diff --git "a/training_script.ipynb" "b/training_script.ipynb" new file mode 100644--- /dev/null +++ "b/training_script.ipynb" @@ -0,0 +1,3224 @@ +{ + "nbformat": 4, + "nbformat_minor": 0, + "metadata": { + "colab": { + "provenance": [], + "gpuType": "T4" + }, + "kernelspec": { + "name": "python3", + "display_name": "Python 3" + }, + "language_info": { + "name": "python" + }, + "accelerator": "GPU", + "widgets": { + "application/vnd.jupyter.widget-state+json": { + "0459621153dd4c9bb5b5dbb67eb67fdd": { + "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_92b2f88442e944278e01ebcf9d8a7d2a", + "IPY_MODEL_3d3d36743d1346e9adcfeb86f7a75fb4", + "IPY_MODEL_821a9faf4d8543a08637668655e90dfa" + ], + "layout": "IPY_MODEL_4722e3dcee964f7f8cf2185dc85077a8" + } + }, + "92b2f88442e944278e01ebcf9d8a7d2a": { + "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_229b1aab70a24285bbd4480f47e7a043", + "placeholder": "​", + "style": "IPY_MODEL_e2450a9986664e9f9e73f4fd2e3060a9", + "value": "Downloading config.json: 100%" + } + }, + "3d3d36743d1346e9adcfeb86f7a75fb4": { + "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_6071bbafcdab4e2983b1b4de3b871447", + "max": 2036, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_ab91e2077e834725b11190526fed19ed", + "value": 2036 + } + }, + "821a9faf4d8543a08637668655e90dfa": { + "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_fd9727afdc484dfa85684e52de2a482c", + "placeholder": "​", + "style": "IPY_MODEL_03dbd16046e14df1b42a43eeb7f55073", + "value": " 2.04k/2.04k [00:00<00:00, 42.4kB/s]" + } + }, + "4722e3dcee964f7f8cf2185dc85077a8": { + "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 + } + }, + "229b1aab70a24285bbd4480f47e7a043": { + "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 + } + }, + "e2450a9986664e9f9e73f4fd2e3060a9": { + "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": "" + } + }, + "6071bbafcdab4e2983b1b4de3b871447": { + "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 + } + }, + "ab91e2077e834725b11190526fed19ed": { + "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": "" + } + }, + "fd9727afdc484dfa85684e52de2a482c": { + "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 + } + }, + "03dbd16046e14df1b42a43eeb7f55073": { + "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": "" + } + }, + "40a3bc724702467f8ab2c78ce56769e2": { + "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_3079574cdd0a4a3899d26bce4011cb4e", + "IPY_MODEL_9767d884907e422ab303bd2d09a408eb", + "IPY_MODEL_9d37aa8b388a4fdaaebaa445427f651e" + ], + "layout": "IPY_MODEL_6435ec23688e4e7f83a6f4e48c9dc400" + } + }, + "3079574cdd0a4a3899d26bce4011cb4e": { + "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_ddf75c9845894eb588af9c6c0c492288", + "placeholder": "​", + "style": "IPY_MODEL_36846a12832f43aaaeaaa1401bc1c7cc", + "value": "Downloading model.safetensors: 100%" + } + }, + "9767d884907e422ab303bd2d09a408eb": { + "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_956c489f47234421a6f1914bd6d3f860", + "max": 145229176, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_0e3b20a61dd84175be38102385fb31ea", + "value": 145229176 + } + }, + "9d37aa8b388a4fdaaebaa445427f651e": { + "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_cc7e6860dd9e4617ab9eb5c36eeec57d", + "placeholder": "​", + "style": "IPY_MODEL_5b4fd5dfba5e45b6bddb7c3980da033e", + "value": " 145M/145M [00:06<00:00, 23.7MB/s]" + } + }, + "6435ec23688e4e7f83a6f4e48c9dc400": { + "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 + } + }, + "ddf75c9845894eb588af9c6c0c492288": { + "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 + } + }, + "36846a12832f43aaaeaaa1401bc1c7cc": { + "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": "" + } + }, + "956c489f47234421a6f1914bd6d3f860": { + "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 + } + }, + "0e3b20a61dd84175be38102385fb31ea": { + "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": "" + } + }, + "cc7e6860dd9e4617ab9eb5c36eeec57d": { + "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 + } + }, + "5b4fd5dfba5e45b6bddb7c3980da033e": { + "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": "" + } + }, + "07f416522f32421ba04e23bddf4498d3": { + "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_5a1102727f8242fcb6fb9da4c2e8caf5", + "IPY_MODEL_2953f35810f84600917171810d614177", + "IPY_MODEL_743d02cf83f440cabe97b20bfcb80212" + ], + "layout": "IPY_MODEL_97f67a7cccba47e8a8afaee84facc035" + } + }, + "5a1102727f8242fcb6fb9da4c2e8caf5": { + "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_2b95c5e4ea874bf2aa5b63c90357e44f", + "placeholder": "​", + "style": "IPY_MODEL_58493a7b09db41c489da6640df4b43dd", + "value": "Downloading tokenizer_config.json: 100%" + } + }, + "2953f35810f84600917171810d614177": { + "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_5519ee296bee4407b876385b0ede4044", + "max": 672, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_f4bc881f3a404c729679d378bda3868b", + "value": 672 + } + }, + "743d02cf83f440cabe97b20bfcb80212": { + "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_86ee1a7aeead40c9b658bcf240f0900a", + "placeholder": "​", + "style": "IPY_MODEL_a6cd8b9801224592b52bbe1f9277f409", + "value": " 672/672 [00:00<00:00, 42.2kB/s]" + } + }, + "97f67a7cccba47e8a8afaee84facc035": { + "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 + } + }, + "2b95c5e4ea874bf2aa5b63c90357e44f": { + "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 + } + }, + "58493a7b09db41c489da6640df4b43dd": { + "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": "" + } + }, + "5519ee296bee4407b876385b0ede4044": { + "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 + } + }, + "f4bc881f3a404c729679d378bda3868b": { + "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": "" + } + }, + "86ee1a7aeead40c9b658bcf240f0900a": { + "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 + } + }, + "a6cd8b9801224592b52bbe1f9277f409": { + "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": "" + } + }, + "3298b9d7218b4b0c855f08317c5f1a37": { + "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_d5cd31cae11a403893b869b4d83a6fb5", + "IPY_MODEL_769ebebcde1a4a8096c6489be076abaf", + "IPY_MODEL_df9faedf82394537abcef03c00c299ca" + ], + "layout": "IPY_MODEL_bf8263f105194277b784bdcfe9348bff" + } + }, + "d5cd31cae11a403893b869b4d83a6fb5": { + "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_6ee738bb43684db1be624712f6fc5f8f", + "placeholder": "​", + "style": "IPY_MODEL_85f7d9cbe90444b091584d217e7cf896", + "value": "Downloading vocab.json: 