diff --git "a/Kopie_von_LLaMA_Factory_Tutorial.ipynb" "b/Kopie_von_LLaMA_Factory_Tutorial.ipynb" new file mode 100644--- /dev/null +++ "b/Kopie_von_LLaMA_Factory_Tutorial.ipynb" @@ -0,0 +1,7321 @@ +{ + "nbformat": 4, + "nbformat_minor": 0, + "metadata": { + "colab": { + "provenance": [], + "gpuType": "T4" + }, + "kernelspec": { + "name": "python3", + "display_name": "Python 3" + }, + "language_info": { + "name": "python" + }, + "accelerator": "GPU", + "widgets": { + "application/vnd.jupyter.widget-state+json": { + "f95ce7e75ebc4e20905fed28cad2f5c3": { + "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_2ec65871301e461abaeaa378b971530b", + "IPY_MODEL_91b90a9bd5a24705b922afedf691f2b8", + "IPY_MODEL_d816934e6db644eea770054078c2147c" + ], + "layout": "IPY_MODEL_482a79ad0b3e4e7e9fc85e4b254e2ac1" + } + }, + "2ec65871301e461abaeaa378b971530b": { + "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_4f8ccf5c128f4b6681c781d80e80a8db", + "placeholder": "​", + "style": "IPY_MODEL_c6d77271c1564aebbe595eabb86f62d5", + "value": "tokenizer_config.json: 100%" + } + }, + "91b90a9bd5a24705b922afedf691f2b8": { + "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_ecde876399eb4e8b96326609aac75d9f", + "max": 967, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_21a2f8d812a246ba9c9e019e8df16567", + "value": 967 + } + }, + "d816934e6db644eea770054078c2147c": { + "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_f16b58b67bd34422bc450f8686042bb1", + "placeholder": "​", + "style": "IPY_MODEL_9d6fbbc562ab4a668078987404a72dc2", + "value": " 967/967 [00:00<00:00, 61.7kB/s]" + } + }, + "482a79ad0b3e4e7e9fc85e4b254e2ac1": { + "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 + } + }, + "4f8ccf5c128f4b6681c781d80e80a8db": { + "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 + } + }, + "c6d77271c1564aebbe595eabb86f62d5": { + "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": "" + } + }, + "ecde876399eb4e8b96326609aac75d9f": { + "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 + } + }, + "21a2f8d812a246ba9c9e019e8df16567": { + "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": "" + } + }, + "f16b58b67bd34422bc450f8686042bb1": { + "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 + } + }, + "9d6fbbc562ab4a668078987404a72dc2": { + "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": "" + } + }, + "8aea46e7ca014923a5877b1e22b96238": { + "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_f2edf85ef88943688a14dafb63fc67b8", + "IPY_MODEL_c75df4143eba4f538af590b6dd681123", + "IPY_MODEL_2621fd2a4181480989bbf6057929bb45" + ], + "layout": "IPY_MODEL_dc5948cf6cd44f0d95519dc1a790b58e" + } + }, + "f2edf85ef88943688a14dafb63fc67b8": { + "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_9efdadefb26a45ab96f6c3bf39da59ee", + "placeholder": "​", + "style": "IPY_MODEL_c4f0986f8e794a49a33649dc11a15943", + "value": "tokenizer.model: 100%" + } + }, + "c75df4143eba4f538af590b6dd681123": { + "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_51ffe4c2e3944eddad61d9a906148383", + "max": 493443, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_6867b320d79540a28fcc5e2ee1151b81", + "value": 493443 + } + }, + "2621fd2a4181480989bbf6057929bb45": { + "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_9d4ea1d0fa1c41fbaa121299f8a4c75d", + "placeholder": "​", + "style": "IPY_MODEL_7552315cee5042bfaa96e1da3da88338", + "value": " 493k/493k [00:00<00:00, 11.7MB/s]" + } + }, + "dc5948cf6cd44f0d95519dc1a790b58e": { + "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 + } + }, + "9efdadefb26a45ab96f6c3bf39da59ee": { + "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 + } + }, + "c4f0986f8e794a49a33649dc11a15943": { + "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": "" + } + }, + "51ffe4c2e3944eddad61d9a906148383": { + "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 + } + }, + "6867b320d79540a28fcc5e2ee1151b81": { + "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": "" + } + }, + "9d4ea1d0fa1c41fbaa121299f8a4c75d": { + "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 + } + }, + "7552315cee5042bfaa96e1da3da88338": { + "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": "" + } + }, + "84fbcbd613264a3aa92dd64ad95c1866": { + "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_b5aa83fea65d468183e3fa3df50b4f09", + "IPY_MODEL_068a54661fcc48c0903f9c34d87aaa2e", + "IPY_MODEL_34f3d00cc953403ebb19200b6b8b5376" + ], + "layout": "IPY_MODEL_2f7b09c672be4b03a76dd98287158c89" + } + }, + "b5aa83fea65d468183e3fa3df50b4f09": { + "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_9a96b7aa47294f499a515ef38414b9a8", + "placeholder": "​", + "style": "IPY_MODEL_6ecefcd7c2c24b249327fa9525ffc7f2", + "value": "special_tokens_map.json: 100%" + } + }, + "068a54661fcc48c0903f9c34d87aaa2e": { + "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_971344d11977449387c038bbb1cfeb46", + "max": 72, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_5e9d245cca4e48f78ad935e74d58e61e", + "value": 72 + } + }, + "34f3d00cc953403ebb19200b6b8b5376": { + "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_1e95ecd607b84695a15e4e597c3de738", + "placeholder": "​", + "style": "IPY_MODEL_8f63de6c55224c49a000e0a1a10ca547", + "value": " 72.0/72.0 [00:00<00:00, 4.68kB/s]" + } + }, + "2f7b09c672be4b03a76dd98287158c89": { + "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 + } + }, + "9a96b7aa47294f499a515ef38414b9a8": { + "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 + } + }, + "6ecefcd7c2c24b249327fa9525ffc7f2": { + "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": "" + } + }, + "971344d11977449387c038bbb1cfeb46": { + "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 + } + }, + "5e9d245cca4e48f78ad935e74d58e61e": { + "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": "" + } + }, + "1e95ecd607b84695a15e4e597c3de738": { + "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 + } + }, + "8f63de6c55224c49a000e0a1a10ca547": { + "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": "" + } + }, + "5eb823b8b3a048e5acef70db28c25029": { + "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_5f20cd4e7d674661949ab350a8587e53", + "IPY_MODEL_1150955b86354a2584904da92bc78406", + "IPY_MODEL_8679589efdc74a1cb94a795d5695a5b5" + ], + "layout": "IPY_MODEL_9624777e25014932bd7ffe7d8aea1203" + } + }, + "5f20cd4e7d674661949ab350a8587e53": { + "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_d3e0367018fa418faa057118fabac7f3", + "placeholder": "​", + "style": "IPY_MODEL_cb3cd80934f14f02b3fb2f252ccb935d", + "value": "tokenizer.json: 100%" + } + }, + "1150955b86354a2584904da92bc78406": { + "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_e523abbd1d0f4a18946a93303db2ee2d", + "max": 1795303, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_2d8b051636b94083a153a374075c037b", + "value": 1795303 + } + }, + "8679589efdc74a1cb94a795d5695a5b5": { + "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_3d716cb97ce44c3986a09285a277e839", + "placeholder": "​", + "style": "IPY_MODEL_470f3df55db74a3aabe7a79ea3f54105", + "value": " 1.80M/1.80M [00:00<00:00, 14.5MB/s]" + } + }, + "9624777e25014932bd7ffe7d8aea1203": { + "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 + } + }, + "d3e0367018fa418faa057118fabac7f3": { + "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 + } + }, + "cb3cd80934f14f02b3fb2f252ccb935d": { + "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": "" + } + }, + "e523abbd1d0f4a18946a93303db2ee2d": { + "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 + } + }, + "2d8b051636b94083a153a374075c037b": { + "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": "" + } + }, + "3d716cb97ce44c3986a09285a277e839": { + "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 + } + }, + "470f3df55db74a3aabe7a79ea3f54105": { + "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": "" + } + }, + "9d445d452abf4bddb831eecaddb39304": { + "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_de4671b0d5ca48b38f9f569aa0748b3a", + "IPY_MODEL_0d523ae3438b4f3ab1b9856d07a666c2", + "IPY_MODEL_fa7f42fe5b3e4b9ea8aed8f648db7b93" + ], + "layout": "IPY_MODEL_df06640522b14700b7a9a60b3c826069" + } + }, + "de4671b0d5ca48b38f9f569aa0748b3a": { + "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_b8c19471f312480aa4bb4a82874410a6", + "placeholder": "​", + "style": "IPY_MODEL_0a09e4f5f6704ddb9f96a76459715ed8", + "value": "Generating train split: " + } + }, + "0d523ae3438b4f3ab1b9856d07a666c2": { + "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_d32a415f1615417ba22471f22d0fdbf2", + "max": 1, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_5fdb36111b0e4d909e6ec9e17b2ececa", + "value": 1 + } + }, + "fa7f42fe5b3e4b9ea8aed8f648db7b93": { + "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_b502f88e55024af3acffd709fe438007", + "placeholder": "​", + "style": "IPY_MODEL_6fffcde2c1a7439c9d01d54299213851", + "value": " 20202/0 [00:01<00:00, 18891.16 examples/s]" + } + }, + "df06640522b14700b7a9a60b3c826069": { + "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 + } + }, + "b8c19471f312480aa4bb4a82874410a6": { + "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 + } + }, + "0a09e4f5f6704ddb9f96a76459715ed8": { + "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": "" + } + }, + "d32a415f1615417ba22471f22d0fdbf2": { + "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" + } + }, + "5fdb36111b0e4d909e6ec9e17b2ececa": { + "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": "" + } + }, + "b502f88e55024af3acffd709fe438007": { + "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 + } + }, + "6fffcde2c1a7439c9d01d54299213851": { + "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": "" + } + }, + "687f256662104276b36936259a30f0ef": { + "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_6a539c18f8dd4264afa56e3edc6d6a6a", + "IPY_MODEL_da21c4d52dbd4dd2b70d79510aa115c4", + "IPY_MODEL_1ef39344e7594e11a2c601a0a57b5f53" + ], + "layout": "IPY_MODEL_6d44e4c010684a8c96d0d7929bf63663" + } + }, + "6a539c18f8dd4264afa56e3edc6d6a6a": { + "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_92c89cfa23304f4e8dc436820a762519", + "placeholder": "​", + "style": "IPY_MODEL_ce5187af896746df9314eab72b1d4519", + "value": "Converting format of dataset: 100%" + } + }, + "da21c4d52dbd4dd2b70d79510aa115c4": { + "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_a8992951c4af49e2ad05c55ed5886661", + "max": 500, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_31541b1f4e2c40b0ba0c23c175877e2e", + "value": 500 + } + }, + "1ef39344e7594e11a2c601a0a57b5f53": { + "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_5497233cde16423f9d60134249e3640e", + "placeholder": "​", + "style": "IPY_MODEL_2d2b6e583ab24a6a83ded68d29d515bb", + "value": " 500/500 [00:00<00:00, 8683.82 examples/s]" + } + }, + "6d44e4c010684a8c96d0d7929bf63663": { + "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 + } + }, + "92c89cfa23304f4e8dc436820a762519": { + "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 + } + }, + "ce5187af896746df9314eab72b1d4519": { + "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": "" + } + }, + "a8992951c4af49e2ad05c55ed5886661": { + "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 + } + }, + "31541b1f4e2c40b0ba0c23c175877e2e": { + "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": "" + } + }, + "5497233cde16423f9d60134249e3640e": { + "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 + } + }, + "2d2b6e583ab24a6a83ded68d29d515bb": { + "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": "" + } + }, + "dfca1c390ec94938ab880b29b5cfd01f": { + "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_de7e0d4c1d6f4833ad5ef265ba2f04ac", + "IPY_MODEL_6b8dd06a1fcc433cb43508c84fb55ea0", + "IPY_MODEL_2e2a66729e2242c4be9f49963e718cd5" + ], + "layout": "IPY_MODEL_2927e4ef6daf414298e114f59b087592" + } + }, + "de7e0d4c1d6f4833ad5ef265ba2f04ac": { + "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_04f2d402b98440b587f93e6283276921", + "placeholder": "​", + "style": "IPY_MODEL_2679bd2e2cd34aefb7d918ffdb16ff2b", + "value": "Running tokenizer on dataset: 100%" + } + }, + "6b8dd06a1fcc433cb43508c84fb55ea0": { + "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_dd36da30f98245b08cfe5642a704a05c", + "max": 500, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_791bb77d7a6e411eb01f9306dfd0af28", + "value": 500 + } + }, + "2e2a66729e2242c4be9f49963e718cd5": { + "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_25dd4496d6974fe1a2c790a5518b8f79", + "placeholder": "​", + "style": "IPY_MODEL_f0490977e2374b05abe4af44c38ef6e7", + "value": " 500/500 [00:01<00:00, 407.16 examples/s]" + } + }, + "2927e4ef6daf414298e114f59b087592": { + "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 + } + }, + "04f2d402b98440b587f93e6283276921": { + "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 + } + }, + "2679bd2e2cd34aefb7d918ffdb16ff2b": { + "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": "" + } + }, + "dd36da30f98245b08cfe5642a704a05c": { + "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 + } + }, + "791bb77d7a6e411eb01f9306dfd0af28": { + "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": "" + } + }, + "25dd4496d6974fe1a2c790a5518b8f79": { + "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 + } + }, + "f0490977e2374b05abe4af44c38ef6e7": { + "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": "" + } + }, + "af18f88fe69a43cf985f26f793266348": { + "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_ba26598d19b3417b85570d1df4d72e29", + "IPY_MODEL_dece02013e43434b90e34c1c4e891b39", + "IPY_MODEL_16774d0fa73b4a9da13e976ef86ba7f2" + ], + "layout": "IPY_MODEL_c27c2e11f0a440c1961249efa0f52549" + } + }, + "ba26598d19b3417b85570d1df4d72e29": { + "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_da925912eea742ca9f9f2f6bf0682d4e", + "placeholder": "​", + "style": "IPY_MODEL_c610798dc27c41fb92aef1d74cb39537", + "value": "config.json: 100%" + } + }, + "dece02013e43434b90e34c1c4e891b39": { + "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_fe09e0a3b5de4a969f76083fcd9f6ff4", + "max": 571, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_0ca77f0a650446db9d52cf228d7cd610", + "value": 571 + } + }, + "16774d0fa73b4a9da13e976ef86ba7f2": { + "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_54f227c080b340e6a10fc86823dcae7f", + "placeholder": "​", + "style": "IPY_MODEL_cdc60571f14a40e89bfdb894973eb408", + "value": " 571/571 [00:00<00:00, 22.0kB/s]" + } + }, + "c27c2e11f0a440c1961249efa0f52549": { + "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 + } + }, + "da925912eea742ca9f9f2f6bf0682d4e": { + "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 + } + }, + "c610798dc27c41fb92aef1d74cb39537": { + "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": "" + } + }, + "fe09e0a3b5de4a969f76083fcd9f6ff4": { + "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 + } + }, + "0ca77f0a650446db9d52cf228d7cd610": { + "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": "" + } + }, + "54f227c080b340e6a10fc86823dcae7f": { + "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 + } + }, + "cdc60571f14a40e89bfdb894973eb408": { + "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": "" + } + }, + "900a50758c5d4c82993d65ef940a24d7": { + "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_0a1b5a63a6da42a6a4d9145d6782d3a0", + "IPY_MODEL_afe4c5d8e9694ddd838e622bcbdb7b76", + "IPY_MODEL_ce8389a7a56e4229b548da25de6d3dfd" + ], + "layout": "IPY_MODEL_13a6d6e2c85e497f99dab8f0e90796c0" + } + }, + "0a1b5a63a6da42a6a4d9145d6782d3a0": { + "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_e2d2c569765140bbb92adc8dea169d95", + "placeholder": "​", + "style": "IPY_MODEL_9169e2eb72fa4d949b1ad31e18851fc1", + "value": "model.safetensors.index.json: 100%" + } + }, + "afe4c5d8e9694ddd838e622bcbdb7b76": { + "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_78c1753419d14545a1f23b64f21df6cd", + "max": 25125, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_63e53148010642e18b4af6f7ca566ed2", + "value": 25125 + } + }, + "ce8389a7a56e4229b548da25de6d3dfd": { + "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_9f73a969648d4636882dcbc7349d8b25", + "placeholder": "​", + "style": "IPY_MODEL_5b3ae5ea41fc4bb6884c881c993fddcc", + "value": " 25.1k/25.1k [00:00<00:00, 1.38MB/s]" + } + }, + "13a6d6e2c85e497f99dab8f0e90796c0": { + "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 + } + }, + "e2d2c569765140bbb92adc8dea169d95": { + "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 + } + }, + "9169e2eb72fa4d949b1ad31e18851fc1": { + "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": "" + } + }, + "78c1753419d14545a1f23b64f21df6cd": { + "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 + } + }, + "63e53148010642e18b4af6f7ca566ed2": { + "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": "" + } + }, + "9f73a969648d4636882dcbc7349d8b25": { + "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 + } + }, + "5b3ae5ea41fc4bb6884c881c993fddcc": { + "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": "" + } + }, + "1090cb2ed1c74dbc818bf64f8f89e761": { + "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_0a275e74c45d471ba6efce60f6170b3a", + "IPY_MODEL_b23d2e0455774b1ba42db3ac1bad9c69", + "IPY_MODEL_de0d22ef70e8490286cd3cb35a23bd9c" + ], + "layout": "IPY_MODEL_9aa8d77e15eb4d549ec9d2579486528c" + } + }, + "0a275e74c45d471ba6efce60f6170b3a": { + "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_1960bc2f403d4d4e9ca0c49c5b191ff0", + "placeholder": "​", + "style": "IPY_MODEL_144ddbb6ed7745348cda9fe695269b0d", + "value": "Downloading shards: 100%" + } + }, + "b23d2e0455774b1ba42db3ac1bad9c69": { + "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_3e7e570583b548bbb84a1c8b290f2234", + "max": 2, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_7d78cba869fe469c839d11b54180d9a5", + "value": 2 + } + }, + "de0d22ef70e8490286cd3cb35a23bd9c": { + "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_f1f0a8a751c44294900c997175a5e052", + "placeholder": "​", + "style": "IPY_MODEL_bb22ba5411684a9babfe752dd00d0ea6", + "value": " 2/2 [01:31<00:00, 41.58s/it]" + } + }, + "9aa8d77e15eb4d549ec9d2579486528c": { + "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 + } + }, + "1960bc2f403d4d4e9ca0c49c5b191ff0": { + "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 + } + }, + "144ddbb6ed7745348cda9fe695269b0d": { + "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": "" + } + }, + "3e7e570583b548bbb84a1c8b290f2234": { + "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 + } + }, + "7d78cba869fe469c839d11b54180d9a5": { + "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": "" + } + }, + "f1f0a8a751c44294900c997175a5e052": { + "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 + } + }, + "bb22ba5411684a9babfe752dd00d0ea6": { + "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": "" + } + }, + "7ef769cb6a3646e4b058eace7866b32b": { + "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_f2d3c9fdf75a4b2d8db817293cf46af5", + "IPY_MODEL_cd4e951c119f406c93221f9bec663792", + "IPY_MODEL_fcad30d4033f4c64a0a8efeb7feabd91" + ], + "layout": "IPY_MODEL_6c8fc51a084444d8ab98b7ec58105ce5" + } + }, + "f2d3c9fdf75a4b2d8db817293cf46af5": { + "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_169366de76ba4cf4ac7f61fc90494aa1", + "placeholder": "​", + "style": "IPY_MODEL_eff454fe170c4a4283301ede36d1c77c", + "value": "model-00001-of-00002.safetensors: 100%" + } + }, + "cd4e951c119f406c93221f9bec663792": { + "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_c97b3bba56c34fb196f4776ce9469738", + "max": 9942981696, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_b058e907e5f2450dae4c4c23d12cb09b", + "value": 9942981696 + } + }, + "fcad30d4033f4c64a0a8efeb7feabd91": { + "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_8fef758e915c433bb1f2101601d24f7d", + "placeholder": "​", + "style": "IPY_MODEL_595362c21c804a80a05102d069502e45", + "value": " 9.94G/9.94G [01:08<00:00, 91.0MB/s]" + } + }, + "6c8fc51a084444d8ab98b7ec58105ce5": { + "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 + } + }, + "169366de76ba4cf4ac7f61fc90494aa1": { + "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 + } + }, + "eff454fe170c4a4283301ede36d1c77c": { + "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": "" + } + }, + "c97b3bba56c34fb196f4776ce9469738": { + "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 + } + }, + "b058e907e5f2450dae4c4c23d12cb09b": { + "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": "" + } + }, + "8fef758e915c433bb1f2101601d24f7d": { + "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 + } + }, + "595362c21c804a80a05102d069502e45": { + "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": "" + } + }, + "f3dd024cf93348f99300f66c6ed74426": { + "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_64d9b7b9bead4c63a79850f812a65725", + "IPY_MODEL_e2077ca32a48446ab8a598cfd24560ac", + "IPY_MODEL_e03f20206724468ba155dde1a5e4c84f" + ], + "layout": "IPY_MODEL_5c28873d8a7548deb1cfe1d4f980ad4b" + } + }, + "64d9b7b9bead4c63a79850f812a65725": { + "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_90c0eb3147074d8798ad2ccfa4eb9dd3", + "placeholder": "​", + "style": "IPY_MODEL_0a9a4e707f604881873acc0f4d7a42c0", + "value": "model-00002-of-00002.safetensors: 100%" + } + }, + "e2077ca32a48446ab8a598cfd24560ac": { + "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_76cf1a5a96e140459d2de7d881144f88", + "max": 4540516344, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_5e08f61a9fc44792bd3a43116e38d804", + "value": 4540516344 + } + }, + "e03f20206724468ba155dde1a5e4c84f": { + "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_fcca954f131d4fe1b047f999df5ea5a3", + "placeholder": "​", + "style": "IPY_MODEL_bd521cdb23e84164b76a844037b5e202", + "value": " 4.54G/4.54G [00:22<00:00, 253MB/s]" + } + }, + "5c28873d8a7548deb1cfe1d4f980ad4b": { + "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 + } + }, + "90c0eb3147074d8798ad2ccfa4eb9dd3": { + "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 + } + }, + "0a9a4e707f604881873acc0f4d7a42c0": { + "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": "" + } + }, + "76cf1a5a96e140459d2de7d881144f88": { + "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 + } + }, + "5e08f61a9fc44792bd3a43116e38d804": { + "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": "" + } + }, + "fcca954f131d4fe1b047f999df5ea5a3": { + "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 + } + }, + "bd521cdb23e84164b76a844037b5e202": { + "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": "" + } + }, + "1911489caa474fc7aeede1e94cf673b2": { + "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_e43f16a9a7eb4396a73e47dbe86d86dd", + "IPY_MODEL_8ada8f039d38464b9ee5c9fc19d58d86", + "IPY_MODEL_8a56009da9114d7c89b28196eda64fde" + ], + "layout": "IPY_MODEL_7df19c3a808144a99c366c157630a227" + } + }, + "e43f16a9a7eb4396a73e47dbe86d86dd": { + "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_3311434267ca41a6980c903b63e1cb9b", + "placeholder": "​", + "style": "IPY_MODEL_ffa60fc9bc164af2b79bd6212dcb46a0", + "value": "Loading checkpoint shards: 100%" + } + }, + "8ada8f039d38464b9ee5c9fc19d58d86": { + "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_0174ba072a7b4d0aae5c81a71f021f56", + "max": 2, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_313b26430be34cf79cffcadf2a25b804", + "value": 2 + } + }, + "8a56009da9114d7c89b28196eda64fde": { + "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_6f8f413a8286463097ae9c6f4abe6018", + "placeholder": "​", + "style": "IPY_MODEL_43ed32f70e834038a88e60bad7ee312d", + "value": " 2/2 [01:09<00:00, 32.33s/it]" + } + }, + "7df19c3a808144a99c366c157630a227": { + "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 + } + }, + "3311434267ca41a6980c903b63e1cb9b": { + "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 + } + }, + "ffa60fc9bc164af2b79bd6212dcb46a0": { + "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": "" + } + }, + "0174ba072a7b4d0aae5c81a71f021f56": { + "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 + } + }, + "313b26430be34cf79cffcadf2a25b804": { + "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": "" + } + }, + "6f8f413a8286463097ae9c6f4abe6018": { + "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 + } + }, + "43ed32f70e834038a88e60bad7ee312d": { + "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": "" + } + }, + "a26d44fa1e5f4b7bbdd8031bc5399240": { + "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_e78c7a6ad68d4f418581e6dddfb1d299", + "IPY_MODEL_713ef5f962a94e4fbdb59b7ff44e532b", + "IPY_MODEL_04bd33cea6cd49cf9c723a26de46c26c" + ], + "layout": "IPY_MODEL_f10ae252772c42f6ab84e517967922cb" + } + }, + "e78c7a6ad68d4f418581e6dddfb1d299": { + "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_b86d1631f0494048b3c45a8278dae598", + "placeholder": "​", + "style": "IPY_MODEL_9638f2fe85e4416195fad7be5ea51e28", + "value": "generation_config.json: 100%" + } + }, + "713ef5f962a94e4fbdb59b7ff44e532b": { + "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_320520e310914745a7a77cbfc41e856a", + "max": 116, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_bd29d07316d141b7afb8971ebc468668", + "value": 116 + } + }, + "04bd33cea6cd49cf9c723a26de46c26c": { + "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_73e1f901f3be40159693451332e52fe1", + "placeholder": "​", + "style": "IPY_MODEL_6f7241c2ce2140b3b59bd2d7b8db5276", + "value": " 116/116 [00:00<00:00, 8.68kB/s]" + } + }, + "f10ae252772c42f6ab84e517967922cb": { + "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 + } + }, + "b86d1631f0494048b3c45a8278dae598": { + "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 + } + }, + "9638f2fe85e4416195fad7be5ea51e28": { + "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": "" + } + }, + "320520e310914745a7a77cbfc41e856a": { + "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 + } + }, + "bd29d07316d141b7afb8971ebc468668": { + "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": "" + } + }, + "73e1f901f3be40159693451332e52fe1": { + "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 + } + }, + "6f7241c2ce2140b3b59bd2d7b8db5276": { + "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": "" + } + }, + "775689b53d674875af95dacb5a804c1d": { + "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_83ac0f982b664dd7ab1bf4003b649f7c", + "IPY_MODEL_93385c2627614f39a8cdaef41770d5dc", + "IPY_MODEL_6a68f4f93136476ba5dda0240ca5239a" + ], + "layout": "IPY_MODEL_a52bd50efc7c4a51ba349df39ca8934e" + } + }, + "83ac0f982b664dd7ab1bf4003b649f7c": { + "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_4c3db643b3cf49ba8faba63e21d1aa42", + "placeholder": "​", + "style": "IPY_MODEL_c1b46640ed8f453292dde7f7bc0be403", + "value": "Loading checkpoint shards: 100%" + } + }, + "93385c2627614f39a8cdaef41770d5dc": { + "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_f45df54413f543caa78f8f44474d600c", + "max": 2, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_957f211021b043d0a8da929b5b3e92c4", + "value": 