diff --git "a/Starcoder2_3b_finetuning.ipynb" "b/Starcoder2_3b_finetuning.ipynb" new file mode 100644--- /dev/null +++ "b/Starcoder2_3b_finetuning.ipynb" @@ -0,0 +1,7711 @@ +{ + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "name": "python3" + }, + "language_info": { + "name": "python", + "version": "3.10.13", + "mimetype": "text/x-python", + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "pygments_lexer": "ipython3", + "nbconvert_exporter": "python", + "file_extension": ".py" + }, + "kaggle": { + "accelerator": "nvidiaTeslaT4", + "dataSources": [], + "isInternetEnabled": true, + "language": "python", + "sourceType": "notebook", + "isGpuEnabled": true + }, + "colab": { + "provenance": [], + "gpuType": "T4" + }, + "accelerator": "GPU", + "widgets": { + "application/vnd.jupyter.widget-state+json": { + "1234072a81334f8db0a10d1b44d034f5": { + "model_module": "@jupyter-widgets/controls", + "model_name": "VBoxModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "VBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "VBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_6bba1b4558b0432aa44c558e5d4ebdf8", + "IPY_MODEL_4ac3b065ad9546398e2691ceb371c233", + "IPY_MODEL_accba8f890814d5f92464b3471966bbf", + "IPY_MODEL_bb0db85e948443019c9d645280175b47" + ], + "layout": "IPY_MODEL_34ba7411d5de41c9ac7ef9ade5a5ad9b" + } + }, + "0b7664f082d34d9b9b86979e0a7f55e7": { + "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_aec899db50df4647ae5ac36c07ee294f", + "placeholder": "​", + "style": "IPY_MODEL_d5f8193d213d4860aaa0c842ba7c9c07", + "value": "

Copy a token from your Hugging Face\ntokens page and paste it below.
Immediately click login after copying\nyour token or it might be stored in plain text in this notebook file.
" + } + }, + "5b777f1e81ff439b8dca5e5d9eedf67b": { + "model_module": "@jupyter-widgets/controls", + "model_name": "PasswordModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "PasswordModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "PasswordView", + "continuous_update": true, + "description": "Token:", + "description_tooltip": null, + "disabled": false, + "layout": "IPY_MODEL_eed45bc885fd4adcbce829b0c9afbf48", + "placeholder": "​", + "style": "IPY_MODEL_d2fdd03aa4e148bcac64eab9229af61c", + "value": "" + } + }, + "3c3e316bad6542ee8da7b7d478bc0de0": { + "model_module": "@jupyter-widgets/controls", + "model_name": "CheckboxModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "CheckboxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "CheckboxView", + "description": "Add token as git credential?", + "description_tooltip": null, + "disabled": false, + "indent": true, + "layout": "IPY_MODEL_917ad72239a24a2ca19578077bd3f190", + "style": "IPY_MODEL_c08f5bb3f3b0400eac10e333a78f30b8", + "value": true + } + }, + "48c07121dcd247bb96d38eb1bdd2a073": { + "model_module": "@jupyter-widgets/controls", + "model_name": "ButtonModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ButtonModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ButtonView", + "button_style": "", + "description": "Login", + "disabled": false, + "icon": "", + "layout": "IPY_MODEL_8594f76b97fa4814a5ae0235f3ad0961", + "style": "IPY_MODEL_bea5cf62b00b446bb2ef49329771a398", + "tooltip": "" + } + }, + "663c38b3e97c4855a959bbc4582c2412": { + "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_a1667ab01c674d93b8456e84ea587d03", + "placeholder": "​", + "style": "IPY_MODEL_1504ebc3efdf41b5854a6596a175aedb", + "value": "\nPro Tip: If you don't already have one, you can create a dedicated\n'notebooks' token with 'write' access, that you can then easily reuse for all\nnotebooks. " + } + }, + "34ba7411d5de41c9ac7ef9ade5a5ad9b": { + "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": "center", + "align_self": null, + "border": null, + "bottom": null, + "display": "flex", + "flex": null, + "flex_flow": "column", + "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": "50%" + } + }, + "aec899db50df4647ae5ac36c07ee294f": { + "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 + } + }, + "d5f8193d213d4860aaa0c842ba7c9c07": { + "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": "" + } + }, + "eed45bc885fd4adcbce829b0c9afbf48": { + "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 + } + }, + "d2fdd03aa4e148bcac64eab9229af61c": { + "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": "" + } + }, + "917ad72239a24a2ca19578077bd3f190": { + "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 + } + }, + "c08f5bb3f3b0400eac10e333a78f30b8": { + "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": "" + } + }, + "8594f76b97fa4814a5ae0235f3ad0961": { + "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 + } + }, + "bea5cf62b00b446bb2ef49329771a398": { + "model_module": "@jupyter-widgets/controls", + "model_name": "ButtonStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ButtonStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "button_color": null, + "font_weight": "" + } + }, + "a1667ab01c674d93b8456e84ea587d03": { + "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 + } + }, + "1504ebc3efdf41b5854a6596a175aedb": { + "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": "" + } + }, + "7b5c33a1c5b44424b673c2d7611013e9": { + "model_module": "@jupyter-widgets/controls", + "model_name": "LabelModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "LabelModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "LabelView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_468b9dc57b164213b7e58acc369f5c0d", + "placeholder": "​", + "style": "IPY_MODEL_7923884bad934c0ca2c1a47529d65325", + "value": "Connecting..." + } + }, + "468b9dc57b164213b7e58acc369f5c0d": { + "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 + } + }, + "7923884bad934c0ca2c1a47529d65325": { + "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": "" + } + }, + "6bba1b4558b0432aa44c558e5d4ebdf8": { + "model_module": "@jupyter-widgets/controls", + "model_name": "LabelModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "LabelModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "LabelView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_505b4a8563564747a4f4ac0934ce58ca", + "placeholder": "​", + "style": "IPY_MODEL_fd9c755b79314b858fe405bf087f80f6", + "value": "Token is valid (permission: write)." + } + }, + "4ac3b065ad9546398e2691ceb371c233": { + "model_module": "@jupyter-widgets/controls", + "model_name": "LabelModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "LabelModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "LabelView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_8a7d1ba404dd49a1bb517d12f7a993f6", + "placeholder": "​", + "style": "IPY_MODEL_18d9e77db3da4e23902226007712d51d", + "value": "Your token has been saved in your configured git credential helpers (store)." + } + }, + "accba8f890814d5f92464b3471966bbf": { + "model_module": "@jupyter-widgets/controls", + "model_name": "LabelModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "LabelModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "LabelView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_a30e755f34e142f8baab95721c9b9870", + "placeholder": "​", + "style": "IPY_MODEL_15d307d0cd1540f6af402f319a668e05", + "value": "Your token has been saved to /root/.cache/huggingface/token" + } + }, + "bb0db85e948443019c9d645280175b47": { + "model_module": "@jupyter-widgets/controls", + "model_name": "LabelModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "LabelModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "LabelView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_87ce8a9512264f15b3804982249aed56", + "placeholder": "​", + "style": "IPY_MODEL_da3475cbed5240c3a5b860377caa0697", + "value": "Login successful" + } + }, + "505b4a8563564747a4f4ac0934ce58ca": { + "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 + } + }, + "fd9c755b79314b858fe405bf087f80f6": { + "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": "" + } + }, + "8a7d1ba404dd49a1bb517d12f7a993f6": { + "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 + } + }, + "18d9e77db3da4e23902226007712d51d": { + "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": "" + } + }, + "a30e755f34e142f8baab95721c9b9870": { + "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 + } + }, + "15d307d0cd1540f6af402f319a668e05": { + "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": "" + } + }, + "87ce8a9512264f15b3804982249aed56": { + "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 + } + }, + "da3475cbed5240c3a5b860377caa0697": { + "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": "" + } + }, + "ac5e93b72ad84752b974c04b8f4b51f9": { + "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_595a2f42de714f18a84afa6285659917", + "IPY_MODEL_02a3c25f3e0a4a6d96e45b7b3498bee3", + "IPY_MODEL_213c1c2d6d894b41928b06676c2a85a3" + ], + "layout": "IPY_MODEL_17eeebd01aff4bfba2aa60981ad04cb7" + } + }, + "595a2f42de714f18a84afa6285659917": { + "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_94d14274f2b7457d96dca9e428052fb5", + "placeholder": "​", + "style": "IPY_MODEL_3c30f1269ee94513b3e9e7d956b6ecb5", + "value": "config.json: 100%" + } + }, + "02a3c25f3e0a4a6d96e45b7b3498bee3": { + "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_eb104275736f40c0a81dd9edbcad19e3", + "max": 700, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_b391ef4a80334864bc7d30949da49c23", + "value": 700 + } + }, + "213c1c2d6d894b41928b06676c2a85a3": { + "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_6e240a79806744f08df735a282e6725e", + "placeholder": "​", + "style": "IPY_MODEL_76e63eb18b094e94a85435668c52ff1e", + "value": " 700/700 [00:00<00:00, 26.7kB/s]" + } + }, + "17eeebd01aff4bfba2aa60981ad04cb7": { + "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 + } + }, + "94d14274f2b7457d96dca9e428052fb5": { + "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 + } + }, + "3c30f1269ee94513b3e9e7d956b6ecb5": { + "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": "" + } + }, + "eb104275736f40c0a81dd9edbcad19e3": { + "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 + } + }, + "b391ef4a80334864bc7d30949da49c23": { + "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": "" + } + }, + "6e240a79806744f08df735a282e6725e": { + "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 + } + }, + "76e63eb18b094e94a85435668c52ff1e": { + "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": "" + } + }, + "1fc1ff1816834137915e52e70d4c917d": { + "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_98718e4f687c49d5a20c2a629ff0469a", + "IPY_MODEL_fb04e6c11c444b9abd5f463cc8b46265", + "IPY_MODEL_33f085f426774d6f972080287dd0c437" + ], + "layout": "IPY_MODEL_3b1e906cec344cbaac4ccb7a48187425" + } + }, + "98718e4f687c49d5a20c2a629ff0469a": { + "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_5cc3a36008ac4f2087b98648fd700ee3", + "placeholder": "​", + "style": "IPY_MODEL_df4d348d5ec5406bbdb474d20673c645", + "value": "model.safetensors: 100%" + } + }, + "fb04e6c11c444b9abd5f463cc8b46265": { + "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_c02c433ec2e64c099e7da34cd3d205ec", + "max": 12121539344, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_57b5060a7b2a456a9b831d873abeb7eb", + "value": 12121539344 + } + }, + "33f085f426774d6f972080287dd0c437": { + "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_8513434391504f609724d09b10b07ff3", + "placeholder": "​", + "style": "IPY_MODEL_b842553532ed4de788baa84c872fd965", + "value": " 12.1G/12.1G [01:24<00:00, 105MB/s]" + } + }, + "3b1e906cec344cbaac4ccb7a48187425": { + "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 + } + }, + "5cc3a36008ac4f2087b98648fd700ee3": { + "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 + } + }, + "df4d348d5ec5406bbdb474d20673c645": { + "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": "" + } + }, + "c02c433ec2e64c099e7da34cd3d205ec": { + "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 + } + }, + "57b5060a7b2a456a9b831d873abeb7eb": { + "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": "" + } + }, + "8513434391504f609724d09b10b07ff3": { + "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 + } + }, + "b842553532ed4de788baa84c872fd965": { + "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": "" + } + }, + "1756abe3f1c945309c4850ea7edf53c3": { + "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_aaa81f1b7f56417391118bce6b954d31", + "IPY_MODEL_eccee39b070c4e48a8a05249e73a00bf", + "IPY_MODEL_c00e5e033d154908a639190e7f31ebbc" + ], + "layout": "IPY_MODEL_9f7435b84b314146a12760549e405ecd" + } + }, + "aaa81f1b7f56417391118bce6b954d31": { + "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_3faa7cfc5c8c486992f0aaae8f2c049d", + "placeholder": "​", + "style": "IPY_MODEL_0d01332406a2400dac1a88671c0d9c49", + "value": "Downloading readme: 100%" + } + }, + "eccee39b070c4e48a8a05249e73a00bf": { + "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_eb501c7b4e86403a9179fc1f262d36db", + "max": 3302, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_9a3edf74b7204c7f829dba42694ff04b", + "value": 3302 + } + }, + "c00e5e033d154908a639190e7f31ebbc": { + "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_799545200e8542aca53babb5fc26f2a1", + "placeholder": "​", + "style": "IPY_MODEL_4049302bc5ba4f919b07d957e48197ec", + "value": " 3.30k/3.30k [00:00<00:00, 204kB/s]" + } + }, + "9f7435b84b314146a12760549e405ecd": { + "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 + } + }, + "3faa7cfc5c8c486992f0aaae8f2c049d": { + "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 + } + }, + "0d01332406a2400dac1a88671c0d9c49": { + "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": "" + } + }, + "eb501c7b4e86403a9179fc1f262d36db": { + "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 + } + }, + "9a3edf74b7204c7f829dba42694ff04b": { + "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": "" + } + }, + "799545200e8542aca53babb5fc26f2a1": { + "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 + } + }, + "4049302bc5ba4f919b07d957e48197ec": { + "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": "" + } + }, + "81be94da65914dff85a41ad123ab7245": { + "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_6dcead4c258d41fb93ca5b1a036a63be", + "IPY_MODEL_df833f4e9b084c8e8c1fec08d85a1178", + "IPY_MODEL_e6c7cb83e6264b8193ea41dffc2e68e5" + ], + "layout": "IPY_MODEL_f00235276ec44e338e54dd3f8aba8bf7" + } + }, + "6dcead4c258d41fb93ca5b1a036a63be": { + "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_26c6d218bf184fffaf61095e94d137ea", + "placeholder": "​", + "style": "IPY_MODEL_ee4addeb906f4cd9af90d9c5907f2f3a", + "value": "Downloading data: 100%" + } + }, + "df833f4e9b084c8e8c1fec08d85a1178": { + "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_3a11aa6dd86444c4b5ed304d7fc72e84", + "max": 158040830, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_0b3289489db64bc695dbcaacf7c383c2", + "value": 158040830 + } + }, + "e6c7cb83e6264b8193ea41dffc2e68e5": { + "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_0bf58a8cdc5f4a28a3f2fce6d6099839", + "placeholder": "​", + "style": "IPY_MODEL_55ea809c6cac4e9487ca84271888fa44", + "value": " 158M/158M [00:22<00:00, 7.44MB/s]" + } + }, + "f00235276ec44e338e54dd3f8aba8bf7": { + "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 + } + }, + "26c6d218bf184fffaf61095e94d137ea": { + "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 + } + }, + "ee4addeb906f4cd9af90d9c5907f2f3a": { + "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": "" + } + }, + "3a11aa6dd86444c4b5ed304d7fc72e84": { + "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 + } + }, + "0b3289489db64bc695dbcaacf7c383c2": { + "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": "" + } + }, + "0bf58a8cdc5f4a28a3f2fce6d6099839": { + "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 + } + }, + "55ea809c6cac4e9487ca84271888fa44": { + "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": "" + } + }, + "8144f11931cd43dd83f6c6105c77148c": { + "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_87ae209b51f6419b9d946dfe0761b419", + "IPY_MODEL_76bfaa03980346df9c4e3546320c48b4", + "IPY_MODEL_c1621007cdb84ad6816a3cdd504236fd" + ], + "layout": "IPY_MODEL_cb5f92092a7244b89352ed2c1c8ee2b2" + } + }, + "87ae209b51f6419b9d946dfe0761b419": { + "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_e344fee89bf64365afce471ea8869383", + "placeholder": "​", + "style": "IPY_MODEL_0ea57b58135046fd9779f1c591b07846", + "value": "Generating train split: " + } + }, + "76bfaa03980346df9c4e3546320c48b4": { + "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_2687cbf6b58e470385fdbba0c1c36250", + "max": 1, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_ab7b72a1d40147d58c4cd17d2220761c", + "value": 1 + } + }, + "c1621007cdb84ad6816a3cdd504236fd": { + "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_655e8f1ac2384cc685541a4c0658fc67", + "placeholder": "​", + "style": "IPY_MODEL_a57e6e531c2547e5be36d63cfbc82367", + "value": " 10000/0 [00:01<00:00, 7559.84 examples/s]" + } + }, + "cb5f92092a7244b89352ed2c1c8ee2b2": { + "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 + } + }, + "e344fee89bf64365afce471ea8869383": { + "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 + } + }, + "0ea57b58135046fd9779f1c591b07846": { + "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": "" + } + }, + "2687cbf6b58e470385fdbba0c1c36250": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": "20px" + } + }, + "ab7b72a1d40147d58c4cd17d2220761c": { + "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": "" + } + }, + "655e8f1ac2384cc685541a4c0658fc67": { + "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 + } + }, + "a57e6e531c2547e5be36d63cfbc82367": { + "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": "" + } + }, + "646a4fc394534c4ebf99c28954687415": { + "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_f2b7859f61c74cb39875b7b817319c11", + "IPY_MODEL_22cbb36078fe4571ae4e85d7e61dfbff", + "IPY_MODEL_d20021af6fc8426688335f600bdc7cd7" + ], + "layout": "IPY_MODEL_24354a4974284c8eb6399e2d79930c48" + } + }, + "f2b7859f61c74cb39875b7b817319c11": { + "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_dbfa10aab4b14e138a38b4053dd798f3", + "placeholder": "​", + "style": "IPY_MODEL_058a015021a54f4dbf1d2f537b1815e0", + "value": "tokenizer_config.json: 100%" + } + }, + "22cbb36078fe4571ae4e85d7e61dfbff": { + "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_c6c2660f516a40148f8292369f97e351", + "max": 7877, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_493dd540e403418d954f0a5e90882d0c", + "value": 7877 + } + }, + "d20021af6fc8426688335f600bdc7cd7": { + "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_3aa94ea4e4c24c47a55a5c8246eff0a3", + "placeholder": "​", + "style": "IPY_MODEL_627cc61dfc1f4496966b04e02a5be337", + "value": " 7.88k/7.88k [00:00<00:00, 462kB/s]" + } + }, + "24354a4974284c8eb6399e2d79930c48": { + "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 + } + }, + "dbfa10aab4b14e138a38b4053dd798f3": { + "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 + } + }, + "058a015021a54f4dbf1d2f537b1815e0": { + "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": "" + } + }, + "c6c2660f516a40148f8292369f97e351": { + "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 + } + }, + "493dd540e403418d954f0a5e90882d0c": { + "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": "" + } + }, + "3aa94ea4e4c24c47a55a5c8246eff0a3": { + "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 + } + }, + "627cc61dfc1f4496966b04e02a5be337": { + "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": "" + } + }, + "b35b1837f69e4df887acaaaeb31e6bcd": { + "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_56cb96aa6c9d4a17a522afdaa7c364a4", + "IPY_MODEL_ccfefb3fdedc4b4ca10faa9d9cd2048f", + "IPY_MODEL_e41cec5e54904ab49d61944655aaff88" + ], + "layout": "IPY_MODEL_695e4e8b824844a5840ac260fb8e04fb" + } + }, + "56cb96aa6c9d4a17a522afdaa7c364a4": { + "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_80a902fa11d5466386b0b2982ffd47ae", + "placeholder": "​", + "style": "IPY_MODEL_d0f6c9bd037d43c59ea781b772c4add7", + "value": "vocab.json: 100%" + } + }, + "ccfefb3fdedc4b4ca10faa9d9cd2048f": { + "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_419b88c918764f5f8326927b6e134891", + "max": 777202, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_60e56e1bef8b48d8bab7a9cc0f75194e", + "value": 777202 + } + }, + "e41cec5e54904ab49d61944655aaff88": { + "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_a9282e4d38f443f1b313fc88d41e10ff", + "placeholder": "​", + "style": "IPY_MODEL_25631d86db9342558569d74f62af26a1", + "value": " 777k/777k [00:00<00:00, 4.22MB/s]" + } + }, + "695e4e8b824844a5840ac260fb8e04fb": { + "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 + } + }, + "80a902fa11d5466386b0b2982ffd47ae": { + "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 + } + }, + "d0f6c9bd037d43c59ea781b772c4add7": { + "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": "" + } + }, + "419b88c918764f5f8326927b6e134891": { + "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 + } + }, + "60e56e1bef8b48d8bab7a9cc0f75194e": { + "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": "" + } + }, + "a9282e4d38f443f1b313fc88d41e10ff": { + "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 + } + }, + "25631d86db9342558569d74f62af26a1": { + "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": "" + } + }, + "2513457b311444e6b88be9b9dd3a36a9": { + "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_aecd1317708843f683505a0fc2a149a5", + "IPY_MODEL_a8d18e08a61d4a558b72df74564b35e8", + "IPY_MODEL_6d31885ff5ab4e61bdb28d83a3667573" + ], + "layout": "IPY_MODEL_e85efef9c567460391ca8ba29282d88c" + } + }, + "aecd1317708843f683505a0fc2a149a5": { + "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_870235731ae54eda8c05f4a016a9350a", + "placeholder": "​", + "style": "IPY_MODEL_32fccbc1a3de400484ff9f1fef764324", + "value": "merges.txt: 100%" + } + }, + "a8d18e08a61d4a558b72df74564b35e8": { + "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_69dc5d5004af457fae599ddeac72af3b", + "max": 441705, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_680f00ce60f54e3ea2391f88ec77aca2", + "value": 441705 + } + }, + "6d31885ff5ab4e61bdb28d83a3667573": { + "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_efe4495376db4cba9f3199b5b3c3890c", + "placeholder": "​", + "style": "IPY_MODEL_5f7bd750e403447e93b5fa14e4c211a7", + "value": " 442k/442k [00:00<00:00, 30.8MB/s]" + } + }, + "e85efef9c567460391ca8ba29282d88c": { + "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 + } + }, + "870235731ae54eda8c05f4a016a9350a": { + "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 + } + }, + "32fccbc1a3de400484ff9f1fef764324": { + "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": "" + } + }, + "69dc5d5004af457fae599ddeac72af3b": { + "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 + } + }, + "680f00ce60f54e3ea2391f88ec77aca2": { + "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": "" + } + }, + "efe4495376db4cba9f3199b5b3c3890c": { + "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 + } + }, + "5f7bd750e403447e93b5fa14e4c211a7": { + "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": "" + } + }, + "ff4fee480b184d9fadc1e4e15a3bf95d": { + "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_dbf8025e542940cca0ec3e325c237fc0", + "IPY_MODEL_f2ac0170745b4b008520fc58a978bd41", + "IPY_MODEL_bef691089e0048feb2d93485caafc43b" + ], + "layout": "IPY_MODEL_9bdc297a1be24b46b3b8019aedbff158" + } + }, + "dbf8025e542940cca0ec3e325c237fc0": { + "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_a858d85200684a4ea825cb2c1309eba1", + "placeholder": "​", + "style": "IPY_MODEL_60e967512bf64d118adaa771d1ed7ae2", + "value": "tokenizer.json: 100%" + } + }, + "f2ac0170745b4b008520fc58a978bd41": { + "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_f3dcf437ccbb4a0fbe0bfd97fcdd7025", + "max": 2060919, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_2372a60079a9467a886019863946de6c", + "value": 2060919 + } + }, + "bef691089e0048feb2d93485caafc43b": { + "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_5789ec36c69b40a091ccfaac4e719ceb", + "placeholder": "​", + "style": "IPY_MODEL_6904515f20fe45fcb54c954ee4f50216", + "value": " 2.06M/2.06M [00:00<00:00, 6.67MB/s]" + } + }, + "9bdc297a1be24b46b3b8019aedbff158": { + "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 + } + }, + "a858d85200684a4ea825cb2c1309eba1": { + "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 + } + }, + "60e967512bf64d118adaa771d1ed7ae2": { + "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": "" + } + }, + "f3dcf437ccbb4a0fbe0bfd97fcdd7025": { + "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 + } + }, + "2372a60079a9467a886019863946de6c": { + "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": "" + } + }, + "5789ec36c69b40a091ccfaac4e719ceb": { + "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 + } + }, + "6904515f20fe45fcb54c954ee4f50216": { + "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": "" + } + }, + "d4fb19288f8a47b39805aa9d0683b1c8": { + "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_24c48b1ab4d54ea98ed13457ddcd997b", + "IPY_MODEL_c29532e36d33437b9f4f943d77b4dd59", + "IPY_MODEL_9142737465e2441d94091244c1597898" + ], + "layout": "IPY_MODEL_965991b2ed3e4180b837d81990943cf2" + } + }, + "24c48b1ab4d54ea98ed13457ddcd997b": { + "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_4b33ac8b868747d78ff11d7c887737eb", + "placeholder": "​", + "style": "IPY_MODEL_ceacee8c50524687a5bd18427e442c6d", + "value": "special_tokens_map.json: 100%" + } + }, + "c29532e36d33437b9f4f943d77b4dd59": { + "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_2589f0a4872c4ff8ba3eba0c4d6a2d3e", + "max": 958, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_fee2ced1fa644a65b7bed410a43f6bcb", + "value": 958 + } + }, + "9142737465e2441d94091244c1597898": { + "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_3b3912eedf5d421eaee802c99965466b", + "placeholder": "​", + "style": "IPY_MODEL_139794710d3b49c688f00cb81cdacc4f", + "value": " 958/958 [00:00<00:00, 61.6kB/s]" + } + }, + "965991b2ed3e4180b837d81990943cf2": { + "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 + } + }, + "4b33ac8b868747d78ff11d7c887737eb": { + "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 + } + }, + "ceacee8c50524687a5bd18427e442c6d": { + "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": "" + } + }, + "2589f0a4872c4ff8ba3eba0c4d6a2d3e": { + "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 + } + }, + "fee2ced1fa644a65b7bed410a43f6bcb": { + "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": "" + } + }, + "3b3912eedf5d421eaee802c99965466b": { + "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 + } + }, + "139794710d3b49c688f00cb81cdacc4f": { + "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": "" + } + }, + "050a699a05124be795092f99afafff51": { + "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_1a58bd80107744fe9fd43127c95a31b4", + "IPY_MODEL_2390cf93ec524486a1887c18f1355f3e", + "IPY_MODEL_71efa66726994a7995385953cf9901c8" + ], + "layout": "IPY_MODEL_c67495f5f6334b93a8d860140ce22103" + } + }, + "1a58bd80107744fe9fd43127c95a31b4": { + "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_24742629adec40d19ae71d1be953b14b", + "placeholder": "​", + "style": "IPY_MODEL_699021597d3b46548b6272a5ac54f3ce", + "value": "Map: 100%" + } + }, + "2390cf93ec524486a1887c18f1355f3e": { + "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_43c7388594d849c6b0f3b7002c8d0e04", + "max": 10000, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_3d7cb9d6d77040e890ec864e613a2edb", + "value": 10000 + } + }, + "71efa66726994a7995385953cf9901c8": { + "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_56da6bb3b3a84a7a82907fdb314cdb69", + "placeholder": "​", + "style": "IPY_MODEL_1da9ad06b499439d8d8359f6156fcf8d", + "value": " 10000/10000 [03:00<00:00, 62.10 examples/s]" + } + }, + "c67495f5f6334b93a8d860140ce22103": { + "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 + } + }, + "24742629adec40d19ae71d1be953b14b": { + "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 + } + }, + "699021597d3b46548b6272a5ac54f3ce": { + "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": "" + } + }, + "43c7388594d849c6b0f3b7002c8d0e04": { + "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 + } + }, + "3d7cb9d6d77040e890ec864e613a2edb": { + "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": "" + } + }, + "56da6bb3b3a84a7a82907fdb314cdb69": { + "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 + } + }, + "1da9ad06b499439d8d8359f6156fcf8d": { + "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": "" + } + }, + "d703edc27af048da83dbbbc1c2b2300f": { + "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_e613228e7a9741a9b9600549b8000e83", + "IPY_MODEL_b9ca1c6ebd264dfcb34628323d678bfb", + "IPY_MODEL_e2965aaf069346cf9a4d3dd65c28a78f" + ], + "layout": "IPY_MODEL_27057a26339e4f2cae7f9cd303143ee5" + } + }, + "e613228e7a9741a9b9600549b8000e83": { + "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_f346f035b8cc4b21a753bddf040bda77", + "placeholder": "​", + "style": "IPY_MODEL_5b0752a53bd749f29ba244e012cbb5c0", + "value": "model.safetensors: 100%" + } + }, + "b9ca1c6ebd264dfcb34628323d678bfb": { + "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_2cc86efa5a7c4b408519ce873cfa3f7b", + "max": 2245371860, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_ac3042c7e79a43b2a5894087b06e8f9c", + "value": 2245371860 + } + }, + "e2965aaf069346cf9a4d3dd65c28a78f": { + "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_309cc692723d4c69938e97aa1dd34334", + "placeholder": "​", + "style": "IPY_MODEL_da336fed4e414d6196c5e1c821aac58f", + "value": " 2.25G/2.25G [00:56<00:00, 37.6MB/s]" + } + }, + "27057a26339e4f2cae7f9cd303143ee5": { + "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 + } + }, + "f346f035b8cc4b21a753bddf040bda77": { + "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 + } + }, + "5b0752a53bd749f29ba244e012cbb5c0": { + "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": "" + } + }, + "2cc86efa5a7c4b408519ce873cfa3f7b": { + "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 + } + }, + "ac3042c7e79a43b2a5894087b06e8f9c": { + "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": "" + } + }, + "309cc692723d4c69938e97aa1dd34334": { + "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 + } + }, + "da336fed4e414d6196c5e1c821aac58f": { + "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": "" + } + }, + "ae3ca4f42c1e42bb95663d01f76cff44": { + "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_d319697500914bbea3ea00a082046735", + "IPY_MODEL_864ac8715b344559bc32b366c22ed120", + "IPY_MODEL_d07da602cff649c89653a070f11cd7d9" + ], + "layout": "IPY_MODEL_232dcf4bebe347558d9246988f9297cc" + } + }, + "d319697500914bbea3ea00a082046735": { + "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_ebf2ea8c28bd44c78a6315b2edfe9533", + "placeholder": "​", + "style": "IPY_MODEL_30f4904bf9db4ed993b7494c32312b89", + "value": "Upload 3 LFS files: 100%" + } + }, + "864ac8715b344559bc32b366c22ed120": { + "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_25908616492b43529a70d377ffa67f46", + "max": 3, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_1cbb793261cf489b9b7e955afecfe18d", + "value": 3 + } + }, + "d07da602cff649c89653a070f11cd7d9": { + "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_5c966b0fd0ca49469335466b0d95f481", + "placeholder": "​", + "style": "IPY_MODEL_3325008942994d5d9804d0dbeca0683f", + "value": " 3/3 [00:56<00:00, 33.16s/it]" + } + }, + "232dcf4bebe347558d9246988f9297cc": { + "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 + } + }, + "ebf2ea8c28bd44c78a6315b2edfe9533": { + "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 + } + }, + "30f4904bf9db4ed993b7494c32312b89": { + "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": "" + } + }, + "25908616492b43529a70d377ffa67f46": { + "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 + } + }, + "1cbb793261cf489b9b7e955afecfe18d": { + "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": "" + } + }, + "5c966b0fd0ca49469335466b0d95f481": { + "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 + } + }, + "3325008942994d5d9804d0dbeca0683f": { + "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": "" + } + }, + "2a466ebd1c294da69f0ea6834c86102e": { + "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_fe707e7bd7d847738644da570c5d69ca", + "IPY_MODEL_51c7c1b43fe74bea9763f5215f4bd0ae", + "IPY_MODEL_faf70d38ae5048a1b661eb17e56c35b7" + ], + "layout": "IPY_MODEL_3a3a6d72eeef4846bad8987c0f5f98dd" + } + }, + "fe707e7bd7d847738644da570c5d69ca": { + "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_2f939d69a04241eea33743770ce6bb1a", + "placeholder": "​", + "style": "IPY_MODEL_b0f752a283894ad580cec435e7add34d", + "value": "training_args.bin: 100%" + } + }, + "51c7c1b43fe74bea9763f5215f4bd0ae": { + "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_a3b6c7f8cb6a4c43ba17427ee414808b", + "max": 4920, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_7a702890a92b4220b5c46293476b7752", + "value": 4920 + } + }, + "faf70d38ae5048a1b661eb17e56c35b7": { + "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_8e80290d0db547209a2b3dc3ccbac976", + "placeholder": "​", + "style": "IPY_MODEL_5fdeba11def34cfbbcf8273add3d75b0", + "value": " 4.92k/4.92k [00:00<00:00, 17.6kB/s]" + } + }, + "3a3a6d72eeef4846bad8987c0f5f98dd": { + "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 + } + }, + "2f939d69a04241eea33743770ce6bb1a": { + "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 + } + }, + "b0f752a283894ad580cec435e7add34d": { + "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": "" + } + }, + "a3b6c7f8cb6a4c43ba17427ee414808b": { + "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 + } + }, + "7a702890a92b4220b5c46293476b7752": { + "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": "" + } + }, + "8e80290d0db547209a2b3dc3ccbac976": { + "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 + } + }, + "5fdeba11def34cfbbcf8273add3d75b0": { + "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": "" + } + }, + "126d9b8f5a5f436b9f16ad7171fb91b8": { + "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_c9f70ce3fa3b45eb9e077a6477114ed5", + "IPY_MODEL_f20df2aa6d164766991789c629494990", + "IPY_MODEL_639d34946dc74f978a551191b54050e2" + ], + "layout": "IPY_MODEL_5d7d12397d1b42ee9f8b1c10ac802c89" + } + }, + "c9f70ce3fa3b45eb9e077a6477114ed5": { + "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_7eb14ebcb61343e095ff69c7ffc027cd", + "placeholder": "​", + "style": "IPY_MODEL_2afb975011384469b18b79dd8c8d9951", + "value": "adapter_model.safetensors: 100%" + } + }, + "f20df2aa6d164766991789c629494990": { + "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_1aaf67fcf8e3410089c0710d962d6e22", + "max": 18218008, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_6bf5f75ef0054b579ecee9129b3282c4", + "value": 18218008 + } + }, + "639d34946dc74f978a551191b54050e2": { + "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_280caf0602a44c1d964fe1736cd3f41e", + "placeholder": "​", + "style": "IPY_MODEL_0ec3acf0d68c49b8bbd612a43cb3f9de", + "value": " 18.2M/18.2M [00:01<00:00, 19.7MB/s]" + } + }, + "5d7d12397d1b42ee9f8b1c10ac802c89": { + "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 + } + }, + "7eb14ebcb61343e095ff69c7ffc027cd": { + "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 + } + }, + "2afb975011384469b18b79dd8c8d9951": { + "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": "" + } + }, + "1aaf67fcf8e3410089c0710d962d6e22": { + "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 + } + }, + "6bf5f75ef0054b579ecee9129b3282c4": { + "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": "" + } + }, + "280caf0602a44c1d964fe1736cd3f41e": { + "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 + } + }, + "0ec3acf0d68c49b8bbd612a43cb3f9de": { + "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": "" + } + } + } + } + }, + "nbformat_minor": 0, + "nbformat": 4, + "cells": [ + { + "cell_type": "code", + "source": [ + "!pip install torchvision\n", + "!pip install torchaudio" + ], + "metadata": { + "execution": { + "iopub.status.busy": "2024-03-19T20:02:16.165964Z", + "iopub.execute_input": "2024-03-19T20:02:16.166770Z", + "iopub.status.idle": "2024-03-19T20:02:37.929017Z", + "shell.execute_reply.started": "2024-03-19T20:02:16.166735Z", + "shell.execute_reply": "2024-03-19T20:02:37.928090Z" + }, + "trusted": true, + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "QOzZcFl_0sZ1", + "outputId": "654959dc-c83e-4541-b1fa-1177b973d358" + }, + "execution_count": null, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Requirement already satisfied: torchvision in /usr/local/lib/python3.10/dist-packages (0.17.1+cu121)\n", + "Requirement already satisfied: numpy in /usr/local/lib/python3.10/dist-packages (from torchvision) (1.25.2)\n", + "Requirement already satisfied: torch==2.2.1 in /usr/local/lib/python3.10/dist-packages (from torchvision) (2.2.1+cu121)\n", + "Requirement already satisfied: pillow!=8.3.*,>=5.3.0 in /usr/local/lib/python3.10/dist-packages (from torchvision) (9.4.0)\n", + "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from torch==2.2.1->torchvision) (3.13.1)\n", + "Requirement already satisfied: typing-extensions>=4.8.0 in /usr/local/lib/python3.10/dist-packages (from torch==2.2.1->torchvision) (4.10.0)\n", + "Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch==2.2.1->torchvision) (1.12)\n", + "Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch==2.2.1->torchvision) (3.2.1)\n", + "Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch==2.2.1->torchvision) (3.1.3)\n", + "Requirement already satisfied: fsspec in /usr/local/lib/python3.10/dist-packages (from torch==2.2.1->torchvision) (2023.6.0)\n", + "Collecting nvidia-cuda-nvrtc-cu12==12.1.105 (from torch==2.2.1->torchvision)\n", + " Downloading nvidia_cuda_nvrtc_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (23.7 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m23.7/23.7 MB\u001b[0m \u001b[31m37.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hCollecting nvidia-cuda-runtime-cu12==12.1.105 (from torch==2.2.1->torchvision)\n", + " Downloading nvidia_cuda_runtime_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (823 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m823.6/823.6 kB\u001b[0m \u001b[31m47.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hCollecting nvidia-cuda-cupti-cu12==12.1.105 (from torch==2.2.1->torchvision)\n", + " Downloading nvidia_cuda_cupti_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (14.1 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m14.1/14.1 MB\u001b[0m \u001b[31m75.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hCollecting nvidia-cudnn-cu12==8.9.2.26 (from torch==2.2.1->torchvision)\n", + " Downloading nvidia_cudnn_cu12-8.9.2.26-py3-none-manylinux1_x86_64.whl (731.7 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m731.7/731.7 MB\u001b[0m \u001b[31m2.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hCollecting nvidia-cublas-cu12==12.1.3.1 (from torch==2.2.1->torchvision)\n", + " Downloading nvidia_cublas_cu12-12.1.3.1-py3-none-manylinux1_x86_64.whl (410.6 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m410.6/410.6 MB\u001b[0m \u001b[31m2.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hCollecting nvidia-cufft-cu12==11.0.2.54 (from torch==2.2.1->torchvision)\n", + " Downloading nvidia_cufft_cu12-11.0.2.54-py3-none-manylinux1_x86_64.whl (121.6 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m121.6/121.6 MB\u001b[0m \u001b[31m8.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hCollecting nvidia-curand-cu12==10.3.2.106 (from torch==2.2.1->torchvision)\n", + " Downloading nvidia_curand_cu12-10.3.2.106-py3-none-manylinux1_x86_64.whl (56.5 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m56.5/56.5 MB\u001b[0m \u001b[31m13.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hCollecting nvidia-cusolver-cu12==11.4.5.107 (from torch==2.2.1->torchvision)\n", + " Downloading nvidia_cusolver_cu12-11.4.5.107-py3-none-manylinux1_x86_64.whl (124.2 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m124.2/124.2 MB\u001b[0m \u001b[31m8.