100%" + } + }, + "769ebebcde1a4a8096c6489be076abaf": { + "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_54437e3f4abb4d1196e779aecd81473f", + "max": 422, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_600c7ef145d14d1691ade8f80044782f", + "value": 422 + } + }, + "df9faedf82394537abcef03c00c299ca": { + "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_03defb6b43f046ee91195eab47aca2a6", + "placeholder": "​", + "style": "IPY_MODEL_bca6940077eb464dac62506b0c07b165", + "value": " 422/422 [00:00<00:00, 28.4kB/s]" + } + }, + "bf8263f105194277b784bdcfe9348bff": { + "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 + } + }, + "6ee738bb43684db1be624712f6fc5f8f": { + "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 + } + }, + "85f7d9cbe90444b091584d217e7cf896": { + "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": "" + } + }, + "54437e3f4abb4d1196e779aecd81473f": { + "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 + } + }, + "600c7ef145d14d1691ade8f80044782f": { + "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": "" + } + }, + "03defb6b43f046ee91195eab47aca2a6": { + "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 + } + }, + "bca6940077eb464dac62506b0c07b165": { + "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": "" + } + }, + "fbaf8fe87deb472484fd6203d345c0d0": { + "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_7407ba67b5854c929d42a9a5f0f6ab34", + "IPY_MODEL_cc4b0623b43741afa7f8ffcf774a6321", + "IPY_MODEL_739a85881ea641ef8e636e4758852176" + ], + "layout": "IPY_MODEL_629c47e8500f45b58887a87dd018b950" + } + }, + "7407ba67b5854c929d42a9a5f0f6ab34": { + "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_ca454ba2b768440bb6496dcf0b833a47", + "placeholder": "​", + "style": "IPY_MODEL_0d296c0876024caca80befb264394422", + "value": "Downloading added_tokens.json: 100%" + } + }, + "cc4b0623b43741afa7f8ffcf774a6321": { + "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_49e51f8f13144b7c897c83add6a2765d", + "max": 18, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_d90c73a1cc894ef8905bb59fcb4f4fd8", + "value": 18 + } + }, + "739a85881ea641ef8e636e4758852176": { + "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_dbdc0e89f0554fd286e25cf53c2aafdc", + "placeholder": "​", + "style": "IPY_MODEL_0f29167f9f80431cae660dc790d189a7", + "value": " 18.0/18.0 [00:00<00:00, 963B/s]" + } + }, + "629c47e8500f45b58887a87dd018b950": { + "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 + } + }, + "ca454ba2b768440bb6496dcf0b833a47": { + "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 + } + }, + "0d296c0876024caca80befb264394422": { + "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": "" + } + }, + "49e51f8f13144b7c897c83add6a2765d": { + "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 + } + }, + "d90c73a1cc894ef8905bb59fcb4f4fd8": { + "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": "" + } + }, + "dbdc0e89f0554fd286e25cf53c2aafdc": { + "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 + } + }, + "0f29167f9f80431cae660dc790d189a7": { + "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": "" + } + }, + "f2df09555bba4131bdddca6d8df251de": { + "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_8c19f3d4505244309cf32c171b9989ac", + "IPY_MODEL_c535ce84edb7404eacf299d1c1d68e85", + "IPY_MODEL_5cff10d745a7459a91f93ca600d856c9" + ], + "layout": "IPY_MODEL_4bcbfde596524b12bfd0decf8262f256" + } + }, + "8c19f3d4505244309cf32c171b9989ac": { + "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_4f527d0641d9424f86f5e09e7b2a055a", + "placeholder": "​", + "style": "IPY_MODEL_8a953c76dfdf49f0b42efd9c95baa9ad", + "value": "Downloading (…)cial_tokens_map.json: 100%" + } + }, + "c535ce84edb7404eacf299d1c1d68e85": { + "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_20c441186d0042f89067974330da0e6a", + "max": 276, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_0f1a83d1163d4430b27a10718164f819", + "value": 276 + } + }, + "5cff10d745a7459a91f93ca600d856c9": { + "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_10322be4f8a04fe7b242a9f76feb1885", + "placeholder": "​", + "style": "IPY_MODEL_9c63b360b27f438abed74630301e76c9", + "value": " 276/276 [00:00<00:00, 21.6kB/s]" + } + }, + "4bcbfde596524b12bfd0decf8262f256": { + "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 + } + }, + "4f527d0641d9424f86f5e09e7b2a055a": { + "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 + } + }, + "8a953c76dfdf49f0b42efd9c95baa9ad": { + "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": "" + } + }, + "20c441186d0042f89067974330da0e6a": { + "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 + } + }, + "0f1a83d1163d4430b27a10718164f819": { + "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": "" + } + }, + "10322be4f8a04fe7b242a9f76feb1885": { + "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 + } + }, + "9c63b360b27f438abed74630301e76c9": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + } + } + } + }, + "cells": [ + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "t-Nj-LTqmhc3", + "colab": { + "base_uri": "https://localhost:8080/" + }, + "outputId": "c8027759-0e64-45c4-f49f-6e55a92adca3" + }, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + " Attempting uninstall: huggingface-hub\n", + " Found existing installation: huggingface-hub 0.20.3\n", + " Uninstalling huggingface-hub-0.20.3:\n", + " Successfully uninstalled huggingface-hub-0.20.3\n", + "Successfully installed accelerate-0.30.1 datasets-2.19.1 dill-0.3.8 docker-pycreds-0.4.0 gitdb-4.0.11 gitpython-3.1.43 huggingface-hub-0.23.0 multiprocess-0.70.16 nvidia-cublas-cu12-12.1.3.1 nvidia-cuda-cupti-cu12-12.1.105 nvidia-cuda-nvrtc-cu12-12.1.105 nvidia-cuda-runtime-cu12-12.1.105 nvidia-cudnn-cu12-8.9.2.26 nvidia-cufft-cu12-11.0.2.54 nvidia-curand-cu12-10.3.2.106 nvidia-cusolver-cu12-11.4.5.107 nvidia-cusparse-cu12-12.1.0.106 nvidia-nccl-cu12-2.19.3 nvidia-nvjitlink-cu12-12.4.127 nvidia-nvtx-cu12-12.1.105 sentry-sdk-2.1.1 setproctitle-1.3.3 smmap-5.0.1 wandb-0.17.0 xxhash-3.4.1\n" + ] + } + ], + "source": [ + "!git clone https://github.com/ylacombe/finetune-hf-vits.git\n", + "%cd finetune-hf-vits\n", + "%pip install -r requirements.txt" + ] + }, + { + "cell_type": "code", + "source": [ + "!pip uninstall -y transformers datasets accelerate # remove the ones installed when you run pip install -r requirements.txt\n", + "%pip install transformers==4.35.1 datasets[audio]==2.14.7 accelerate==0.24.1" + ], + "metadata": { + "id": "CG6syq3umrR_" + }, + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "!git config --global credential.helper store\n", + "!huggingface-cli login" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "QZMV9rptms06", + "outputId": "f87e3a0c-fc06-4b62-ce62-0ff1d1dd3d14" + }, + "execution_count": null, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "\n", + " _| _| _| _| _|_|_| _|_|_| _|_|_| _| _| _|_|_| _|_|_|_| _|_| _|_|_| _|_|_|_|\n", + " _| _| _| _| _| _| _| _|_| _| _| _| _| _| _| _|\n", + " _|_|_|_| _| _| _| _|_| _| _|_| _| _| _| _| _| _|_| _|_|_| _|_|_|_| _| _|_|_|\n", + " _| _| _| _| _| _| _| _| _| _| _|_| _| _| _| _| _| _| _|\n", + " _| _| _|_| _|_|_| _|_|_| _|_|_| _| _| _|_|_| _| _| _| _|_|_| _|_|_|_|\n", + " \n", + " To login, `huggingface_hub` requires a token generated from https://huggingface.co/settings/tokens .