{ "nbformat": 4, "nbformat_minor": 0, "metadata": { "colab": { "provenance": [], "authorship_tag": "ABX9TyPWA6TPs4SBsVRMd84AemzZ", "include_colab_link": true }, "kernelspec": { "name": "python3", "display_name": "Python 3" }, "language_info": { "name": "python" }, "widgets": { "application/vnd.jupyter.widget-state+json": { "e98d3ff3b65b40e8b41330044c395232": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_9b893dc5ad2e46cfbda6f718cf8128a8", "IPY_MODEL_365e927746d14a3992990fa0d8fd6a0f", "IPY_MODEL_d9f23d76cbfc44a0bf30d90fbddb0485" ], "layout": "IPY_MODEL_4bc8f03e112045fabb3f3ae6be481a5e" } }, "9b893dc5ad2e46cfbda6f718cf8128a8": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_358e2095f97e4f76b2288c057cf8876b", "placeholder": "​", "style": "IPY_MODEL_b17052883dee4e8fb2051b1bf1dbe07d", "value": "config.json: 100%" } }, "365e927746d14a3992990fa0d8fd6a0f": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_1bf4f55b70a54437a2406a6929ef7f46", "max": 1361, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_85f6494f7317403e9c1e37379e4db09b", "value": 1361 } }, "d9f23d76cbfc44a0bf30d90fbddb0485": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_69d5cae02a0b4df492150b8293151380", "placeholder": "​", "style": "IPY_MODEL_33d3e1fa1a264e22a59270f1f914265c", "value": " 1.36k/1.36k [00:00<00:00, 55.3kB/s]" } }, "4bc8f03e112045fabb3f3ae6be481a5e": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "358e2095f97e4f76b2288c057cf8876b": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "b17052883dee4e8fb2051b1bf1dbe07d": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "1bf4f55b70a54437a2406a6929ef7f46": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "85f6494f7317403e9c1e37379e4db09b": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "69d5cae02a0b4df492150b8293151380": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "33d3e1fa1a264e22a59270f1f914265c": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "2640fcd360904eeb807229f4d22dbfa9": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_f3591d6a118246629ac869b56c66a957", "IPY_MODEL_4798326ec81f436d92645d441c508a05", "IPY_MODEL_ed290c11812f49c1b17e333ba34983a0" ], "layout": "IPY_MODEL_b43bc8070c4e4e4f81501496977f526d" } }, "f3591d6a118246629ac869b56c66a957": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_448b15d0127349b0b526e82650aa53a8", "placeholder": "​", "style": "IPY_MODEL_383c0bda66c94c32b689a15df60a47bc", "value": "tokenizer.json: 100%" } }, "4798326ec81f436d92645d441c508a05": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_33590954265a48a0bf3b093367769479", "max": 682152, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_02c5e937f2c14866855f18242edfe04b", "value": 682152 } }, "ed290c11812f49c1b17e333ba34983a0": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_174576b3adc3406e8b96c089c963e036", "placeholder": "​", "style": "IPY_MODEL_a3c028d3b16d4cafa493f56eea1acabf", "value": " 682k/682k [00:00<00:00, 