enumerate(funsd_dataset['test']):\n"," image = Image.open(image_ocr['image_path'])\n"," image = image.convert(\"RGB\")\n"," width, height = image.size\n","\n"," if apply_ocr:\n"," encoded_inputs = processor(\n"," image,\n"," padding=\"max_length\", truncation=True, return_tensors=\"pt\", return_token_type_ids=True\n"," ).to(device)\n"," else:\n"," encoded_inputs = processor(\n"," image, image_ocr['words'], boxes=image_ocr['bboxes'], word_labels=image_ocr['ner_tags'],\n"," padding=\"max_length\", truncation=True, return_tensors=\"pt\"\n"," ).to(device)\n","\n"," # Decode the words so it is easier to debug\n"," input_ids = encoded_inputs.input_ids\n"," words = processor.tokenizer.decode(input_ids[0], skip_special_tokens=False).split()\n","\n"," # Inference\n"," outputs = model(**encoded_inputs)\n"," predictions = outputs.logits.argmax(-1).squeeze().tolist()\n"," token_boxes = encoded_inputs.bbox.squeeze().tolist()\n","\n"," true_predictions = [id2label[prediction] for prediction in predictions]\n"," true_boxes = [unnormalize_box(box, width, height) for box in token_boxes]\n"," draw = ImageDraw.Draw(image)\n","\n"," font = ImageFont.load_default()\n"," label2color = {'question':'blue', 'answer':'green', 'header':'orange', 'other':'violet'}\n","\n"," # Draw the output\n"," for prediction, box in zip(true_predictions, true_boxes):\n"," predicted_label = iob_to_label(prediction).lower()\n"," draw.rectangle(box, outline=label2color[predicted_label])\n"," draw.text(\n"," (box[0]+10, box[1]-10), text=predicted_label, fill=label2color[predicted_label], font=font\n"," )\n","\n"," # Save prediction in drive\n"," if save:\n"," if apply_ocr:\n"," save_path = f'../Tese/LayoutLMv3_0/TestDataWithOcr/funds_test_{i}.png'\n"," else:\n"," save_path = f'../Tese/LayoutLMv3_0/TestDataWithoutOcr/funds_test_{i}.png'\n","\n"," os.makedirs(os.path.dirname(save_path), exist_ok=True)\n"," image.save(save_path)\n","\n","\n","\n","#ocrless_inference()\n","inference(apply_ocr=True, save=False)"],"metadata":{"collapsed":true,"id":"jv5ieoYdFKUZ"},"execution_count":null,"outputs":[]}]}