From c285083a3d8fd792cbfe0b8e78681034206957b1 Mon Sep 17 00:00:00 2001 From: Jason Phang Date: Mon, 4 Jan 2021 23:47:19 -0500 Subject: [PATCH] edge probing notebook --- .../notebooks/jiant_EdgeProbing_Example.ipynb | 3500 +++++++++++++++++ 1 file changed, 3500 insertions(+) create mode 100644 examples/notebooks/jiant_EdgeProbing_Example.ipynb diff --git a/examples/notebooks/jiant_EdgeProbing_Example.ipynb b/examples/notebooks/jiant_EdgeProbing_Example.ipynb new file mode 100644 index 000000000..0defefa03 --- /dev/null +++ b/examples/notebooks/jiant_EdgeProbing_Example.ipynb @@ -0,0 +1,3500 @@ +{ + "nbformat": 4, + "nbformat_minor": 0, + "metadata": { + "accelerator": "GPU", + "colab": { + "name": "jiant STILTs Example", + "provenance": [], + "collapsed_sections": [], + "toc_visible": true + }, + "kernelspec": { + "display_name": "Python 3", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.7.2" + }, + "widgets": { + "application/vnd.jupyter.widget-state+json": { + "0ad0c4ef8cc64749b6bd2ccb2ba41563": { + "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_d0fb730b54044b8583fdf3ee0476cb52", + "_model_module": "@jupyter-widgets/controls", + "children": [ + "IPY_MODEL_4d260f0aaa1d4e1498c8895bf3c418b2", + "IPY_MODEL_bf55400872a34cbcb3527870b2191c8f" + ] + } + }, + "d0fb730b54044b8583fdf3ee0476cb52": { + "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 + } + }, + "4d260f0aaa1d4e1498c8895bf3c418b2": { + "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", + "state": { + "_view_name": "ProgressView", + "style": "IPY_MODEL_1a0f2e4658744f6abfbfd1a3c8ae0d81", + "_dom_classes": [], + "description": "Downloading: 100%", + "_model_name": "FloatProgressModel", + "bar_style": "success", + "max": 481, + "_view_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "value": 481, + "_view_count": null, + "_view_module_version": "1.5.0", + "orientation": "horizontal", + "min": 0, + "description_tooltip": null, + "_model_module": "@jupyter-widgets/controls", + "layout": "IPY_MODEL_448fafdecf8c46588f95cc4383942e59" + } + }, + "bf55400872a34cbcb3527870b2191c8f": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "state": { + "_view_name": "HTMLView", + "style": "IPY_MODEL_a233d58461ad4ab98181153139d76571", + "_dom_classes": [], + "description": "", + "_model_name": "HTMLModel", + "placeholder": "​", + "_view_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "value": " 481/481 [00:15<00:00, 31.4B/s]", + "_view_count": null, + "_view_module_version": "1.5.0", + "description_tooltip": null, + "_model_module": "@jupyter-widgets/controls", + "layout": "IPY_MODEL_660a5872700947a4b20a7eb2d3eb80ac" + } + }, + "1a0f2e4658744f6abfbfd1a3c8ae0d81": { + "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" + } + }, + "448fafdecf8c46588f95cc4383942e59": { + "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 + } + }, + "a233d58461ad4ab98181153139d76571": { + "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" + } + }, + "660a5872700947a4b20a7eb2d3eb80ac": { + "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 + } + }, + "273d939ae19a47ae976c3a7afe9403b8": { + "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_e99430b62eb141798053b07ea119a1ad", + "_model_module": "@jupyter-widgets/controls", + "children": [ + "IPY_MODEL_cb0bcb188961445b96feec69f0477eea", + "IPY_MODEL_40a3f4a2ac2240469a787a06e4a6a361" + ] + } + }, + "e99430b62eb141798053b07ea119a1ad": { + "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 + } + }, + "cb0bcb188961445b96feec69f0477eea": { + "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", + "state": { + "_view_name": "ProgressView", + "style": "IPY_MODEL_ca9f84de217a46acaf4906bad6851c7b", + "_dom_classes": [], + "description": "Downloading: 100%", + "_model_name": "FloatProgressModel", + "bar_style": "success", + "max": 501200538, + "_view_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "value": 501200538, + "_view_count": null, + "_view_module_version": "1.5.0", + "orientation": "horizontal", + "min": 0, + "description_tooltip": null, + "_model_module": "@jupyter-widgets/controls", + "layout": "IPY_MODEL_a27515c619da49e187318ae10c3afb46" + } + }, + "40a3f4a2ac2240469a787a06e4a6a361": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "state": { + "_view_name": "HTMLView", + "style": "IPY_MODEL_e8f2532f90134a07b1e2727a7b83471c", + "_dom_classes": [], + "description": "", + "_model_name": "HTMLModel", + "placeholder": "​", + "_view_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "value": " 501M/501M [00:07<00:00, 68.8MB/s]", + "_view_count": null, + "_view_module_version": "1.5.0", + "description_tooltip": null, + "_model_module": "@jupyter-widgets/controls", + "layout": "IPY_MODEL_fe65d5ec01ea4f95a19808d8894d1e2c" + } + }, + "ca9f84de217a46acaf4906bad6851c7b": { + "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" + } + }, + "a27515c619da49e187318ae10c3afb46": { + "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 + } + }, + "e8f2532f90134a07b1e2727a7b83471c": { + "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" + } + }, + "fe65d5ec01ea4f95a19808d8894d1e2c": { + "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 + } + }, + "cba1747a59364cab89af52f64d7d2be4": { + "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_04c29dbb9a154153a86eb7e35d7a374e", + "_model_module": "@jupyter-widgets/controls", + "children": [ + "IPY_MODEL_78f0337d61ff43b3ba17719c4f9e05fa", + "IPY_MODEL_49fcb769f4e34e2d870b8aff33267cb9" + ] + } + }, + "04c29dbb9a154153a86eb7e35d7a374e": { + "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 + } + }, + "78f0337d61ff43b3ba17719c4f9e05fa": { + "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", + "state": { + "_view_name": "ProgressView", + "style": "IPY_MODEL_f9770a94eb4044dd90fe74991c56d1c5", + "_dom_classes": [], + "description": "Downloading: 100%", + "_model_name": "FloatProgressModel", + "bar_style": "success", + "max": 898823, + "_view_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "value": 898823, + "_view_count": null, + "_view_module_version": "1.5.0", + "orientation": "horizontal", + "min": 0, + "description_tooltip": null, + "_model_module": "@jupyter-widgets/controls", + "layout": "IPY_MODEL_afe39f56bc4c40f8967a6e5b358d9476" + } + }, + "49fcb769f4e34e2d870b8aff33267cb9": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "state": { + "_view_name": "HTMLView", + "style": "IPY_MODEL_e1c00cf74ea94eb9b61afd46bb042025", + "_dom_classes": [], + "description": "", + "_model_name": "HTMLModel", + "placeholder": "​", + "_view_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "value": " 899k/899k [00:00<00:00, 