3.63MB/s]" } }, "b43bc8070c4e4e4f81501496977f526d": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "448b15d0127349b0b526e82650aa53a8": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "383c0bda66c94c32b689a15df60a47bc": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "33590954265a48a0bf3b093367769479": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "02c5e937f2c14866855f18242edfe04b": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "174576b3adc3406e8b96c089c963e036": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "a3c028d3b16d4cafa493f56eea1acabf": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "e042bab138d742abb0a3d46cf6eb4d50": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_2af0d76afe4a4c62822664a344915448", "IPY_MODEL_b01320e281054ed1ae082de3701e5796", "IPY_MODEL_7926d75f31af4ac99aef8a26ab77a490" ], "layout": "IPY_MODEL_1eed6ed8836b4ebba473f293856b8f3f" } }, "2af0d76afe4a4c62822664a344915448": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_fef02e8a62d64c089ef74b893f56196b", "placeholder": "​", "style": "IPY_MODEL_fbc03aee82ba45f08131ea811be9e651", "value": "added_tokens.json: 100%" } }, "b01320e281054ed1ae082de3701e5796": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_da50c33359384719ad1ac9cbdc06e92a", "max": 4, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_cfe9a3d2147b43d59cb2fdcfa0e22c3b", "value": 4 } }, "7926d75f31af4ac99aef8a26ab77a490": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_16427a0efa8f47498bb4914b33dfcc89", "placeholder": "​", "style": "IPY_MODEL_0cb76b132007406ebf6d6ef53d6e7a03", "value": " 4.00/4.00 [00:00<00:00, 239B/s]" } }, "1eed6ed8836b4ebba473f293856b8f3f": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "fef02e8a62d64c089ef74b893f56196b": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "fbc03aee82ba45f08131ea811be9e651": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "da50c33359384719ad1ac9cbdc06e92a": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "cfe9a3d2147b43d59cb2fdcfa0e22c3b": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "16427a0efa8f47498bb4914b33dfcc89": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "0cb76b132007406ebf6d6ef53d6e7a03": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "55f830f90cc74393bc0940b10139e5ea": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_6be67f5791bf4694ba7c33cfe379d53b", "IPY_MODEL_faeefa2cc411407a9b9973d2977a8323", "IPY_MODEL_23f8ef13d07d40f59bd51f9ff353d616" ], "layout": "IPY_MODEL_a84736ba5df146d0a5ac51a46d11f407" } }, "6be67f5791bf4694ba7c33cfe379d53b": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_d5ecd83c9c414f2a94e76099376ee043", "placeholder": "​", "style": "IPY_MODEL_9249e0bc9e2b4e11b0de38ea1f3f5a95", "value": "special_tokens_map.json: 100%" } }, "faeefa2cc411407a9b9973d2977a8323": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_663ad4669f3d4ba1b67c38d4310d8c31", "max": 112, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_5cc5896e72dc4bd494a45782fbe5bb73", "value": 112 } }, "23f8ef13d07d40f59bd51f9ff353d616": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_ce52bb8f149b436bab21906c653ab3cd", "placeholder": "​", "style": "IPY_MODEL_e3d2fd5f3a6d49b198fa6d4fea25a62a", "value": " 112/112 [00:00<00:00, 6.86kB/s]" } }, "a84736ba5df146d0a5ac51a46d11f407": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "d5ecd83c9c414f2a94e76099376ee043": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "9249e0bc9e2b4e11b0de38ea1f3f5a95": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "663ad4669f3d4ba1b67c38d4310d8c31": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "5cc5896e72dc4bd494a45782fbe5bb73": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "ce52bb8f149b436bab21906c653ab3cd": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "e3d2fd5f3a6d49