2 + } + }, + "6a68f4f93136476ba5dda0240ca5239a": { + "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_63b452a4cbc546f0a6f956e2a5f5c0b9", + "placeholder": "​", + "style": "IPY_MODEL_5f7f24bf6b0b4797b019e8122d37fffe", + "value": " 2/2 [00:43<00:00, 43.65s/it]" + } + }, + "a52bd50efc7c4a51ba349df39ca8934e": { + "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 + } + }, + "4c3db643b3cf49ba8faba63e21d1aa42": { + "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 + } + }, + "c1b46640ed8f453292dde7f7bc0be403": { + "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": "" + } + }, + "f45df54413f543caa78f8f44474d600c": { + "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 + } + }, + "957f211021b043d0a8da929b5b3e92c4": { + "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": "" + } + }, + "63b452a4cbc546f0a6f956e2a5f5c0b9": { + "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 + } + }, + "5f7f24bf6b0b4797b019e8122d37fffe": { + "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": "" + } + }, + "2542ffb4be9846888c31c3b28d1fc8ee": { + "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_36125ba0485d4736896dbe41b5332273", + "IPY_MODEL_55a3d7ba21984835b0ccbeacb00cd74b", + "IPY_MODEL_ce80e04267264ca295383372b23d756e" + ], + "layout": "IPY_MODEL_8bd42cd71c55476dbc94e4e3b1cbcf67" + } + }, + "36125ba0485d4736896dbe41b5332273": { + "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_a928892a06694dd09e61b2c6db9707b3", + "placeholder": "​", + "style": "IPY_MODEL_422a58f5fa7646ed9003810b846d7868", + "value": "adapter_config.json: 100%" + } + }, + "55a3d7ba21984835b0ccbeacb00cd74b": { + "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_feff6dd972f842bf99c7f907971175a1", + "max": 728, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_8428dd401aac4812af6de9a840f3fbc8", + "value": 728 + } + }, + "ce80e04267264ca295383372b23d756e": { + "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_c54bf007b00143b4b21232d940043adc", + "placeholder": "​", + "style": "IPY_MODEL_f05412ea9aca4e158fc02755ca47f1b2", + "value": " 728/728 [00:00<00:00, 42.4kB/s]" + } + }, + "8bd42cd71c55476dbc94e4e3b1cbcf67": { + "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 + } + }, + "a928892a06694dd09e61b2c6db9707b3": { + "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 + } + }, + "422a58f5fa7646ed9003810b846d7868": { + "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": "" + } + }, + "feff6dd972f842bf99c7f907971175a1": { + "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 + } + }, + "8428dd401aac4812af6de9a840f3fbc8": { + "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": "" + } + }, + "c54bf007b00143b4b21232d940043adc": { + "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 + } + }, + "f05412ea9aca4e158fc02755ca47f1b2": { + "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": "" + } + }, + "818c371aa671498397a3a4c16e737f07": { + "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_b8707b2d77314eadba4ff5d77d12fead", + "IPY_MODEL_36c8c7b46fa74ea191e1b863b6b67773", + "IPY_MODEL_61ee25e87bbe4e8abcab805c97f3ac68" + ], + "layout": "IPY_MODEL_facd485690bd4aaab13fef6568fb03ae" + } + }, + "b8707b2d77314eadba4ff5d77d12fead": { + "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_78a7c76072bd4090976ddc2b7de874d8", + "placeholder": "​", + "style": "IPY_MODEL_9e1ac20517484497ae9a0ea565093858", + "value": "adapter_model.safetensors: 100%" + } + }, + "36c8c7b46fa74ea191e1b863b6b67773": { + "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_03684e6c259f46c684efe940626be82c", + "max": 167832240, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_8ca6e75fec51431eb1934c29c6c1b45f", + "value": 167832240 + } + }, + "61ee25e87bbe4e8abcab805c97f3ac68": { + "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_f7b4a6ea97c641cbbef74f26bbe132e1", + "placeholder": "​", + "style": "IPY_MODEL_3c6097f3850a4e7bb282ac4cfd0a5db3", + "value": " 168M/168M [00:03<00:00, 51.1MB/s]" + } + }, + "facd485690bd4aaab13fef6568fb03ae": { + "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 + } + }, + "78a7c76072bd4090976ddc2b7de874d8": { + "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 + } + }, + "9e1ac20517484497ae9a0ea565093858": { + "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": "" + } + }, + "03684e6c259f46c684efe940626be82c": { + "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 + } + }, + "8ca6e75fec51431eb1934c29c6c1b45f": { + "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": "" + } + }, + "f7b4a6ea97c641cbbef74f26bbe132e1": { + "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 + } + }, + "3c6097f3850a4e7bb282ac4cfd0a5db3": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + } + } + } + }, + "cells": [ + { + "cell_type": "markdown", + "source": [ + "# LLaMA Factory Colab Tutorial\n", + "\n", + "Please use a **free** Tesla T4 Colab GPU to run this!\n", + "\n", + "Project homepage: https://github.com/hiyouga/LLaMA-Factory" + ], + "metadata": { + "id": "1oHFCsV0z-Jw" + } + }, + { + "cell_type": "markdown", + "source": [ + "## Install Dependencies" + ], + "metadata": { + "id": "lr7rB3szzhtx" + } + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "giM74oK1rRIH", + "colab": { + "base_uri": "https://localhost:8080/" + }, + "outputId": "9fe5da00-83ad-4e40-ae59-56b14d35af98" + }, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Cloning into 'LLaMA-Factory'...\n", + "remote: Enumerating objects: 9045, done.\u001b[K\n", + "remote: Counting objects: 100% (1266/1266), done.\u001b[K\n", + "remote: Compressing objects: 100% (213/213), done.\u001b[K\n", + "remote: Total 9045 (delta 1120), reused 1063 (delta 1053), pack-reused 7779\u001b[K\n", + "Receiving objects: 100% (9045/9045), 212.73 MiB | 15.36 MiB/s, done.\n", + "Resolving deltas: 100% (6661/6661), done.\n", + "Updating files: 100% (192/192), done.\n", + "/content/LLaMA-Factory\n", + "\u001b[0m\u001b[01;34massets\u001b[0m/ docker-compose.yml \u001b[01;34mexamples\u001b[0m/ pyproject.toml requirements.txt \u001b[01;34msrc\u001b[0m/\n", + "CITATION.cff Dockerfile LICENSE README.md \u001b[01;34mscripts\u001b[0m/ \u001b[01;34mtests\u001b[0m/\n", + "\u001b[01;34mdata\u001b[0m/ \u001b[01;34mevaluation\u001b[0m/ Makefile README_zh.md setup.py\n", + "Processing /content/LLaMA-Factory\n", + " Installing build dependencies ... \u001b[?25l\u001b[?25hdone\n", + " Getting requirements to build wheel ... \u001b[?25l\u001b[?25hdone\n", + " Installing backend dependencies ... \u001b[?25l\u001b[?25hdone\n", + " Preparing metadata (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n", + "Requirement already satisfied: torch>=1.13.1 in /usr/local/lib/python3.10/dist-packages (from llmtuner==0.6.2.dev0) (2.2.1+cu121)\n", + "Requirement already satisfied: transformers>=4.37.2 in /usr/local/lib/python3.10/dist-packages (from llmtuner==0.6.2.dev0) (4.38.2)\n", + "Collecting datasets>=2.14.3 (from llmtuner==0.6.2.dev0)\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[31m8.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hCollecting accelerate>=0.27.2 (from llmtuner==0.6.2.dev0)\n", + " Downloading accelerate-0.29.1-py3-none-any.whl (297 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m297.3/297.3 kB\u001b[0m \u001b[31m12.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hCollecting peft>=0.10.0 (from llmtuner==0.6.2.dev0)\n", + " Downloading peft-0.10.0-py3-none-any.whl (199 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m199.1/199.1 kB\u001b[0m \u001b[31m12.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hCollecting trl>=0.8.1 (from llmtuner==0.6.2.dev0)\n", + " Downloading trl-0.8.1-py3-none-any.whl (225 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m225.0/225.0 kB\u001b[0m \u001b[31m13.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hCollecting gradio<=4.21.0,>=4.0.0 (from llmtuner==0.6.2.dev0)\n", + " Downloading gradio-4.21.0-py3-none-any.whl (17.0 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m17.0/17.0 MB\u001b[0m \u001b[31m48.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hRequirement already satisfied: scipy in /usr/local/lib/python3.10/dist-packages (from llmtuner==0.6.2.dev0) (1.11.4)\n", + "Collecting einops (from llmtuner==0.6.2.dev0)\n", + " Downloading einops-0.7.0-py3-none-any.whl (44 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m44.6/44.6 kB\u001b[0m \u001b[31m6.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hRequirement already satisfied: sentencepiece in /usr/local/lib/python3.10/dist-packages (from llmtuner==0.6.2.dev0) (0.1.99)\n", + "Requirement already satisfied: protobuf in /usr/local/lib/python3.10/dist-packages (from llmtuner==0.6.2.dev0) (3.20.3)\n", + "Collecting uvicorn (from llmtuner==0.6.2.dev0)\n", + " Downloading uvicorn-0.29.0-py3-none-any.whl (60 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m60.8/60.8 kB\u001b[0m \u001b[31m7.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hRequirement already satisfied: pydantic in /usr/local/lib/python3.10/dist-packages (from llmtuner==0.6.2.dev0) (2.6.4)\n", + "Collecting fastapi (from llmtuner==0.6.2.dev0)\n", + " Downloading fastapi-0.110.1-py3-none-any.whl (91 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m91.9/91.9 kB\u001b[0m \u001b[31m12.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hCollecting sse-starlette (from llmtuner==0.6.2.dev0)\n", + " Downloading sse_starlette-2.1.0-py3-none-any.whl (9.2 kB)\n", + "Requirement already satisfied: matplotlib in /usr/local/lib/python3.10/dist-packages (from llmtuner==0.6.2.dev0) (3.7.1)\n", + "Collecting fire (from llmtuner==0.6.2.dev0)\n", + " Downloading fire-0.6.0.tar.gz (88 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m88.4/88.4 kB\u001b[0m \u001b[31m12.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25h Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n", + "Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from accelerate>=0.27.2->llmtuner==0.6.2.dev0) (1.25.2)\n", + "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from accelerate>=0.27.2->llmtuner==0.6.2.dev0) (24.0)\n", + "Requirement already satisfied: psutil in /usr/local/lib/python3.10/dist-packages (from accelerate>=0.27.2->llmtuner==0.6.2.dev0) (5.9.5)\n", + "Requirement already satisfied: pyyaml in /usr/local/lib/python3.10/dist-packages (from accelerate>=0.27.2->llmtuner==0.6.2.dev0) (6.0.1)\n", + "Requirement already satisfied: huggingface-hub in /usr/local/lib/python3.10/dist-packages (from accelerate>=0.27.2->llmtuner==0.6.2.dev0) (0.20.3)\n", + "Requirement already satisfied: safetensors>=0.3.1 in /usr/local/lib/python3.10/dist-packages (from accelerate>=0.27.2->llmtuner==0.6.2.dev0) (0.4.2)\n", + "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from datasets>=2.14.3->llmtuner==0.6.2.dev0) (3.13.3)\n", + "Requirement already satisfied: pyarrow>=12.0.0 in /usr/local/lib/python3.10/dist-packages (from datasets>=2.14.3->llmtuner==0.6.2.dev0) (14.0.2)\n", + "Requirement already satisfied: pyarrow-hotfix in /usr/local/lib/python3.10/dist-packages (from datasets>=2.14.3->llmtuner==0.6.2.dev0) (0.6)\n", + "Collecting dill<0.3.9,>=0.3.0 (from datasets>=2.14.3->llmtuner==0.6.2.dev0)\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[31m15.7 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>=2.14.3->llmtuner==0.6.2.dev0) (2.0.3)\n", + "Requirement already satisfied: requests>=2.19.0 in /usr/local/lib/python3.10/dist-packages (from datasets>=2.14.3->llmtuner==0.6.2.dev0) (2.31.0)\n", + "Requirement already satisfied: tqdm>=4.62.1 in /usr/local/lib/python3.10/dist-packages (from datasets>=2.14.3->llmtuner==0.6.2.dev0) (4.66.2)\n", + "Collecting xxhash (from datasets>=2.14.3->llmtuner==0.6.2.dev0)\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[31m24.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hCollecting multiprocess (from datasets>=2.14.3->llmtuner==0.6.2.dev0)\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[31m18.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hRequirement already satisfied: fsspec[http]<=2024.2.0,>=2023.1.0 in /usr/local/lib/python3.10/dist-packages (from datasets>=2.14.3->llmtuner==0.6.2.dev0) (2023.6.0)\n", + "Requirement already satisfied: aiohttp in /usr/local/lib/python3.10/dist-packages (from datasets>=2.14.3->llmtuner==0.6.2.dev0) (3.9.3)\n", + "Collecting aiofiles<24.0,>=22.0 (from gradio<=4.21.0,>=4.0.0->llmtuner==0.6.2.dev0)\n", + " Downloading aiofiles-23.2.1-py3-none-any.whl (15 kB)\n", + "Requirement already satisfied: altair<6.0,>=4.2.0 in /usr/local/lib/python3.10/dist-packages (from gradio<=4.21.0,>=4.0.0->llmtuner==0.6.2.dev0) (4.2.2)\n", + "Collecting ffmpy (from gradio<=4.21.0,>=4.0.0->llmtuner==0.6.2.dev0)\n", + " Downloading ffmpy-0.3.2.tar.gz (5.5 kB)\n", + " Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n", + "Collecting gradio-client==0.12.0 (from gradio<=4.21.0,>=4.0.0->llmtuner==0.6.2.dev0)\n", + " Downloading gradio_client-0.12.0-py3-none-any.whl (310 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m310.7/310.7 kB\u001b[0m \u001b[31m35.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hCollecting httpx>=0.24.1 (from gradio<=4.21.0,>=4.0.0->llmtuner==0.6.2.dev0)\n", + " Downloading httpx-0.27.0-py3-none-any.whl (75 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m75.6/75.6 kB\u001b[0m \u001b[31m11.