\n", + "Token: \n", + "Add token as git credential? (Y/n) y\n", + "Token is valid (permission: write).\n", + "Your token has been saved in your configured git credential helpers (store).\n", + "Your token has been saved to /root/.cache/huggingface/token\n", + "Login successful\n" + ] + } + ] + }, + { + "cell_type": "code", + "source": [ + "%cd monotonic_align\n", + "%mkdir monotonic_align\n", + "!python setup.py build_ext --inplace\n", + "%cd .." + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "YKIastLHmuAx", + "outputId": "f4d2bcbb-da30-4c67-a068-38d1bb4697a0" + }, + "execution_count": null, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "/content/finetune-hf-vits/monotonic_align\n", + "Compiling core.pyx because it changed.\n", + "[1/1] Cythonizing core.pyx\n", + "/usr/local/lib/python3.10/dist-packages/Cython/Compiler/Main.py:381: FutureWarning: Cython directive 'language_level' not set, using '3str' for now (Py3). This has changed from earlier releases! File: /content/finetune-hf-vits/monotonic_align/core.pyx\n", + " tree = Parsing.p_module(s, pxd, full_module_name)\n", + "performance hint: core.pyx:7:5: Exception check on 'maximum_path_each' will always require the GIL to be acquired.\n", + "Possible solutions:\n", + "\t1. Declare 'maximum_path_each' as 'noexcept' if you control the definition and you're sure you don't want the function to raise exceptions.\n", + "\t2. Use an 'int' return type on 'maximum_path_each' to allow an error code to be returned.\n", + "performance hint: core.pyx:38:6: Exception check on 'maximum_path_c' will always require the GIL to be acquired.\n", + "Possible solutions:\n", + "\t1. Declare 'maximum_path_c' as 'noexcept' if you control the definition and you're sure you don't want the function to raise exceptions.\n", + "\t2. Use an 'int' return type on 'maximum_path_c' to allow an error code to be returned.\n", + "performance hint: core.pyx:42:21: Exception check after calling 'maximum_path_each' will always require the GIL to be acquired.\n", + "Possible solutions:\n", + "\t1. Declare 'maximum_path_each' as 'noexcept' if you control the definition and you're sure you don't want the function to raise exceptions.\n", + "\t2. Use an 'int' return type on 'maximum_path_each' to allow an error code to be returned.\n", + "/content/finetune-hf-vits\n" + ] + } + ] + }, + { + "cell_type": "code", + "source": [ + "# !python convert_original_discriminator_checkpoint.py --language_code che --pytorch_dump_folder_path model_che --push_to_hub mms-tts-kbd-discriminator" + ], + "metadata": { + "id": "wvs_R9BqvBOS" + }, + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "!accelerate launch run_vits_finetuning.py ../config.json" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "nGs98HbEm5i3", + "outputId": "93e189e4-dcc1-426d-d7d0-e86409f44e96" + }, + "execution_count": null, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "/usr/local/lib/python3.10/dist-packages/transformers/utils/generic.py:441: UserWarning: torch.utils._pytree._register_pytree_node is deprecated. Please use torch.utils._pytree.register_pytree_node instead.\n", + " _torch_pytree._register_pytree_node(\n", + "/usr/local/lib/python3.10/dist-packages/transformers/utils/generic.py:309: UserWarning: torch.utils._pytree._register_pytree_node is deprecated. Please use torch.utils._pytree.register_pytree_node instead.\n", + " _torch_pytree._register_pytree_node(\n", + "The following values were not passed to `accelerate launch` and had defaults used instead:\n", + "\t`--num_processes` was set to a value of `1`\n", + "\t`--num_machines` was set to a value of `1`\n", + "\t`--mixed_precision` was set to a value of `'no'`\n", + "\t`--dynamo_backend` was set to a value of `'no'`\n", + "To avoid this warning pass in values for each of the problematic parameters or run `accelerate config`.\n", + "/usr/local/lib/python3.10/dist-packages/transformers/utils/generic.py:441: UserWarning: torch.utils._pytree._register_pytree_node is deprecated. Please use torch.utils._pytree.register_pytree_node instead.\n", + " _torch_pytree._register_pytree_node(\n", + "/usr/local/lib/python3.10/dist-packages/transformers/utils/generic.py:309: UserWarning: torch.utils._pytree._register_pytree_node is deprecated. Please use torch.utils._pytree.register_pytree_node instead.\n", + " _torch_pytree._register_pytree_node(\n", + "/usr/local/lib/python3.10/dist-packages/transformers/utils/generic.py:309: UserWarning: torch.utils._pytree._register_pytree_node is deprecated. Please use torch.utils._pytree.register_pytree_node instead.\n", + " _torch_pytree._register_pytree_node(\n", + "05/13/2024 00:06:11 - WARNING - __main__ - Process rank: 0, device: cuda:0, n_gpu: 1distributed training: False, 16-bits training: True\n", + "05/13/2024 00:06:11 - INFO - __main__ - Training/evaluation parameters VITSTrainingArguments(\n", + "_n_gpu=1,\n", + "adafactor=False,\n", + "adam_beta1=0.8,\n", + "adam_beta2=0.99,\n", + "adam_epsilon=1e-08,\n", + "auto_find_batch_size=False,\n", + "bf16=False,\n", + "bf16_full_eval=False,\n", + "data_seed=None,\n", + "dataloader_drop_last=False,\n", + "dataloader_num_workers=0,\n", + "dataloader_pin_memory=True,\n", + "ddp_backend=None,\n", + "ddp_broadcast_buffers=None,\n", + "ddp_bucket_cap_mb=None,\n", + "ddp_find_unused_parameters=None,\n", + "ddp_timeout=1800,\n", + "debug=[],\n", + "deepspeed=None,\n", + "disable_tqdm=False,\n", + "dispatch_batches=None,\n", + "do_eval=True,\n", + "do_predict=False,\n", + "do_step_schedule_per_epoch=True,\n", + "do_train=True,\n", + "eval_accumulation_steps=None,\n", + "eval_delay=0,\n", + "eval_steps=100,\n", + "evaluation_strategy=no,\n", + "fp16=True,\n", + "fp16_backend=auto,\n", + "fp16_full_eval=False,\n", + "fp16_opt_level=O1,\n", + "fsdp=[],\n", + "fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_grad_ckpt': False},\n", + "fsdp_min_num_params=0,\n", + "fsdp_transformer_layer_cls_to_wrap=None,\n", + "full_determinism=False,\n", + "gradient_accumulation_steps=1,\n", + "gradient_checkpointing=False,\n", + "gradient_checkpointing_kwargs=None,\n", + "greater_is_better=None,\n", + "group_by_length=False,\n", + "half_precision_backend=auto,\n", + "hub_always_push=False,\n", + "hub_model_id=mms_finetune_kbd_murat,\n", + "hub_private_repo=False,\n", + "hub_strategy=every_save,\n", + "hub_token=,\n", + "ignore_data_skip=False,\n", + "include_inputs_for_metrics=False,\n", + "include_tokens_per_second=False,\n", + "jit_mode_eval=False,\n", + "label_names=None,\n", + "label_smoothing_factor=0.0,\n", + "learning_rate=0.0001,\n", + "length_column_name=length,\n", + "load_best_model_at_end=False,\n", + "local_rank=0,\n", + "log_level=passive,\n", + "log_level_replica=warning,\n", + "log_on_each_node=True,\n", + "logging_dir=./tmp/vits_kbd_finetuned_che_model/runs/May13_00-06-10_db5dbab3f05c,\n", + "logging_first_step=False,\n", + "logging_nan_inf_filter=True,\n", + "logging_steps=500,\n", + "logging_strategy=steps,\n", + "lr_decay=0.999875,\n", + "lr_scheduler_type=linear,\n", + "max_grad_norm=1.0,\n", + "max_steps=100,\n", + "metric_for_best_model=None,\n", + "mp_parameters=,\n", + "neftune_noise_alpha=None,\n", + "no_cuda=False,\n", + "num_train_epochs=3.0,\n", + "optim=adamw_torch,\n", + "optim_args=None,\n", + "output_dir=./tmp/vits_kbd_finetuned_che_model,\n", + "overwrite_output_dir=False,\n", + "past_index=-1,\n", + "per_device_eval_batch_size=16,\n", + "per_device_train_batch_size=16,\n", + "prediction_loss_only=False,\n", + "push_to_hub=True,\n", + "push_to_hub_model_id=None,\n", + "push_to_hub_organization=None,\n", + "push_to_hub_token=,\n", + "ray_scope=last,\n", + "remove_unused_columns=True,\n", + "report_to=['tensorboard', 'wandb'],\n", + "resume_from_checkpoint=None,\n", + "run_name=./tmp/vits_kbd_finetuned_che_model,\n", + "save_on_each_node=False,\n", + "save_safetensors=True,\n", + "save_steps=500,\n", + "save_strategy=steps,\n", + "save_total_limit=None,\n", + "seed=456,\n", + "skip_memory_metrics=True,\n", + "split_batches=False,\n", + "tf32=None,\n", + "torch_compile=False,\n", + "torch_compile_backend=None,\n", + "torch_compile_mode=None,\n", + "torchdynamo=None,\n", + "tpu_metrics_debug=False,\n", + "tpu_num_cores=None,\n", + "use_cpu=False,\n", + "use_ipex=False,\n", + "use_legacy_prediction_loop=False,\n", + "use_mps_device=False,\n", + "warmup_ratio=0.01,\n", + "warmup_steps=0,\n", + "weight_decay=0.0,\n", + "weight_disc=3,\n", + "weight_duration=1,\n", + "weight_fmaps=1,\n", + "weight_gen=1,\n", + "weight_kl=1.5,\n", + "weight_mel=35,\n", + ")\n", + "05/13/2024 00:06:11 - INFO - __main__ - Training/evaluation parameters VITSTrainingArguments(\n", + "_n_gpu=1,\n", + "adafactor=False,\n", + "adam_beta1=0.8,\n", + "adam_beta2=0.99,\n", + "adam_epsilon=1e-08,\n", + "auto_find_batch_size=False,\n", + "bf16=False,\n", + "bf16_full_eval=False,\n", + "data_seed=None,\n", + "dataloader_drop_last=False,\n", + "dataloader_num_workers=0,\n", + "dataloader_pin_memory=True,\n", + "ddp_backend=None,\n", + "ddp_broadcast_buffers=None,\n", + "ddp_bucket_cap_mb=None,\n", + "ddp_find_unused_parameters=None,\n", + "ddp_timeout=1800,\n", + "debug=[],\n", + "deepspeed=None,\n", + "disable_tqdm=False,\n", + "dispatch_batches=None,\n", + "do_eval=True,\n", + "do_predict=False,\n", + "do_step_schedule_per_epoch=True,\n", + "do_train=True,\n", + "eval_accumulation_steps=None,\n", + "eval_delay=0,\n", + "eval_steps=100,\n", + "evaluation_strategy=no,\n", + "fp16=True,\n", + "fp16_backend=auto,\n", + "fp16_full_eval=False,\n", + "fp16_opt_level=O1,\n", + "fsdp=[],\n", + "fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_grad_ckpt': False},\n", + "fsdp_min_num_params=0,\n", + "fsdp_transformer_layer_cls_to_wrap=None,\n", + "full_determinism=False,\n", + "gradient_accumulation_steps=1,\n", + "gradient_checkpointing=False,\n", + "gradient_checkpointing_kwargs=None,\n", + "greater_is_better=None,\n", + "group_by_length=False,\n", + "half_precision_backend=auto,\n", + "hub_always_push=False,\n", + "hub_model_id=mms_finetune_kbd_murat,\n", + "hub_private_repo=False,\n", + "hub_strategy=every_save,\n", + "hub_token=,\n", + "ignore_data_skip=False,\n", + "include_inputs_for_metrics=False,\n", + "include_tokens_per_second=False,\n", + "jit_mode_eval=False,\n", + "label_names=None,\n", + "label_smoothing_factor=0.0,\n", + "learning_rate=0.0001,\n", + "length_column_name=length,\n", + "load_best_model_at_end=False,\n", + "local_rank=0,\n", + "log_level=passive,\n", + "log_level_replica=warning,\n", + "log_on_each_node=True,\n", + "logging_dir=./tmp/vits_kbd_finetuned_che_model/runs/May13_00-06-10_db5dbab3f05c,\n", + "logging_first_step=False,\n", + "logging_nan_inf_filter=True,\n", + "logging_steps=500,\n", + "logging_strategy=steps,\n", + "lr_decay=0.999875,\n", + "lr_scheduler_type=linear,\n", + "max_grad_norm=1.0,\n", + "max_steps=100,\n", + "metric_for_best_model=None,\n", + "mp_parameters=,\n", + "neftune_noise_alpha=None,\n", + "no_cuda=False,\n", + "num_train_epochs=3.0,\n", + "optim=adamw_torch,\n", + "optim_args=None,\n", + "output_dir=./tmp/vits_kbd_finetuned_che_model,\n", + "overwrite_output_dir=False,\n", + "past_index=-1,\n", + "per_device_eval_batch_size=16,\n", + "per_device_train_batch_size=16,\n", + "prediction_loss_only=False,\n", + "push_to_hub=True,\n", + "push_to_hub_model_id=None,\n", + "push_to_hub_organization=None,\n", + "push_to_hub_token=,\n", + "ray_scope=last,\n", + "remove_unused_columns=True,\n", + "report_to=['tensorboard', 'wandb'],\n", + "resume_from_checkpoint=None,\n", + "run_name=./tmp/vits_kbd_finetuned_che_model,\n", + "save_on_each_node=False,\n", + "save_safetensors=True,\n", + "save_steps=500,\n", + "save_strategy=steps,\n", + "save_total_limit=None,\n", + "seed=456,\n", + "skip_memory_metrics=True,\n", + "split_batches=False,\n", + "tf32=None,\n", + "torch_compile=False,\n", + "torch_compile_backend=None,\n", + "torch_compile_mode=None,\n", + "torchdynamo=None,\n", + "tpu_metrics_debug=False,\n", + "tpu_num_cores=None,\n", + "use_cpu=False,\n", + "use_ipex=False,\n", + "use_legacy_prediction_loop=False,\n", + "use_mps_device=False,\n", + "warmup_ratio=0.01,\n", + "warmup_steps=0,\n", + "weight_decay=0.0,\n", + "weight_disc=3,\n", + "weight_duration=1,\n", + "weight_fmaps=1,\n", + "weight_gen=1,\n", + "weight_kl=1.5,\n", + "weight_mel=35,\n", + ")\n", + "05/13/2024 00:06:11 - INFO - __main__ - Checkpoint detected, resuming training at ./tmp/vits_kbd_finetuned_che_model/checkpoint-5000. To avoid this behavior, change the `--output_dir` or add `--overwrite_output_dir` to train from scratch.