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hCollecting nvidia-cusparse-cu12==12.1.0.106 (from torch==2.2.1->torchvision)\n", + " Downloading nvidia_cusparse_cu12-12.1.0.106-py3-none-manylinux1_x86_64.whl (196.0 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m196.0/196.0 MB\u001b[0m \u001b[31m6.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hCollecting nvidia-nccl-cu12==2.19.3 (from torch==2.2.1->torchvision)\n", + " Downloading nvidia_nccl_cu12-2.19.3-py3-none-manylinux1_x86_64.whl (166.0 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m166.0/166.0 MB\u001b[0m \u001b[31m7.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hCollecting nvidia-nvtx-cu12==12.1.105 (from torch==2.2.1->torchvision)\n", + " Downloading nvidia_nvtx_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (99 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m99.1/99.1 kB\u001b[0m \u001b[31m12.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hRequirement already satisfied: triton==2.2.0 in /usr/local/lib/python3.10/dist-packages (from torch==2.2.1->torchvision) (2.2.0)\n", + "Collecting nvidia-nvjitlink-cu12 (from nvidia-cusolver-cu12==11.4.5.107->torch==2.2.1->torchvision)\n", + " Downloading nvidia_nvjitlink_cu12-12.4.99-py3-none-manylinux2014_x86_64.whl (21.1 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m21.1/21.1 MB\u001b[0m \u001b[31m56.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hRequirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->torch==2.2.1->torchvision) (2.1.5)\n", + "Requirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/dist-packages (from sympy->torch==2.2.1->torchvision) (1.3.0)\n", + "Installing collected packages: nvidia-nvtx-cu12, nvidia-nvjitlink-cu12, nvidia-nccl-cu12, nvidia-curand-cu12, nvidia-cufft-cu12, nvidia-cuda-runtime-cu12, nvidia-cuda-nvrtc-cu12, nvidia-cuda-cupti-cu12, nvidia-cublas-cu12, nvidia-cusparse-cu12, nvidia-cudnn-cu12, nvidia-cusolver-cu12\n", + "Successfully installed 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-cu12-12.4.99 nvidia-nvtx-cu12-12.1.105\n", + "Requirement already satisfied: torchaudio in /usr/local/lib/python3.10/dist-packages (2.2.1+cu121)\n", + "Requirement already satisfied: torch==2.2.1 in /usr/local/lib/python3.10/dist-packages (from torchaudio) (2.2.1+cu121)\n", + "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from torch==2.2.1->torchaudio) (3.13.1)\n", + "Requirement already satisfied: typing-extensions>=4.8.0 in /usr/local/lib/python3.10/dist-packages (from torch==2.2.1->torchaudio) (4.10.0)\n", + "Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch==2.2.1->torchaudio) (1.12)\n", + "Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch==2.2.1->torchaudio) (3.2.1)\n", + "Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch==2.2.1->torchaudio) (3.1.3)\n", + "Requirement already satisfied: fsspec in /usr/local/lib/python3.10/dist-packages (from torch==2.2.1->torchaudio) (2023.6.0)\n", + "Requirement already satisfied: nvidia-cuda-nvrtc-cu12==12.1.105 in /usr/local/lib/python3.10/dist-packages (from torch==2.2.1->torchaudio) (12.1.105)\n", + "Requirement already satisfied: nvidia-cuda-runtime-cu12==12.1.105 in /usr/local/lib/python3.10/dist-packages (from torch==2.2.1->torchaudio) (12.1.105)\n", + "Requirement already satisfied: nvidia-cuda-cupti-cu12==12.1.105 in /usr/local/lib/python3.10/dist-packages (from torch==2.2.1->torchaudio) (12.1.105)\n", + "Requirement already satisfied: nvidia-cudnn-cu12==8.9.2.26 in /usr/local/lib/python3.10/dist-packages (from torch==2.2.1->torchaudio) (8.9.2.26)\n", + "Requirement already satisfied: nvidia-cublas-cu12==12.1.3.1 in /usr/local/lib/python3.10/dist-packages (from torch==2.2.1->torchaudio) (12.1.3.1)\n", + "Requirement already satisfied: nvidia-cufft-cu12==11.0.2.54 in /usr/local/lib/python3.10/dist-packages (from torch==2.2.1->torchaudio) (11.0.2.54)\n", + "Requirement already satisfied: nvidia-curand-cu12==10.3.2.106 in /usr/local/lib/python3.10/dist-packages (from torch==2.2.1->torchaudio) (10.3.2.106)\n", + "Requirement already satisfied: nvidia-cusolver-cu12==11.4.5.107 in /usr/local/lib/python3.10/dist-packages (from torch==2.2.1->torchaudio) (11.4.5.107)\n", + "Requirement already satisfied: nvidia-cusparse-cu12==12.1.0.106 in /usr/local/lib/python3.10/dist-packages (from torch==2.2.1->torchaudio) (12.1.0.106)\n", + "Requirement already satisfied: nvidia-nccl-cu12==2.19.3 in /usr/local/lib/python3.10/dist-packages (from torch==2.2.1->torchaudio) (2.19.3)\n", + "Requirement already satisfied: nvidia-nvtx-cu12==12.1.105 in /usr/local/lib/python3.10/dist-packages (from torch==2.2.1->torchaudio) (12.1.105)\n", + "Requirement already satisfied: triton==2.2.0 in /usr/local/lib/python3.10/dist-packages (from torch==2.2.1->torchaudio) (2.2.0)\n", + "Requirement already satisfied: nvidia-nvjitlink-cu12 in /usr/local/lib/python3.10/dist-packages (from nvidia-cusolver-cu12==11.4.5.107->torch==2.2.1->torchaudio) (12.4.99)\n", + "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->torch==2.2.1->torchaudio) (2.1.5)\n", + "Requirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/dist-packages (from sympy->torch==2.2.1->torchaudio) (1.3.0)\n" + ] + } + ] + }, + { + "cell_type": "code", + "source": [ + "!pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu121" + ], + "metadata": { + "execution": { + "iopub.status.busy": "2024-03-19T20:02:37.931189Z", + "iopub.execute_input": "2024-03-19T20:02:37.931653Z", + "iopub.status.idle": "2024-03-19T20:02:50.038811Z", + "shell.execute_reply.started": "2024-03-19T20:02:37.931618Z", + "shell.execute_reply": "2024-03-19T20:02:50.037731Z" + }, + "trusted": true, + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "O4OyG3Hf0sZ2", + "outputId": "652cbe7c-4624-4a84-fc19-606e7f37f186" + }, + "execution_count": null, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Looking in indexes: https://download.pytorch.org/whl/cu121\n", + "Requirement already satisfied: torch in /usr/local/lib/python3.10/dist-packages (2.2.1+cu121)\n", + "Requirement already satisfied: torchvision in /usr/local/lib/python3.10/dist-packages (0.17.1+cu121)\n", + "Requirement already satisfied: torchaudio in /usr/local/lib/python3.10/dist-packages (2.2.1+cu121)\n", + "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from torch) (3.13.1)\n", + "Requirement already satisfied: typing-extensions>=4.8.0 in /usr/local/lib/python3.10/dist-packages (from torch) (4.10.0)\n", + "Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch) (1.12)\n", + "Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch) (3.2.1)\n", + "Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch) (3.1.3)\n", + "Requirement already satisfied: fsspec in /usr/local/lib/python3.10/dist-packages (from torch) (2023.6.0)\n", + "Requirement already satisfied: nvidia-cuda-nvrtc-cu12==12.1.105 in /usr/local/lib/python3.10/dist-packages (from torch) (12.1.105)\n", + "Requirement already satisfied: nvidia-cuda-runtime-cu12==12.1.105 in /usr/local/lib/python3.10/dist-packages (from torch) (12.1.105)\n", + "Requirement already satisfied: nvidia-cuda-cupti-cu12==12.1.105 in /usr/local/lib/python3.10/dist-packages (from torch) (12.1.105)\n", + "Requirement already satisfied: nvidia-cudnn-cu12==8.9.2.26 in /usr/local/lib/python3.10/dist-packages (from torch) (8.9.2.26)\n", + "Requirement already satisfied: nvidia-cublas-cu12==12.1.3.1 in /usr/local/lib/python3.10/dist-packages (from torch) (12.1.3.1)\n", + "Requirement already satisfied: nvidia-cufft-cu12==11.0.2.54 in /usr/local/lib/python3.10/dist-packages (from torch) (11.0.2.54)\n", + "Requirement already satisfied: nvidia-curand-cu12==10.3.2.106 in /usr/local/lib/python3.10/dist-packages (from torch) (10.3.2.106)\n", + "Requirement already satisfied: nvidia-cusolver-cu12==11.4.5.107 in /usr/local/lib/python3.10/dist-packages (from torch) (11.4.5.107)\n", + "Requirement already satisfied: nvidia-cusparse-cu12==12.1.0.106 in /usr/local/lib/python3.10/dist-packages (from torch) (12.1.0.106)\n", + "Requirement already satisfied: nvidia-nccl-cu12==2.19.3 in /usr/local/lib/python3.10/dist-packages (from torch) (2.19.3)\n", + "Requirement already satisfied: nvidia-nvtx-cu12==12.1.105 in /usr/local/lib/python3.10/dist-packages (from torch) (12.1.105)\n", + "Requirement already satisfied: triton==2.2.0 in /usr/local/lib/python3.10/dist-packages (from torch) (2.2.0)\n", + "Requirement already satisfied: nvidia-nvjitlink-cu12 in /usr/local/lib/python3.10/dist-packages (from nvidia-cusolver-cu12==11.4.5.107->torch) (12.4.99)\n", + "Requirement already satisfied: numpy in /usr/local/lib/python3.10/dist-packages (from torchvision) (1.25.2)\n", + "Requirement already satisfied: pillow!=8.3.*,>=5.3.0 in /usr/local/lib/python3.10/dist-packages (from torchvision) (9.4.0)\n", + "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->torch) (2.1.5)\n", + "Requirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/dist-packages (from sympy->torch) (1.3.0)\n" + ] + } + ] + }, + { + "cell_type": "code", + "source": [ + "!git clone https://github.com/bigcode-project/starcoder2.git" + ], + "metadata": { + "execution": { + "iopub.status.busy": "2024-03-19T20:02:50.040282Z", + "iopub.execute_input": "2024-03-19T20:02:50.040611Z", + "iopub.status.idle": "2024-03-19T20:02:51.596094Z", + "shell.execute_reply.started": "2024-03-19T20:02:50.040584Z", + "shell.execute_reply": "2024-03-19T20:02:51.595169Z" + }, + "trusted": true, + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "IVmVDux90sZ2", + "outputId": "18615f26-4591-4661-8c26-a71ae3baf0a9" + }, + "execution_count": null, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Cloning into 'starcoder2'...\n", + "remote: Enumerating objects: 44, done.\u001b[K\n", + "remote: Counting objects: 100% (44/44), done.\u001b[K\n", + "remote: Compressing objects: 100% (41/41), done.\u001b[K\n", + "remote: Total 44 (delta 19), reused 7 (delta 2), pack-reused 0\u001b[K\n", + "Receiving objects: 100% (44/44), 20.97 KiB | 3.00 MiB/s, done.\n", + "Resolving deltas: 100% (19/19), done.\n" + ] + } + ] + }, + { + "cell_type": "code", + "source": [ + "%cd \"starcoder2\"" + ], + "metadata": { + "execution": { + "iopub.status.busy": "2024-03-19T20:02:51.598325Z", + "iopub.execute_input": "2024-03-19T20:02:51.598646Z", + "iopub.status.idle": "2024-03-19T20:02:51.604661Z", + "shell.execute_reply.started": "2024-03-19T20:02:51.598620Z", + "shell.execute_reply": "2024-03-19T20:02:51.603748Z" + }, + "trusted": true, + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "C5LY2OSP0sZ2", + "outputId": "4d659936-7f47-4fab-9fc5-42ae18e9f67d" + }, + "execution_count": null, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "/content/starcoder2\n" + ] + } + ] + }, + { + "cell_type": "code", + "source": [ + "!pip install -r \"requirements.txt\"" + ], + "metadata": { + "execution": { + "iopub.status.busy": "2024-03-19T20:02:51.605843Z", + "iopub.execute_input": "2024-03-19T20:02:51.606154Z", + "iopub.status.idle": "2024-03-19T20:03:57.774917Z", + "shell.execute_reply.started": "2024-03-19T20:02:51.606124Z", + "shell.execute_reply": "2024-03-19T20:03:57.773685Z" + }, + "trusted": true, + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "FsYI5dOO0sZ3", + "outputId": "b8a59cca-17b6-4e52-a05c-3568c99e7f63" + }, + "execution_count": null, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Collecting git+https://github.com/huggingface/transformers.git (from -r requirements.txt (line 1))\n", + " Cloning https://github.com/huggingface/transformers.git to /tmp/pip-req-build-c119vx02\n", + " Running command git clone --filter=blob:none --quiet https://github.com/huggingface/transformers.git /tmp/pip-req-build-c119vx02\n", + " Resolved https://github.com/huggingface/transformers.git to commit e85654f5ec485c96223ffc294038aae036d180da\n", + " Installing build dependencies ... \u001b[?25l\u001b[?25hdone\n", + " Getting requirements to build wheel ... \u001b[?25l\u001b[?25hdone\n", + " Preparing metadata (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n", + "Collecting accelerate==0.27.1 (from -r requirements.txt (line 2))\n", + " Downloading accelerate-0.27.1-py3-none-any.whl (279 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m279.7/279.7 kB\u001b[0m \u001b[31m7.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hCollecting datasets>=2.16.1 (from -r requirements.txt (line 3))\n", + " Downloading datasets-2.18.0-py3-none-any.whl (510 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m510.5/510.5 kB\u001b[0m \u001b[31m14.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hCollecting bitsandbytes==0.41.3 (from -r requirements.txt (line 4))\n", + " Downloading bitsandbytes-0.41.3-py3-none-any.whl (92.6 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m92.6/92.6 MB\u001b[0m \u001b[31m9.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hCollecting peft==0.8.2 (from -r requirements.txt (line 5))\n", + " Downloading peft-0.8.2-py3-none-any.whl (183 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m183.4/183.4 kB\u001b[0m \u001b[31m23.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hCollecting trl==0.7.10 (from -r requirements.txt (line 6))\n", + " Downloading trl-0.7.10-py3-none-any.whl (150 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m150.9/150.9 kB\u001b[0m \u001b[31m18.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hCollecting wandb==0.16.3 (from -r requirements.txt (line 7))\n", + " Downloading wandb-0.16.3-py3-none-any.whl (2.2 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.2/2.2 MB\u001b[0m \u001b[31m56.