3.43MB/s]", + "_view_count": null, + "_view_module_version": "1.5.0", + "description_tooltip": null, + "_model_module": "@jupyter-widgets/controls", + "layout": "IPY_MODEL_0aee9253d3a14716a0a67dfda31f7a0f" + } + }, + "f9770a94eb4044dd90fe74991c56d1c5": { + "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" + } + }, + "afe39f56bc4c40f8967a6e5b358d9476": { + "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 + } + }, + "e1c00cf74ea94eb9b61afd46bb042025": { + "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" + } + }, + "0aee9253d3a14716a0a67dfda31f7a0f": { + "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 + } + }, + "c795cd64b082451f9876de86ea6353ea": { + "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_089916ffd2064364acae7fbb0f77113e", + "_model_module": "@jupyter-widgets/controls", + "children": [ + "IPY_MODEL_74b9301d8a3a4bd7a6fb4c15cd6f26a0", + "IPY_MODEL_aa6beffff7f34d59a6552f45725f1c77" + ] + } + }, + "089916ffd2064364acae7fbb0f77113e": { + "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 + } + }, + "74b9301d8a3a4bd7a6fb4c15cd6f26a0": { + "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", + "state": { + "_view_name": "ProgressView", + "style": "IPY_MODEL_908f97b966be42d0a995df0dbb3ebd2b", + "_dom_classes": [], + "description": "Downloading: 100%", + "_model_name": "FloatProgressModel", + "bar_style": "success", + "max": 456318, + "_view_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "value": 456318, + "_view_count": null, + "_view_module_version": "1.5.0", + "orientation": "horizontal", + "min": 0, + "description_tooltip": null, + "_model_module": "@jupyter-widgets/controls", + "layout": "IPY_MODEL_a4067515d3e34605a03e21fe7e4b1957" + } + }, + "aa6beffff7f34d59a6552f45725f1c77": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "state": { + "_view_name": "HTMLView", + "style": "IPY_MODEL_9783cdbe47fd4177ba89e447bf843a25", + "_dom_classes": [], + "description": "", + "_model_name": "HTMLModel", + "placeholder": "​", + "_view_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "value": " 456k/456k [00:00<00:00, 3.95MB/s]", + "_view_count": null, + "_view_module_version": "1.5.0", + "description_tooltip": null, + "_model_module": "@jupyter-widgets/controls", + "layout": "IPY_MODEL_4fb3f4ea5d9c4705b3e9b0dd0408fe07" + } + }, + "908f97b966be42d0a995df0dbb3ebd2b": { + "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" + } + }, + "a4067515d3e34605a03e21fe7e4b1957": { + "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 + } + }, + "9783cdbe47fd4177ba89e447bf843a25": { + "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" + } + }, + "4fb3f4ea5d9c4705b3e9b0dd0408fe07": { + "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 + } + }, + "558652d65c9c42e5b2487711ea8c5183": { + "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_b59db489de7a410fb16ac4c64554c2db", + "_model_module": "@jupyter-widgets/controls", + "children": [ + "IPY_MODEL_648bd87cbe344ce786e78d902456be01", + "IPY_MODEL_763685078bfa425a84652935a1d49965" + ] + } + }, + "b59db489de7a410fb16ac4c64554c2db": { + "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 + } + }, + "648bd87cbe344ce786e78d902456be01": { + "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", + "state": { + "_view_name": "ProgressView", + "style": "IPY_MODEL_5cada33c5612410482ab58422f866621", + "_dom_classes": [], + "description": "Tokenizing: 100%", + "_model_name": "FloatProgressModel", + "bar_style": "success", + "max": 1000, + "_view_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "value": 1000, + "_view_count": null, + "_view_module_version": "1.5.0", + "orientation": "horizontal", + "min": 0, + "description_tooltip": null, + "_model_module": "@jupyter-widgets/controls", + "layout": "IPY_MODEL_635bed807450413797ec7d1c8a16444d" + } + }, + "763685078bfa425a84652935a1d49965": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "state": { + "_view_name": "HTMLView", + "style": "IPY_MODEL_9878a78abe8e41c585f63ed1e77309ea", + "_dom_classes": [], + "description": "", + "_model_name": "HTMLModel", + "placeholder": "​", + "_view_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "value": " 1000/1000 [00:13<00:00, 72.72it/s]", + "_view_count": null, + "_view_module_version": "1.5.0", + "description_tooltip": null, + "_model_module": "@jupyter-widgets/controls", + "layout": "IPY_MODEL_2b0ee8fa0e614926b8ea2befa8d93893" + } + }, + "5cada33c5612410482ab58422f866621": { + "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" + } + }, + "635bed807450413797ec7d1c8a16444d": { + "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 + } + }, + "9878a78abe8e41c585f63ed1e77309ea": { + "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" + } + }, + "2b0ee8fa0e614926b8ea2befa8d93893": { + "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 + } + }, + "6bfcf6f5ebc144e88f55e1501c398ab3": { + "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_0fe088ff545b4642993a0395bc0351af", + "_model_module": "@jupyter-widgets/controls", + "children": [ + "IPY_MODEL_6644d495d3ab4198962cc3e4fd130fe0", + "IPY_MODEL_95e0eeb66af842fc9a5ea7072e665045" + ] + } + }, + "0fe088ff545b4642993a0395bc0351af": { + "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 + } + }, + "6644d495d3ab4198962cc3e4fd130fe0": { + "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", + "state": { + "_view_name": "ProgressView", + "style": "IPY_MODEL_13039f3a86204fdea19dd335aaa66519", + "_dom_classes": [], + "description": "Tokenizing: 100%", + "_model_name": "FloatProgressModel", + "bar_style": "success", + "max": 100, + "_view_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "value": 100, + "_view_count": null, + "_view_module_version": "1.5.0", + "orientation": "horizontal", + "min": 0, + "description_tooltip": null, + "_model_module": "@jupyter-widgets/controls", + "layout": "IPY_MODEL_effe903b59b24573b1c3e406b986dfac" + } + }, + "95e0eeb66af842fc9a5ea7072e665045": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "state": { + "_view_name": "HTMLView", + "style": "IPY_MODEL_b6aeddb44c3147e2ab912d84759bc139", + "_dom_classes": [], + "description": "", + "_model_name": "HTMLModel", + "placeholder": "​", + "_view_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "value": " 100/100 [00:02<00:00, 38.47it/s]", + "_view_count": null, + "_view_module_version": "1.5.0", + "description_tooltip": null, + "_model_module": "@jupyter-widgets/controls", + "layout": "IPY_MODEL_1b51de8cdcbd4c01af4de5865e9c575d" + } + }, + "13039f3a86204fdea19dd335aaa66519": { + "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" + } + }, + "effe903b59b24573b1c3e406b986dfac": { + "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 + } + }, + "b6aeddb44c3147e2ab912d84759bc139": { + "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" + } + }, + "1b51de8cdcbd4c01af4de5865e9c575d": { + "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 + } + }, + "f081100984b44e45a77fff620f998508": { + "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_69d9699a4d7147b5bf9ada54c4839488", + "_model_module": "@jupyter-widgets/controls", + "children": [ + "IPY_MODEL_e8e3b6cf03e04df99ac9799dbbe997cf", + "IPY_MODEL_0ca001e7315c41359a48a37579ad7ac6" + ] + } + }, + "69d9699a4d7147b5bf9ada54c4839488": { + "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 + } + }, + "e8e3b6cf03e04df99ac9799dbbe997cf": { + "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", + "state": { + "_view_name": "ProgressView", + "style": "IPY_MODEL_d4f840d6919047c795fbe22cc096ae39", + "_dom_classes": [], + "description": "Training: 100%", + "_model_name": "FloatProgressModel", + "bar_style": "danger", + "max": 375, + "_view_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "value": 374, + "_view_count": null, + "_view_module_version": "1.5.0", + "orientation": "horizontal", + "min": 0, + "description_tooltip": null, + "_model_module": "@jupyter-widgets/controls", + "layout": "IPY_MODEL_db4132b9258440179d76382ed537257c" + } + }, + "0ca001e7315c41359a48a37579ad7ac6": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "state": { + "_view_name": "HTMLView", + "style": "IPY_MODEL_9ae696b3d7bd470787c4de833990a614", + "_dom_classes": [], + "description": "", + "_model_name": "HTMLModel", + "placeholder": "​", + "_view_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "value": " 374/375 [01:19<00:00, 4.69it/s]", + "_view_count": null, + "_view_module_version": "1.5.0", + "description_tooltip": null, + "_model_module": "@jupyter-widgets/controls", + "layout": "IPY_MODEL_17a6d908da41486995c53d7436990b8b" + } + }, + "d4f840d6919047c795fbe22cc096ae39": { + "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" + } + }, + "db4132b9258440179d76382ed537257c": { + "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 + } + }, + "9ae696b3d7bd470787c4de833990a614": { + "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" + } + }, + "17a6d908da41486995c53d7436990b8b": { + "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 + } + }, + "7b6147ac6008406c932bb5c5fbf9c8ad": { + "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_d41d7ce333404ac8b12feed2031f1cd2", + "_model_module": "@jupyter-widgets/controls", + "children": [ + "IPY_MODEL_ff00a73e3d474420ab697edb5626da1b", + "IPY_MODEL_70693f5e1708442d9377b03600d256c4" + ] + } + }, + "d41d7ce333404ac8b12feed2031f1cd2": { + "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 + } + }, + "ff00a73e3d474420ab697edb5626da1b": { + "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", + "state": { + "_view_name": "ProgressView", + "style": "IPY_MODEL_d5045b7014fa46518bb0378cf52fa76f", + "_dom_classes": [], + "description": "Eval (semeval, Val): 100%", + "_model_name": "FloatProgressModel", + "bar_style": "success", + "max": 7, + "_view_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "value": 7, + "_view_count": null, + "_view_module_version": "1.5.0", + "orientation": "horizontal", + "min": 0, + "description_tooltip": null, + "_model_module": "@jupyter-widgets/controls", + "layout": "IPY_MODEL_e23242c190344c098076d1fc8140e6f2" + } + }, + "70693f5e1708442d9377b03600d256c4": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "state": { + "_view_name": "HTMLView", + "style": "IPY_MODEL_e1a1f7ae889e45ad9b825d752c74a38d", + "_dom_classes": [], + "description": "", + "_model_name": "HTMLModel", + "placeholder": "​", + "_view_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "value": " 7/7 [00:05<00:00, 1.18it/s]", + "_view_count": null, + "_view_module_version": "1.5.0", + "description_tooltip": null, + "_model_module": "@jupyter-widgets/controls", + "layout": "IPY_MODEL_bc31ec29b5f24d838401db71b345aeed" + } + }, + "d5045b7014fa46518bb0378cf52fa76f": { + "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" + } + }, + "e23242c190344c098076d1fc8140e6f2": { + "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 + } + }, + "e1a1f7ae889e45ad9b825d752c74a38d": { + "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" + } + }, + "bc31ec29b5f24d838401db71b345aeed": { + "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 + } + }, + "4b138e183eaf406a8fec6a2cc36f067a": { + "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_ab66645a63274e67a823bed7702d5da2", + "_model_module": "@jupyter-widgets/controls", + "children": [ + "IPY_MODEL_b093c8725cf24d37861f2b38837f4bc4", + "IPY_MODEL_62651b48746c4536a6814fefa89c91e6" + ] + } + }, + "ab66645a63274e67a823bed7702d5da2": { + "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 + } + }, + "b093c8725cf24d37861f2b38837f4bc4": { + "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", + "state": { + "_view_name": "ProgressView", + "style": "IPY_MODEL_f5d8d08063f340f6b32bf7f2f0fd5821", + "_dom_classes": [], + "description": "Eval (semeval, Val): 100%", + "_model_name": "FloatProgressModel", + "bar_style": "success", + "max": 7, + "_view_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "value": 7, + "_view_count": null, + "_view_module_version": "1.5.0", + "orientation": "horizontal", + "min": 0, + "description_tooltip": null, + "_model_module": "@jupyter-widgets/controls", + "layout": "IPY_MODEL_3dbe5ad38b23422481c2e51acdc78b20" + } + }, + "62651b48746c4536a6814fefa89c91e6": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "state": { + "_view_name": "HTMLView", + "style": "IPY_MODEL_9a83595e4bb74bc0948be54799248d16", + "_dom_classes": [], + "description": "", + "_model_name": "HTMLModel", + "placeholder": "​", + "_view_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "value": " 7/7 [00:01<00:00, 4.72it/s]", + "_view_count": null, + "_view_module_version": "1.5.0", + "description_tooltip": null, + "_model_module": "@jupyter-widgets/controls", + "layout": "IPY_MODEL_27e02234b1764aed9156f565ec454246" + } + }, + "f5d8d08063f340f6b32bf7f2f0fd5821": { + "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" + } + }, + "3dbe5ad38b23422481c2e51acdc78b20": { + "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 + } + }, + "9a83595e4bb74bc0948be54799248d16": { + "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" + } + }, + "27e02234b1764aed9156f565ec454246": { + "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 + } + }, + "ad747e2552c5429484dcd3d19c366a96": { + "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_54e47f0d45d24009aa83fbb5d614e98a", + "_model_module": "@jupyter-widgets/controls", + "children": [ + "IPY_MODEL_ab6394febb5b4d48b9d26d9846f0eb87", + "IPY_MODEL_e34035b4fc8348f2ab108b9edc5d0322" + ] + } + }, + "54e47f0d45d24009aa83fbb5d614e98a": { + "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 + } + }, + "ab6394febb5b4d48b9d26d9846f0eb87": { + "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", + "state": { + "_view_name": "ProgressView", + "style": "IPY_MODEL_0bce1deff0d64bf7a96b6307efd4544e", + "_dom_classes": [], + "description": "Eval (semeval, Val): 100%", + "_model_name": "FloatProgressModel", + "bar_style": "success", + "max": 7, + "_view_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "value": 7, + "_view_count": null, + "_view_module_version": "1.5.0", + "orientation": "horizontal", + "min": 0, + "description_tooltip": null, + "_model_module": "@jupyter-widgets/controls", + "layout": "IPY_MODEL_91fac974c5eb4f19b7b0cf18e3521d82" + } + }, + "e34035b4fc8348f2ab108b9edc5d0322": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "state": { + "_view_name": "HTMLView", + "style": "IPY_MODEL_968570f0cb0a45c7ab5ab76e00936ae3", + "_dom_classes": [], + "description": "", + "_model_name": "HTMLModel", + "placeholder": "​", + "_view_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "value": " 7/7 [00:00<00:00, 9.29it/s]", + "_view_count": null, + "_view_module_version": "1.5.0", + "description_tooltip": null, + "_model_module": "@jupyter-widgets/controls", + "layout": "IPY_MODEL_03fb6747a39646e3b7dda6f877ce19fe" + } + }, + "0bce1deff0d64bf7a96b6307efd4544e": { + "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" + } + }, + "91fac974c5eb4f19b7b0cf18e3521d82": { + "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 + } + }, + "968570f0cb0a45c7ab5ab76e00936ae3": { + "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" + } + }, + "03fb6747a39646e3b7dda6f877ce19fe": { + "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": "O9I9rz0pTamX" + }, + "source": [ + "# Edge-Probing Fine-tuning Example" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "EiowR0WNTd1C" + }, + "source": [ + "In this notebook, we will:\n", + "\n", + "* Train a RoBERTa base model on Edge-Probing (Semeval) and evaluate its performance\n", + "* Because the Edge-Probing data is not publicly available, we will simulate the run with a single example. This will serve as a guide for users who have access to the task data, or similarly formatted data.\n", + "* **The encoder is not frozen for training runs in this notebook.**\n", + "\n", + "The code shown in this notebook will work, but the results will not be representative of the task!" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "rXbD_U1_VDnw" + }, + "source": [ + "## Setup" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "tC9teoazUnW8" + }, + "source": [ + "#### Install dependencies\n", + "\n", + "First, we will install libraries we need for this code." + ] + }, + { + "cell_type": "code", + "metadata": { + "id": "8aU3Z9szuMU9" + }, + "source": [ + "%%capture\n", + "!git clone https://github.com/nyu-mll/jiant.git\n", + "%cd jiant\n", + "!pip install -r requirements-no-torch.txt\n", + "!pip install --no-deps -e ./\n", + "%cd .." + ], + "execution_count": 1, + "outputs": [] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "rQKSAhYzVIlv" + }, + "source": [ + "## `jiant` Pipeline" + ] + }, + { + "cell_type": "code", + "metadata": { + "id": "v88oXqmBvFuK" + }, + "source": [ + "import sys\n", + "sys.path.insert(0, \"/content/jiant\")" + ], + "execution_count": 2, + "outputs": [] + }, + { + "cell_type": "code", + "metadata": { + "id": "ibmMT7CXv1_P" + }, + "source": [ + "import jiant.proj.main.tokenize_and_cache as tokenize_and_cache\n", + "import jiant.proj.main.export_model as export_model\n", + "import jiant.proj.main.scripts.configurator as configurator\n", + "import jiant.proj.main.runscript as main_runscript\n", + "import jiant.shared.caching as caching\n", + "import jiant.utils.python.io as py_io\n", + "import jiant.utils.display as display\n", + "import os" + ], + "execution_count": 3, + "outputs": [] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "-ihjR1g_1phl" + }, + "source": [ + "## Creating sample Edge-Probing data.\n", + "\n", + "Because the Edge-Probing data is not publicly available, we will simulate the run with a single example. We will write 1000 copies for the training set and 100 copies for the validation set. We will also write the corresponding task config." + ] + }, + { + "cell_type": "code", + "metadata": { + "id": "jKCz8VksvFlN" + }, + "source": [ + "example = {\n", + " \"text\": \"The current view is that the chronic inflammation in the distal part of the stomach caused by Helicobacter pylori infection results in an increased acid production from the non-infected upper corpus region of the stomach.\",\n", + " \"info\": {\"id\": 7},\n", + " \"targets\": [\n", + " {\n", + " \"label\": \"Cause-Effect(e2,e1)\",\n", + " \"span1\": [7,8],\n", + " \"span2\": [19, 20],\n", + " \"info\": {\"comment\": \"\"}\n", + " }\n", + " ]\n", + "}\n", + "# Simulate a training set of 1000 examples\n", + "train_data = [example] * 1000\n", + "# Simulate a validation set of 100 examples\n", + "val_data = [example] * 100" + ], + "execution_count": 4, + "outputs": [] + }, + { + "cell_type": "code", + "metadata": { + "id": "Uvt8Zi86yHHa" + }, + "source": [ + "os.makedirs(\"/content/tasks/configs/\", exist_ok=True)\n", + "os.makedirs(\"/content/tasks/data/semeval\", exist_ok=True)\n", + "py_io.write_jsonl(\n", + " data=train_data,\n", + " path=\"/content/tasks/data/semeval/train.jsonl\",\n", + ")\n", + "py_io.write_jsonl(\n", + " data=val_data,\n", + " path=\"/content/tasks/data/semeval/val.jsonl\",\n", + ")\n", + "py_io.write_json({\n", + " \"task\": \"semeval\",\n", + " \"paths\": {\n", + " \"train\": \"/content/tasks/data/semeval/train.jsonl\",\n", + " \"val\": \"/content/tasks/data/semeval/val.jsonl\",\n", + " },\n", + " \"name\": \"semeval\"\n", + "}, \"/content/tasks/configs/semeval_config.json\")" + ], + "execution_count": 5, + "outputs": [] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "HPZHyLOlVp07" + }, + "source": [ + "#### Download model\n", + "\n", + "Next, we will download a `roberta-base` model. This also includes the tokenizer." + ] + }, + { + "cell_type": "code", + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 269, + "referenced_widgets": [ + "0ad0c4ef8cc64749b6bd2ccb2ba41563", + "d0fb730b54044b8583fdf3ee0476cb52", + "4d260f0aaa1d4e1498c8895bf3c418b2", + "bf55400872a34cbcb3527870b2191c8f", + "1a0f2e4658744f6abfbfd1a3c8ae0d81", + "448fafdecf8c46588f95cc4383942e59", + "a233d58461ad4ab98181153139d76571", + "660a5872700947a4b20a7eb2d3eb80ac", + "273d939ae19a47ae976c3a7afe9403b8", + "e99430b62eb141798053b07ea119a1ad", + "cb0bcb188961445b96feec69f0477eea", + "40a3f4a2ac2240469a787a06e4a6a361", + "ca9f84de217a46acaf4906bad6851c7b", + "a27515c619da49e187318ae10c3afb46", + "e8f2532f90134a07b1e2727a7b83471c", + "fe65d5ec01ea4f95a19808d8894d1e2c", + "cba1747a59364cab89af52f64d7d2be4", + "04c29dbb9a154153a86eb7e35d7a374e", + "78f0337d61ff43b3ba17719c4f9e05fa", + "49fcb769f4e34e2d870b8aff33267cb9", + "f9770a94eb4044dd90fe74991c56d1c5", + "afe39f56bc4c40f8967a6e5b358d9476", + "e1c00cf74ea94eb9b61afd46bb042025", + "0aee9253d3a14716a0a67dfda31f7a0f", + "c795cd64b082451f9876de86ea6353ea", + "089916ffd2064364acae7fbb0f77113e", + "74b9301d8a3a4bd7a6fb4c15cd6f26a0", + "aa6beffff7f34d59a6552f45725f1c77", + "908f97b966be42d0a995df0dbb3ebd2b", + "a4067515d3e34605a03e21fe7e4b1957", + "9783cdbe47fd4177ba89e447bf843a25", + "4fb3f4ea5d9c4705b3e9b0dd0408fe07" + ] + }, + "id": "K06qUGjkKWa7", + "outputId": "c21bdffa-0ff3-49f3-e734-af5530ab4711" + }, + "source": [ + "export_model.lookup_and_export_model(\n", + " model_type=\"roberta-base\",\n", + " output_base_path=\"./models/roberta-base\",\n", + ")" + ], + "execution_count": 6, + "outputs": [ + { + "output_type": "display_data", + "data": { + "application/vnd.jupyter.widget-view+json": { + "model_id": "0ad0c4ef8cc64749b6bd2ccb2ba41563", + "version_minor": 0, + "version_major": 2 + }, + "text/plain": [ + "HBox(children=(FloatProgress(value=0.0, description='Downloading', max=481.0, 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": "273d939ae19a47ae976c3a7afe9403b8", + "version_minor": 0, + "version_major": 2 + }, + "text/plain": [ + "HBox(children=(FloatProgress(value=0.0, description='Downloading', max=501200538.0, style=ProgressStyle(descri…" + ] + }, + "metadata": { + "tags": [] + } + }, + { + "output_type": "stream", + "text": [ + "\n" + ], + "name": "stdout" + }, + { + "output_type": "stream", + "text": [ + "Some weights of RobertaForMaskedLM were not initialized from the model checkpoint at roberta-base and are newly initialized: ['lm_head.decoder.bias']\n", + "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n" + ], + "name": "stderr" + }, + { + "output_type": "display_data", + "data": { + "application/vnd.jupyter.widget-view+json": { + "model_id": "cba1747a59364cab89af52f64d7d2be4", + "version_minor": 0, + "version_major": 2 + }, + "text/plain": [ + "HBox(children=(FloatProgress(value=0.0, description='Downloading', max=898823.0, style=ProgressStyle(descripti…" + ] + }, + "metadata": { + "tags": [] + } + }, + { + "output_type": "stream", + "text": [ + "\n" + ], + "name": "stdout" + }, + { + "output_type": "display_data", + "data": { + "application/vnd.jupyter.widget-view+json": { + "model_id": "c795cd64b082451f9876de86ea6353ea", + "version_minor": 0, + "version_major": 2 + }, + "text/plain": [ + "HBox(children=(FloatProgress(value=0.0, description='Downloading', max=456318.0, style=ProgressStyle(descripti…" + ] + }, + "metadata": { + "tags": [] + } + }, + { + "output_type": "stream", + "text": [ + "\n" + ], + "name": "stdout" + } + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "dV-T-8r1V0wf" + }, + "source": [ + "#### Tokenize and cache\n", + "\n", + "With the model and data ready, we can now tokenize and cache the inputs features for our task. This converts the input examples to tokenized features ready to be consumed by the model, and saved them to disk in chunks." + ] + }, + { + "cell_type": "code", + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 168, + "referenced_widgets": [ + "558652d65c9c42e5b2487711ea8c5183", + "b59db489de7a410fb16ac4c64554c2db", + "648bd87cbe344ce786e78d902456be01", + "763685078bfa425a84652935a1d49965", + "5cada33c5612410482ab58422f866621", + "635bed807450413797ec7d1c8a16444d", + "9878a78abe8e41c585f63ed1e77309ea", + "2b0ee8fa0e614926b8ea2befa8d93893", + "6bfcf6f5ebc144e88f55e1501c398ab3", + "0fe088ff545b4642993a0395bc0351af", + "6644d495d3ab4198962cc3e4fd130fe0", + "95e0eeb66af842fc9a5ea7072e665045", + "13039f3a86204fdea19dd335aaa66519", + "effe903b59b24573b1c3e406b986dfac", + "b6aeddb44c3147e2ab912d84759bc139", + "1b51de8cdcbd4c01af4de5865e9c575d" + ] + }, + "id": "22bNWQajO4zm", + "outputId": "a8cf3ed5-c86f-42aa-9a20-c9e97dc51998" + }, + "source": [ + "# Tokenize and cache each task\n", + "task_name = \"semeval\"\n", + "\n", + "tokenize_and_cache.main(tokenize_and_cache.RunConfiguration(\n", + " task_config_path=f\"./tasks/configs/{task_name}_config.json\",\n", + " model_type=\"roberta-base\",\n", + " model_tokenizer_path=\"./models/roberta-base/tokenizer\",\n", + " output_dir=f\"./cache/{task_name}\",\n", + " phases=[\"train\", \"val\"],\n", + "))" + ], + "execution_count": 7, + "outputs": [ + { + "output_type": "stream", + "text": [ + "SemevalTask\n", + " [train]: /content/tasks/data/semeval/train.jsonl\n", + " [val]: /content/tasks/data/semeval/val.jsonl\n" + ], + "name": "stdout" + }, + { + "output_type": "display_data", + "data": { + "application/vnd.jupyter.widget-view+json": { + "model_id": "558652d65c9c42e5b2487711ea8c5183", + "version_minor": 0, + "version_major": 2 + }, + "text/plain": [ + "HBox(children=(FloatProgress(value=0.0, description='Tokenizing', max=1000.0, 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": "6bfcf6f5ebc144e88f55e1501c398ab3", + "version_minor": 0, + "version_major": 2 + }, + "text/plain": [ + "HBox(children=(FloatProgress(value=0.0, description='Tokenizing', style=ProgressStyle(description_width='initi…" + ] + }, + "metadata": { + "tags": [] + } + }, + { + "output_type": "stream", + "text": [ + "\n" + ], + "name": "stdout" + } + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "JJ-mWSQQWJsw" + }, + "source": [ + "We can inspect the first examples of the first chunk of each task." + ] + }, + { + "cell_type": "code", + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "iLk_X0KypUyr", + "outputId": "5779503a-c60e-4d51-e587-caabb11815ff" + }, + "source": [ + "row = caching.ChunkedFilesDataCache(\"./cache/semeval/train\").load_chunk(0)[0][\"data_row\"]\n", + "print(row.input_ids)\n", + "print(row.tokens)\n", + "print(row.tokens[row.spans[0][0]: row.spans[0][1]+1])\n", + "print(row.tokens[row.spans[1][0]: row.spans[1][1]+1])" + ], + "execution_count": 14, + "outputs": [ + { + "output_type": "stream", + "text": [ + "[ 0 133 595 1217 16 14 5 7642 16000 11 5 7018\n", + " 337 233 9 5 9377 1726 30 31141 2413 35995 181 4360\n", + " 6249 7910 775 11 41 