\n", + "/usr/local/lib/python3.10/dist-packages/datasets/table.py:1421: FutureWarning: promote has been superseded by mode='default'.\n", + " table = cls._concat_blocks(blocks, axis=0)\n", + "[INFO|configuration_utils.py:717] 2024-05-13 00:06:17,139 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--anzorq--mms-tts-kbd-discriminator/snapshots/3f655bed8e8f4a13aed6a5b13d8066495d971bee/config.json\n", + "[INFO|configuration_utils.py:777] 2024-05-13 00:06:17,140 >> Model config VitsConfig {\n", + " \"activation_dropout\": 0.1,\n", + " \"architectures\": [\n", + " \"VitsModelForPreTraining\"\n", + " ],\n", + " \"attention_dropout\": 0.1,\n", + " \"depth_separable_channels\": 2,\n", + " \"depth_separable_num_layers\": 3,\n", + " \"discriminator_kernel_size\": 5,\n", + " \"discriminator_period_channels\": [\n", + " 1,\n", + " 32,\n", + " 128,\n", + " 512,\n", + " 1024\n", + " ],\n", + " \"discriminator_periods\": [\n", + " 2,\n", + " 3,\n", + " 5,\n", + " 7,\n", + " 11\n", + " ],\n", + " \"discriminator_scale_channels\": [\n", + " 1,\n", + " 16,\n", + " 64,\n", + " 256,\n", + " 1024\n", + " ],\n", + " \"discriminator_stride\": 3,\n", + " \"duration_predictor_dropout\": 0.5,\n", + " \"duration_predictor_filter_channels\": 256,\n", + " \"duration_predictor_flow_bins\": 10,\n", + " \"duration_predictor_kernel_size\": 3,\n", + " \"duration_predictor_num_flows\": 4,\n", + " \"duration_predictor_tail_bound\": 5.0,\n", + " \"ffn_dim\": 768,\n", + " \"ffn_kernel_size\": 3,\n", + " \"flow_size\": 192,\n", + " \"hidden_act\": \"relu\",\n", + " \"hidden_dropout\": 0.1,\n", + " \"hidden_size\": 192,\n", + " \"hop_length\": 256,\n", + " \"initializer_range\": 0.02,\n", + " \"layer_norm_eps\": 1e-05,\n", + " \"layerdrop\": 0.1,\n", + " \"leaky_relu_slope\": 0.1,\n", + " \"model_type\": \"vits\",\n", + " \"noise_scale\": 0.667,\n", + " \"noise_scale_duration\": 0.8,\n", + " \"num_attention_heads\": 2,\n", + " \"num_hidden_layers\": 6,\n", + " \"num_speakers\": 1,\n", + " \"posterior_encoder_num_wavenet_layers\": 16,\n", + " \"prior_encoder_num_flows\": 4,\n", + " \"prior_encoder_num_wavenet_layers\": 4,\n", + " \"resblock_dilation_sizes\": [\n", + " [\n", + " 1,\n", + " 3,\n", + " 5\n", + " ],\n", + " [\n", + " 1,\n", + " 3,\n", + " 5\n", + " ],\n", + " [\n", + " 1,\n", + " 3,\n", + " 5\n", + " ]\n", + " ],\n", + " \"resblock_kernel_sizes\": [\n", + " 3,\n", + " 7,\n", + " 11\n", + " ],\n", + " \"sampling_rate\": 16000,\n", + " \"segment_size\": 8192,\n", + " \"speaker_embedding_size\": 0,\n", + " \"speaking_rate\": 1.0,\n", + " \"spectrogram_bins\": 513,\n", + " \"torch_dtype\": \"float32\",\n", + " \"transformers_version\": \"4.35.1\",\n", + " \"upsample_initial_channel\": 512,\n", + " \"upsample_kernel_sizes\": [\n", + " 16,\n", + " 16,\n", + " 4,\n", + " 4\n", + " ],\n", + " \"upsample_rates\": [\n", + " 8,\n", + " 8,\n", + " 2,\n", + " 2\n", + " ],\n", + " \"use_bias\": true,\n", + " \"use_stochastic_duration_prediction\": true,\n", + " \"vocab_size\": 36,\n", + " \"wavenet_dilation_rate\": 1,\n", + " \"wavenet_dropout\": 0.0,\n", + " \"wavenet_kernel_size\": 5,\n", + " \"window_size\": 4\n", + "}\n", + "\n", + "[INFO|feature_extraction_utils.py:537] 2024-05-13 00:06:17,393 >> loading configuration file preprocessor_config.json from cache at /root/.cache/huggingface/hub/models--anzorq--mms-tts-kbd-discriminator/snapshots/3f655bed8e8f4a13aed6a5b13d8066495d971bee/preprocessor_config.json\n", + "[INFO|feature_extraction_utils.py:579] 2024-05-13 00:06:17,395 >> Feature extractor VitsFeatureExtractor {\n", + " \"feature_extractor_type\": \"VitsFeatureExtractor\",\n", + " \"feature_size\": 80,\n", + " \"hop_length\": 256,\n", + " \"max_wav_value\": 32768.0,\n", + " \"n_fft\": 1024,\n", + " \"padding_side\": \"right\",\n", + " \"padding_value\": 0.0,\n", + " \"return_attention_mask\": false,\n", + " \"sampling_rate\": 16000\n", + "}\n", + "\n", + "[INFO|tokenization_utils_base.py:2022] 2024-05-13 00:06:17,647 >> loading file vocab.json from cache at /root/.cache/huggingface/hub/models--anzorq--mms-tts-kbd-discriminator/snapshots/3f655bed8e8f4a13aed6a5b13d8066495d971bee/vocab.json\n", + "[INFO|tokenization_utils_base.py:2022] 2024-05-13 00:06:17,647 >> loading file added_tokens.json from cache at /root/.cache/huggingface/hub/models--anzorq--mms-tts-kbd-discriminator/snapshots/3f655bed8e8f4a13aed6a5b13d8066495d971bee/added_tokens.json\n", + "[INFO|tokenization_utils_base.py:2022] 2024-05-13 00:06:17,647 >> loading file special_tokens_map.json from cache at /root/.cache/huggingface/hub/models--anzorq--mms-tts-kbd-discriminator/snapshots/3f655bed8e8f4a13aed6a5b13d8066495d971bee/special_tokens_map.json\n", + "[INFO|tokenization_utils_base.py:2022] 2024-05-13 00:06:17,647 >> loading file tokenizer_config.json from cache at /root/.cache/huggingface/hub/models--anzorq--mms-tts-kbd-discriminator/snapshots/3f655bed8e8f4a13aed6a5b13d8066495d971bee/tokenizer_config.json\n", + "[INFO|tokenization_utils_base.py:2022] 2024-05-13 00:06:17,647 >> loading file tokenizer.json from cache at None\n", + "[INFO|modeling_utils.py:3121] 2024-05-13 00:06:17,872 >> loading weights file model.safetensors from cache at /root/.cache/huggingface/hub/models--anzorq--mms-tts-kbd-discriminator/snapshots/3f655bed8e8f4a13aed6a5b13d8066495d971bee/model.safetensors\n", + "[INFO|modeling_utils.py:3950] 2024-05-13 00:06:20,461 >> All model checkpoint weights were used when initializing VitsModelForPreTraining.\n", + "\n", + "[INFO|modeling_utils.py:3958] 2024-05-13 00:06:20,461 >> All the weights of VitsModelForPreTraining were initialized from the model checkpoint at anzorq/mms-tts-kbd-discriminator.\n", + "If your task is similar to the task the model of the checkpoint was trained on, you can already use VitsModelForPreTraining for predictions without further training.\n", + "/usr/local/lib/python3.10/dist-packages/torch/nn/utils/weight_norm.py:28: UserWarning: torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm.\n", + " warnings.warn(\"torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm.\")\n", + "05/13/2024 00:06:20 - INFO - __main__ - Only one speaker detected on the training set. Embeddings are not reinitialized.