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hRequirement already satisfied: huggingface_hub==0.20.3 in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 8)) (0.20.3)\n", + "Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from accelerate==0.27.1->-r requirements.txt (line 2)) (1.25.2)\n", + "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from accelerate==0.27.1->-r requirements.txt (line 2)) (24.0)\n", + "Requirement already satisfied: psutil in /usr/local/lib/python3.10/dist-packages (from accelerate==0.27.1->-r requirements.txt (line 2)) (5.9.5)\n", + "Requirement already satisfied: pyyaml in /usr/local/lib/python3.10/dist-packages (from accelerate==0.27.1->-r requirements.txt (line 2)) (6.0.1)\n", + "Requirement already satisfied: torch>=1.10.0 in /usr/local/lib/python3.10/dist-packages (from accelerate==0.27.1->-r requirements.txt (line 2)) (2.2.1+cu121)\n", + "Requirement already satisfied: safetensors>=0.3.1 in /usr/local/lib/python3.10/dist-packages (from accelerate==0.27.1->-r requirements.txt (line 2)) (0.4.2)\n", + "Requirement already satisfied: tqdm in /usr/local/lib/python3.10/dist-packages (from peft==0.8.2->-r requirements.txt (line 5)) (4.66.2)\n", + "Collecting tyro>=0.5.11 (from trl==0.7.10->-r requirements.txt (line 6))\n", + " Downloading tyro-0.7.3-py3-none-any.whl (79 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m79.8/79.8 kB\u001b[0m \u001b[31m10.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hRequirement already satisfied: Click!=8.0.0,>=7.1 in /usr/local/lib/python3.10/dist-packages (from wandb==0.16.3->-r requirements.txt (line 7)) (8.1.7)\n", + "Collecting GitPython!=3.1.29,>=1.0.0 (from wandb==0.16.3->-r requirements.txt (line 7))\n", + " Downloading GitPython-3.1.42-py3-none-any.whl (195 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m195.4/195.4 kB\u001b[0m \u001b[31m22.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hRequirement already satisfied: requests<3,>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from wandb==0.16.3->-r requirements.txt (line 7)) (2.31.0)\n", + "Collecting sentry-sdk>=1.0.0 (from wandb==0.16.3->-r requirements.txt (line 7))\n", + " Downloading sentry_sdk-1.43.0-py2.py3-none-any.whl (264 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m264.6/264.6 kB\u001b[0m \u001b[31m33.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hCollecting docker-pycreds>=0.4.0 (from wandb==0.16.3->-r requirements.txt (line 7))\n", + " Downloading docker_pycreds-0.4.0-py2.py3-none-any.whl (9.0 kB)\n", + "Collecting setproctitle (from wandb==0.16.3->-r requirements.txt (line 7))\n", + " Downloading setproctitle-1.3.3-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (30 kB)\n", + "Requirement already satisfied: setuptools in /usr/local/lib/python3.10/dist-packages (from wandb==0.16.3->-r requirements.txt (line 7)) (67.7.2)\n", + "Requirement already satisfied: appdirs>=1.4.3 in /usr/local/lib/python3.10/dist-packages (from wandb==0.16.3->-r requirements.txt (line 7)) (1.4.4)\n", + "Requirement already satisfied: protobuf!=4.21.0,<5,>=3.19.0 in /usr/local/lib/python3.10/dist-packages (from wandb==0.16.3->-r requirements.txt (line 7)) (3.20.3)\n", + "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from huggingface_hub==0.20.3->-r requirements.txt (line 8)) (3.13.1)\n", + "Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.10/dist-packages (from huggingface_hub==0.20.3->-r requirements.txt (line 8)) (2023.6.0)\n", + "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface_hub==0.20.3->-r requirements.txt (line 8)) (4.10.0)\n", + "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers==4.40.0.dev0->-r requirements.txt (line 1)) (2023.12.25)\n", + "Requirement already satisfied: tokenizers<0.19,>=0.14 in /usr/local/lib/python3.10/dist-packages (from transformers==4.40.0.dev0->-r requirements.txt (line 1)) (0.15.2)\n", + "Requirement already satisfied: pyarrow>=12.0.0 in /usr/local/lib/python3.10/dist-packages (from datasets>=2.16.1->-r requirements.txt (line 3)) (14.0.2)\n", + "Requirement already satisfied: pyarrow-hotfix in /usr/local/lib/python3.10/dist-packages (from datasets>=2.16.1->-r requirements.txt (line 3)) (0.6)\n", + "Collecting dill<0.3.9,>=0.3.0 (from datasets>=2.16.1->-r requirements.txt (line 3))\n", + " Downloading dill-0.3.8-py3-none-any.whl (116 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m116.3/116.3 kB\u001b[0m \u001b[31m19.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hRequirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (from datasets>=2.16.1->-r requirements.txt (line 3)) (1.5.3)\n", + "Collecting xxhash (from datasets>=2.16.1->-r requirements.txt (line 3))\n", + " Downloading xxhash-3.4.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (194 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m194.1/194.1 kB\u001b[0m \u001b[31m24.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hCollecting multiprocess (from datasets>=2.16.1->-r requirements.txt (line 3))\n", + " Downloading multiprocess-0.70.16-py310-none-any.whl (134 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m134.8/134.8 kB\u001b[0m \u001b[31m19.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hRequirement already satisfied: aiohttp in /usr/local/lib/python3.10/dist-packages (from datasets>=2.16.1->-r requirements.txt (line 3)) (3.9.3)\n", + "Requirement already satisfied: six>=1.4.0 in /usr/local/lib/python3.10/dist-packages (from docker-pycreds>=0.4.0->wandb==0.16.3->-r requirements.txt (line 7)) (1.16.0)\n", + "Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets>=2.16.1->-r requirements.txt (line 3)) (1.3.1)\n", + "Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets>=2.16.1->-r requirements.txt (line 3)) (23.2.0)\n", + "Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets>=2.16.1->-r requirements.txt (line 3)) (1.4.1)\n", + "Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets>=2.16.1->-r requirements.txt (line 3)) (6.0.5)\n", + "Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets>=2.16.1->-r requirements.txt (line 3)) (1.9.4)\n", + "Requirement already satisfied: async-timeout<5.0,>=4.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets>=2.16.1->-r requirements.txt (line 3)) (4.0.3)\n", + "Collecting gitdb<5,>=4.0.1 (from GitPython!=3.1.29,>=1.0.0->wandb==0.16.3->-r requirements.txt (line 7))\n", + " Downloading gitdb-4.0.11-py3-none-any.whl (62 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m62.7/62.7 kB\u001b[0m \u001b[31m8.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hRequirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests<3,>=2.0.0->wandb==0.16.3->-r requirements.txt (line 7)) (3.3.2)\n", + "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests<3,>=2.0.0->wandb==0.16.3->-r requirements.txt (line 7)) (3.6)\n", + "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests<3,>=2.0.0->wandb==0.16.3->-r requirements.txt (line 7)) (2.0.7)\n", + "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests<3,>=2.0.0->wandb==0.16.3->-r requirements.txt (line 7)) (2024.2.2)\n", + "Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate==0.27.1->-r requirements.txt (line 2)) (1.12)\n", + "Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate==0.27.1->-r requirements.txt (line 2)) (3.2.1)\n", + "Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate==0.27.1->-r requirements.txt (line 2)) (3.1.3)\n", + "Requirement already satisfied: nvidia-cuda-nvrtc-cu12==12.1.105 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate==0.27.1->-r requirements.txt (line 2)) (12.1.105)\n", + "Requirement already satisfied: nvidia-cuda-runtime-cu12==12.1.105 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate==0.27.1->-r requirements.txt (line 2)) (12.1.105)\n", + "Requirement already satisfied: nvidia-cuda-cupti-cu12==12.1.105 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate==0.27.1->-r requirements.txt (line 2)) (12.1.105)\n", + "Requirement already satisfied: nvidia-cudnn-cu12==8.9.2.26 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate==0.27.1->-r requirements.txt (line 2)) (8.9.2.26)\n", + "Requirement already satisfied: nvidia-cublas-cu12==12.1.3.1 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate==0.27.1->-r requirements.txt (line 2)) (12.1.3.1)\n", + "Requirement already satisfied: nvidia-cufft-cu12==11.0.2.54 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate==0.27.1->-r requirements.txt (line 2)) (11.0.2.54)\n", + "Requirement already satisfied: nvidia-curand-cu12==10.3.2.106 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate==0.27.1->-r requirements.txt (line 2)) (10.3.2.106)\n", + "Requirement already satisfied: nvidia-cusolver-cu12==11.4.5.107 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate==0.27.1->-r requirements.txt (line 2)) (11.4.5.107)\n", + "Requirement already satisfied: nvidia-cusparse-cu12==12.1.0.106 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate==0.27.1->-r requirements.txt (line 2)) (12.1.0.106)\n", + "Requirement already satisfied: nvidia-nccl-cu12==2.19.3 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate==0.27.1->-r requirements.txt (line 2)) (2.19.3)\n", + "Requirement already satisfied: nvidia-nvtx-cu12==12.1.105 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate==0.27.1->-r requirements.txt (line 2)) (12.1.105)\n", + "Requirement already satisfied: triton==2.2.0 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate==0.27.1->-r requirements.txt (line 2)) (2.2.0)\n", + "Requirement already satisfied: nvidia-nvjitlink-cu12 in /usr/local/lib/python3.10/dist-packages (from nvidia-cusolver-cu12==11.4.5.107->torch>=1.10.0->accelerate==0.27.1->-r requirements.txt (line 2)) (12.4.99)\n", + "Collecting docstring-parser>=0.14.1 (from tyro>=0.5.11->trl==0.7.10->-r requirements.txt (line 6))\n", + " Downloading docstring_parser-0.16-py3-none-any.whl (36 kB)\n", + "Requirement already satisfied: rich>=11.1.0 in /usr/local/lib/python3.10/dist-packages (from tyro>=0.5.11->trl==0.7.10->-r requirements.txt (line 6)) (13.7.1)\n", + "Collecting shtab>=1.5.6 (from tyro>=0.5.11->trl==0.7.10->-r requirements.txt (line 6))\n", + " Downloading shtab-1.7.1-py3-none-any.whl (14 kB)\n", + "Requirement already satisfied: python-dateutil>=2.8.1 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets>=2.16.1->-r requirements.txt (line 3)) (2.8.2)\n", + "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets>=2.16.1->-r requirements.txt (line 3)) (2023.4)\n", + "Collecting smmap<6,>=3.0.1 (from gitdb<5,>=4.0.1->GitPython!=3.1.29,>=1.0.0->wandb==0.16.3->-r requirements.txt (line 7))\n", + " Downloading smmap-5.0.1-py3-none-any.whl (24 kB)\n", + "Requirement already satisfied: markdown-it-py>=2.2.0 in /usr/local/lib/python3.10/dist-packages (from rich>=11.1.0->tyro>=0.5.11->trl==0.7.10->-r requirements.txt (line 6)) (3.0.0)\n", + "Requirement already satisfied: pygments<3.0.0,>=2.13.0 in /usr/local/lib/python3.10/dist-packages (from rich>=11.1.0->tyro>=0.5.11->trl==0.7.10->-r requirements.txt (line 6)) (2.16.1)\n", + "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->torch>=1.10.0->accelerate==0.27.1->-r requirements.txt (line 2)) (2.1.5)\n", + "Requirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/dist-packages (from sympy->torch>=1.10.0->accelerate==0.27.1->-r requirements.txt (line 2)) (1.3.0)\n", + "Requirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.10/dist-packages (from markdown-it-py>=2.2.0->rich>=11.1.0->tyro>=0.5.11->trl==0.7.10->-r requirements.txt (line 6)) (0.1.2)\n", + "Building wheels for collected packages: transformers\n", + " Building wheel for transformers (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n", + " Created wheel for transformers: filename=transformers-4.40.0.dev0-py3-none-any.whl size=8802995 sha256=cd6e5debbd346bdc641b0881aaa5ef3b1b0940b81d43afe6980bc8fa7fec8213\n", + " Stored in directory: /tmp/pip-ephem-wheel-cache-t3mn2qvd/wheels/e7/9c/5b/e1a9c8007c343041e61cc484433d512ea9274272e3fcbe7c16\n", + "Successfully built transformers\n", + "Installing collected packages: bitsandbytes, xxhash, smmap, shtab, setproctitle, sentry-sdk, docstring-parser, docker-pycreds, dill, multiprocess, gitdb, tyro, GitPython, wandb, transformers, datasets, accelerate, trl, peft\n", + " Attempting uninstall: transformers\n", + " Found existing installation: transformers 4.38.2\n", + " Uninstalling transformers-4.38.2:\n", + " Successfully uninstalled transformers-4.38.2\n", + "Successfully installed GitPython-3.1.42 accelerate-0.27.1 bitsandbytes-0.41.3 datasets-2.18.0 dill-0.3.8 docker-pycreds-0.4.0 docstring-parser-0.16 gitdb-4.0.11 multiprocess-0.70.16 peft-0.8.2 sentry-sdk-1.43.0 setproctitle-1.3.3 shtab-1.7.1 smmap-5.0.1 transformers-4.40.0.dev0 trl-0.7.10 tyro-0.7.3 wandb-0.16.3 xxhash-3.4.1\n" + ] + } + ] + }, + { + "cell_type": "code", + "source": [ + "%pwd" + ], + "metadata": { + "execution": { + "iopub.status.busy": "2024-03-19T20:03:57.777954Z", + "iopub.execute_input": "2024-03-19T20:03:57.778381Z", + "iopub.status.idle": "2024-03-19T20:03:57.788089Z", + "shell.execute_reply.started": "2024-03-19T20:03:57.778345Z", + "shell.execute_reply": "2024-03-19T20:03:57.787200Z" + }, + "trusted": true, + "colab": { + "base_uri": "https://localhost:8080/", + "height": 35 + }, + "id": "MDdUs8ZB0sZ3", + "outputId": "18792733-9e19-4748-e088-f7ca6edf9941" + }, + "execution_count": null, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "'/content/starcoder2'" + ], + "application/vnd.google.colaboratory.intrinsic+json": { + "type": "string" + } + }, + "metadata": {}, + "execution_count": 6 + } + ] + }, + { + "cell_type": "code", + "source": [ + "import