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hRequirement already satisfied: importlib-resources<7.0,>=1.3 in /usr/local/lib/python3.10/dist-packages (from gradio<=4.21.0,>=4.0.0->llmtuner==0.6.2.dev0) (6.4.0)\n", + "Requirement already satisfied: jinja2<4.0 in /usr/local/lib/python3.10/dist-packages (from gradio<=4.21.0,>=4.0.0->llmtuner==0.6.2.dev0) (3.1.3)\n", + "Requirement already satisfied: markupsafe~=2.0 in /usr/local/lib/python3.10/dist-packages (from gradio<=4.21.0,>=4.0.0->llmtuner==0.6.2.dev0) (2.1.5)\n", + "Collecting orjson~=3.0 (from gradio<=4.21.0,>=4.0.0->llmtuner==0.6.2.dev0)\n", + " Downloading orjson-3.10.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (144 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m144.8/144.8 kB\u001b[0m \u001b[31m19.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hRequirement already satisfied: pillow<11.0,>=8.0 in /usr/local/lib/python3.10/dist-packages (from gradio<=4.21.0,>=4.0.0->llmtuner==0.6.2.dev0) (9.4.0)\n", + "Collecting pydub (from gradio<=4.21.0,>=4.0.0->llmtuner==0.6.2.dev0)\n", + " Downloading pydub-0.25.1-py2.py3-none-any.whl (32 kB)\n", + "Collecting python-multipart>=0.0.9 (from gradio<=4.21.0,>=4.0.0->llmtuner==0.6.2.dev0)\n", + " Downloading python_multipart-0.0.9-py3-none-any.whl (22 kB)\n", + "Collecting ruff>=0.2.2 (from gradio<=4.21.0,>=4.0.0->llmtuner==0.6.2.dev0)\n", + " Downloading ruff-0.3.5-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (8.7 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m8.7/8.7 MB\u001b[0m \u001b[31m93.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hCollecting semantic-version~=2.0 (from gradio<=4.21.0,>=4.0.0->llmtuner==0.6.2.dev0)\n", + " Downloading semantic_version-2.10.0-py2.py3-none-any.whl (15 kB)\n", + "Collecting tomlkit==0.12.0 (from gradio<=4.21.0,>=4.0.0->llmtuner==0.6.2.dev0)\n", + " Downloading tomlkit-0.12.0-py3-none-any.whl (37 kB)\n", + "Requirement already satisfied: typer[all]<1.0,>=0.9 in /usr/local/lib/python3.10/dist-packages (from gradio<=4.21.0,>=4.0.0->llmtuner==0.6.2.dev0) (0.9.4)\n", + "Requirement already satisfied: typing-extensions~=4.0 in /usr/local/lib/python3.10/dist-packages (from gradio<=4.21.0,>=4.0.0->llmtuner==0.6.2.dev0) (4.10.0)\n", + "Collecting websockets<12.0,>=10.0 (from gradio-client==0.12.0->gradio<=4.21.0,>=4.0.0->llmtuner==0.6.2.dev0)\n", + " Downloading websockets-11.0.3-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (129 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m129.9/129.9 kB\u001b[0m \u001b[31m17.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hRequirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib->llmtuner==0.6.2.dev0) (1.2.0)\n", + "Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.10/dist-packages (from matplotlib->llmtuner==0.6.2.dev0) (0.12.1)\n", + "Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib->llmtuner==0.6.2.dev0) (4.50.0)\n", + "Requirement already satisfied: kiwisolver>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib->llmtuner==0.6.2.dev0) (1.4.5)\n", + "Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib->llmtuner==0.6.2.dev0) (3.1.2)\n", + "Requirement already satisfied: python-dateutil>=2.7 in /usr/local/lib/python3.10/dist-packages (from matplotlib->llmtuner==0.6.2.dev0) (2.8.2)\n", + "Requirement already satisfied: annotated-types>=0.4.0 in /usr/local/lib/python3.10/dist-packages (from pydantic->llmtuner==0.6.2.dev0) (0.6.0)\n", + "Requirement already satisfied: pydantic-core==2.16.3 in /usr/local/lib/python3.10/dist-packages (from pydantic->llmtuner==0.6.2.dev0) (2.16.3)\n", + "Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch>=1.13.1->llmtuner==0.6.2.dev0) (1.12)\n", + "Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch>=1.13.1->llmtuner==0.6.2.dev0) (3.2.1)\n", + "Collecting nvidia-cuda-nvrtc-cu12==12.1.105 (from torch>=1.13.1->llmtuner==0.6.2.dev0)\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[31m65.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hCollecting nvidia-cuda-runtime-cu12==12.1.105 (from torch>=1.13.1->llmtuner==0.6.2.dev0)\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[31m67.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hCollecting nvidia-cuda-cupti-cu12==12.1.105 (from torch>=1.13.1->llmtuner==0.6.2.dev0)\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[31m94.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hCollecting nvidia-cudnn-cu12==8.9.2.26 (from torch>=1.13.1->llmtuner==0.6.2.dev0)\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[31m2.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hCollecting nvidia-cublas-cu12==12.1.3.1 (from torch>=1.13.1->llmtuner==0.6.2.dev0)\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[31m3.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hCollecting nvidia-cufft-cu12==11.0.2.54 (from torch>=1.13.1->llmtuner==0.6.2.dev0)\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>=1.13.1->llmtuner==0.6.2.dev0)\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[31m11.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hCollecting nvidia-cusolver-cu12==11.4.5.107 (from torch>=1.13.1->llmtuner==0.6.2.dev0)\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[31m8.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hCollecting nvidia-cusparse-cu12==12.1.0.106 (from torch>=1.13.1->llmtuner==0.6.2.dev0)\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[31m6.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hCollecting nvidia-nccl-cu12==2.19.3 (from torch>=1.13.1->llmtuner==0.6.2.dev0)\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[31m7.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hCollecting nvidia-nvtx-cu12==12.1.105 (from torch>=1.13.1->llmtuner==0.6.2.dev0)\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[31m13.2 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>=1.13.1->llmtuner==0.6.2.dev0) (2.2.0)\n", + "Collecting nvidia-nvjitlink-cu12 (from nvidia-cusolver-cu12==11.4.5.107->torch>=1.13.1->llmtuner==0.6.2.dev0)\n", + " Downloading nvidia_nvjitlink_cu12-12.4.127-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[31m78.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hRequirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers>=4.37.2->llmtuner==0.6.2.dev0) (2023.12.25)\n", + "Requirement already satisfied: tokenizers<0.19,>=0.14 in /usr/local/lib/python3.10/dist-packages (from transformers>=4.37.2->llmtuner==0.6.2.dev0) (0.15.2)\n", + "Collecting tyro>=0.5.11 (from trl>=0.8.1->llmtuner==0.6.2.dev0)\n", + " Downloading tyro-0.8.2-py3-none-any.whl (80 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m80.1/80.1 kB\u001b[0m \u001b[31m10.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hRequirement already satisfied: click>=7.0 in /usr/local/lib/python3.10/dist-packages (from uvicorn->llmtuner==0.6.2.dev0) (8.1.7)\n", + "Collecting h11>=0.8 (from uvicorn->llmtuner==0.6.2.dev0)\n", + " Downloading h11-0.14.0-py3-none-any.whl (58 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m58.3/58.3 kB\u001b[0m \u001b[31m8.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hCollecting starlette<0.38.0,>=0.37.2 (from fastapi->llmtuner==0.6.2.dev0)\n", + " Downloading starlette-0.37.2-py3-none-any.whl (71 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m71.9/71.9 kB\u001b[0m \u001b[31m9.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hRequirement already satisfied: six in /usr/local/lib/python3.10/dist-packages (from fire->llmtuner==0.6.2.dev0) (1.16.0)\n", + "Requirement already satisfied: termcolor in /usr/local/lib/python3.10/dist-packages (from fire->llmtuner==0.6.2.dev0) (2.4.0)\n", + "Requirement already satisfied: anyio in /usr/local/lib/python3.10/dist-packages (from sse-starlette->llmtuner==0.6.2.dev0) (3.7.1)\n", + "Requirement already satisfied: entrypoints in /usr/local/lib/python3.10/dist-packages (from altair<6.0,>=4.2.0->gradio<=4.21.0,>=4.0.0->llmtuner==0.6.2.dev0) (0.4)\n", + "Requirement already satisfied: jsonschema>=3.0 in /usr/local/lib/python3.10/dist-packages (from altair<6.0,>=4.2.0->gradio<=4.21.0,>=4.0.0->llmtuner==0.6.2.dev0) (4.19.2)\n", + "Requirement already satisfied: toolz in /usr/local/lib/python3.10/dist-packages (from altair<6.0,>=4.2.0->gradio<=4.21.0,>=4.0.0->llmtuner==0.6.2.dev0) (0.12.1)\n", + "Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets>=2.14.3->llmtuner==0.6.2.dev0) (1.3.1)\n", + "Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets>=2.14.3->llmtuner==0.6.2.dev0) (23.2.0)\n", + "Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets>=2.14.3->llmtuner==0.6.2.dev0) (1.4.1)\n", + "Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets>=2.14.3->llmtuner==0.6.2.dev0) (6.0.5)\n", + "Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets>=2.14.3->llmtuner==0.6.2.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>=2.14.3->llmtuner==0.6.2.dev0) (4.0.3)\n", + "Requirement already satisfied: certifi in /usr/local/lib/python3.10/dist-packages (from httpx>=0.24.1->gradio<=4.21.0,>=4.0.0->llmtuner==0.6.2.dev0) (2024.2.2)\n", + "Collecting httpcore==1.* (from httpx>=0.24.1->gradio<=4.21.0,>=4.0.0->llmtuner==0.6.2.dev0)\n", + " Downloading httpcore-1.0.5-py3-none-any.whl (77 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m77.9/77.9 kB\u001b[0m \u001b[31m11.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hRequirement already satisfied: idna in /usr/local/lib/python3.10/dist-packages (from httpx>=0.24.1->gradio<=4.21.0,>=4.0.0->llmtuner==0.6.2.dev0) (3.6)\n", + "Requirement already satisfied: sniffio in /usr/local/lib/python3.10/dist-packages (from httpx>=0.24.1->gradio<=4.21.0,>=4.0.0->llmtuner==0.6.2.dev0) (1.3.1)\n", + "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets>=2.14.3->llmtuner==0.6.2.dev0) (2023.4)\n", + "Requirement already satisfied: tzdata>=2022.1 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets>=2.14.3->llmtuner==0.6.2.dev0) (2024.1)\n", + "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->datasets>=2.14.3->llmtuner==0.6.2.dev0) (3.3.2)\n", + "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->datasets>=2.14.3->llmtuner==0.6.2.dev0) (2.0.7)\n", + "Requirement already satisfied: exceptiongroup in /usr/local/lib/python3.10/dist-packages (from anyio->sse-starlette->llmtuner==0.6.2.dev0) (1.2.0)\n", + "Collecting colorama<0.5.0,>=0.4.3 (from typer[all]<1.0,>=0.9->gradio<=4.21.0,>=4.0.0->llmtuner==0.6.2.dev0)\n", + " Downloading colorama-0.4.6-py2.py3-none-any.whl (25 kB)\n", + "Collecting shellingham<2.0.0,>=1.3.0 (from typer[all]<1.0,>=0.9->gradio<=4.21.0,>=4.0.0->llmtuner==0.6.2.dev0)\n", + " Downloading shellingham-1.5.4-py2.py3-none-any.whl (9.8 kB)\n", + "Requirement already satisfied: rich<14.0.0,>=10.11.0 in /usr/local/lib/python3.10/dist-packages (from typer[all]<1.0,>=0.9->gradio<=4.21.0,>=4.0.0->llmtuner==0.6.2.dev0) (13.7.1)\n", + "Requirement already satisfied: docstring-parser>=0.14.1 in /usr/local/lib/python3.10/dist-packages (from tyro>=0.5.11->trl>=0.8.1->llmtuner==0.6.2.dev0) (0.16)\n", + "Collecting shtab>=1.5.6 (from tyro>=0.5.11->trl>=0.8.1->llmtuner==0.6.2.dev0)\n", + " Downloading shtab-1.7.1-py3-none-any.whl (14 kB)\n", + "Requirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/dist-packages (from sympy->torch>=1.13.1->llmtuner==0.6.2.dev0) (1.3.0)\n", + "Requirement already satisfied: jsonschema-specifications>=2023.03.6 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=3.0->altair<6.0,>=4.2.0->gradio<=4.21.0,>=4.0.0->llmtuner==0.6.2.dev0) (2023.12.1)\n", + "Requirement already satisfied: referencing>=0.28.4 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=3.0->altair<6.0,>=4.2.0->gradio<=4.21.0,>=4.0.0->llmtuner==0.6.2.dev0) (0.34.0)\n", + "Requirement already satisfied: rpds-py>=0.7.1 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=3.0->altair<6.0,>=4.2.0->gradio<=4.21.0,>=4.0.0->llmtuner==0.6.2.dev0) (0.18.0)\n", + "Requirement already satisfied: markdown-it-py>=2.2.0 in /usr/local/lib/python3.10/dist-packages (from rich<14.0.0,>=10.11.0->typer[all]<1.0,>=0.9->gradio<=4.21.0,>=4.0.0->llmtuner==0.6.2.