\n", + "[INFO|feature_extraction_utils.py:425] 2024-05-13 00:06:20,525 >> Feature extractor saved in ./tmp/vits_kbd_finetuned_che_model/preprocessor_config.json\n", + "[INFO|tokenization_utils_base.py:2428] 2024-05-13 00:06:20,525 >> tokenizer config file saved in ./tmp/vits_kbd_finetuned_che_model/tokenizer_config.json\n", + "[INFO|tokenization_utils_base.py:2437] 2024-05-13 00:06:20,525 >> Special tokens file saved in ./tmp/vits_kbd_finetuned_che_model/special_tokens_map.json\n", + "[INFO|tokenization_utils_base.py:2488] 2024-05-13 00:06:20,526 >> added tokens file saved in ./tmp/vits_kbd_finetuned_che_model/added_tokens.json\n", + "[INFO|configuration_utils.py:461] 2024-05-13 00:06:20,527 >> Configuration saved in ./tmp/vits_kbd_finetuned_che_model/config.json\n", + "[INFO|configuration_utils.py:461] 2024-05-13 00:06:20,532 >> Configuration saved in /tmp/tmpwp5gvzgz/config.json\n", + "[INFO|modeling_utils.py:2193] 2024-05-13 00:06:20,899 >> Model weights saved in /tmp/tmpwp5gvzgz/pytorch_model.bin\n", + "[INFO|configuration_utils.py:715] 2024-05-13 00:06:20,899 >> loading configuration file /tmp/tmpwp5gvzgz/config.json\n", + "[INFO|configuration_utils.py:777] 2024-05-13 00:06:20,901 >> Model config VitsConfig {\n", + " \"_name_or_path\": \"anzorq/mms-tts-kbd-discriminator\",\n", + " \"activation_dropout\": 0.1,\n", + " \"architectures\": [\n", + " \"VitsDiscriminator\"\n", + " ],\n", + " \"attention_dropout\": 0.1,\n", + " \"depth_separable_channels\": 2,\n", + " \"depth_separable_num_layers\": 3,\n", + " \"discriminator_kernel_size\": 5,\n", + " \"discriminator_period_channels\": [\n", + " 1,\n", + " 32,\n", + " 128,\n", + " 512,\n", + " 1024\n", + " ],\n", + " \"discriminator_periods\": [\n", + " 2,\n", + " 3,\n", + " 5,\n", + " 7,\n", + " 11\n", + " ],\n", + " \"discriminator_scale_channels\": [\n", + " 1,\n", + " 16,\n", + " 64,\n", + " 256,\n", + " 1024\n", + " ],\n", + " \"discriminator_stride\": 3,\n", + " \"duration_predictor_dropout\": 0.5,\n", + " \"duration_predictor_filter_channels\": 256,\n", + " \"duration_predictor_flow_bins\": 10,\n", + " \"duration_predictor_kernel_size\": 3,\n", + " \"duration_predictor_num_flows\": 4,\n", + " \"duration_predictor_tail_bound\": 5.0,\n", + " \"ffn_dim\": 768,\n", + " \"ffn_kernel_size\": 3,\n", + " \"flow_size\": 192,\n", + " \"hidden_act\": \"relu\",\n", + " \"hidden_dropout\": 0.1,\n", + " \"hidden_size\": 192,\n", + " \"hop_length\": 256,\n", + " \"initializer_range\": 0.02,\n", + " \"layer_norm_eps\": 1e-05,\n", + " \"layerdrop\": 0.1,\n", + " \"leaky_relu_slope\": 0.1,\n", + " \"model_type\": \"vits\",\n", + " \"noise_scale\": 0.667,\n", + " \"noise_scale_duration\": 0.8,\n", + " \"num_attention_heads\": 2,\n", + " \"num_hidden_layers\": 6,\n", + " \"num_speakers\": 1,\n", + " \"posterior_encoder_num_wavenet_layers\": 16,\n", + " \"prior_encoder_num_flows\": 4,\n", + " \"prior_encoder_num_wavenet_layers\": 4,\n", + " \"resblock_dilation_sizes\": [\n", + " [\n", + " 1,\n", + " 3,\n", + " 5\n", + " ],\n", + " [\n", + " 1,\n", + " 3,\n", + " 5\n", + " ],\n", + " [\n", + " 1,\n", + " 3,\n", + " 5\n", + " ]\n", + " ],\n", + " \"resblock_kernel_sizes\": [\n", + " 3,\n", + " 7,\n", + " 11\n", + " ],\n", + " \"sampling_rate\": 16000,\n", + " \"segment_size\": 8192,\n", + " \"speaker_embedding_size\": 0,\n", + " \"speaking_rate\": 1.0,\n", + " \"spectrogram_bins\": 513,\n", + " \"torch_dtype\": \"float32\",\n", + " \"transformers_version\": \"4.35.1\",\n", + " \"upsample_initial_channel\": 512,\n", + " \"upsample_kernel_sizes\": [\n", + " 16,\n", + " 16,\n", + " 4,\n", + " 4\n", + " ],\n", + " \"upsample_rates\": [\n", + " 8,\n", + " 8,\n", + " 2,\n", + " 2\n", + " ],\n", + " \"use_bias\": true,\n", + " \"use_stochastic_duration_prediction\": true,\n", + " \"vocab_size\": 36,\n", + " \"wavenet_dilation_rate\": 1,\n", + " \"wavenet_dropout\": 0.0,\n", + " \"wavenet_kernel_size\": 5,\n", + " \"window_size\": 4\n", + "}\n", + "\n", + "[INFO|modeling_utils.py:3118] 2024-05-13 00:06:20,902 >> loading weights file /tmp/tmpwp5gvzgz/model.safetensors\n", + "[INFO|modeling_utils.py:3950] 2024-05-13 00:06:21,345 >> All model checkpoint weights were used when initializing VitsDiscriminator.\n", + "\n", + "[INFO|modeling_utils.py:3958] 2024-05-13 00:06:21,345 >> All the weights of VitsDiscriminator were initialized from the model checkpoint at /tmp/tmpwp5gvzgz.\n", + "If your task is similar to the task the model of the checkpoint was trained on, you can already use VitsDiscriminator for predictions without further training.\n", + "2024-05-13 00:06:22.163784: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n", + "2024-05-13 00:06:22.163840: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n", + "2024-05-13 00:06:22.165230: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n", + "2024-05-13 00:06:23.193468: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT\n", + "\u001b[34m\u001b[1mwandb\u001b[0m: Currently logged in as: \u001b[33myoutube-algorithm\u001b[0m. Use \u001b[1m`wandb login --relogin`\u001b[0m to force relogin\n", + "\u001b[34m\u001b[1mwandb\u001b[0m: Tracking run with wandb version 0.17.0\n", + "\u001b[34m\u001b[1mwandb\u001b[0m: Run data is saved locally in \u001b[35m\u001b[1m/content/finetune-hf-vits/wandb/run-20240513_000625-i64rhtdn\u001b[0m\n", + "\u001b[34m\u001b[1mwandb\u001b[0m: Run \u001b[1m`wandb offline`\u001b[0m to turn off syncing.\n", + "\u001b[34m\u001b[1mwandb\u001b[0m: Syncing run \u001b[33msuper-fog-25\u001b[0m\n", + "\u001b[34m\u001b[1mwandb\u001b[0m: ⭐️ View project at \u001b[34m\u001b[4mhttps://wandb.ai/youtube-algorithm/vits_kbd\u001b[0m\n", + "\u001b[34m\u001b[1mwandb\u001b[0m: 🚀 View run at \u001b[34m\u001b[4mhttps://wandb.ai/youtube-algorithm/vits_kbd/runs/i64rhtdn\u001b[0m\n", + "05/13/2024 00:06:26 - INFO - __main__ - ***** Running training *****\n", + "05/13/2024 00:06:26 - INFO - __main__ - Num examples = 12964\n", + "05/13/2024 00:06:26 - INFO - __main__ - Num Epochs = 1\n", + "05/13/2024 00:06:26 - INFO - __main__ - Instantaneous batch size per device = 16\n", + "05/13/2024 00:06:26 - INFO - __main__ - Total train batch size (w. parallel, distributed & accumulation) = 16\n", + "05/13/2024 00:06:26 - INFO - __main__ - Gradient Accumulation steps = 1\n", + "05/13/2024 00:06:26 - INFO - __main__ - Total optimization steps = 100\n", + "Steps: 0% 0/100 [00:00> Configuration saved in ./tmp/vits_kbd_finetuned_che_model/config.json\n", + "[INFO|modeling_utils.py:2193] 2024-05-13 00:08:52,669 >> Model weights saved in ./tmp/vits_kbd_finetuned_che_model/pytorch_model.bin\n", + "[INFO|configuration_utils.py:715] 2024-05-13 00:08:52,673 >> loading configuration file ./tmp/vits_kbd_finetuned_che_model/config.json\n", + "[INFO|configuration_utils.py:777] 2024-05-13 00:08:52,675 >> Model config VitsConfig {\n", + " \"_name_or_path\": \"anzorq/mms-tts-kbd-discriminator\",\n", + " \"activation_dropout\": 