wandb\n", + "wandb.login()" + ], + "metadata": { + "execution": { + "iopub.status.busy": "2024-03-19T20:03:57.789710Z", + "iopub.execute_input": "2024-03-19T20:03:57.790002Z", + "iopub.status.idle": "2024-03-19T20:04:11.138702Z", + "shell.execute_reply.started": "2024-03-19T20:03:57.789976Z", + "shell.execute_reply": "2024-03-19T20:04:11.137773Z" + }, + "trusted": true, + "colab": { + "base_uri": "https://localhost:8080/", + "height": 121 + }, + "id": "9QDruTSo0sZ3", + "outputId": "f6c13c74-754b-4d0e-cd18-049b771d2e7e" + }, + "execution_count": null, + "outputs": [ + { + "output_type": "display_data", + "data": { + "text/plain": [ + "" + ], + "application/javascript": [ + "\n", + " window._wandbApiKey = new Promise((resolve, reject) => {\n", + " function loadScript(url) {\n", + " return new Promise(function(resolve, reject) {\n", + " let newScript = document.createElement(\"script\");\n", + " newScript.onerror = reject;\n", + " newScript.onload = resolve;\n", + " document.body.appendChild(newScript);\n", + " newScript.src = url;\n", + " });\n", + " }\n", + " loadScript(\"https://cdn.jsdelivr.net/npm/postmate/build/postmate.min.js\").then(() => {\n", + " const iframe = document.createElement('iframe')\n", + " iframe.style.cssText = \"width:0;height:0;border:none\"\n", + " document.body.appendChild(iframe)\n", + " const handshake = new Postmate({\n", + " container: iframe,\n", + " url: 'https://wandb.ai/authorize'\n", + " });\n", + " const timeout = setTimeout(() => reject(\"Couldn't auto authenticate\"), 5000)\n", + " handshake.then(function(child) {\n", + " child.on('authorize', data => {\n", + " clearTimeout(timeout)\n", + " resolve(data)\n", + " });\n", + " });\n", + " })\n", + " });\n", + " " + ] + }, + "metadata": {} + }, + { + "output_type": "stream", + "name": "stderr", + "text": [ + "\u001b[34m\u001b[1mwandb\u001b[0m: Logging into wandb.ai. (Learn how to deploy a W&B server locally: https://wandb.me/wandb-server)\n", + "\u001b[34m\u001b[1mwandb\u001b[0m: You can find your API key in your browser here: https://wandb.ai/authorize\n", + "wandb: Paste an API key from your profile and hit enter, or press ctrl+c to quit:" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + " ··········\n" + ] + }, + { + "output_type": "stream", + "name": "stderr", + "text": [ + "\u001b[34m\u001b[1mwandb\u001b[0m: Appending key for api.wandb.ai to your netrc file: /root/.netrc\n" + ] + }, + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "True" + ] + }, + "metadata": {}, + "execution_count": 7 + } + ] + }, + { + "cell_type": "code", + "source": [ + "from huggingface_hub import notebook_login\n", + "\n", + "notebook_login()" + ], + "metadata": { + "execution": { + "iopub.status.busy": "2024-03-19T20:04:11.139793Z", + "iopub.execute_input": "2024-03-19T20:04:11.140165Z", + "iopub.status.idle": "2024-03-19T20:04:11.292102Z", + "shell.execute_reply.started": "2024-03-19T20:04:11.140141Z", + "shell.execute_reply": "2024-03-19T20:04:11.291085Z" + }, + "trusted": true, + "colab": { + "base_uri": "https://localhost:8080/", + "height": 145, + "referenced_widgets": [ + "1234072a81334f8db0a10d1b44d034f5", + "0b7664f082d34d9b9b86979e0a7f55e7", + "5b777f1e81ff439b8dca5e5d9eedf67b", + "3c3e316bad6542ee8da7b7d478bc0de0", + "48c07121dcd247bb96d38eb1bdd2a073", + "663c38b3e97c4855a959bbc4582c2412", + "34ba7411d5de41c9ac7ef9ade5a5ad9b", + "aec899db50df4647ae5ac36c07ee294f", + "d5f8193d213d4860aaa0c842ba7c9c07", + "eed45bc885fd4adcbce829b0c9afbf48", + "d2fdd03aa4e148bcac64eab9229af61c", + "917ad72239a24a2ca19578077bd3f190", + "c08f5bb3f3b0400eac10e333a78f30b8", + "8594f76b97fa4814a5ae0235f3ad0961", + "bea5cf62b00b446bb2ef49329771a398", + "a1667ab01c674d93b8456e84ea587d03", + "1504ebc3efdf41b5854a6596a175aedb", + "7b5c33a1c5b44424b673c2d7611013e9", + "468b9dc57b164213b7e58acc369f5c0d", + "7923884bad934c0ca2c1a47529d65325", + "6bba1b4558b0432aa44c558e5d4ebdf8", + "4ac3b065ad9546398e2691ceb371c233", + "accba8f890814d5f92464b3471966bbf", + "bb0db85e948443019c9d645280175b47", + "505b4a8563564747a4f4ac0934ce58ca", + "fd9c755b79314b858fe405bf087f80f6", + "8a7d1ba404dd49a1bb517d12f7a993f6", + "18d9e77db3da4e23902226007712d51d", + "a30e755f34e142f8baab95721c9b9870", + "15d307d0cd1540f6af402f319a668e05", + "87ce8a9512264f15b3804982249aed56", + "da3475cbed5240c3a5b860377caa0697" + ] + }, + "id": "IdMgve-D0sZ3", + "outputId": "42bc84b3-2421-4663-bb03-6d9b220d1391" + }, + "execution_count": null, + "outputs": [ + { + "output_type": "display_data", + "data": { + "text/plain": [ + "VBox(children=(HTML(value='
=1.4.0 in /usr/local/lib/python3.10/dist-packages (from trl==0.7.12.dev0) (2.2.1+cu121)\n", + "Requirement already satisfied: transformers>=4.31.0 in /usr/local/lib/python3.10/dist-packages (from trl==0.7.12.dev0) (4.40.0.dev0)\n", + "Requirement already satisfied: numpy>=1.18.2 in /usr/local/lib/python3.10/dist-packages (from trl==0.7.12.dev0) (1.25.2)\n", + "Requirement already satisfied: accelerate in /usr/local/lib/python3.10/dist-packages (from trl==0.7.12.dev0) (0.27.1)\n", + "Requirement already satisfied: datasets in /usr/local/lib/python3.10/dist-packages (from trl==0.7.12.dev0) (2.18.0)\n", + "Requirement already satisfied: tyro>=0.5.11 in /usr/local/lib/python3.10/dist-packages (from trl==0.7.12.dev0) (0.7.3)\n", + "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from torch>=1.4.0->trl==0.7.12.dev0) (3.13.1)\n", + "Requirement already satisfied: typing-extensions>=4.8.0 in /usr/local/lib/python3.10/dist-packages (from torch>=1.4.0->trl==0.7.12.dev0) (4.10.0)\n", + "Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch>=1.4.0->trl==0.7.12.dev0) (1.12)\n", + "Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch>=1.4.0->trl==0.7.12.dev0) (3.2.1)\n", + "Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch>=1.4.0->trl==0.7.12.dev0) (3.1.3)\n", + "Requirement already satisfied: fsspec in /usr/local/lib/python3.10/dist-packages (from torch>=1.4.0->trl==0.7.12.dev0) (2023.6.0)\n", + "Requirement already satisfied: nvidia-cuda-nvrtc-cu12==12.1.105 in /usr/local/lib/python3.10/dist-packages (from torch>=1.4.0->trl==0.7.12.dev0) (12.1.105)\n", + "Requirement already satisfied: nvidia-cuda-runtime-cu12==12.1.105 in /usr/local/lib/python3.10/dist-packages (from torch>=1.4.0->trl==0.7.12.dev0) (12.1.105)\n", + "Requirement already satisfied: nvidia-cuda-cupti-cu12==12.1.105 in /usr/local/lib/python3.10/dist-packages (from torch>=1.4.0->trl==0.7.12.dev0) (12.1.105)\n", + "Requirement already satisfied: nvidia-cudnn-cu12==8.9.2.26 in /usr/local/lib/python3.10/dist-packages (from torch>=1.4.0->trl==0.7.12.dev0) (8.9.2.26)\n", + "Requirement already satisfied: nvidia-cublas-cu12==12.1.3.1 in /usr/local/lib/python3.10/dist-packages (from torch>=1.4.0->trl==0.7.12.dev0) (12.1.3.1)\n", + "Requirement already satisfied: nvidia-cufft-cu12==11.0.2.54 in /usr/local/lib/python3.10/dist-packages (from torch>=1.4.0->trl==0.7.12.dev0) (11.0.2.54)\n", + "Requirement already satisfied: nvidia-curand-cu12==10.3.2.106 in /usr/local/lib/python3.10/dist-packages (from torch>=1.4.0->trl==0.7.12.dev0) (10.3.2.106)\n", + "Requirement already satisfied: nvidia-cusolver-cu12==11.4.5.107 in /usr/local/lib/python3.10/dist-packages (from torch>=1.4.0->trl==0.7.12.dev0) (11.4.5.107)\n", + "Requirement already satisfied: nvidia-cusparse-cu12==12.1.0.106 in /usr/local/lib/python3.10/dist-packages (from torch>=1.4.0->trl==0.7.12.dev0) (12.1.0.106)\n", + "Requirement already satisfied: nvidia-nccl-cu12==2.19.3 in /usr/local/lib/python3.10/dist-packages (from torch>=1.4.0->trl==0.7.12.dev0) (2.19.3)\n", + "Requirement already satisfied: nvidia-nvtx-cu12==12.1.105 in /usr/local/lib/python3.10/dist-packages (from torch>=1.4.0->trl==0.7.12.dev0) (12.1.105)\n", + "Requirement already satisfied: triton==2.2.0 in /usr/local/lib/python3.10/dist-packages (from torch>=1.4.0->trl==0.7.12.dev0) (2.2.0)\n", + "Requirement already satisfied: nvidia-nvjitlink-cu12 in /usr/local/lib/python3.10/dist-packages (from nvidia-cusolver-cu12==11.4.5.107->torch>=1.4.0->trl==0.7.12.dev0) (12.4.99)\n", + "Requirement already satisfied: huggingface-hub<1.0,>=0.19.3 in /usr/local/lib/python3.10/dist-packages (from transformers>=4.31.0->trl==0.7.12.dev0) (0.20.3)\n", + "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from transformers>=4.31.0->trl==0.7.12.dev0) (24.0)\n", + "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from transformers>=4.31.0->trl==0.7.12.dev0) (6.0.1)\n", + "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers>=4.31.0->trl==0.7.12.dev0) (2023.12.25)\n", + "Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from transformers>=4.31.0->trl==0.7.12.dev0) (2.31.0)\n", + "Requirement already satisfied: tokenizers<0.19,>=0.14 in /usr/local/lib/python3.10/dist-packages (from transformers>=4.31.0->trl==0.7.12.dev0) (0.15.2)\n", + "Requirement already satisfied: safetensors>=0.4.1 in /usr/local/lib/python3.10/dist-packages (from transformers>=4.31.0->trl==0.7.12.dev0) (0.4.2)\n", + "Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.10/dist-packages (from transformers>=4.31.0->trl==0.7.12.dev0) (4.66.2)\n", + "Requirement already satisfied: docstring-parser>=0.14.1 in /usr/local/lib/python3.10/dist-packages (from tyro>=0.5.11->trl==0.7.12.dev0) (0.16)\n", + "Requirement already satisfied: rich>=11.1.0 in /usr/local/lib/python3.10/dist-packages (from tyro>=0.5.11->trl==0.7.12.dev0) (13.7.1)\n", + "Requirement already satisfied: shtab>=1.5.6 in /usr/local/lib/python3.10/dist-packages (from tyro>=0.5.11->trl==0.7.12.dev0) (1.7.1)\n", + "Requirement already satisfied: psutil in /usr/local/lib/python3.10/dist-packages (from accelerate->trl==0.7.12.dev0) (5.9.5)\n", + "Requirement already satisfied: pyarrow>=12.0.0 in /usr/local/lib/python3.10/dist-packages (from datasets->trl==0.7.12.dev0) (14.0.2)\n", + "Requirement already satisfied: pyarrow-hotfix in /usr/local/lib/python3.10/dist-packages (from datasets->trl==0.7.12.dev0) (0.6)\n", + "Requirement already satisfied: dill<0.3.9,>=0.3.0 in /usr/local/lib/python3.10/dist-packages (from datasets->trl==0.7.12.dev0) (0.3.8)\n", + "Requirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (from datasets->trl==0.7.12.dev0) (1.5.3)\n", + "Requirement already satisfied: xxhash in /usr/local/lib/python3.10/dist-packages (from datasets->trl==0.7.12.dev0) (3.4.1)\n", + "Requirement already satisfied: multiprocess in /usr/local/lib/python3.10/dist-packages (from datasets->trl==0.7.12.dev0) (0.70.16)\n", + "Requirement already satisfied: aiohttp in /usr/local/lib/python3.10/dist-packages (from datasets->trl==0.7.12.dev0) (3.9.3)\n", + "Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets->trl==0.7.12.dev0) (1.3.1)\n", + "Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets->trl==0.7.12.dev0) (23.2.0)\n", + "Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets->trl==0.7.12.dev0) (1.4.1)\n", + "Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets->trl==0.7.12.dev0) (6.0.5)\n", + "Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets->trl==0.7.12.dev0) (1.9.4)\n", + "Requirement already satisfied: async-timeout<5.0,>=4.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets->trl==0.7.12.dev0) (4.0.3)\n", + "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->transformers>=4.31.0->trl==0.7.12.dev0) (3.3.2)\n", + "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->transformers>=4.31.0->trl==0.7.12.dev0) (3.6)\n", + "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->transformers>=4.31.0->trl==0.7.12.dev0) (2.0.7)\n", + "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->transformers>=4.31.0->trl==0.7.12.dev0) (2024.2.2)\n", + "Requirement already satisfied: markdown-it-py>=2.2.0 in /usr/local/lib/python3.10/dist-packages (from rich>=11.1.0->tyro>=0.5.11->trl==0.7.12.dev0) (3.0.0)\n", + "Requirement already satisfied: pygments<3.0.0,>=2.13.0 in /usr/local/lib/python3.10/dist-packages (from rich>=11.1.0->tyro>=0.5.11->trl==0.7.12.dev0) (2.16.1)\n", + "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->torch>=1.4.0->trl==0.7.12.dev0) (2.1.5)\n", + "Requirement already satisfied: python-dateutil>=2.8.1 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets->trl==0.7.12.dev0) (2.8.2)\n", + "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets->trl==0.7.12.dev0) (2023.4)\n", + "Requirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/dist-packages (from sympy->torch>=1.4.0->trl==0.7.12.dev0) (1.3.0)\n", + "Requirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.10/dist-packages (from markdown-it-py>=2.2.0->rich>=11.1.0->tyro>=0.5.11->trl==0.7.12.dev0) (0.1.2)\n", + "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.8.1->pandas->datasets->trl==0.7.12.dev0) (1.16.0)\n", + "Building wheels for collected packages: trl\n", + " Building wheel for trl (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n", + " Created wheel for trl: filename=trl-0.7.12.dev0-py3-none-any.whl size=173433 sha256=53a43dc49d7d8c02ff9a31724023c0fb3c1b64348ccce2eea04682f7dde954c6\n", + " Stored in directory: /root/.cache/pip/wheels/ad/f5/b1/f5ac48230936583c88cfde8596bc92cad4b0a4b24d0f819c06\n", + "Successfully built trl\n", + "Installing collected packages: trl\n", + " Attempting uninstall: trl\n", + " Found existing installation: trl 0.7.10\n", + " Uninstalling trl-0.7.10:\n", + " Successfully uninstalled trl-0.7.10\n", + "Successfully installed trl-0.7.12.dev0\n" + ] + } + ] + }, + { + "cell_type": "code", + "source": [ + "# Code adapted from https://github.com/huggingface/trl/blob/main/examples/research_projects/stack_llama/scripts/supervised_finetuning.py\n", + "# and