b198fa6d4fea25a62a": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "31b6b31860874febb8929d1f14b7350f": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_60c916e5b88940c0aed3a4775fb8e881", "IPY_MODEL_00e10f47acdb417fa95014733c819c00", "IPY_MODEL_74d52b6cc9844c9aa00c027a8485a162" ], "layout": "IPY_MODEL_56e566b98ecd45b6a9ba1d23015c776a" } }, "60c916e5b88940c0aed3a4775fb8e881": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_2b18ca494bb14af9ad207798d12bc6e6", "placeholder": "​", "style": "IPY_MODEL_3752e3e731ae40fb95d6a4c6aec2568e", "value": "model.safetensors: 100%" } }, "00e10f47acdb417fa95014733c819c00": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_e72290250a3b4ac19baef7cdd7115b26", "max": 495468126, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_9c07fd1e879442759ffa2908f1025793", "value": 495468126 } }, "74d52b6cc9844c9aa00c027a8485a162": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_db0337641f894ac1bb4ee6d952169bae", "placeholder": "​", "style": "IPY_MODEL_75d90aed4db8458b8cacb626c43bad22", "value": " 495M/495M [00:06<00:00, 136MB/s]" } }, "56e566b98ecd45b6a9ba1d23015c776a": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "2b18ca494bb14af9ad207798d12bc6e6": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "3752e3e731ae40fb95d6a4c6aec2568e": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "e72290250a3b4ac19baef7cdd7115b26": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "9c07fd1e879442759ffa2908f1025793": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "db0337641f894ac1bb4ee6d952169bae": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "75d90aed4db8458b8cacb626c43bad22": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } } } } }, "cells": [ { "cell_type": "markdown", "metadata": { "id": "view-in-github", "colab_type": "text" }, "source": [ "\"Open" ] }, { "cell_type": "code", "execution_count": 12, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "w40KeByWJt5H", "outputId": "61017485-c151-48ac-860e-bf23d2a3192d" }, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount(\"/content/drive\", force_remount=True).\n" ] } ], "source": [ "from google.colab import drive\n", "drive.mount('/content/drive')" ] }, { "cell_type": "code", "source": [ "diary = pd.read_csv('/content/drive/MyDrive/diary.csv')" ], "metadata": { "id": "xzH-3s9NKG-M" }, "execution_count": 14, "outputs": [] }, { "cell_type": "code", "source": [ "diary.head()" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 380 }, "id": "b53-B2gNKNJ2", "outputId": "e6bb614c-8fd1-4f1d-b479-7ce24b1b006b" }, "execution_count": 21, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ " 일기 \\\n", "0 오늘은 오랜 기간 준비해온 시험을 보러 다녀왔어. 시험 전날부터 긴장과 불안이 가시... \n", "1 오늘은 오랜 기간 준비해온 시험을 보러 다녀왔어. 시험 전날부터 긴장과 불안이 가시... \n", "2 오늘은 오랜 기간 준비해온 시험을 보러 다녀왔어. 시험 전날부터 긴장과 불안이 가시... \n", "3 오늘은 내가 사랑하는 사람과 소중한 시간을 보내러 다녀왔어. 그 동안 서로 바쁘게 ... \n", "4 오늘은 내가 사랑하는 사람과 소중한 시간을 보내러 다녀왔어. 그 동안 서로 바쁘게 ... \n", "\n", " 요약 \\\n", "0 오랜 기간 준비해온 시험을 보러 다녀왔어요. 불안과 긴장 속에서도 최선을 다해 시험... \n", "1 오랜 기간 준비해온 시험을 보러 다녀왔어요. 시험 중에는 최대한 집중하고 최선을 다... \n", "2 오랜 기간 준비한 시험을 보러 다녀왔어요. 시험 중에는 최선을 다해 문제를 해결하려... \n", "3 사랑하는 사람과 함께한 소중한 시간이었어요. 서로의 이야기를 나누고 응원해주며 사랑... \n", "4 사랑하는 사람과 함께한 소중한 시간이었어요. 서로의 이야기를 나누고 사랑을 나눌 수... \n", "\n", " 해시태그 \n", "0 #시험 #노력 #성취감 #안도감 #자부심 \n", "1 #시험 #노력 #집중 #결과기다림 #휴식 \n", "2 #시험 #노력 #문제해결 #결과기다림 #휴식 \n", "3 #사랑하는사람과함께 #소중한시간 #서로의이해 #사랑과애정 #감사함 \n", "4 #사랑하는사람과함께 #소중한시간 #서로의이야기 #배려와사랑 #행복함 " ], "text/html": [ "\n", "