0.1,\n", + " \"architectures\": [\n", + " \"VitsModelForPreTraining\"\n", + " ],\n", + " \"attention_dropout\": 0.1,\n", + " \"depth_separable_channels\": 2,\n", + " \"depth_separable_num_layers\": 3,\n", + " \"discriminator_kernel_size\": 5,\n", + " \"discriminator_period_channels\": [\n", + " 1,\n", + " 32,\n", + " 128,\n", + " 512,\n", + " 1024\n", + " ],\n", + " \"discriminator_periods\": [\n", + " 2,\n", + " 3,\n", + " 5,\n", + " 7,\n", + " 11\n", + " ],\n", + " \"discriminator_scale_channels\": [\n", + " 1,\n", + " 16,\n", + " 64,\n", + " 256,\n", + " 1024\n", + " ],\n", + " \"discriminator_stride\": 3,\n", + " \"duration_predictor_dropout\": 0.5,\n", + " \"duration_predictor_filter_channels\": 256,\n", + " \"duration_predictor_flow_bins\": 10,\n", + " \"duration_predictor_kernel_size\": 3,\n", + " \"duration_predictor_num_flows\": 4,\n", + " \"duration_predictor_tail_bound\": 5.0,\n", + " \"ffn_dim\": 768,\n", + " \"ffn_kernel_size\": 3,\n", + " \"flow_size\": 192,\n", + " \"hidden_act\": \"relu\",\n", + " \"hidden_dropout\": 0.1,\n", + " \"hidden_size\": 192,\n", + " \"hop_length\": 256,\n", + " \"initializer_range\": 0.02,\n", + " \"layer_norm_eps\": 1e-05,\n", + " \"layerdrop\": 0.1,\n", + " \"leaky_relu_slope\": 0.1,\n", + " \"model_type\": \"vits\",\n", + " \"noise_scale\": 0.667,\n", + " \"noise_scale_duration\": 0.8,\n", + " \"num_attention_heads\": 2,\n", + " \"num_hidden_layers\": 6,\n", + " \"num_speakers\": 1,\n", + " \"posterior_encoder_num_wavenet_layers\": 16,\n", + " \"prior_encoder_num_flows\": 4,\n", + " \"prior_encoder_num_wavenet_layers\": 4,\n", + " \"resblock_dilation_sizes\": [\n", + " [\n", + " 1,\n", + " 3,\n", + " 5\n", + " ],\n", + " [\n", + " 1,\n", + " 3,\n", + " 5\n", + " ],\n", + " [\n", + " 1,\n", + " 3,\n", + " 5\n", + " ]\n", + " ],\n", + " \"resblock_kernel_sizes\": [\n", + " 3,\n", + " 7,\n", + " 11\n", + " ],\n", + " \"sampling_rate\": 16000,\n", + " \"segment_size\": 8192,\n", + " \"speaker_embedding_size\": 0,\n", + " \"speaking_rate\": 1.0,\n", + " \"spectrogram_bins\": 513,\n", + " \"torch_dtype\": \"float32\",\n", + " \"transformers_version\": \"4.35.1\",\n", + " \"upsample_initial_channel\": 512,\n", + " \"upsample_kernel_sizes\": [\n", + " 16,\n", + " 16,\n", + " 4,\n", + " 4\n", + " ],\n", + " \"upsample_rates\": [\n", + " 8,\n", + " 8,\n", + " 2,\n", + " 2\n", + " ],\n", + " \"use_bias\": true,\n", + " \"use_stochastic_duration_prediction\": true,\n", + " \"vocab_size\": 36,\n", + " \"wavenet_dilation_rate\": 1,\n", + " \"wavenet_dropout\": 0.0,\n", + " \"wavenet_kernel_size\": 5,\n", + " \"window_size\": 4\n", + "}\n", + "\n", + "[INFO|modeling_utils.py:3118] 2024-05-13 00:08:52,675 >> loading weights file ./tmp/vits_kbd_finetuned_che_model/model.safetensors\n", + "[INFO|modeling_utils.py:3940] 2024-05-13 00:08:53,441 >> Some weights of the model checkpoint at ./tmp/vits_kbd_finetuned_che_model were not used when initializing VitsModel: ['discriminator.discriminators.0.convs.1.weight', 'discriminator.discriminators.4.final_conv.bias', 'discriminator.discriminators.1.convs.0.bias', 'discriminator.discriminators.5.convs.4.bias', 'discriminator.discriminators.1.convs.2.weight', 'discriminator.discriminators.3.convs.0.weight', 'discriminator.discriminators.2.final_conv.weight', 'discriminator.discriminators.2.convs.2.bias', 'discriminator.discriminators.4.convs.0.weight', 'discriminator.discriminators.3.convs.1.bias', 'discriminator.discriminators.1.final_conv.weight', 'discriminator.discriminators.0.convs.4.bias', 'discriminator.discriminators.5.convs.1.bias', 'discriminator.discriminators.0.final_conv.bias', 'discriminator.discriminators.3.convs.0.bias', 'discriminator.discriminators.0.convs.3.weight', 'discriminator.discriminators.4.convs.3.bias', 'discriminator.discriminators.1.convs.1.bias', 'discriminator.discriminators.3.convs.1.weight', 'discriminator.discriminators.1.convs.0.weight', 'discriminator.discriminators.5.convs.2.bias', 'discriminator.discriminators.2.convs.3.weight', 'discriminator.discriminators.1.convs.4.bias', 'discriminator.discriminators.0.convs.2.weight', 'discriminator.discriminators.3.final_conv.weight', 'discriminator.discriminators.2.final_conv.bias', 'discriminator.discriminators.5.convs.3.weight', 'discriminator.discriminators.2.convs.0.weight', 'discriminator.discriminators.4.convs.2.weight', 'discriminator.discriminators.4.final_conv.weight', 'discriminator.discriminators.2.convs.4.weight', 'discriminator.discriminators.2.convs.1.weight', 'discriminator.discriminators.3.convs.3.weight', 'discriminator.discriminators.3.convs.3.bias', 'discriminator.discriminators.2.convs.3.bias', 'discriminator.discriminators.3.final_conv.bias', 'discriminator.discriminators.5.convs.0.weight', 'discriminator.discriminators.1.convs.4.weight', 'discriminator.discriminators.0.convs.5.bias', 'discriminator.discriminators.4.convs.3.weight', 'discriminator.discriminators.2.convs.0.bias', 'discriminator.discriminators.0.convs.5.weight', 'discriminator.discriminators.5.convs.1.weight', 'discriminator.discriminators.3.convs.2.bias', 'discriminator.discriminators.1.final_conv.bias', 'discriminator.discriminators.4.convs.4.bias', 'discriminator.discriminators.4.convs.0.bias', 'discriminator.discriminators.4.convs.1.weight', 'discriminator.discriminators.1.convs.1.weight', 'discriminator.discriminators.5.convs.2.weight', 'discriminator.discriminators.5.final_conv.bias', 'discriminator.discriminators.2.convs.2.weight', 'discriminator.discriminators.2.convs.4.bias', 'discriminator.discriminators.1.convs.3.bias', 'discriminator.discriminators.4.convs.4.weight', 'discriminator.discriminators.4.convs.2.bias', 'discriminator.discriminators.4.convs.1.bias', 'discriminator.discriminators.0.final_conv.weight', 'discriminator.discriminators.5.convs.4.weight', 'discriminator.discriminators.3.convs.2.weight', 'discriminator.discriminators.3.convs.4.weight', 'discriminator.discriminators.1.convs.3.weight', 'discriminator.discriminators.0.convs.0.bias', 'discriminator.discriminators.1.convs.2.bias', 'discriminator.discriminators.2.convs.1.bias', 'discriminator.discriminators.5.final_conv.weight', 'discriminator.discriminators.3.convs.4.bias', 'discriminator.discriminators.0.convs.1.bias', 'discriminator.discriminators.5.convs.3.bias', 'discriminator.discriminators.0.convs.0.weight', 'discriminator.discriminators.0.convs.4.weight', 'discriminator.discriminators.0.convs.3.bias', 'discriminator.discriminators.5.convs.0.bias', 'discriminator.discriminators.0.convs.2.bias']\n", + "- This IS expected if you are initializing VitsModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).