1130 10395 931 31 5 786 12\n", + " 37597 196 2853 42168 976 9 5 9377 4 2 1 1\n", + " 1 1 1 1 1 1 1 1 1 1 1 1\n", + " 1 1 1 1 1 1 1 1 1 1 1 1\n", + " 1 1 1 1 1 1 1 1 1 1 1 1\n", + " 1 1 1 1 1 1 1 1 1 1 1 1\n", + " 1 1 1 1 1 1 1 1 1 1 1 1\n", + " 1 1 1 1 1 1 1 1 1 1 1 1\n", + " 1 1 1 1 1 1 1 1]\n", + "['', 'The', 'Ġcurrent', 'Ġview', 'Ġis', 'Ġthat', 'Ġthe', 'Ġchronic', 'Ġinflammation', 'Ġin', 'Ġthe', 'Ġdist', 'al', 'Ġpart', 'Ġof', 'Ġthe', 'Ġstomach', 'Ġcaused', 'Ġby', 'ĠHelic', 'ob', 'acter', 'Ġp', 'yl', 'ori', 'Ġinfection', 'Ġresults', 'Ġin', 'Ġan', 'Ġincreased', 'Ġacid', 'Ġproduction', 'Ġfrom', 'Ġthe', 'Ġnon', '-', 'infect', 'ed', 'Ġupper', 'Ġcorpus', 'Ġregion', 'Ġof', 'Ġthe', 'Ġstomach', '.', '']\n", + "['Ġinflammation']\n", + "['Ġinfection']\n" + ], + "name": "stdout" + } + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "3MBuH19IWOr0" + }, + "source": [ + "#### Writing a run config\n", + "\n", + "Here we are going to write what we call a `jiant_task_container_config`. This configuration file basically defines a lot of the subtleties of our training pipeline, such as what tasks we will train on, do evaluation on, batch size for each task. The new version of `jiant` leans heavily toward explicitly specifying everything, for the purpose of inspectability and leaving minimal surprises for the user, even as the cost of being more verbose.\n", + "\n", + "We use a helper \"Configurator\" to write out a `jiant_task_container_config`, since most of our setup is pretty standard. \n", + "\n", + "**Depending on what GPU your Colab session is assigned to, you may need to lower the train batch size.**" + ] + }, + { + "cell_type": "code", + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "pQYtl7xTKsiP", + "outputId": "00d58dc6-3d0d-40fa-8a3f-d19553803567" + }, + "source": [ + "jiant_run_config = configurator.SimpleAPIMultiTaskConfigurator(\n", + " task_config_base_path=\"./tasks/configs\",\n", + " task_cache_base_path=\"./cache\",\n", + " train_task_name_list=[\"semeval\"],\n", + " val_task_name_list=[\"semeval\"],\n", + " train_batch_size=8,\n", + " eval_batch_size=16,\n", + " epochs=3,\n", + " num_gpus=1,\n", + ").create_config()\n", + "os.makedirs(\"./run_configs/\", exist_ok=True)\n", + "py_io.write_json(jiant_run_config, \"./run_configs/semeval_run_config.json\")\n", + "display.show_json(jiant_run_config)" + ], + "execution_count": 15, + "outputs": [ + { + "output_type": "stream", + "text": [ + "{\n", + " \"task_config_path_dict\": {\n", + " \"semeval\": \"./tasks/configs/semeval_config.json\"\n", + " },\n", + " \"task_cache_config_dict\": {\n", + " \"semeval\": {\n", + " \"train\": \"./cache/semeval/train\",\n", + " \"val\": \"./cache/semeval/val\",\n", + " \"val_labels\": \"./cache/semeval/val_labels\"\n", + " }\n", + " },\n", + " \"sampler_config\": {\n", + " \"sampler_type\": \"ProportionalMultiTaskSampler\"\n", + " },\n", + " \"global_train_config\": {\n", + " \"max_steps\": 375,\n", + " \"warmup_steps\": 37\n", + " },\n", + " \"task_specific_configs_dict\": {\n", + " \"semeval\": {\n", + " \"train_batch_size\": 8,\n", + " \"eval_batch_size\": 16,\n", + " \"gradient_accumulation_steps\": 1,\n", + " \"eval_subset_num\": 500\n", + " }\n", + " },\n", + " \"taskmodels_config\": {\n", + " \"task_to_taskmodel_map\": {\n", + " \"semeval\": \"semeval\"\n", + " },\n", + " \"taskmodel_config_map\": {\n", + " \"semeval\": null\n", + " }\n", + " },\n", + " \"task_run_config\": {\n", + " \"train_task_list\": [\n", + " \"semeval\"\n", + " ],\n", + " \"train_val_task_list\": [\n", + " \"semeval\"\n", + " ],\n", + " \"val_task_list\": [\n", + " \"semeval\"\n", + " ],\n", + " \"test_task_list\": []\n", + " },\n", + " \"metric_aggregator_config\": {\n", + " \"metric_aggregator_type\": \"EqualMetricAggregator\"\n", + " }\n", + "}\n" + ], + "name": "stdout" + } + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "-UF501yoXHBi" + }, + "source": [ + "To briefly go over the major components of the `jiant_task_container_config`:\n", + "\n", + "* `task_config_path_dict`: The paths to the task config files we wrote above.\n", + "* `task_cache_config_dict`: The paths to the task features caches we generated above.\n", + "* `sampler_config`: Determines how to sample from different tasks during training.\n", + "* `global_train_config`: The number of total steps and warmup steps during training.\n", + "* `task_specific_configs_dict`: Task-specific arguments for each task, such as training batch size and gradient accumulation steps.\n", + "* `taskmodels_config`: Task-model specific arguments for each task-model, including what tasks use which model.\n", + "* `metric_aggregator_config`: Determines how to weight/aggregate the metrics across multiple tasks." + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "BBKkvXzdYPqZ" + }, + "source": [ + "#### Start training\n", + "\n", + "Finally, we can start our training run. \n", + "\n", + "Before starting training, the script also prints out the list of parameters in our model." + ] + }, + { + "cell_type": "code", + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 1000, + "referenced_widgets": [ + "f081100984b44e45a77fff620f998508", + "69d9699a4d7147b5bf9ada54c4839488", + "e8e3b6cf03e04df99ac9799dbbe997cf", + "0ca001e7315c41359a48a37579ad7ac6", + "d4f840d6919047c795fbe22cc096ae39", + "db4132b9258440179d76382ed537257c", + "9ae696b3d7bd470787c4de833990a614", + "17a6d908da41486995c53d7436990b8b", + "7b6147ac6008406c932bb5c5fbf9c8ad", + "d41d7ce333404ac8b12feed2031f1cd2", + "ff00a73e3d474420ab697edb5626da1b", + "70693f5e1708442d9377b03600d256c4", + "d5045b7014fa46518bb0378cf52fa76f", + "e23242c190344c098076d1fc8140e6f2", + "e1a1f7ae889e45ad9b825d752c74a38d", + "bc31ec29b5f24d838401db71b345aeed", + "4b138e183eaf406a8fec6a2cc36f067a", + "ab66645a63274e67a823bed7702d5da2", + "b093c8725cf24d37861f2b38837f4bc4", + "62651b48746c4536a6814fefa89c91e6", + "f5d8d08063f340f6b32bf7f2f0fd5821", + "3dbe5ad38b23422481c2e51acdc78b20", + "9a83595e4bb74bc0948be54799248d16", + "27e02234b1764aed9156f565ec454246", + "ad747e2552c5429484dcd3d19c366a96", + "54e47f0d45d24009aa83fbb5d614e98a", + "ab6394febb5b4d48b9d26d9846f0eb87", + "e34035b4fc8348f2ab108b9edc5d0322", + "0bce1deff0d64bf7a96b6307efd4544e", + "91fac974c5eb4f19b7b0cf18e3521d82", + "968570f0cb0a45c7ab5ab76e00936ae3", + "03fb6747a39646e3b7dda6f877ce19fe" + ] + }, + "id": "JdwWPgjQWx6I", + "outputId": "ba7e86d3-76e4-47bc-b61a-188783502323" + }, + "source": [ + "run_args = main_runscript.RunConfiguration(\n", + " jiant_task_container_config_path=\"./run_configs/semeval_run_config.json\",\n", + " output_dir=\"./runs/semeval\",\n", + " model_type=\"roberta-base\",\n", + " model_path=\"./models/roberta-base/model/roberta-base.p\",\n", + " model_config_path=\"./models/roberta-base/model/roberta-base.json\",\n", + " model_tokenizer_path=\"./models/roberta-base/tokenizer\",\n", + " learning_rate=1e-5,\n", + " eval_every_steps=500,\n", + " do_train=True,\n", + " do_val=True,\n", + " do_save=True,\n", + " force_overwrite=True,\n", + ")\n", + "main_runscript.run_loop(run_args)" + ], + "execution_count": 16, + "outputs": [ + { + "output_type": "stream", + "text": [ + " jiant_task_container_config_path: ./run_configs/semeval_run_config.json\n", + " output_dir: ./runs/semeval\n", + " model_type: roberta-base\n", + " model_path: ./models/roberta-base/model/roberta-base.p\n", + " model_config_path: ./models/roberta-base/model/roberta-base.json\n", + " model_tokenizer_path: ./models/roberta-base/tokenizer\n", + " model_load_mode: from_transformers\n", + " do_train: True\n", + " do_val: True\n", + " do_save: True\n", + " do_save_last: False\n", + " do_save_best: False\n", + " write_val_preds: False\n", + " write_test_preds: False\n", + " eval_every_steps: 500\n", + " save_every_steps: 0\n", + " save_checkpoint_every_steps: 0\n", + " no_improvements_for_n_evals: 0\n", + " keep_checkpoint_when_done: False\n", + " force_overwrite: True\n", + " seed: -1\n", + " learning_rate: 1e-05\n", + " adam_epsilon: 1e-08\n", + " max_grad_norm: 1.0\n", + " optimizer_type: adam\n", + " no_cuda: False\n", + " fp16: False\n", + " fp16_opt_level: O1\n", + " local_rank: -1\n", + " server_ip: \n", + " server_port: \n", + "device: cuda n_gpu: 1, distributed training: False, 16-bits training: False\n", + "Using seed: 195818355\n", + "{\n", + " \"jiant_task_container_config_path\": \"./run_configs/semeval_run_config.json\",\n", + " \"output_dir\": \"./runs/semeval\",\n", + " \"model_type\": \"roberta-base\",\n", + " \"model_path\": \"./models/roberta-base/model/roberta-base.p\",\n", + " \"model_config_path\": \"./models/roberta-base/model/roberta-base.json\",\n", + " \"model_tokenizer_path\": \"./models/roberta-base/tokenizer\",\n", + " \"model_load_mode\": \"from_transformers\",\n", + " \"do_train\": true,\n", + " \"do_val\": true,\n", + " \"do_save\": true,\n", + " \"do_save_last\": false,\n", + " \"do_save_best\": false,\n", + " \"write_val_preds\": false,\n", + " \"write_test_preds\": false,\n", + " \"eval_every_steps\": 500,\n", + " \"save_every_steps\": 0,\n", + " \"save_checkpoint_every_steps\": 0,\n", + " \"no_improvements_for_n_evals\": 0,\n", + " \"keep_checkpoint_when_done\": false,\n", + " \"force_overwrite\": true,\n", + " \"seed\": 195818355,\n", + " \"learning_rate\": 1e-05,\n", + " \"adam_epsilon\": 1e-08,\n", + " \"max_grad_norm\": 1.0,\n", + " \"optimizer_type\": \"adam\",\n", + " \"no_cuda\": false,\n", + " \"fp16\": false,\n", + " \"fp16_opt_level\": \"O1\",\n", + " \"local_rank\": -1,\n", + " \"server_ip\": \"\",\n", + " \"server_port\": \"\"\n", + "}\n", + "1\n", + "Creating Tasks:\n", + " semeval (SemevalTask): ./tasks/configs/semeval_config.json\n" + ], + "name": "stdout" + }, + { + "output_type": "stream", + "text": [ + "/content/jiant/jiant/proj/main/components/container_setup.py:78: UserWarning: task semeval from ./tasks/configs/semeval_config.json has conflicting names: semeval/semval. Using semeval\n", + " task_name, task_config_path, task_name, task.name, task_name,\n" + ], + "name": "stderr" + }, + { + "output_type": "stream", + "text": [ + "No optimizer decay for:\n", + " encoder.embeddings.LayerNorm.weight\n", + " encoder.embeddings.LayerNorm.bias\n", + " encoder.encoder.layer.0.attention.self.query.bias\n", + " encoder.encoder.layer.0.attention.self.key.bias\n", + " encoder.encoder.layer.0.attention.self.value.bias\n", + " encoder.encoder.layer.0.attention.output.dense.bias\n", + " encoder.encoder.layer.0.attention.output.LayerNorm.weight\n", + " encoder.encoder.layer.0.attention.output.LayerNorm.bias\n", + " encoder.encoder.layer.0.intermediate.dense.bias\n", + " encoder.encoder.layer.0.output.dense.bias\n", + " encoder.encoder.layer.0.output.LayerNorm.weight\n", + " encoder.encoder.layer.0.output.LayerNorm.bias\n", + " encoder.encoder.layer.1.attention.self.query.bias\n", + " encoder.encoder.layer.1.attention.self.key.bias\n", + " encoder.encoder.layer.1.attention.self.value.bias\n", + " encoder.encoder.layer.1.attention.output.dense.bias\n", + " encoder.encoder.layer.1.attention.output.LayerNorm.weight\n", + " encoder.encoder.layer.1.attention.output.LayerNorm.bias\n", + " encoder.encoder.layer.1.intermediate.dense.bias\n", + " encoder.encoder.layer.1.output.dense.bias\n", + " encoder.encoder.layer.1.output.LayerNorm.weight\n", + " encoder.encoder.layer.1.output.LayerNorm.bias\n", + " encoder.encoder.layer.2.attention.self.query.bias\n", + " encoder.encoder.layer.2.attention.self.key.bias\n", + " encoder.encoder.layer.2.attention.self.value.bias\n", + " encoder.encoder.layer.2.attention.output.dense.bias\n", + " encoder.encoder.layer.2.attention.output.LayerNorm.weight\n", + " encoder.encoder.layer.2.attention.output.LayerNorm.bias\n", + " encoder.encoder.layer.2.intermediate.dense.bias\n", + " encoder.encoder.layer.2.output.dense.bias\n", + " encoder.encoder.layer.2.output.LayerNorm.weight\n", + " encoder.encoder.layer.2.output.LayerNorm.bias\n", + " encoder.encoder.layer.3.attention.self.query.bias\n", + " encoder.encoder.layer.3.attention.self.key.bias\n", + " encoder.encoder.layer.3.attention.self.value.bias\n", + " encoder.encoder.layer.3.attention.output.dense.bias\n", + " encoder.encoder.layer.3.attention.output.LayerNorm.weight\n", + " encoder.encoder.layer.3.attention.output.LayerNorm.bias\n", + " encoder.encoder.layer.3.intermediate.dense.bias\n", + " encoder.encoder.layer.3.output.dense.bias\n", + " encoder.encoder.layer.3.output.LayerNorm.weight\n", + " encoder.encoder.layer.3.output.LayerNorm.bias\n", + " encoder.encoder.layer.4.attention.self.query.bias\n", + " encoder.encoder.layer.4.attention.self.key.bias\n", + " encoder.encoder.layer.4.attention.self.value.bias\n", + " encoder.encoder.layer.4.attention.output.dense.bias\n", + " encoder.encoder.layer.4.attention.output.LayerNorm.weight\n", + " encoder.encoder.layer.4.attention.output.LayerNorm.bias\n", + " encoder.encoder.layer.4.intermediate.dense.bias\n", + " encoder.encoder.layer.4.output.dense.bias\n", + " encoder.encoder.layer.4.output.LayerNorm.weight\n", + " encoder.encoder.layer.4.output.LayerNorm.bias\n", + " encoder.encoder.layer.5.attention.self.query.bias\n", + " encoder.encoder.layer.5.attention.self.key.bias\n", + " encoder.encoder.layer.5.attention.self.value.