\n", "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
일기요약해시태그
0오늘은 오랜 기간 준비해온 시험을 보러 다녀왔어. 시험 전날부터 긴장과 불안이 가시...오랜 기간 준비해온 시험을 보러 다녀왔어요. 불안과 긴장 속에서도 최선을 다해 시험...#시험 #노력 #성취감 #안도감 #자부심
1오늘은 오랜 기간 준비해온 시험을 보러 다녀왔어. 시험 전날부터 긴장과 불안이 가시...오랜 기간 준비해온 시험을 보러 다녀왔어요. 시험 중에는 최대한 집중하고 최선을 다...#시험 #노력 #집중 #결과기다림 #휴식
2오늘은 오랜 기간 준비해온 시험을 보러 다녀왔어. 시험 전날부터 긴장과 불안이 가시...오랜 기간 준비한 시험을 보러 다녀왔어요. 시험 중에는 최선을 다해 문제를 해결하려...#시험 #노력 #문제해결 #결과기다림 #휴식
3오늘은 내가 사랑하는 사람과 소중한 시간을 보내러 다녀왔어. 그 동안 서로 바쁘게 ...사랑하는 사람과 함께한 소중한 시간이었어요. 서로의 이야기를 나누고 응원해주며 사랑...#사랑하는사람과함께 #소중한시간 #서로의이해 #사랑과애정 #감사함
4오늘은 내가 사랑하는 사람과 소중한 시간을 보내러 다녀왔어. 그 동안 서로 바쁘게 ...사랑하는 사람과 함께한 소중한 시간이었어요. 서로의 이야기를 나누고 사랑을 나눌 수...#사랑하는사람과함께 #소중한시간 #서로의이야기 #배려와사랑 #행복함
\n", "
\n", "
\n", "\n", "
\n", " \n", "\n", " \n", "\n", " \n", "
\n", "\n", "\n", "
\n", " \n", "\n", "\n", "\n", " \n", "
\n", "
\n", "
\n" ] }, "metadata": {}, "execution_count": 21 } ] }, { "cell_type": "markdown", "source": [ "## HashTag Modelling" ], "metadata": { "id": "o3qABNsMLqai" } }, { "cell_type": "code", "source": [ "!pip install datasets transformers==4.28.0" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "yLal2QebLg2T", "outputId": "8970fa47-a16f-4bfd-ef74-8947a89a74c5" }, "execution_count": 23, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Collecting datasets\n", " Downloading datasets-2.15.0-py3-none-any.whl (521 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m521.2/521.2 kB\u001b[0m \u001b[31m6.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hCollecting transformers==4.28.0\n", " Downloading transformers-4.28.0-py3-none-any.whl (7.0 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m7.0/7.0 MB\u001b[0m \u001b[31m25.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hRequirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from transformers==4.28.0) (3.13.1)\n", "Requirement already satisfied: huggingface-hub<1.0,>=0.11.0 in /usr/local/lib/python3.10/dist-packages (from transformers==4.28.0) (0.19.4)\n", "Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from transformers==4.28.0) (1.23.5)\n", "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from transformers==4.28.0) (23.2)\n", "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from transformers==4.28.0) (6.0.1)\n", "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers==4.28.0) (2023.6.3)\n", "Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from transformers==4.28.0) (2.31.0)\n", "Collecting tokenizers!=0.11.3,<0.14,>=0.11.1 (from transformers==4.28.0)\n", " Downloading tokenizers-0.13.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (7.8 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m7.8/7.8 MB\u001b[0m \u001b[31m53.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hRequirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.10/dist-packages (from transformers==4.28.0) (4.66.1)\n", "Requirement already satisfied: pyarrow>=8.0.0 in /usr/local/lib/python3.10/dist-packages (from datasets) (9.0.0)\n", "Collecting pyarrow-hotfix (from datasets)\n", " Downloading pyarrow_hotfix-0.6-py3-none-any.whl (7.9 kB)\n", "Collecting dill<0.3.8,>=0.3.0 (from datasets)\n", " Downloading dill-0.3.7-py3-none-any.whl (115 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m115.3/115.3 kB\u001b[0m \u001b[31m12.