\n", + "- This IS NOT expected if you are initializing VitsModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).\n", + "[INFO|modeling_utils.py:3958] 2024-05-13 00:08:53,441 >> All the weights of VitsModel were initialized from the model checkpoint at ./tmp/vits_kbd_finetuned_che_model.\n", + "If your task is similar to the task the model of the checkpoint was trained on, you can already use VitsModel for predictions without further training.\n", + "[INFO|configuration_utils.py:461] 2024-05-13 00:08:54,375 >> Configuration saved in /tmp/tmpshmzw11a/config.json\n", + "[INFO|modeling_utils.py:2193] 2024-05-13 00:08:54,684 >> Model weights saved in /tmp/tmpshmzw11a/pytorch_model.bin\n", + "[INFO|hub.py:780] 2024-05-13 00:08:55,147 >> Uploading the following files to anzorq/mms_finetune_kbd_murat: model.safetensors,config.json\n", + "\n", + "model.safetensors: 0% 0.00/145M [00:00> Feature extractor saved in /tmp/tmpp2xnpltz/preprocessor_config.json\n", + "[INFO|hub.py:780] 2024-05-13 00:09:22,764 >> Uploading the following files to anzorq/mms_finetune_kbd_murat: preprocessor_config.json\n", + "[INFO|tokenization_utils_base.py:2428] 2024-05-13 00:09:23,794 >> tokenizer config file saved in /tmp/tmpllxoyho6/tokenizer_config.json\n", + "[INFO|tokenization_utils_base.py:2437] 2024-05-13 00:09:23,794 >> Special tokens file saved in /tmp/tmpllxoyho6/special_tokens_map.json\n", + "[INFO|tokenization_utils_base.py:2488] 2024-05-13 00:09:23,794 >> added tokens file saved in /tmp/tmpllxoyho6/added_tokens.json\n", + "[INFO|hub.py:780] 2024-05-13 00:09:23,795 >> Uploading the following files to anzorq/mms_finetune_kbd_murat: special_tokens_map.json,vocab.json,added_tokens.json,tokenizer_config.json\n", + "05/13/2024 00:09:24 - INFO - __main__ - ***** Training / Inference Done *****\n", + "/usr/local/lib/python3.10/dist-packages/wandb/sdk/wandb_run.py:2304: UserWarning: Run (i64rhtdn) is finished. The call to `_console_raw_callback` will be ignored. Please make sure that you are using an active run.\n", + " lambda data: self._console_raw_callback(\"stderr\", data),\n", + "Steps: 100% 100/100 [02:58<00:00, 1.78s/it, lr=0.0001, step_loss=30.2, step_loss_disc=2.58, step_loss_duration=2.11, step_loss_fake_disc=1.12, step_loss_fmaps=7.19, step_loss_gen=2.24, step_loss_kl=2.11, step_loss_mel=0.442, step_loss_real_disc=1.46]\n" + ] + } + ] + }, + { + "cell_type": "markdown", + "source": [ + "#### Inference" + ], + "metadata": { + "id": "JldEYLcUSdpK" + } + }, + { + "cell_type": "code", + "source": [ + "from transformers import pipeline\n", + "import scipy\n", + "\n", + "model_id = \"anzorq/mms_finetune_kbd_murat\"\n", + "synthesiser = pipeline(\"text-to-speech\", model_id, device=0) # add device=0 if you want to use a GPU" + ], + "metadata": { + "id": "HX1qdzF6Zvii", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 333, + "referenced_widgets": [ + "0459621153dd4c9bb5b5dbb67eb67fdd", + "92b2f88442e944278e01ebcf9d8a7d2a", + "3d3d36743d1346e9adcfeb86f7a75fb4", + "821a9faf4d8543a08637668655e90dfa", + "4722e3dcee964f7f8cf2185dc85077a8", + "229b1aab70a24285bbd4480f47e7a043", + "e2450a9986664e9f9e73f4fd2e3060a9", + "6071bbafcdab4e2983b1b4de3b871447", + "ab91e2077e834725b11190526fed19ed", + "fd9727afdc484dfa85684e52de2a482c", + "03dbd16046e14df1b42a43eeb7f55073", + "40a3bc724702467f8ab2c78ce56769e2", + "3079574cdd0a4a3899d26bce4011cb4e", + "9767d884907e422ab303bd2d09a408eb", + "9d37aa8b388a4fdaaebaa445427f651e", + "6435ec23688e4e7f83a6f4e48c9dc400", + "ddf75c9845894eb588af9c6c0c492288", + "36846a12832f43aaaeaaa1401bc1c7cc", + "956c489f47234421a6f1914bd6d3f860", + "0e3b20a61dd84175be38102385fb31ea", + "cc7e6860dd9e4617ab9eb5c36eeec57d", + "5b4fd5dfba5e45b6bddb7c3980da033e", + "07f416522f32421ba04e23bddf4498d3", + "5a1102727f8242fcb6fb9da4c2e8caf5", + "2953f35810f84600917171810d614177", + "743d02cf83f440cabe97b20bfcb80212", + "97f67a7cccba47e8a8afaee84facc035", + "2b95c5e4ea874bf2aa5b63c90357e44f", + "58493a7b09db41c489da6640df4b43dd", + "5519ee296bee4407b876385b0ede4044", + "f4bc881f3a404c729679d378bda3868b", + "86ee1a7aeead40c9b658bcf240f0900a", + "a6cd8b9801224592b52bbe1f9277f409", + "3298b9d7218b4b0c855f08317c5f1a37", + "d5cd31cae11a403893b869b4d83a6fb5", + "769ebebcde1a4a8096c6489be076abaf", + "df9faedf82394537abcef03c00c299ca", + "bf8263f105194277b784bdcfe9348bff", + "6ee738bb43684db1be624712f6fc5f8f", + "85f7d9cbe90444b091584d217e7cf896", + "54437e3f4abb4d1196e779aecd81473f", + "600c7ef145d14d1691ade8f80044782f", + "03defb6b43f046ee91195eab47aca2a6", + "bca6940077eb464dac62506b0c07b165", + "fbaf8fe87deb472484fd6203d345c0d0", + "7407ba67b5854c929d42a9a5f0f6ab34", + "cc4b0623b43741afa7f8ffcf774a6321", + "739a85881ea641ef8e636e4758852176", + "629c47e8500f45b58887a87dd018b950", + "ca454ba2b768440bb6496dcf0b833a47", + "0d296c0876024caca80befb264394422", + "49e51f8f13144b7c897c83add6a2765d", + "d90c73a1cc894ef8905bb59fcb4f4fd8", + "dbdc0e89f0554fd286e25cf53c2aafdc", + "0f29167f9f80431cae660dc790d189a7", + "f2df09555bba4131bdddca6d8df251de", + "8c19f3d4505244309cf32c171b9989ac", + "c535ce84edb7404eacf299d1c1d68e85", + "5cff10d745a7459a91f93ca600d856c9", + "4bcbfde596524b12bfd0decf8262f256", + "4f527d0641d9424f86f5e09e7b2a055a", + "8a953c76dfdf49f0b42efd9c95baa9ad", + "20c441186d0042f89067974330da0e6a", + "0f1a83d1163d4430b27a10718164f819", + "10322be4f8a04fe7b242a9f76feb1885", + "9c63b360b27f438abed74630301e76c9" + ] + }, + "outputId": "2cb566a7-5de8-40db-90ef-cd498ebb7a75" + }, + "execution_count": null, + "outputs": [ + { + "output_type": "stream", + "name": "stderr", + "text": [ + "/usr/local/lib/python3.10/dist-packages/transformers/utils/generic.py:441: UserWarning: torch.utils._pytree._register_pytree_node is deprecated. Please use torch.utils._pytree.register_pytree_node instead.\n", + " _torch_pytree._register_pytree_node(\n", + "/usr/local/lib/python3.10/dist-packages/transformers/utils/generic.py:309: UserWarning: torch.utils._pytree._register_pytree_node is deprecated. Please use torch.utils._pytree.register_pytree_node instead.\n", + " _torch_pytree._register_pytree_node(\n", + "/usr/local/lib/python3.10/dist-packages/transformers/utils/generic.py:309: UserWarning: torch.utils._pytree._register_pytree_node is deprecated. Please use torch.utils._pytree.register_pytree_node instead.\n", + " _torch_pytree._register_pytree_node(\n" + ] + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "Downloading config.json: 0%| | 0.00/2.04k [00:00" + ], + "text/html": [ + "\n", + " \n", + " " + ] + }, + "metadata": {}, + "execution_count": 22 + } + ] + } + ] +} \ No newline at end of file