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<14.0.0,>=10.11.0->typer[all]<1.0,>=0.9->gradio<=4.21.0,>=4.0.0->llmtuner==0.6.2.dev0) (2.16.1)\n", + "Requirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.10/dist-packages (from markdown-it-py>=2.2.0->rich<14.0.0,>=10.11.0->typer[all]<1.0,>=0.9->gradio<=4.21.0,>=4.0.0->llmtuner==0.6.2.dev0) (0.1.2)\n", + "Building wheels for collected packages: llmtuner, fire, ffmpy\n", + " Building wheel for llmtuner (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n", + " Created wheel for llmtuner: filename=llmtuner-0.6.2.dev0-py3-none-any.whl size=141100 sha256=b11cc75b5fe3ed380a90e9f63b7a892b5582d2de917863a5b5bdeb2bce0a8470\n", + " Stored in directory: /root/.cache/pip/wheels/de/aa/c5/27b5682c5592b7c0eecc3e208f176dedf6b11a61cf2a910b85\n", + " Building wheel for fire (setup.py) ... \u001b[?25l\u001b[?25hdone\n", + " Created wheel for fire: filename=fire-0.6.0-py2.py3-none-any.whl size=117029 sha256=3bc5d75e599317c0fd7f6b8995702dcabf764b97b546c6fb8a61e65a6874f01a\n", + " Stored in directory: /root/.cache/pip/wheels/d6/6d/5d/5b73fa0f46d01a793713f8859201361e9e581ced8c75e5c6a3\n", + " Building wheel for ffmpy (setup.py) ... \u001b[?25l\u001b[?25hdone\n", + " Created wheel for ffmpy: filename=ffmpy-0.3.2-py3-none-any.whl size=5584 sha256=da73faaa3cee3e9001eed296dc6ed7bbc459ee4b0eec21b0971b178b46d95d01\n", + " Stored in directory: /root/.cache/pip/wheels/bd/65/9a/671fc6dcde07d4418df0c592f8df512b26d7a0029c2a23dd81\n", + "Successfully built llmtuner fire ffmpy\n", + "Installing collected packages: pydub, ffmpy, xxhash, websockets, tomlkit, shtab, shellingham, semantic-version, ruff, python-multipart, orjson, 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, h11, fire, einops, dill, colorama, aiofiles, uvicorn, starlette, nvidia-cusparse-cu12, nvidia-cudnn-cu12, multiprocess, httpcore, tyro, sse-starlette, nvidia-cusolver-cu12, httpx, fastapi, gradio-client, datasets, gradio, accelerate, trl, peft, llmtuner\n", + "Successfully installed accelerate-0.29.1 aiofiles-23.2.1 colorama-0.4.6 datasets-2.18.0 dill-0.3.8 einops-0.7.0 fastapi-0.110.1 ffmpy-0.3.2 fire-0.6.0 gradio-4.21.0 gradio-client-0.12.0 h11-0.14.0 httpcore-1.0.5 httpx-0.27.0 llmtuner-0.6.2.dev0 multiprocess-0.70.16 nvidia-cublas-cu12-12.1.3.1 nvidia-cuda-cupti-cu12-12.1.105 nvidia-cuda-nvrtc-cu12-12.1.105 nvidia-cuda-runtime-cu12-12.1.105 nvidia-cudnn-cu12-8.9.2.26 nvidia-cufft-cu12-11.0.2.54 nvidia-curand-cu12-10.3.2.106 nvidia-cusolver-cu12-11.4.5.107 nvidia-cusparse-cu12-12.1.0.106 nvidia-nccl-cu12-2.19.3 nvidia-nvjitlink-cu12-12.4.127 nvidia-nvtx-cu12-12.1.105 orjson-3.10.0 peft-0.10.0 pydub-0.25.1 python-multipart-0.0.9 ruff-0.3.5 semantic-version-2.10.0 shellingham-1.5.4 shtab-1.7.1 sse-starlette-2.1.0 starlette-0.37.2 tomlkit-0.12.0 trl-0.8.1 tyro-0.8.2 uvicorn-0.29.0 websockets-11.0.3 xxhash-3.4.1\n" + ] + } + ], + "source": [ + "%rm -rf LLaMA-Factory\n", + "!git clone https://github.com/hiyouga/LLaMA-Factory.git\n", + "%cd LLaMA-Factory\n", + "%ls\n", + "!pip install ." + ] + }, + { + "cell_type": "markdown", + "source": [ + "### Check GPU environment" + ], + "metadata": { + "id": "H9RXn_YQnn9f" + } + }, + { + "cell_type": "code", + "source": [ + "import torch\n", + "try:\n", + " assert torch.cuda.is_available() is True\n", + "except AssertionError:\n", + " print(\"Please set up a GPU before using LLaMA Factory: https://medium.com/mlearning-ai/training-yolov4-on-google-colab-316f8fff99c6\")" + ], + "metadata": { + "id": "ZkN-ktlsnrdU" + }, + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "markdown", + "source": [ + "### Log in with Hugging Face account to upload model (Optional)" + ], + "metadata": { + "id": "okkbTMoZCQNf" + } + }, + { + "cell_type": "code", + "source": [ + "# @title Standardtext für Titel\n", + "!huggingface-cli login" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "6OIm0O7oA5sy", + "outputId": "4adbdc1a-5748-4ca1-9586-236761980293" + }, + "execution_count": null, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "\n", + " _| _| _| _| _|_|_| _|_|_| _|_|_| _| _| _|_|_| _|_|_|_| _|_| _|_|_| _|_|_|_|\n", + " _| _| _| _| _| _| _| _|_| _| _| _| _| _| _| _|\n", + " _|_|_|_| _| _| _| _|_| _| _|_| _| _| _| _| _| _|_| _|_|_| _|_|_|_| _| _|_|_|\n", + " _| _| _| _| _| _| _| _| _| _| _|_| _| _| _| _| _| _| _|\n", + " _| _| _|_| _|_|_| _|_|_| _|_|_| _| _| _|_|_| _| _| _| _|_|_| _|_|_|_|\n", + "\n", + " To login, `huggingface_hub` requires a token generated from https://huggingface.co/settings/tokens .\n", + "Token: \n", + "Add token as git credential? (Y/n) y\n", + "Token is valid (permission: write).\n", + "\u001b[1m\u001b[31mCannot authenticate through git-credential as no helper is defined on your machine.\n", + "You might have to re-authenticate when pushing to the Hugging Face Hub.\n", + "Run the following command in your terminal in case you want to set the 'store' credential helper as default.\n", + "\n", + "git config --global credential.helper store\n", + "\n", + "Read https://git-scm.com/book/en/v2/Git-Tools-Credential-Storage for more details.\u001b[0m\n", + "Token has not been saved to git credential helper.\n", + "Your token has been saved to /root/.cache/huggingface/token\n", + "Login successful\n" + ] + } + ] + }, + { + "cell_type": "markdown", + "source": [ + "## Fine-tune model via LLaMA Board" + ], + "metadata": { + "id": "2QiXcvdzzW3Y" + } + }, + { + "cell_type": "code", + "source": [ + "from llmtuner import create_ui\n", + "\n", + "create_ui().queue().launch(share=True)" + ], + "metadata": { + "id": "YLsdS6V5yUMy" + }, + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "markdown", + "source": [ + "## Fine-tune model via Command Line" + ], + "metadata": { + "id": "rgR3UFhB0Ifq" + } + }, + { + "cell_type": "code", + "source": [ + "from llmtuner import run_exp\n", + "run_exp(dict(\n", + " stage=\"sft\",\n", + " do_train=True,\n", + " model_name_or_path=\"mistralai/Mistral-7B-v0.1\",\n", + " dataset=\"oaast_sft\",\n", + " template=\"mistral\",\n", + " finetuning_type=\"lora\",\n", + " lora_target=\"all\",\n", + " output_dir=\"test_identity\",\n", + " per_device_train_batch_size=4,\n", + " gradient_accumulation_steps=4,\n", + " lr_scheduler_type=\"cosine\",\n", + " logging_steps=10,\n", + " save_steps=100,\n", + " learning_rate=1e-4,\n", + " num_train_epochs=5.0,\n", + " max_samples=500,\n", + " max_grad_norm=1.0,\n", + " fp16=True,\n", + "))" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 1000, + "referenced_widgets": [ + "f95ce7e75ebc4e20905fed28cad2f5c3", + "2ec65871301e461abaeaa378b971530b", + "91b90a9bd5a24705b922afedf691f2b8", + "d816934e6db644eea770054078c2147c", + "482a79ad0b3e4e7e9fc85e4b254e2ac1", + "4f8ccf5c128f4b6681c781d80e80a8db", + "c6d77271c1564aebbe595eabb86f62d5", + "ecde876399eb4e8b96326609aac75d9f", + "21a2f8d812a246ba9c9e019e8df16567", + "f16b58b67bd34422bc450f8686042bb1", + "9d6fbbc562ab4a668078987404a72dc2", + "8aea46e7ca014923a5877b1e22b96238", + "f2edf85ef88943688a14dafb63fc67b8", + "c75df4143eba4f538af590b6dd681123", + "2621fd2a4181480989bbf6057929bb45", + "dc5948cf6cd44f0d95519dc1a790b58e", + "9efdadefb26a45ab96f6c3bf39da59ee", + "c4f0986f8e794a49a33649dc11a15943", + "51ffe4c2e3944eddad61d9a906148383", + "6867b320d79540a28fcc5e2ee1151b81", + "9d4ea1d0fa1c41fbaa121299f8a4c75d", + "7552315cee5042bfaa96e1da3da88338", + "84fbcbd613264a3aa92dd64ad95c1866", + "b5aa83fea65d468183e3fa3df50b4f09", + "068a54661fcc48c0903f9c34d87aaa2e", + "34f3d00cc953403ebb19200b6b8b5376", + "2f7b09c672be4b03a76dd98287158c89", + "9a96b7aa47294f499a515ef38414b9a8", + "6ecefcd7c2c24b249327fa9525ffc7f2", + "971344d11977449387c038bbb1cfeb46", + "5e9d245cca4e48f78ad935e74d58e61e", + "1e95ecd607b84695a15e4e597c3de738", + "8f63de6c55224c49a000e0a1a10ca547", + "5eb823b8b3a048e5acef70db28c25029", + "5f20cd4e7d674661949ab350a8587e53", + "1150955b86354a2584904da92bc78406", + "8679589efdc74a1cb94a795d5695a5b5", + "9624777e25014932bd7ffe7d8aea1203", + "d3e0367018fa418faa057118fabac7f3", + "cb3cd80934f14f02b3fb2f252ccb935d", + "e523abbd1d0f4a18946a93303db2ee2d", + "2d8b051636b94083a153a374075c037b", + "3d716cb97ce44c3986a09285a277e839", + "470f3df55db74a3aabe7a79ea3f54105", + "9d445d452abf4bddb831eecaddb39304", + "de4671b0d5ca48b38f9f569aa0748b3a", + "0d523ae3438b4f3ab1b9856d07a666c2", + "fa7f42fe5b3e4b9ea8aed8f648db7b93", + "df06640522b14700b7a9a60b3c826069", + "b8c19471f312480aa4bb4a82874410a6", + "0a09e4f5f6704ddb9f96a76459715ed8", + "d32a415f1615417ba22471f22d0fdbf2", + "5fdb36111b0e4d909e6ec9e17b2ececa", + "b502f88e55024af3acffd709fe438007", + "6fffcde2c1a7439c9d01d54299213851", + "687f256662104276b36936259a30f0ef", + "6a539c18f8dd4264afa56e3edc6d6a6a", + "da21c4d52dbd4dd2b70d79510aa115c4", + "1ef39344e7594e11a2c601a0a57b5f53", + "6d44e4c010684a8c96d0d7929bf63663", + "92c89cfa23304f4e8dc436820a762519", + "ce5187af896746df9314eab72b1d4519", + "a8992951c4af49e2ad05c55ed5886661", + "31541b1f4e2c40b0ba0c23c175877e2e", + "5497233cde16423f9d60134249e3640e", + "2d2b6e583ab24a6a83ded68d29d515bb", + "dfca1c390ec94938ab880b29b5cfd01f", + "de7e0d4c1d6f4833ad5ef265ba2f04ac", + "6b8dd06a1fcc433cb43508c84fb55ea0", + "2e2a66729e2242c4be9f49963e718cd5", + "2927e4ef6daf414298e114f59b087592", + "04f2d402b98440b587f93e6283276921", + "2679bd2e2cd34aefb7d918ffdb16ff2b", + "dd36da30f98245b08cfe5642a704a05c", + "791bb77d7a6e411eb01f9306dfd0af28", + "25dd4496d6974fe1a2c790a5518b8f79", + "f0490977e2374b05abe4af44c38ef6e7", + "af18f88fe69a43cf985f26f793266348", + "ba26598d19b3417b85570d1df4d72e29", + "dece02013e43434b90e34c1c4e891b39", + "16774d0fa73b4a9da13e976ef86ba7f2", + "c27c2e11f0a440c1961249efa0f52549", + "da925912eea742ca9f9f2f6bf0682d4e", + "c610798dc27c41fb92aef1d74cb39537", + "fe09e0a3b5de4a969f76083fcd9f6ff4", + "0ca77f0a650446db9d52cf228d7cd610", + "54f227c080b340e6a10fc86823dcae7f", + "cdc60571f14a40e89bfdb894973eb408", + "900a50758c5d4c82993d65ef940a24d7", + "0a1b5a63a6da42a6a4d9145d6782d3a0", + "afe4c5d8e9694ddd838e622bcbdb7b76", + "ce8389a7a56e4229b548da25de6d3dfd", + "13a6d6e2c85e497f99dab8f0e90796c0", + "e2d2c569765140bbb92adc8dea169d95", + "9169e2eb72fa4d949b1ad31e18851fc1", + "78c1753419d14545a1f23b64f21df6cd", + "63e53148010642e18b4af6f7ca566ed2", + "9f73a969648d4636882dcbc7349d8b25", + "5b3ae5ea41fc4bb6884c881c993fddcc", + "1090cb2ed1c74dbc818bf64f8f89e761", + "0a275e74c45d471ba6efce60f6170b3a", + "b23d2e0455774b1ba42db3ac1bad9c69", + "de0d22ef70e8490286cd3cb35a23bd9c", + "9aa8d77e15eb4d549ec9d2579486528c", + "1960bc2f403d4d4e9ca0c49c5b191ff0", + "144ddbb6ed7745348cda9fe695269b0d", + "3e7e570583b548bbb84a1c8b290f2234", + "7d78cba869fe469c839d11b54180d9a5", + "f1f0a8a751c44294900c997175a5e052", + "bb22ba5411684a9babfe752dd00d0ea6", + "7ef769cb6a3646e4b058eace7866b32b", + "f2d3c9fdf75a4b2d8db817293cf46af5", + "cd4e951c119f406c93221f9bec663792", + "fcad30d4033f4c64a0a8efeb7feabd91", + "6c8fc51a084444d8ab98b7ec58105ce5", + "169366de76ba4cf4ac7f61fc90494aa1", + "eff454fe170c4a4283301ede36d1c77c", + "c97b3bba56c34fb196f4776ce9469738", + "b058e907e5f2450dae4c4c23d12cb09b", + "8fef758e915c433bb1f2101601d24f7d", + "595362c21c804a80a05102d069502e45", + "f3dd024cf93348f99300f66c6ed74426", + "64d9b7b9bead4c63a79850f812a65725", + "e2077ca32a48446ab8a598cfd24560ac", + "e03f20206724468ba155dde1a5e4c84f", + "5c28873d8a7548deb1cfe1d4f980ad4b", + "90c0eb3147074d8798ad2ccfa4eb9dd3", + "0a9a4e707f604881873acc0f4d7a42c0", + "76cf1a5a96e140459d2de7d881144f88", + "5e08f61a9fc44792bd3a43116e38d804", + "fcca954f131d4fe1b047f999df5ea5a3", + "bd521cdb23e84164b76a844037b5e202", + "1911489caa474fc7aeede1e94cf673b2", + "e43f16a9a7eb4396a73e47dbe86d86dd", + "8ada8f039d38464b9ee5c9fc19d58d86", + "8a56009da9114d7c89b28196eda64fde", + "7df19c3a808144a99c366c157630a227", + "3311434267ca41a6980c903b63e1cb9b", + "ffa60fc9bc164af2b79bd6212dcb46a0", + "0174ba072a7b4d0aae5c81a71f021f56", + "313b26430be34cf79cffcadf2a25b804", + "6f8f413a8286463097ae9c6f4abe6018", + "43ed32f70e834038a88e60bad7ee312d", + "a26d44fa1e5f4b7bbdd8031bc5399240", + "e78c7a6ad68d4f418581e6dddfb1d299", + "713ef5f962a94e4fbdb59b7ff44e532b", + "04bd33cea6cd49cf9c723a26de46c26c", + "f10ae252772c42f6ab84e517967922cb", + "b86d1631f0494048b3c45a8278dae598", + "9638f2fe85e4416195fad7be5ea51e28", + "320520e310914745a7a77cbfc41e856a", + "bd29d07316d141b7afb8971ebc468668", + "73e1f901f3be40159693451332e52fe1", + "6f7241c2ce2140b3b59bd2d7b8db5276" + ] + }, + "id": "CS0Qk5OR0i4Q", + "outputId": "79a2419f-3d71-4ff2-b935-4a6cbaf9418d" + }, + "execution_count": null, + "outputs": [ + { + "output_type": "stream", + "name": "stderr", + "text": [ + "[INFO|training_args.py:1902] 2024-04-07 15:17:58,474 >> PyTorch: setting up devices\n", + "[INFO|training_args.py:1611] 2024-04-07 15:17:58,514 >> The default value for the training argument `--report_to` will change in v5 (from all installed integrations to none). In v5, you will need to use `--report_to all` to get the same behavior as now. You should start updating your code and make this info disappear :-).\n" + ] + }, + { + "output_type": "stream", + "name": "stdout", + "text": [ + "04/07/2024 15:17:58 - INFO - llmtuner.hparams.parser - Process rank: 0, device: cuda:0, n_gpu: 1, distributed training: False, compute dtype: torch.float16\n" + ] + }, + { + "output_type": "stream", + "name": "stderr", + "text": [ + "INFO:llmtuner.hparams.parser:Process rank: 0, device: cuda:0, n_gpu: 1, distributed training: False, compute dtype: torch.float16\n" + ] + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "tokenizer_config.json: 0%| | 0.00/967 [00:00> loading file tokenizer.model from cache at /root/.cache/huggingface/hub/models--mistralai--Mistral-7B-v0.1/snapshots/26bca36bde8333b5d7f72e9ed20ccda6a618af24/tokenizer.model\n", + "[INFO|tokenization_utils_base.py:2046] 2024-04-07 15:18:05,098 >> loading file added_tokens.json from cache at None\n", + "[INFO|tokenization_utils_base.py:2046] 2024-04-07 15:18:05,100 >> loading file special_tokens_map.json from cache at /root/.cache/huggingface/hub/models--mistralai--Mistral-7B-v0.1/snapshots/26bca36bde8333b5d7f72e9ed20ccda6a618af24/special_tokens_map.json\n", + "[INFO|tokenization_utils_base.py:2046] 2024-04-07 15:18:05,102 >> loading file tokenizer_config.json from cache at /root/.cache/huggingface/hub/models--mistralai--Mistral-7B-v0.1/snapshots/26bca36bde8333b5d7f72e9ed20ccda6a618af24/tokenizer_config.json\n", + "[INFO|tokenization_utils_base.py:2046] 2024-04-07 15:18:05,103 >> loading file tokenizer.json from cache at /root/.cache/huggingface/hub/models--mistralai--Mistral-7B-v0.1/snapshots/26bca36bde8333b5d7f72e9ed20ccda6a618af24/tokenizer.json\n" + ] + }, + { + "output_type": "stream", + "name": "stdout", + "text": [ + "04/07/2024 15:18:05 - INFO - llmtuner.data.template - Add pad token: \n" + ] + }, + { + "output_type": "stream", + "name": "stderr", + "text": [ + "INFO:llmtuner.data.template:Add pad token: \n" + ] + }, + { + "output_type": "stream", + "name": "stdout", + "text": [ + "04/07/2024 15:18:05 - INFO - llmtuner.data.loader - Loading dataset oaast_sft.json...\n" + ] + }, + { + "output_type": "stream", + "name": "stderr", + "text": [ + "INFO:llmtuner.data.loader:Loading dataset oaast_sft.json...