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hRequirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (from datasets) (1.5.3)\n", "Requirement already satisfied: xxhash in /usr/local/lib/python3.10/dist-packages (from datasets) (3.4.1)\n", "Collecting multiprocess (from datasets)\n", " Downloading multiprocess-0.70.15-py310-none-any.whl (134 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m134.8/134.8 kB\u001b[0m \u001b[31m13.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hRequirement already satisfied: fsspec[http]<=2023.10.0,>=2023.1.0 in /usr/local/lib/python3.10/dist-packages (from datasets) (2023.6.0)\n", "Requirement already satisfied: aiohttp in /usr/local/lib/python3.10/dist-packages (from datasets) (3.8.6)\n", "Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (23.1.0)\n", "Requirement already satisfied: charset-normalizer<4.0,>=2.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (3.3.2)\n", "Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (6.0.4)\n", "Requirement already satisfied: async-timeout<5.0,>=4.0.0a3 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (4.0.3)\n", "Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (1.9.2)\n", "Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (1.4.0)\n", "Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (1.3.1)\n", "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub<1.0,>=0.11.0->transformers==4.28.0) (4.5.0)\n", "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->transformers==4.28.0) (3.4)\n", "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->transformers==4.28.0) (2.0.7)\n", "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->transformers==4.28.0) (2023.7.22)\n", "Requirement already satisfied: python-dateutil>=2.8.1 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets) (2.8.2)\n", "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets) (2023.3.post1)\n", "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.8.1->pandas->datasets) (1.16.0)\n", "Installing collected packages: tokenizers, pyarrow-hotfix, dill, multiprocess, transformers, datasets\n", " Attempting uninstall: tokenizers\n", " Found existing installation: tokenizers 0.15.0\n", " Uninstalling tokenizers-0.15.0:\n", " Successfully uninstalled tokenizers-0.15.0\n", " Attempting uninstall: transformers\n", " Found existing installation: transformers 4.35.2\n", " Uninstalling transformers-4.35.2:\n", " Successfully uninstalled transformers-4.35.2\n", "Successfully installed datasets-2.15.0 dill-0.3.7 multiprocess-0.70.15 pyarrow-hotfix-0.6 tokenizers-0.13.3 transformers-4.28.0\n" ] } ] }, { "cell_type": "code", "source": [ "from transformers import (\n", " AutoModelForSeq2SeqLM,\n", " AutoTokenizer,\n", " Seq2SeqTrainingArguments,\n", " Seq2SeqTrainer,\n", " DataCollatorForSeq2Seq,\n", ")\n", "from tokenizers import Tokenizer\n", "from typing import Dict, List, Optional\n", "from torch.utils.data import Dataset\n", "\n", "import pandas as pd\n", "import numpy as np\n", "import matplotlib.pyplot as plt\n", "\n", "from IPython.display import display\n", "from typing import Dict" ], "metadata": { "id": "pbB6rTmXLgMo" }, "execution_count": 24, "outputs": [] }, { "cell_type": "code", "source": [ "model_name = \"gogamza/kobart-base-v2\"\n", "tokenizer = AutoTokenizer.from_pretrained(model_name)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 