https://huggingface.co/blog/gemma-peft\n", + "import argparse\n", + "import multiprocessing\n", + "import os\n", + "\n", + "import torch\n", + "import transformers\n", + "from accelerate import PartialState\n", + "from datasets import load_dataset\n", + "from peft import LoraConfig\n", + "from transformers import (\n", + " AutoModelForCausalLM,\n", + " BitsAndBytesConfig,\n", + " logging,\n", + " set_seed,\n", + ")\n", + "from trl import SFTTrainer\n", + "\n" + ], + "metadata": { + "execution": { + "iopub.status.busy": "2024-03-19T20:04:39.980277Z", + "iopub.execute_input": "2024-03-19T20:04:39.980608Z", + "iopub.status.idle": "2024-03-19T20:04:56.922413Z", + "shell.execute_reply.started": "2024-03-19T20:04:39.980583Z", + "shell.execute_reply": "2024-03-19T20:04:56.921624Z" + }, + "trusted": true, + "id": "qQuVp9kt0sZ3" + }, + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "\n", + "\n", + "parser = argparse.ArgumentParser()\n", + "parser.add_argument(\"--model_id\", type=str, default=\"bigcode/starcoder2-3b\")\n", + "parser.add_argument(\"--dataset_name\", type=str, default=\"bigcode/the-stack-smol\")\n", + "parser.add_argument(\"--subset\", type=str, default=\"data/sql\")\n", + "parser.add_argument(\"--split\", type=str, default=\"train\")\n", + "parser.add_argument(\"--dataset_text_field\", type=str, default=\"content\")\n", + "\n", + "parser.add_argument(\"--max_seq_length\", type=int, default=512)\n", + "parser.add_argument(\"--max_steps\", type=int, default=1000)\n", + "parser.add_argument(\"--micro_batch_size\", type=int, default=1)\n", + "parser.add_argument(\"--gradient_accumulation_steps\", type=int, default=4)\n", + "parser.add_argument(\"--weight_decay\", type=float, default=0.01)\n", + "parser.add_argument(\"--fp16\", type=bool, default=True)\n", + "\n", + "parser.add_argument(\"--attention_dropout\", type=float, default=0.1)\n", + "parser.add_argument(\"--learning_rate\", type=float, default=2e-4)\n", + "parser.add_argument(\"--lr_scheduler_type\", type=str, default=\"cosine\")\n", + "parser.add_argument(\"--warmup_steps\", type=int, default=100)\n", + "parser.add_argument(\"--seed\", type=int, default=0)\n", + "parser.add_argument(\"--output_dir\", type=str, default=\"finetune_starcoder2\")\n", + "parser.add_argument(\"--num_proc\", type=int, default=2)#was none since i have 2 gpus why not\n", + "parser.add_argument(\"--push_to_hub\", type=bool, default=True)\n", + "\n", + "args = parser.parse_args(args=[])\n" + ], + "metadata": { + "execution": { + "iopub.status.busy": "2024-03-19T20:04:56.923522Z", + "iopub.execute_input": "2024-03-19T20:04:56.924095Z", + "iopub.status.idle": "2024-03-19T20:04:56.935605Z", + "shell.execute_reply.started": "2024-03-19T20:04:56.924067Z", + "shell.execute_reply": "2024-03-19T20:04:56.934593Z" + }, + "trusted": true, + "id": "GRT0JgpF0sZ4" + }, + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "args" + ], + "metadata": { + "execution": { + "iopub.status.busy": "2024-03-19T20:04:56.936862Z", + "iopub.execute_input": "2024-03-19T20:04:56.937191Z", + "iopub.status.idle": "2024-03-19T20:04:56.966429Z", + "shell.execute_reply.started": "2024-03-19T20:04:56.937157Z", + "shell.execute_reply": "2024-03-19T20:04:56.965564Z" + }, + "trusted": true, + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "gaSUzOv40sZ4", + "outputId": "1f56d30a-c60c-476e-cc4c-34f74286f63f" + }, + "execution_count": null, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "Namespace(model_id='bigcode/starcoder2-3b', dataset_name='bigcode/the-stack-smol', subset='data/sql', split='train', dataset_text_field='content', max_seq_length=512, max_steps=1000, micro_batch_size=1, gradient_accumulation_steps=4, weight_decay=0.01, fp16=True, attention_dropout=0.1, learning_rate=0.0002, lr_scheduler_type='cosine', warmup_steps=100, seed=0, output_dir='finetune_starcoder2', num_proc=2, push_to_hub=True)" + ] + }, + "metadata": {}, + "execution_count": 12 + } + ] + }, + { + "cell_type": "code", + "source": [ + "\n", + "def print_trainable_parameters(model):\n", + " \"\"\"\n", + " Prints the number of trainable parameters in the model.\n", + " \"\"\"\n", + " trainable_params = 0\n", + " all_param = 0\n", + " for _, param in model.named_parameters():\n", + " all_param += param.numel()\n", + " if param.requires_grad:\n", + " trainable_params += param.numel()\n", + " print(\n", + " f\"trainable params: {trainable_params} || all params: {all_param} || trainable%: {100 * trainable_params / all_param}\"\n", + " )\n", + "\n", + "\n" + ], + "metadata": { + "execution": { + "iopub.status.busy": "2024-03-19T20:04:56.967468Z", + "iopub.execute_input": "2024-03-19T20:04:56.967754Z", + "iopub.status.idle": "2024-03-19T20:04:56.975477Z", + "shell.execute_reply.started": "2024-03-19T20:04:56.967732Z", + "shell.execute_reply": "2024-03-19T20:04:56.974545Z" + }, + "trusted": true, + "id": "VdpvW4A60sZ4" + }, + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "def main(args):\n", + " # config\n", + " bnb_config = BitsAndBytesConfig(\n", + " load_in_4bit=True,\n", + " bnb_4bit_quant_type=\"nf4\",\n", + " bnb_4bit_compute_dtype=torch.bfloat16,\n", + " )\n", + " lora_config = LoraConfig(\n", + " r=8,\n", + " target_modules=[\n", + " \"q_proj\",\n", + " \"o_proj\",\n", + " \"k_proj\",\n", + " \"v_proj\",\n", + " \"gate_proj\",\n", + " \"up_proj\",\n", + " \"down_proj\",\n", + " ],\n", + " task_type=\"CAUSAL_LM\",\n", + " )\n", + "\n", + " # load model and dataset\n", + " token = os.environ.get(\"HF_TOKEN\", None)\n", + " model = AutoModelForCausalLM.from_pretrained(\n", + " args.model_id,\n", + " quantization_config=bnb_config,\n", + " device_map={\"\": PartialState().process_index},\n", + " attention_dropout=args.attention_dropout,\n", + " )\n", + " print_trainable_parameters(model)\n", + "\n", + " data = load_dataset(\n", + " args.dataset_name,\n", + " data_dir=args.subset,\n", + " split=args.split,\n", + " token=token,\n", + " num_proc=args.num_proc if args.num_proc else multiprocessing.cpu_count(),\n", + " )\n", + "\n", + " # setup the trainer\n", + " trainer = SFTTrainer(\n", + " model=model,\n", + " train_dataset=data,\n", + " max_seq_length=args.max_seq_length,\n", + " args=transformers.TrainingArguments(\n", + " per_device_train_batch_size=args.micro_batch_size,\n", + " gradient_accumulation_steps=args.gradient_accumulation_steps,\n", + " warmup_steps=args.warmup_steps,\n", + " max_steps=args.max_steps,\n", + " learning_rate=args.learning_rate,\n", + " lr_scheduler_type=args.lr_scheduler_type,\n", + " weight_decay=args.weight_decay,\n", + " fp16=args.fp16,\n", + " logging_strategy=\"steps\",\n", + " logging_steps=10,\n", + " output_dir=args.output_dir,\n", + " optim=\"paged_adamw_8bit\",\n", + " seed=args.seed,\n", + " run_name=f\"train-{args.model_id.split('/')[-1]}\",\n", + " report_to=\"wandb\",\n", + " ),\n", + " peft_config=lora_config,\n", + " dataset_text_field=args.dataset_text_field,\n", + " )\n", + "\n", + " # launch\n", + " print(\"Training...\")\n", + " trainer.train()\n", + "\n", + " print(\"Saving the last checkpoint of the model\")\n", + " model.save_pretrained(os.path.join(args.output_dir, \"final_checkpoint/\"))\n", + " if args.push_to_hub:\n", + " trainer.push_to_hub(\"Upload model\")\n", + " print(\"Training Done! 💥\")" + ], + "metadata": { + "execution": { + "iopub.status.busy": "2024-03-19T20:04:56.976790Z", + "iopub.execute_input": "2024-03-19T20:04:56.977037Z", + "iopub.status.idle": "2024-03-19T20:04:56.988637Z", + "shell.execute_reply.started": "2024-03-19T20:04:56.977015Z", + "shell.execute_reply": "2024-03-19T20:04:56.987799Z" + }, + "trusted": true, + "id": "uJ6zaIcX0sZ4" + }, + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "set_seed(args.seed)\n", + "os.makedirs(args.output_dir, exist_ok=True)\n", + "\n", + "logging.set_verbosity_error()\n", + "\n", + "main(args)" + ], + "metadata": { + "execution": { + "iopub.status.busy": "2024-03-19T20:05:53.664781Z", + "iopub.execute_input": "2024-03-19T20:05:53.665168Z" + }, + "trusted": true, + "colab": { + "base_uri": "https://localhost:8080/", + "height": 1000, + "referenced_widgets": [ + "ac5e93b72ad84752b974c04b8f4b51f9", + "595a2f42de714f18a84afa6285659917", + "02a3c25f3e0a4a6d96e45b7b3498bee3", + "213c1c2d6d894b41928b06676c2a85a3", + "17eeebd01aff4bfba2aa60981ad04cb7", + "94d14274f2b7457d96dca9e428052fb5", + "3c30f1269ee94513b3e9e7d956b6ecb5", + "eb104275736f40c0a81dd9edbcad19e3", + "b391ef4a80334864bc7d30949da49c23", + "6e240a79806744f08df735a282e6725e", + "76e63eb18b094e94a85435668c52ff1e", + "1fc1ff1816834137915e52e70d4c917d", + "98718e4f687c49d5a20c2a629ff0469a", + "fb04e6c11c444b9abd5f463cc8b46265", + "33f085f426774d6f972080287dd0c437", + "3b1e906cec344cbaac4ccb7a48187425", + "5cc3a36008ac4f2087b98648fd700ee3", + "df4d348d5ec5406bbdb474d20673c645", + "c02c433ec2e64c099e7da34cd3d205ec", + "57b5060a7b2a456a9b831d873abeb7eb", + "8513434391504f609724d09b10b07ff3", + "b842553532ed4de788baa84c872fd965", + "1756abe3f1c945309c4850ea7edf53c3", + "aaa81f1b7f56417391118bce6b954d31", + "eccee39b070c4e48a8a05249e73a00bf", + "c00e5e033d154908a639190e7f31ebbc", + "9f7435b84b314146a12760549e405ecd", + "3faa7cfc5c8c486992f0aaae8f2c049d", + "0d01332406a2400dac1a88671c0d9c49", + "eb501c7b4e86403a9179fc1f262d36db", + "9a3edf74b7204c7f829dba42694ff04b", + "799545200e8542aca53babb5fc26f2a1", + "4049302bc5ba4f919b07d957e48197ec", + "81be94da65914dff85a41ad123ab7245", + "6dcead4c258d41fb93ca5b1a036a63be", + "df833f4e9b084c8e8c1fec08d85a1178", + "e6c7cb83e6264b8193ea41dffc2e68e5", + "f00235276ec44e338e54dd3f8aba8bf7", + "26c6d218bf184fffaf61095e94d137ea", + "ee4addeb906f4cd9af90d9c5907f2f3a", + "3a11aa6dd86444c4b5ed304d7fc72e84", + "0b3289489db64bc695dbcaacf7c383c2", + "0bf58a8cdc5f4a28a3f2fce6d6099839", + "55ea809c6cac4e9487ca84271888fa44", + "8144f11931cd43dd83f6c6105c77148c", + "87ae209b51f6419b9d946dfe0761b419", + "76bfaa03980346df9c4e3546320c48b4", + "c1621007cdb84ad6816a3cdd504236fd", + "cb5f92092a7244b89352ed2c1c8ee2b2", + "e344fee89bf64365afce471ea8869383", + "0ea57b58135046fd9779f1c591b07846", + "2687cbf6b58e470385fdbba0c1c36250", + "ab7b72a1d40147d58c4cd17d2220761c", + "655e8f1ac2384cc685541a4c0658fc67", + "a57e6e531c2547e5be36d63cfbc82367", + "646a4fc394534c4ebf99c28954687415", + "f2b7859f61c74cb39875b7b817319c11", + "22cbb36078fe4571ae4e85d7e61dfbff", + "d20021af6fc8426688335f600bdc7cd7", + "24354a4974284c8eb6399e2d79930c48", + "dbfa10aab4b14e138a38b4053dd798f3", + "058a015021a54f4dbf1d2f537b1815e0", + "c6c2660f516a40148f8292369f97e351", + "493dd540e403418d954f0a5e90882d0c", + "3aa94ea4e4c24c47a55a5c8246eff0a3", + "627cc61dfc1f4496966b04e02a5be337", + "b35b1837f69e4df887acaaaeb31e6bcd", + "56cb96aa6c9d4a17a522afdaa7c364a4", + "ccfefb3fdedc4b4ca10faa9d9cd2048f", + "e41cec5e54904ab49d61944655aaff88", + "695e4e8b824844a5840ac260fb8e04fb", + "80a902fa11d5466386b0b2982ffd47ae", + "d0f6c9bd037d43c59ea781b772c4add7", + "419b88c918764f5f8326927b6e134891", + "60e56e1bef8b48d8bab7a9cc0f75194e", + "a9282e4d38f443f1b313fc88d41e10ff", + "25631d86db9342558569d74f62af26a1", + "2513457b311444e6b88be9b9dd3a36a9", + "aecd1317708843f683505a0fc2a149a5", + "a8d18e08a61d4a558b72df74564b35e8", + "6d31885ff5ab4e61bdb28d83a3667573", + "e85efef9c567460391ca8ba29282d88c", + "870235731ae54eda8c05f4a016a9350a", + "32fccbc1a3de400484ff9f1fef764324", + "69dc5d5004af457fae599ddeac72af3b", + "680f00ce60f54e3ea2391f88ec77aca2", + "efe4495376db4cba9f3199b5b3c3890c", + "5f7bd750e403447e93b5fa14e4c211a7", + "ff4fee480b184d9fadc1e4e15a3bf95d", + "dbf8025e542940cca0ec3e325c237fc0", + "f2ac0170745b4b008520fc58a978bd41", + "bef691089e0048feb2d93485caafc43b", + "9bdc297a1be24b46b3b8019aedbff158", + "a858d85200684a4ea825cb2c1309eba1", + "60e967512bf64d118adaa771d1ed7ae2", + "f3dcf437ccbb4a0fbe0bfd97fcdd7025", + "2372a60079a9467a886019863946de6c", + "5789ec36c69b40a091ccfaac4e719ceb", + "6904515f20fe45fcb54c954ee4f50216", + "d4fb19288f8a47b39805aa9d0683b1c8", + "24c48b1ab4d54ea98ed13457ddcd997b", + "c29532e36d33437b9f4f943d77b4dd59", + "9142737465e2441d94091244c1597898", + "965991b2ed3e4180b837d81990943cf2", + "4b33ac8b868747d78ff11d7c887737eb", + "ceacee8c50524687a5bd18427e442c6d", + "2589f0a4872c4ff8ba3eba0c4d6a2d3e", + "fee2ced1fa644a65b7bed410a43f6bcb", + "3b3912eedf5d421eaee802c99965466b", + "139794710d3b49c688f00cb81cdacc4f", + "050a699a05124be795092f99afafff51", + "1a58bd80107744fe9fd43127c95a31b4", + "2390cf93ec524486a1887c18f1355f3e", + "71efa66726994a7995385953cf9901c8", + "c67495f5f6334b93a8d860140ce22103", + "24742629adec40d19ae71d1be953b14b", + "699021597d3b46548b6272a5ac54f3ce", + "43c7388594d849c6b0f3b7002c8d0e04", + "3d7cb9d6d77040e890ec864e613a2edb", + "56da6bb3b3a84a7a82907fdb314cdb69", + "1da9ad06b499439d8d8359f6156fcf8d", + "d703edc27af048da83dbbbc1c2b2300f", + "e613228e7a9741a9b9600549b8000e83", + "b9ca1c6ebd264dfcb34628323d678bfb", + "e2965aaf069346cf9a4d3dd65c28a78f", + "27057a26339e4f2cae7f9cd303143ee5", + "f346f035b8cc4b21a753bddf040bda77", + "5b0752a53bd749f29ba244e012cbb5c0", + "2cc86efa5a7c4b408519ce873cfa3f7b", + "ac3042c7e79a43b2a5894087b06e8f9c", + "309cc692723d4c69938e97aa1dd34334", + "da336fed4e414d6196c5e1c821aac58f", + "ae3ca4f42c1e42bb95663d01f76cff44", + "d319697500914bbea3ea00a082046735", + "864ac8715b344559bc32b366c22ed120", + "d07da602cff649c89653a070f11cd7d9", + "232dcf4bebe347558d9246988f9297cc", + "ebf2ea8c28bd44c78a6315b2edfe9533", + "30f4904bf9db4ed993b7494c32312b89", + "25908616492b43529a70d377ffa67f46", + "1cbb793261cf489b9b7e955afecfe18d", + "5c966b0fd0ca49469335466b0d95f481", + "3325008942994d5d9804d0dbeca0683f", + "2a466ebd1c294da69f0ea6834c86102e", + "fe707e7bd7d847738644da570c5d69ca", + "51c7c1b43fe74bea9763f5215f4bd0ae", + "faf70d38ae5048a1b661eb17e56c35b7", + "3a3a6d72eeef4846bad8987c0f5f98dd", + "2f939d69a04241eea33743770ce6bb1a", + "b0f752a283894ad580cec435e7add34d", + "a3b6c7f8cb6a4c43ba17427ee414808b", + "7a702890a92b4220b5c46293476b7752", + "8e80290d0db547209a2b3dc3ccbac976", + "5fdeba11def34cfbbcf8273add3d75b0", + "126d9b8f5a5f436b9f16ad7171fb91b8", + "c9f70ce3fa3b45eb9e077a6477114ed5", + "f20df2aa6d164766991789c629494990", + "639d34946dc74f978a551191b54050e2", + "5d7d12397d1b42ee9f8b1c10ac802c89", + "7eb14ebcb61343e095ff69c7ffc027cd", + "2afb975011384469b18b79dd8c8d9951", + "1aaf67fcf8e3410089c0710d962d6e22", + "6bf5f75ef0054b579ecee9129b3282c4", + "280caf0602a44c1d964fe1736cd3f41e", + "0ec3acf0d68c49b8bbd612a43cb3f9de" + ] + }, + "id": "_Vx_LzBs0sZ5", + "outputId": "c86b96ef-4dae-4ddb-dc6b-fd302bba9bc0" + }, + "execution_count": null, + "outputs": [ + { + "output_type": "display_data", + "data": { + "text/plain": [ + "config.json: 0%| | 0.00/700 [00:00" + ], + "text/html": [ + "wandb version 0.16.4 is available! To upgrade, please run:\n", + " $ pip install wandb --upgrade" + ] + }, + "metadata": {} + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "" + ], + "text/html": [ + "Tracking run with wandb version 0.16.3" + ] + }, + "metadata": {} + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "" + ], + "text/html": [ + "Run data is saved locally in /content/starcoder2/wandb/run-20240322_122024-ww6p0lwc" + ] + }, + "metadata": {} + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "" + ], + "text/html": [ + "Syncing run train-starcoder2-3b to Weights & Biases (docs)