\n" + ] + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "Generating train split: 0 examples [00:00, ? examples/s]" + ], + "application/vnd.jupyter.widget-view+json": { + "version_major": 2, + "version_minor": 0, + "model_id": "9d445d452abf4bddb831eecaddb39304" + } + }, + "metadata": {} + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "Converting format of dataset: 0%| | 0/500 [00:00 [INST] Can you write a short introduction about the relevance of the term \"monopsony\" in economics? Please use examples related to potential monopsonies in the labour market and cite relevant research. [/INST] Monopsony refers to a market structure where there is only one buyer of a good or service. In the context of labor markets, a monopsony occurs when there is only one employer in a particular geographic area or industry, giving them significant power to set wages and working conditions. Research has shown that the existence of monopsonies can lead to lower wages and reduced job opportunities for workers. For example, a study by the National Bureau of Economic Research found that in industries with high levels of concentration, workers earn lower wages and are less likely to receive benefits such as health insurance. [INST] What can be done at a regulatory level to ensure, in a monopsony, that the power over the employees isn't abused? List a few options and focus on the organs that should act. [/INST] Here are some potential regulatory options to address monopsony power over employees:\n", + "\n", + "- Antitrust enforcement agencies like the FTC or DOJ could investigate and take action against dominant employers that are abusing their market power to suppress wages or worsen working conditions. They could force divestitures or other structural remedies.\n", + "- Labor standards agencies could set industry-specific minimum wage floors or other regulations around compensation and working conditions. This would reduce the ability of dominant employers to push wages/conditions below certain thresholds.\n", + "- Sector-specific regulators could impose requirements around how companies hire, compensate, and treat workers. For example, banking regulators could prohibit abusive practices by dominant banks with regard to their employees.\n", + "- Legislatures could pass laws\n", + "label_ids:\n", + "[-100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, 3217, 410, 1265, 28724, 15654, 298, 264, 2668, 4693, 970, 736, 349, 865, 624, 24861, 302, 264, 1179, 442, 2372, 28723, 560, 272, 2758, 302, 7579, 11574, 28725, 264, 1326, 410, 1265, 28724, 12022, 739, 736, 349, 865, 624, 18646, 297, 264, 2830, 2970, 12293, 2698, 442, 4779, 28725, 5239, 706, 5864, 1982, 298, 808, 24110, 304, 2739, 4331, 28723, 7982, 659, 4894, 369, 272, 9025, 302, 1326, 410, 1265, 497, 541, 1736, 298, 3889, 24110, 304, 9397, 2389, 8812, 354, 7433, 28723, 1263, 2757, 28725, 264, 3881, 486, 272, 3610, 18052, 302, 20451, 7982, 1419, 369, 297, 17909, 395, 1486, 6157, 302, 15987, 28725, 7433, 6384, 3889, 24110, 304, 460, 2108, 3917, 298, 5556, 7196, 1259, 390, 2528, 6919, 28723, 2, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, 4003, 460, 741, 4628, 25251, 2877, 298, 2962, 1326, 410, 1265, 28724, 1982, 754, 7896, 28747, 13, 13, 28733, 3821, 279, 19842, 19046, 15467, 737, 272, 401, 8386, 442, 9317, 28798, 829, 17214, 304, 1388, 2992, 1835, 18669, 22271, 369, 460, 534, 8521, 652, 2668, 1982, 298, 22555, 24110, 442, 275, 734, 269, 2739, 4331, 28723, 1306, 829, 4274, 2901, 374, 279, 1238, 442, 799, 21431, 1003, 286, 497, 28723, 13, 28733, 14160, 9890, 15467, 829, 808, 4779, 28733, 15590, 7968, 21062, 21264, 442, 799, 15885, 1401, 19204, 304, 2739, 4331, 28723, 851, 682, 7643, 272, 5537, 302, 18669, 22271, 298, 5696, 24110, 28748, 24952, 3624, 2552, 306, 2874, 4858, 28723, 13, 28733, 318, 3776, 28733, 15590, 15991, 3117, 829, 2824, 645, 8296, 1401, 910, 4799, 15270, 28725, 12613, 380, 28725, 304, 3363, 7433, 28723, 1263, 2757, 28725, 22265, 15991, 3117, 829, 16128, 279, 534, 6657, 10879, 486, 18669, 13283, 395, 4166, 298, 652, 7896, 28723, 13, 28733, 26216, 2863, 829, 1455, 8427, 2]\n", + "labels:\n", + " Monopsony refers to a market structure where there is only one buyer of a good or service. In the context of labor markets, a monopsony occurs when there is only one employer in a particular geographic area or industry, giving them significant power to set wages and working conditions. Research has shown that the existence of monopsonies can lead to lower wages and reduced job opportunities for workers. For example, a study by the National Bureau of Economic Research found that in industries with high levels of concentration, workers earn lower wages and are less likely to receive benefits such as health insurance. Here are some potential regulatory options to address monopsony power over employees:\n", + "\n", + "- Antitrust enforcement agencies like the FTC or DOJ could investigate and take action against dominant employers that are abusing their market power to suppress wages or worsen working conditions. They could force divestitures or other structural remedies.\n", + "- Labor standards agencies could set industry-specific minimum wage floors or other regulations around compensation and working conditions. This would reduce the ability of dominant employers to push wages/conditions below certain thresholds.\n", + "- Sector-specific regulators could impose requirements around how companies hire, compensate, and treat workers. For example, banking regulators could prohibit abusive practices by dominant banks with regard to their employees.\n", + "- Legislatures could pass laws\n" + ] + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "config.json: 0%| | 0.00/571 [00:00> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--mistralai--Mistral-7B-v0.1/snapshots/26bca36bde8333b5d7f72e9ed20ccda6a618af24/config.json\n", + "[INFO|configuration_utils.py:791] 2024-04-07 15:18:08,511 >> Model config MistralConfig {\n", + " \"_name_or_path\": \"mistralai/Mistral-7B-v0.1\",\n", + " \"architectures\": [\n", + " \"MistralForCausalLM\"\n", + " ],\n", + " \"attention_dropout\": 0.0,\n", + " \"bos_token_id\": 1,\n", + " \"eos_token_id\": 2,\n", + " \"hidden_act\": \"silu\",\n", + " \"hidden_size\": 4096,\n", + " \"initializer_range\": 0.02,\n", + " \"intermediate_size\": 14336,\n", + " \"max_position_embeddings\": 32768,\n", + " \"model_type\": \"mistral\",\n", + " \"num_attention_heads\": 32,\n", + " \"num_hidden_layers\": 32,\n", + " \"num_key_value_heads\": 8,\n", + " \"rms_norm_eps\": 1e-05,\n", + " \"rope_theta\": 10000.0,\n", + " \"sliding_window\": 4096,\n", + " \"tie_word_embeddings\": false,\n", + " \"torch_dtype\": \"bfloat16\",\n", + " \"transformers_version\": \"4.38.2\",\n", + " \"use_cache\": true,\n", + " \"vocab_size\": 32000\n", + "}\n", + "\n" + ] + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "model.safetensors.index.json: 0%| | 0.00/25.1k [00:00> loading weights file model.safetensors from cache at /root/.cache/huggingface/hub/models--mistralai--Mistral-7B-v0.1/snapshots/26bca36bde8333b5d7f72e9ed20ccda6a618af24/model.safetensors.index.json\n" + ] + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "Downloading shards: 0%| | 0/2 [00:00> Instantiating MistralForCausalLM model under default dtype torch.float16.\n", + "[INFO|configuration_utils.py:845] 2024-04-07 15:19:40,392 >> Generate config GenerationConfig {\n", + " \"bos_token_id\": 1,\n", + " \"eos_token_id\": 2\n", + "}\n", + "\n" + ] + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "Loading checkpoint shards: 0%| | 0/2 [00:00> All model checkpoint weights were used when initializing MistralForCausalLM.\n", + "\n", + "[INFO|modeling_utils.py:4000] 2024-04-07 15:20:51,823 >> All the weights of MistralForCausalLM were initialized from the model checkpoint at mistralai/Mistral-7B-v0.1.\n", + "If your task is similar to the task the model of the checkpoint was trained on, you can already use MistralForCausalLM for predictions without further training.\n" + ] + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "generation_config.json: 0%| | 0.00/116 [00:00> loading configuration file generation_config.json from cache at /root/.cache/huggingface/hub/models--mistralai--Mistral-7B-v0.1/snapshots/26bca36bde8333b5d7f72e9ed20ccda6a618af24/generation_config.json\n", + "[INFO|configuration_utils.py:845] 2024-04-07 15:20:52,254 >> Generate config GenerationConfig {\n", + " \"bos_token_id\": 1,\n", + " \"eos_token_id\": 2\n", + "}\n", + "\n" + ] + }, + { + "output_type": "stream", + "name": "stdout", + "text": [ + "04/07/2024 15:20:52 - INFO - llmtuner.model.patcher - Gradient checkpointing enabled.\n" + ] + }, + { + "output_type": "stream", + "name": "stderr", + "text": [ + "INFO:llmtuner.model.patcher:Gradient checkpointing enabled.\n" + ] + }, + { + "output_type": "stream", + "name": "stdout", + "text": [ + "04/07/2024 15:20:52 - INFO - llmtuner.model.adapter - Fine-tuning method: LoRA\n" + ] + }, + { + "output_type": "stream", + "name": "stderr", + "text": [ + "INFO:llmtuner.model.adapter:Fine-tuning method: LoRA\n" + ] + }, + { + "output_type": "stream", + "name": "stdout", + "text": [ + "04/07/2024 15:20:52 - INFO - llmtuner.model.utils - Found linear modules: k_proj,v_proj,gate_proj,up_proj,down_proj,o_proj,q_proj\n" + ] + }, + { + "output_type": "stream", + "name": "stderr", + "text": [ + "INFO:llmtuner.model.utils:Found linear modules: k_proj,v_proj,gate_proj,up_proj,down_proj,o_proj,q_proj\n" + ] + }, + { + "output_type": "stream", + "name": "stdout", + "text": [ + "04/07/2024 15:20:53 - INFO - llmtuner.model.loader - trainable params: 20971520 || all params: 7262703616 || trainable%: 0.2888\n" + ] + }, + { + "output_type": "stream", + "name": "stderr", + "text": [ + "INFO:llmtuner.model.loader:trainable params: 20971520 || all params: 7262703616 || trainable%: 0.2888\n", + "/usr/local/lib/python3.10/dist-packages/accelerate/accelerator.py:436: FutureWarning: Passing the following arguments to `Accelerator` is deprecated and will be removed in version 1.0 of Accelerate: dict_keys(['dispatch_batches', 'split_batches', 'even_batches', 'use_seedable_sampler']). Please pass an `accelerate.DataLoaderConfiguration` instead: \n", + "dataloader_config = DataLoaderConfiguration(dispatch_batches=None, split_batches=False, even_batches=True, use_seedable_sampler=True)\n", + " warnings.warn(\n", + "[INFO|trainer.py:601] 2024-04-07 15:20:53,146 >> Using auto half precision backend\n", + "[INFO|trainer.py:1812] 2024-04-07 15:20:53,559 >> ***** Running training *****\n", + "[INFO|trainer.py:1813] 2024-04-07 15:20:53,560 >> Num examples = 500\n", + "[INFO|trainer.py:1814] 2024-04-07 15:20:53,563 >> Num Epochs = 5\n", + "[INFO|trainer.py:1815] 2024-04-07 15:20:53,565 >> Instantaneous batch size per device = 4\n", + "[INFO|trainer.py:1818] 2024-04-07 15:20:53,566 >> Total train batch size (w. parallel, distributed & accumulation) = 16\n", + "[INFO|trainer.py:1819] 2024-04-07 15:20:53,569 >> Gradient Accumulation steps = 4\n", + "[INFO|trainer.py:1820] 2024-04-07 15:20:53,572 >> Total optimization steps = 155\n", + "[INFO|trainer.py:1821] 2024-04-07 15:20:53,583 >> Number of trainable parameters = 20,971,520\n" + ] + }, + { + "output_type": "error", + "ename": "OutOfMemoryError", + "evalue": "CUDA out of memory. Tried to allocate 88.00 MiB. GPU 0 has a total capacity of 14.75 GiB of which 73.06 MiB is free. Process 7257 has 14.67 GiB memory in use. Of the allocated memory 14.29 GiB is allocated by PyTorch, and 263.18 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)", + "traceback": [ + "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[0;31mOutOfMemoryError\u001b[0m Traceback (most recent call last)", + "\u001b[0;32m\u001b[0m in \u001b[0;36m\u001b[0;34m()\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0mllmtuner\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mrun_exp\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m run_exp(dict(\n\u001b[0m\u001b[1;32m 3\u001b[0m \u001b[0mstage\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m\"sft\"\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 4\u001b[0m \u001b[0mdo_train\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mTrue\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 5\u001b[0m \u001b[0mmodel_name_or_path\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m\"mistralai/Mistral-7B-v0.1\"\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/llmtuner/train/tuner.py\u001b[0m in \u001b[0;36mrun_exp\u001b[0;34m(args, callbacks)\u001b[0m\n\u001b[1;32m 31\u001b[0m \u001b[0mrun_pt\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmodel_args\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdata_args\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtraining_args\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfinetuning_args\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcallbacks\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 32\u001b[0m \u001b[0;32melif\u001b[0m \u001b[0mfinetuning_args\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstage\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0;34m\"sft\"\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 33\u001b[0;31m \u001b[0mrun_sft\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmodel_args\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdata_args\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtraining_args\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfinetuning_args\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mgenerating_args\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcallbacks\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 