202, "referenced_widgets": [ "e98d3ff3b65b40e8b41330044c395232", "9b893dc5ad2e46cfbda6f718cf8128a8", "365e927746d14a3992990fa0d8fd6a0f", "d9f23d76cbfc44a0bf30d90fbddb0485", "4bc8f03e112045fabb3f3ae6be481a5e", "358e2095f97e4f76b2288c057cf8876b", "b17052883dee4e8fb2051b1bf1dbe07d", "1bf4f55b70a54437a2406a6929ef7f46", "85f6494f7317403e9c1e37379e4db09b", "69d5cae02a0b4df492150b8293151380", "33d3e1fa1a264e22a59270f1f914265c", "2640fcd360904eeb807229f4d22dbfa9", "f3591d6a118246629ac869b56c66a957", "4798326ec81f436d92645d441c508a05", "ed290c11812f49c1b17e333ba34983a0", "b43bc8070c4e4e4f81501496977f526d", "448b15d0127349b0b526e82650aa53a8", "383c0bda66c94c32b689a15df60a47bc", "33590954265a48a0bf3b093367769479", "02c5e937f2c14866855f18242edfe04b", "174576b3adc3406e8b96c089c963e036", "a3c028d3b16d4cafa493f56eea1acabf", "e042bab138d742abb0a3d46cf6eb4d50", "2af0d76afe4a4c62822664a344915448", "b01320e281054ed1ae082de3701e5796", "7926d75f31af4ac99aef8a26ab77a490", "1eed6ed8836b4ebba473f293856b8f3f", "fef02e8a62d64c089ef74b893f56196b", "fbc03aee82ba45f08131ea811be9e651", "da50c33359384719ad1ac9cbdc06e92a", "cfe9a3d2147b43d59cb2fdcfa0e22c3b", "16427a0efa8f47498bb4914b33dfcc89", "0cb76b132007406ebf6d6ef53d6e7a03", "55f830f90cc74393bc0940b10139e5ea", "6be67f5791bf4694ba7c33cfe379d53b", "faeefa2cc411407a9b9973d2977a8323", "23f8ef13d07d40f59bd51f9ff353d616", "a84736ba5df146d0a5ac51a46d11f407", "d5ecd83c9c414f2a94e76099376ee043", "9249e0bc9e2b4e11b0de38ea1f3f5a95", "663ad4669f3d4ba1b67c38d4310d8c31", "5cc5896e72dc4bd494a45782fbe5bb73", "ce52bb8f149b436bab21906c653ab3cd", "e3d2fd5f3a6d49b198fa6d4fea25a62a" ] }, "id": "C8Sr3OsuLtQt", "outputId": "28502094-d228-41f7-bd30-713502ee4cdf" }, "execution_count": 25, "outputs": [ { "output_type": "display_data", "data": { "text/plain": [ "config.json: 0%| | 0.00/1.36k [00:00" ], "text/html": [ "\n", "
\n", " \n", " \n", " [312/312 50:04, Epoch 24/24]\n", "
\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
StepTraining LossValidation Loss

" ] }, "metadata": {} }, { "output_type": "execute_result", "data": { "text/plain": [ "TrainOutput(global_step=312, training_loss=2.0116772773938303, metrics={'train_runtime': 3038.3985, 'train_samples_per_second': 1.532, 'train_steps_per_second': 0.103, 'total_flos': 132796313395200.0, 'train_loss': 2.0116772773938303, 'epoch': 24.0})" ] }, "metadata": {}, "execution_count": 65 } ] }, { "cell_type": "code", "source": [ "trainer.save_model(\"/content/drive/MyDrive/졸업프로젝트/\")" ], "metadata": { "id": "EfcveaeFS3qA" }, "execution_count": 66, "outputs": [] }, { "cell_type": "code", "source": [ "evaluation_results = trainer.evaluate(eval_dataset=test_dataset)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 94 }, "id": "MJlqQKs6TW2A", "outputId": "5e0b0c4b-773f-4d30-b376-b35b7975b961" }, "execution_count": 97, "outputs": [ { "output_type": "stream", "name": "stderr", "text": [ "/usr/local/lib/python3.10/dist-packages/transformers/tokenization_utils_base.py:3596: UserWarning: `as_target_tokenizer` is deprecated and will be removed in v5 of Transformers. You can tokenize your labels by using the argument `text_target` of the regular `__call__` method (either in the same call as your input texts if you use the same keyword arguments, or in a separate call.\n", " warnings.warn(\n" ] }, { "output_type": "display_data", "data": { "text/plain": [ "" ], "text/html": [ "\n", "