bias\n", + " encoder.encoder.layer.5.attention.output.dense.bias\n", + " encoder.encoder.layer.5.attention.output.LayerNorm.weight\n", + " encoder.encoder.layer.5.attention.output.LayerNorm.bias\n", + " encoder.encoder.layer.5.intermediate.dense.bias\n", + " encoder.encoder.layer.5.output.dense.bias\n", + " encoder.encoder.layer.5.output.LayerNorm.weight\n", + " encoder.encoder.layer.5.output.LayerNorm.bias\n", + " encoder.encoder.layer.6.attention.self.query.bias\n", + " encoder.encoder.layer.6.attention.self.key.bias\n", + " encoder.encoder.layer.6.attention.self.value.bias\n", + " encoder.encoder.layer.6.attention.output.dense.bias\n", + " encoder.encoder.layer.6.attention.output.LayerNorm.weight\n", + " encoder.encoder.layer.6.attention.output.LayerNorm.bias\n", + " encoder.encoder.layer.6.intermediate.dense.bias\n", + " encoder.encoder.layer.6.output.dense.bias\n", + " encoder.encoder.layer.6.output.LayerNorm.weight\n", + " encoder.encoder.layer.6.output.LayerNorm.bias\n", + " encoder.encoder.layer.7.attention.self.query.bias\n", + " encoder.encoder.layer.7.attention.self.key.bias\n", + " encoder.encoder.layer.7.attention.self.value.bias\n", + " encoder.encoder.layer.7.attention.output.dense.bias\n", + " encoder.encoder.layer.7.attention.output.LayerNorm.weight\n", + " encoder.encoder.layer.7.attention.output.LayerNorm.bias\n", + " encoder.encoder.layer.7.intermediate.dense.bias\n", + " encoder.encoder.layer.7.output.dense.bias\n", + " encoder.encoder.layer.7.output.LayerNorm.weight\n", + " encoder.encoder.layer.7.output.LayerNorm.bias\n", + " encoder.encoder.layer.8.attention.self.query.bias\n", + " encoder.encoder.layer.8.attention.self.key.bias\n", + " encoder.encoder.layer.8.attention.self.value.bias\n", + " encoder.encoder.layer.8.attention.output.dense.bias\n", + " encoder.encoder.layer.8.attention.output.LayerNorm.weight\n", + " encoder.encoder.layer.8.attention.output.LayerNorm.bias\n", + " encoder.encoder.layer.8.intermediate.dense.bias\n", + " encoder.encoder.layer.8.output.dense.bias\n", + " encoder.encoder.layer.8.output.LayerNorm.weight\n", + " encoder.encoder.layer.8.output.LayerNorm.bias\n", + " encoder.encoder.layer.9.attention.self.query.bias\n", + " encoder.encoder.layer.9.attention.self.key.bias\n", + " encoder.encoder.layer.9.attention.self.value.bias\n", + " encoder.encoder.layer.9.attention.output.dense.bias\n", + " encoder.encoder.layer.9.attention.output.LayerNorm.weight\n", + " encoder.encoder.layer.9.attention.output.LayerNorm.bias\n", + " encoder.encoder.layer.9.intermediate.dense.bias\n", + " encoder.encoder.layer.9.output.dense.bias\n", + " encoder.encoder.layer.9.output.LayerNorm.weight\n", + " encoder.encoder.layer.9.output.LayerNorm.bias\n", + " encoder.encoder.layer.10.attention.self.query.bias\n", + " encoder.encoder.layer.10.attention.self.key.bias\n", + " encoder.encoder.layer.10.attention.self.value.bias\n", + " encoder.encoder.layer.10.attention.output.dense.bias\n", + " encoder.encoder.layer.10.attention.output.LayerNorm.weight\n", + " encoder.encoder.layer.10.attention.output.LayerNorm.bias\n", + " encoder.encoder.layer.10.intermediate.dense.bias\n", + " encoder.encoder.layer.10.output.dense.bias\n", + " encoder.encoder.layer.10.output.LayerNorm.weight\n", + " encoder.encoder.layer.10.output.LayerNorm.bias\n", + " encoder.encoder.layer.11.attention.self.query.bias\n", + " encoder.encoder.layer.11.attention.self.key.bias\n", + " encoder.encoder.layer.11.attention.self.value.bias\n", + " encoder.encoder.layer.11.attention.output.dense.bias\n", + " encoder.encoder.layer.11.attention.output.LayerNorm.weight\n", + " encoder.encoder.layer.11.attention.output.LayerNorm.bias\n", + " encoder.encoder.layer.11.intermediate.dense.bias\n", + " encoder.encoder.layer.11.output.dense.bias\n", + " encoder.encoder.layer.11.output.LayerNorm.weight\n", + " encoder.encoder.layer.11.output.LayerNorm.bias\n", + " encoder.pooler.dense.bias\n", + " taskmodels_dict.semeval.span_comparison_head.span_attention_extractor._global_attention._module.bias\n", + " taskmodels_dict.semeval.span_comparison_head.classifier.bias\n", + "Using AdamW\n" + ], + "name": "stdout" + }, + { + "output_type": "display_data", + "data": { + "application/vnd.jupyter.widget-view+json": { + "model_id": "f081100984b44e45a77fff620f998508", + "version_minor": 0, + "version_major": 2 + }, + "text/plain": [ + "HBox(children=(FloatProgress(value=0.0, description='Training', max=375.0, style=ProgressStyle(description_wid…" + ] + }, + "metadata": { + "tags": [] + } + }, + { + "output_type": "stream", + "text": [ + "\n" + ], + "name": "stdout" + }, + { + "output_type": "display_data", + "data": { + "application/vnd.jupyter.widget-view+json": { + "model_id": "7b6147ac6008406c932bb5c5fbf9c8ad", + "version_minor": 0, + "version_major": 2 + }, + "text/plain": [ + "HBox(children=(FloatProgress(value=0.0, description='Eval (semeval, Val)', max=7.0, style=ProgressStyle(descri…" + ] + }, + "metadata": { + "tags": [] + } + }, + { + "output_type": "stream", + "text": [ + "\n" + ], + "name": "stdout" + }, + { + "output_type": "display_data", + "data": { + "application/vnd.jupyter.widget-view+json": { + "model_id": "4b138e183eaf406a8fec6a2cc36f067a", + "version_minor": 0, + "version_major": 2 + }, + "text/plain": [ + "HBox(children=(FloatProgress(value=0.0, description='Eval (semeval, Val)', max=7.0, style=ProgressStyle(descri…" + ] + }, + "metadata": { + "tags": [] + } + }, + { + "output_type": "stream", + "text": [ + "\n", + "Loading Best\n" + ], + "name": "stdout" + }, + { + "output_type": "display_data", + "data": { + "application/vnd.jupyter.widget-view+json": { + "model_id": "ad747e2552c5429484dcd3d19c366a96", + "version_minor": 0, + "version_major": 2 + }, + "text/plain": [ + "HBox(children=(FloatProgress(value=0.0, description='Eval (semeval, Val)', max=7.0, style=ProgressStyle(descri…" + ] + }, + "metadata": { + "tags": [] + } + }, + { + "output_type": "stream", + "text": [ + "\n", + "{\n", + " \"aggregated\": 1.0,\n", + " \"semeval\": {\n", + " \"loss\": 0.007899788208305836,\n", + " \"metrics\": {\n", + " \"major\": 1.0,\n", + " \"minor\": {\n", + " \"acc\": 1.0,\n", + " \"f1_micro\": 1.0,\n", + " \"acc_and_f1_micro\": 1.0\n", + " }\n", + " }\n", + " }\n", + "}\n" + ], + "name": "stdout" + } + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "4SXcuHFIYp6Y" + }, + "source": [ + "Since we're training and evaluating on the same (duplicated) example, we should get perfect performance, but hopefully this notebook should be illustrative of the workflow for edge-probing tasks." + ] + } + ] +} \ No newline at end of file