34\u001b[0m \u001b[0;32melif\u001b[0m \u001b[0mfinetuning_args\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstage\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0;34m\"rm\"\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 35\u001b[0m \u001b[0mrun_rm\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmodel_args\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdata_args\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtraining_args\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfinetuning_args\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcallbacks\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/llmtuner/train/sft/workflow.py\u001b[0m in \u001b[0;36mrun_sft\u001b[0;34m(model_args, data_args, training_args, finetuning_args, generating_args, callbacks)\u001b[0m\n\u001b[1;32m 69\u001b[0m \u001b[0;31m# Training\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 70\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mtraining_args\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdo_train\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 71\u001b[0;31m \u001b[0mtrain_result\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtrainer\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtrain\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mresume_from_checkpoint\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mtraining_args\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mresume_from_checkpoint\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 72\u001b[0m \u001b[0mtrainer\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msave_model\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 73\u001b[0m \u001b[0mtrainer\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mlog_metrics\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"train\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtrain_result\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmetrics\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/transformers/trainer.py\u001b[0m in \u001b[0;36mtrain\u001b[0;34m(self, resume_from_checkpoint, trial, ignore_keys_for_eval, **kwargs)\u001b[0m\n\u001b[1;32m 1622\u001b[0m \u001b[0mhf_hub_utils\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0menable_progress_bars\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1623\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1624\u001b[0;31m return inner_training_loop(\n\u001b[0m\u001b[1;32m 1625\u001b[0m \u001b[0margs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1626\u001b[0m \u001b[0mresume_from_checkpoint\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mresume_from_checkpoint\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/transformers/trainer.py\u001b[0m in \u001b[0;36m_inner_training_loop\u001b[0;34m(self, batch_size, args, resume_from_checkpoint, trial, ignore_keys_for_eval)\u001b[0m\n\u001b[1;32m 1959\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1960\u001b[0m \u001b[0;32mwith\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0maccelerator\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0maccumulate\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmodel\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1961\u001b[0;31m \u001b[0mtr_loss_step\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtraining_step\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmodel\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0minputs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1962\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1963\u001b[0m if (\n", + "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/transformers/trainer.py\u001b[0m in \u001b[0;36mtraining_step\u001b[0;34m(self, model, inputs)\u001b[0m\n\u001b[1;32m 2900\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2901\u001b[0m \u001b[0;32mwith\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcompute_loss_context_manager\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2902\u001b[0;31m \u001b[0mloss\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcompute_loss\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmodel\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0minputs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 2903\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2904\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mn_gpu\u001b[0m \u001b[0;34m>\u001b[0m \u001b[0;36m1\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/transformers/trainer.py\u001b[0m in \u001b[0;36mcompute_loss\u001b[0;34m(self, model, inputs, return_outputs)\u001b[0m\n\u001b[1;32m 2923\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2924\u001b[0m \u001b[0mlabels\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2925\u001b[0;31m \u001b[0moutputs\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mmodel\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m**\u001b[0m\u001b[0minputs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 2926\u001b[0m \u001b[0;31m# Save past state if it exists\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2927\u001b[0m \u001b[0;31m# TODO: this needs to be fixed and made cleaner later.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py\u001b[0m in \u001b[0;36m_wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1509\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_compiled_call_impl\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;31m# type: ignore[misc]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1510\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1511\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_call_impl\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1512\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1513\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0m_call_impl\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py\u001b[0m in \u001b[0;36m_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1518\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0m_global_backward_pre_hooks\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0m_global_backward_hooks\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1519\u001b[0m or _global_forward_hooks or _global_forward_pre_hooks):\n\u001b[0;32m-> 1520\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mforward_call\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1521\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1522\u001b[0m \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/accelerate/utils/operations.py\u001b[0m in \u001b[0;36mforward\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 823\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 824\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0mforward\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 825\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mmodel_forward\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 826\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 827\u001b[0m \u001b[0;31m# To act like a decorator so that it can be popped when doing `extract_model_from_parallel`\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/accelerate/utils/operations.py\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 811\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 812\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0m__call__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 813\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mconvert_to_fp32\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmodel_forward\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 814\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 815\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0m__getstate__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/torch/amp/autocast_mode.py\u001b[0m in \u001b[0;36mdecorate_autocast\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 14\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0mdecorate_autocast\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 15\u001b[0m \u001b[0;32mwith\u001b[0m \u001b[0mautocast_instance\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 16\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mfunc\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 17\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 18\u001b[0m \u001b[0mdecorate_autocast\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__script_unsupported\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m\"@autocast() decorator is not supported in script mode\"\u001b[0m \u001b[0;31m# type: ignore[attr-defined]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/peft/peft_model.py\u001b[0m in \u001b[0;36mforward\u001b[0;34m(self, input_ids, attention_mask, inputs_embeds, labels, output_attentions, output_hidden_states, return_dict, task_ids, **kwargs)\u001b[0m\n\u001b[1;32m 1127\u001b[0m \u001b[0;32mwith\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_enable_peft_forward_hooks\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1128\u001b[0m \u001b[0mkwargs\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m{\u001b[0m\u001b[0mk\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mv\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mk\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mv\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mkwargs\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mitems\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mk\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mspecial_peft_forward_args\u001b[0m\u001b[0;34m}\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1129\u001b[0;31m return self.base_model(\n\u001b[0m\u001b[1;32m 1130\u001b[0m \u001b[0minput_ids\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0minput_ids\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1131\u001b[0m \u001b[0mattention_mask\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mattention_mask\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py\u001b[0m in \u001b[0;36m_wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1509\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_compiled_call_impl\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;31m# type: ignore[misc]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1510\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1511\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_call_impl\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1512\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1513\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0m_call_impl\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py\u001b[0m in \u001b[0;36m_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1518\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0m_global_backward_pre_hooks\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0m_global_backward_hooks\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1519\u001b[0m or _global_forward_hooks or _global_forward_pre_hooks):\n\u001b[0;32m-> 1520\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mforward_call\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1521\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1522\u001b[0m \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/peft/tuners/tuners_utils.py\u001b[0m in \u001b[0;36mforward\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 159\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 160\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0mforward\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mAny\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mAny\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 161\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmodel\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mforward\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 162\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 163\u001b[0m \u001b[0;34m@\u001b[0m\u001b[0mabstractmethod\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/transformers/models/mistral/modeling_mistral.py\u001b[0m in \u001b[0;36mforward\u001b[0;34m(self, input_ids, attention_mask, position_ids, past_key_values, inputs_embeds, labels, use_cache, output_attentions, output_hidden_states, return_dict)\u001b[0m\n\u001b[1;32m 1155\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1156\u001b[0m \u001b[0;31m# decoder outputs consists of (dec_features, layer_state, dec_hidden, dec_attn)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1157\u001b[0;31m outputs = self.model(\n\u001b[0m\u001b[1;32m 1158\u001b[0m \u001b[0minput_ids\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0minput_ids\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1159\u001b[0m \u001b[0mattention_mask\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mattention_mask\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py\u001b[0m in \u001b[0;36m_wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1509\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_compiled_call_impl\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;31m# type: ignore[misc]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1510\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1511\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_call_impl\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1512\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1513\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0m_call_impl\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py\u001b[0m