\n", " \n", " \n", " [2/2 00:02]\n", "
\n", " " ] }, "metadata": {} } ] }, { "cell_type": "code", "source": [ "evaluation_results" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "x59DTz83TgmE", "outputId": "bb19ecc7-ed6f-46aa-af0d-35176872ed2e" }, "execution_count": 99, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "{'eval_loss': 1.5491961240768433,\n", " 'eval_runtime': 7.4702,\n", " 'eval_samples_per_second': 2.945,\n", " 'eval_steps_per_second': 0.268,\n", " 'epoch': 24.0}" ] }, "metadata": {}, "execution_count": 99 } ] }, { "cell_type": "code", "source": [ "loss = evaluation_results[\"eval_loss\"]\n", "print(\"평가 손실:\", loss)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "99Igisp0TW4g", "outputId": "5ac24f41-42b7-4a9a-ef05-ba5aa6a0eb30" }, "execution_count": 98, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "평가 손실: 1.5491961240768433\n" ] } ] }, { "cell_type": "code", "source": [ "# 테스트할 문장\n", "test_sentence = \"명절을 맞아 고향에 돌아와 가족과 함께 보낸 특별하고 따뜻한 하루였다. 가족의 사랑과 고향의 소중함을 깨달았다.\"\n", "\n", "# 입력 문장을 토큰화하여 인코딩\n", "input_ids = tokenizer.encode(test_sentence, return_tensors=\"pt\")\n", "\n", "# 모델에 입력 전달하여 디코딩\n", "output = model.generate(input_ids)\n", "\n", "# 디코딩된 출력을 토크나이저를 사용하여 텍스트로 변환\n", "decoded_output = tokenizer.decode(output[0], skip_special_tokens=True)\n", "\n", "# 결과 출력\n", "print(\"입력 문장:\", test_sentence)\n", "print(\"모델 출력:\", decoded_output)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "wTIL89OWfFRN", "outputId": "ba6822cb-c2cc-4ec6-aeae-7e8a4514afdd" }, "execution_count": 82, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "입력 문장: 명절을 맞아 고향에 돌아와 가족과 함께 보낸 특별하고 따뜻한 하루였다. 가족의 사랑과 고향의 소중함을 깨달았다.\n", "모델 출력: #명절 #돌아와 가족과함께 #특별한 하루 #가족과함께 #행복\n" ] } ] }, { "cell_type": "code", "source": [ "def make_tag(text):\n", " # 입력 문장을 토큰화하여 인코딩\n", " input_ids = tokenizer.encode(text, return_tensors=\"pt\")\n", "\n", " # 모델에 입력 전달하여 디코딩\n", " output = model.generate(input_ids)\n", "\n", " # 디코딩된 출력을 토크나이저를 사용하여 텍스트로 변환\n", " decoded_output = tokenizer.decode(output[0], skip_special_tokens=True)\n", "\n", " # 결과 출력\n", " print(\"입력 문장:\", text)\n", " print(\"모델 출력:\", decoded_output)" ], "metadata": { "id": "uBG0WzY5jMTL" }, "execution_count": 93, "outputs": [] }, { "cell_type": "code", "source": [ "make_tag(diary.iloc[-2,1])" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "q44lI3qTseeI", "outputId": "f986aee4-fbb6-4d81-b834-10e09a16da38" }, "execution_count": 94, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "입력 문장: 반려동물과 함께 특별한 일상을 기록하며 즐거움과 행복을 느낀 특별한 경험을 한 날이었어.\n", "모델 출력: #강아지 #즐거움과행복 #충실한친구 #사랑스러운모습 #\n" ] } ] }, { "cell_type": "code", "source": [ "make_tag(diary.iloc[-10,1])" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "P22Eri1Nsh_L", "outputId": "afbfc1e5-0abd-4668-87f3-b46d85588ac6" }, "execution_count": 95, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "입력 문장: 취업 준비를 하며 부족함과 노력을 돌아보고 성장의 기회를 찾은 특별한 경험을 한 날이었어.\n", "모델 출력: #취준생 #취업준비 #부족함과노력 #성장의기회 #\n" ] } ] }, { "cell_type": "code", "source": [ "make_tag(diary.iloc[-45,1])" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "9shx2Ig2TP2X", "outputId": "f54968f0-2fce-49ce-ece8-f837dd555765" }, "execution_count": 103, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "입력 문장: 요가를 시작해서 몸과 마음이 편안해지고 건강을 유지하고 있어요.\n", "모델 출력: #요가 #건강 #편안함 #유연성 #숨쉬기 #\n" ] } ] } ] }