" + ] + }, + "metadata": {} + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "" + ], + "text/html": [ + " View project at https://wandb.ai/sayan112207/huggingface" + ] + }, + "metadata": {} + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "" + ], + "text/html": [ + " View run at https://wandb.ai/sayan112207/huggingface/runs/ww6p0lwc" + ] + }, + "metadata": {} + }, + { + "output_type": "stream", + "name": "stdout", + "text": [ + "{'loss': 2.9315, 'grad_norm': 0.34227195382118225, 'learning_rate': 2e-05, 'epoch': 0.0}\n", + "{'loss': 2.8248, 'grad_norm': 0.5726468563079834, 'learning_rate': 4e-05, 'epoch': 0.01}\n", + "{'loss': 2.5121, 'grad_norm': 0.7665972113609314, 'learning_rate': 6e-05, 'epoch': 0.01}\n", + "{'loss': 2.7369, 'grad_norm': 0.8638845086097717, 'learning_rate': 8e-05, 'epoch': 0.02}\n", + "{'loss': 2.299, 'grad_norm': 1.143310308456421, 'learning_rate': 0.0001, 'epoch': 0.02}\n", + "{'loss': 2.3178, 'grad_norm': 3.2344813346862793, 'learning_rate': 0.00012, 'epoch': 0.02}\n", + "{'loss': 2.0725, 'grad_norm': 1.3525639772415161, 'learning_rate': 0.00014, 'epoch': 0.03}\n", + "{'loss': 1.8408, 'grad_norm': nan, 'learning_rate': 0.00015800000000000002, 'epoch': 0.03}\n", + "{'loss': 2.3955, 'grad_norm': 4.013404369354248, 'learning_rate': 0.00017800000000000002, 'epoch': 0.04}\n", + "{'loss': 2.1926, 'grad_norm': 1.2681958675384521, 'learning_rate': 0.00019800000000000002, 'epoch': 0.04}\n", + "{'loss': 1.8486, 'grad_norm': 4.053075790405273, 'learning_rate': 0.00019995065603657316, 'epoch': 0.04}\n", + "{'loss': 1.8048, 'grad_norm': 2.8900978565216064, 'learning_rate': 0.000199780146829205, 'epoch': 0.05}\n", + "{'loss': 1.9149, 'grad_norm': 1.8991763591766357, 'learning_rate': 0.00019948807088287883, 'epoch': 0.05}\n", + "{'loss': 1.4929, 'grad_norm': 2.0356318950653076, 'learning_rate': 0.00019907478404714436, 'epoch': 0.06}\n", + "{'loss': 2.0439, 'grad_norm': 1.6988109350204468, 'learning_rate': 0.00019854078984834903, 'epoch': 0.06}\n", + "{'loss': 1.9759, 'grad_norm': 3.643787384033203, 'learning_rate': 0.0001978867388761685, 'epoch': 0.06}\n", + "{'loss': 1.6491, 'grad_norm': 4.3542799949646, 'learning_rate': 0.00019711342799096361, 'epoch': 0.07}\n", + "{'loss': 2.0479, 'grad_norm': 1.48356294631958, 'learning_rate': 0.00019622179935292855, 'epoch': 0.07}\n", + "{'loss': 1.6252, 'grad_norm': 4.299762725830078, 'learning_rate': 0.00019521293927421388, 'epoch': 0.08}\n", + "{'loss': 1.8752, 'grad_norm': 2.225804328918457, 'learning_rate': 0.00019408807689542257, 'epoch': 0.08}\n", + "{'loss': 1.9581, 'grad_norm': 2.8029918670654297, 'learning_rate': 0.00019284858268809137, 'epoch': 0.08}\n", + "{'loss': 1.7257, 'grad_norm': 5.8476738929748535, 'learning_rate': 0.0001914959667849825, 'epoch': 0.09}\n", + "{'loss': 1.7003, 'grad_norm': 2.2313828468322754, 'learning_rate': 0.00019003187714021938, 'epoch': 0.09}\n", + "{'loss': 1.8, 'grad_norm': 3.8658030033111572, 'learning_rate': 0.0001884580975215084, 'epoch': 0.1}\n", + "{'loss': 1.5911, 'grad_norm': 3.2242016792297363, 'learning_rate': 0.00018677654533689287, 'epoch': 0.1}\n", + "{'loss': 1.4434, 'grad_norm': 1.3740187883377075, 'learning_rate': 0.00018498926929868642, 'epoch': 0.1}\n", + "{'loss': 1.8384, 'grad_norm': 5.402496814727783, 'learning_rate': 0.00018309844692743283, 'epoch': 0.11}\n", + "{'loss': 1.923, 'grad_norm': 1.3942235708236694, 'learning_rate': 0.00018110638189893267, 'epoch': 0.11}\n", + "{'loss': 1.6347, 'grad_norm': 3.253997802734375, 'learning_rate': 0.00017901550123756906, 'epoch': 0.12}\n", + "{'loss': 2.0972, 'grad_norm': 2.558892011642456, 'learning_rate': 0.00017682835235935236, 'epoch': 0.12}\n", + "{'loss': 1.5171, 'grad_norm': 1.5487256050109863, 'learning_rate': 0.00017454759996828623, 'epoch': 0.12}\n", + "{'loss': 1.6376, 'grad_norm': 2.0409491062164307, 'learning_rate': 0.00017217602280983623, 'epoch': 0.13}\n", + "{'loss': 1.5445, 'grad_norm': 2.144237995147705, 'learning_rate': 0.00016971651028545648, 'epoch': 0.13}\n", + "{'loss': 1.8636, 'grad_norm': 1.4127683639526367, 'learning_rate': 0.00016717205893229903, 'epoch': 0.14}\n", + "{'loss': 1.7837, 'grad_norm': 6.078901767730713, 'learning_rate': 0.00016454576877239507, 'epoch': 0.14}\n", + "{'loss': 1.6061, 'grad_norm': 3.109487295150757, 'learning_rate': 0.0001618408395357554, 'epoch': 0.14}\n", + "{'loss': 1.5021, 'grad_norm': 1.3617849349975586, 'learning_rate': 0.00015906056676199255, 'epoch': 0.15}\n", + "{'loss': 1.6636, 'grad_norm': 3.393275260925293, 'learning_rate': 0.00015620833778521307, 'epoch': 0.15}\n", + "{'loss': 1.6855, 'grad_norm': 0.8995980024337769, 'learning_rate': 0.000153287627607073, 'epoch': 0.16}\n", + "{'loss': 1.5462, 'grad_norm': 2.010761022567749, 'learning_rate': 0.00015030199466302353, 'epoch': 0.16}\n", + "{'loss': 1.6116, 'grad_norm': 0.8446106314659119, 'learning_rate': 0.00014725507648690543, 'epoch': 0.16}\n", + "{'loss': 1.3762, 'grad_norm': 0.8545190691947937, 'learning_rate': 0.00014415058527917452, 'epoch': 0.17}\n", + "{'loss': 1.5378, 'grad_norm': 2.424393892288208, 'learning_rate': 0.00014099230338415728, 'epoch': 0.17}\n", + "{'loss': 1.7943, 'grad_norm': 1.9315241575241089, 'learning_rate': 0.00013778407868184672, 'epoch': 0.18}\n", + "{'loss': 1.4796, 'grad_norm': 10.031947135925293, 'learning_rate': 0.00013452981989985348, 'epoch': 0.18}\n", + "{'loss': 1.4791, 'grad_norm': 5.992521286010742, 'learning_rate': 0.00013123349185122327, 'epoch': 0.18}\n", + "{'loss': 1.6421, 'grad_norm': 2.3296213150024414, 'learning_rate': 0.00012789911060392294, 'epoch': 0.19}\n", + "{'loss': 1.4964, 'grad_norm': 0.8648881912231445, 'learning_rate': 0.00012453073858788026, 'epoch': 0.19}\n", + "{'loss': 1.5299, 'grad_norm': 2.2629246711730957, 'learning_rate': 0.00012113247964553888, 'epoch': 0.2}\n", + "{'loss': 1.636, 'grad_norm': 2.0503945350646973, 'learning_rate': 0.00011770847403195834, 'epoch': 0.2}\n", + "{'loss': 1.5663, 'grad_norm': 1.098511815071106, 'learning_rate': 0.00011426289337055119, 'epoch': 0.2}\n", + "{'loss': 1.447, 'grad_norm': 1.389303207397461, 'learning_rate': 0.0001107999355706023, 'epoch': 0.21}\n", + "{'loss': 1.5855, 'grad_norm': 5.079431533813477, 'learning_rate': 0.00010732381971276318, 'epoch': 0.21}\n", + "{'loss': 1.7709, 'grad_norm': 2.1517255306243896, 'learning_rate': 0.00010383878090875201, 'epoch': 0.22}\n", + "{'loss': 1.4591, 'grad_norm': 2.4005439281463623, 'learning_rate': 0.00010034906514152238, 'epoch': 0.22}\n", + "{'loss': 1.453, 'grad_norm': 3.399737596511841, 'learning_rate': 9.685892409218717e-05, 'epoch': 0.22}\n", + "{'loss': 1.4393, 'grad_norm': 2.539557456970215, 'learning_rate': 9.337260996000002e-05, 'epoch': 0.23}\n", + "{'loss': 1.2233, 'grad_norm': 1.0666978359222412, 'learning_rate': 8.989437028170537e-05, 'epoch': 0.23}\n", + "{'loss': 1.3933, 'grad_norm': 1.396644115447998, 'learning_rate': 8.642844275656957e-05, 'epoch': 0.24}\n", + "{'loss': 1.7393, 'grad_norm': 3.009880781173706, 'learning_rate': 8.297905008339677e-05, 'epoch': 0.24}\n", + "{'loss': 1.3375, 'grad_norm': 1.3349215984344482, 'learning_rate': 7.955039481582097e-05, 'epoch': 0.24}\n", + "{'loss': 1.3724, 'grad_norm': 1.3314404487609863, 'learning_rate': 7.614665424214193e-05, 'epoch': 0.25}\n", + "{'loss': 1.6903, 'grad_norm': 5.373208045959473, 'learning_rate': 7.277197529594257e-05, 'epoch': 0.25}\n", + "{'loss': 1.5309, 'grad_norm': 2.590350389480591, 'learning_rate': 6.943046950368944e-05, 'epoch': 0.26}\n", + "{'loss': 1.3811, 'grad_norm': 2.371265411376953, 'learning_rate': 6.612620797547087e-05, 'epoch': 0.26}\n", + "{'loss': 1.4638, 'grad_norm': 0.8982325196266174, 'learning_rate': 6.286321644497655e-05, 'epoch': 0.26}\n", + "{'loss': 1.2281, 'grad_norm': 0.9514788389205933, 'learning_rate': 5.964547036476099e-05, 'epoch': 0.27}\n", + "{'loss': 1.755, 'grad_norm': 1.8306206464767456, 'learning_rate': 5.647689006276726e-05, 'epoch': 0.27}\n", + "{'loss': 1.7814, 'grad_norm': 0.696087121963501, 'learning_rate': 5.33613359660109e-05, 'epoch': 0.28}\n", + "{'loss': 1.5497, 'grad_norm': 2.2035014629364014, 'learning_rate': 5.0302603897244474e-05, 'epoch': 0.28}\n", + "{'loss': 1.6103, 'grad_norm': 4.5944318771362305, 'learning_rate': 4.7304420450332244e-05, 'epoch': 0.28}\n", + "{'loss': 1.4489, 'grad_norm': 0.8802727460861206, 'learning_rate': 4.437043844996952e-05, 'epoch': 0.29}\n", + "{'loss': 1.4725, 'grad_norm': 2.690830945968628, 'learning_rate': 4.150423250127845e-05, 'epoch': 0.29}\n", + "{'loss': 1.46, 'grad_norm': 1.2414122819900513, 'learning_rate': 3.8709294634702376e-05, 'epoch': 0.3}\n", + "{'loss': 1.4037, 'grad_norm': 1.5004230737686157, 'learning_rate': 3.5989030051504434e-05, 'epoch': 0.3}\n", + "{'loss': 1.6989, 'grad_norm': 2.3970391750335693, 'learning_rate': 3.334675297505476e-05, 'epoch': 0.3}\n", + "{'loss': 1.6084, 'grad_norm': 1.4109355211257935, 'learning_rate': 3.078568261295933e-05, 'epoch': 0.31}\n", + "{'loss': 1.5322, 'grad_norm': 1.381934404373169, 'learning_rate': 2.8308939234951726e-05, 'epoch': 0.31}\n", + "{'loss': 1.3193, 'grad_norm': 1.1329087018966675, 'learning_rate': 2.5919540371325e-05, 'epoch': 0.32}\n", + "{'loss': 1.824, 'grad_norm': 1.6152098178863525, 'learning_rate': 2.362039713653581e-05, 'epoch': 0.32}\n", + "{'loss': 1.6284, 'grad_norm': 3.0661303997039795, 'learning_rate': 2.1414310682459802e-05, 'epoch': 0.32}\n", + "{'loss': 1.6061, 'grad_norm': 2.1982345581054688, 'learning_rate': 1.930396878561983e-05, 'epoch': 0.33}\n", + "{'loss': 1.6587, 'grad_norm': 1.5903258323669434, 'learning_rate': 1.7291942572543807e-05, 'epoch': 0.33}\n", + "{'loss': 1.5601, 'grad_norm': 2.4994590282440186, 'learning_rate': 1.538068338724361e-05, 'epoch': 0.34}\n", + "{'loss': 1.5675, 'grad_norm': 1.3852919340133667, 'learning_rate': 1.3572519804629536e-05, 'epoch': 0.34}\n", + "{'loss': 1.573, 'grad_norm': 1.9808911085128784, 'learning_rate': 1.1869654793500784e-05, 'epoch': 0.34}\n", + "{'loss': 1.4122, 'grad_norm': 1.0273723602294922, 'learning_rate': 1.0274163032567163e-05, 'epoch': 0.35}\n", + "{'loss': 1.6348, 'grad_norm': 2.3089427947998047, 'learning_rate': 8.787988382772705e-06, 'epoch': 0.35}\n", + "{'loss': 1.6846, 'grad_norm': 2.9593446254730225, 'learning_rate': 7.412941519000527e-06, 'epoch': 0.36}\n", + "{'loss': 1.3497, 'grad_norm': 1.250377893447876, 'learning_rate': 6.1506977240444074e-06, 'epoch': 0.36}\n", + "{'loss': 1.3018, 'grad_norm': 0.7037477493286133, 'learning_rate': 5.002794847534764e-06, 'epoch': 0.36}\n", + "{'loss': 1.6822, 'grad_norm': 7.355447769165039, 'learning_rate': 3.970631432305694e-06, 'epoch': 0.37}\n", + "{'loss': 1.6635, 'grad_norm': 3.2042362689971924, 'learning_rate': 3.0554650104861136e-06, 'epoch': 0.37}\n", + "{'loss': 1.5018, 'grad_norm': 3.024123191833496, 'learning_rate': 2.2584105713904125e-06, 'epoch': 0.38}\n", + "{'loss': 1.4566, 'grad_norm': 3.8612897396087646, 'learning_rate': 1.580439203075812e-06, 'epoch': 0.38}\n", + "{'loss': 1.4799, 'grad_norm': 5.22689962387085, 'learning_rate': 1.0223769092211012e-06, 'epoch': 0.38}\n", + "{'loss': 1.5362, 'grad_norm': 5.0023698806762695, 'learning_rate': 5.849036027684606e-07, 'epoch': 0.39}\n", + "{'loss': 1.5031, 'grad_norm': 0.9480083584785461, 'learning_rate': 2.685522775541904e-07, 'epoch': 0.39}\n", + "{'loss': 1.5271, 'grad_norm': 1.9477710723876953, 'learning_rate': 7.370835893788508e-08, 'epoch': 0.4}\n", + "{'loss': 1.5134, 'grad_norm': 1.0355870723724365, 'learning_rate': 6.092342209607083e-10, 'epoch': 0.4}\n", + "{'train_runtime': 2455.9554, 'train_samples_per_second': 1.629, 'train_steps_per_second': 0.407, 'train_loss': 1.6843333339691162, 'epoch': 0.4}\n", + "Saving the last checkpoint of the model\n" + ] + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "model.safetensors: 0%| | 0.00/2.25G [00:00