in \u001b[0;36m_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1518\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0m_global_backward_pre_hooks\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0m_global_backward_hooks\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1519\u001b[0m or _global_forward_hooks or _global_forward_pre_hooks):\n\u001b[0;32m-> 1520\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mforward_call\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1521\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1522\u001b[0m \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/transformers/models/mistral/modeling_mistral.py\u001b[0m in \u001b[0;36mforward\u001b[0;34m(self, input_ids, attention_mask, position_ids, past_key_values, inputs_embeds, use_cache, output_attentions, output_hidden_states, return_dict)\u001b[0m\n\u001b[1;32m 1030\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1031\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mgradient_checkpointing\u001b[0m \u001b[0;32mand\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtraining\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1032\u001b[0;31m layer_outputs = self._gradient_checkpointing_func(\n\u001b[0m\u001b[1;32m 1033\u001b[0m \u001b[0mdecoder_layer\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__call__\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1034\u001b[0m \u001b[0mhidden_states\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/torch/_compile.py\u001b[0m in \u001b[0;36minner\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 22\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mtorch\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_dynamo\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 23\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 24\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mtorch\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_dynamo\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdisable\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfn\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mrecursive\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 25\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 26\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0minner\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/torch/_dynamo/eval_frame.py\u001b[0m in \u001b[0;36m_fn\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 487\u001b[0m \u001b[0mdynamo_config_ctx\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__enter__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 488\u001b[0m \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 489\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mfn\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 490\u001b[0m \u001b[0;32mfinally\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 491\u001b[0m \u001b[0mset_eval_frame\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mprior\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/torch/_dynamo/external_utils.py\u001b[0m in \u001b[0;36minner\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 15\u001b[0m \u001b[0;34m@\u001b[0m\u001b[0mfunctools\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mwraps\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfn\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 16\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0minner\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 17\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mfn\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 18\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 19\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0minner\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/torch/utils/checkpoint.py\u001b[0m in \u001b[0;36mcheckpoint\u001b[0;34m(function, use_reentrant, context_fn, determinism_check, debug, *args, **kwargs)\u001b[0m\n\u001b[1;32m 480\u001b[0m \u001b[0;34m\"use_reentrant=False.\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 481\u001b[0m )\n\u001b[0;32m--> 482\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mCheckpointFunction\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mapply\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfunction\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mpreserve\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 483\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 484\u001b[0m gen = _checkpoint_without_reentrant_generator(\n", + "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/torch/autograd/function.py\u001b[0m in \u001b[0;36mapply\u001b[0;34m(cls, *args, **kwargs)\u001b[0m\n\u001b[1;32m 551\u001b[0m \u001b[0;31m# See NOTE: [functorch vjp and autograd interaction]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 552\u001b[0m \u001b[0margs\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0m_functorch\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mutils\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0munwrap_dead_wrappers\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 553\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0msuper\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mapply\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;31m# type: ignore[misc]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 554\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 555\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mis_setup_ctx_defined\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/torch/utils/checkpoint.py\u001b[0m in \u001b[0;36mforward\u001b[0;34m(ctx, run_function, preserve_rng_state, *args)\u001b[0m\n\u001b[1;32m 259\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 260\u001b[0m \u001b[0;32mwith\u001b[0m \u001b[0mtorch\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mno_grad\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 261\u001b[0;31m \u001b[0moutputs\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mrun_function\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 262\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0moutputs\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 263\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py\u001b[0m in \u001b[0;36m_wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1509\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_compiled_call_impl\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;31m# type: ignore[misc]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1510\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1511\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_call_impl\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1512\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1513\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0m_call_impl\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py\u001b[0m in \u001b[0;36m_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1518\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0m_global_backward_pre_hooks\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0m_global_backward_hooks\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1519\u001b[0m or _global_forward_hooks or _global_forward_pre_hooks):\n\u001b[0;32m-> 1520\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mforward_call\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1521\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1522\u001b[0m \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/transformers/models/mistral/modeling_mistral.py\u001b[0m in \u001b[0;36mforward\u001b[0;34m(self, hidden_states, attention_mask, position_ids, past_key_value, output_attentions, use_cache, **kwargs)\u001b[0m\n\u001b[1;32m 768\u001b[0m \u001b[0mresidual\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mhidden_states\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 769\u001b[0m \u001b[0mhidden_states\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpost_attention_layernorm\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mhidden_states\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 770\u001b[0;31m \u001b[0mhidden_states\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmlp\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mhidden_states\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 771\u001b[0m \u001b[0mhidden_states\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mresidual\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0mhidden_states\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 772\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py\u001b[0m in \u001b[0;36m_wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1509\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_compiled_call_impl\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;31m# type: ignore[misc]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1510\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1511\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_call_impl\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1512\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1513\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0m_call_impl\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py\u001b[0m in \u001b[0;36m_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1518\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0m_global_backward_pre_hooks\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0m_global_backward_hooks\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1519\u001b[0m or _global_forward_hooks or _global_forward_pre_hooks):\n\u001b[0;32m-> 1520\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mforward_call\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1521\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1522\u001b[0m \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/transformers/models/mistral/modeling_mistral.py\u001b[0m in \u001b[0;36mforward\u001b[0;34m(self, x)\u001b[0m\n\u001b[1;32m 177\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 178\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0mforward\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mx\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 179\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdown_proj\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mact_fn\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mgate_proj\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mx\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m*\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mup_proj\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mx\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 180\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 181\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py\u001b[0m in \u001b[0;36m_wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1509\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_compiled_call_impl\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;31m# type: ignore[misc]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1510\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1511\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_call_impl\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1512\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1513\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0m_call_impl\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py\u001b[0m in \u001b[0;36m_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1518\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0m_global_backward_pre_hooks\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0m_global_backward_hooks\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1519\u001b[0m or _global_forward_hooks or _global_forward_pre_hooks):\n\u001b[0;32m-> 1520\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mforward_call\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1521\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1522\u001b[0m \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/peft/tuners/lora/layer.py\u001b[0m in \u001b[0;36mforward\u001b[0;34m(self, x, *args, **kwargs)\u001b[0m\n\u001b[1;32m 507\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 508\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0muse_dora\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mactive_adapter\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 509\u001b[0;31m \u001b[0mresult\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mresult\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0mlora_B\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mlora_A\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdropout\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mx\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m*\u001b[0m \u001b[0mscaling\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 510\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 511\u001b[0m \u001b[0mx\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mdropout\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mx\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py\u001b[0m in \u001b[0;36m_wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1509\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_compiled_call_impl\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;31m# type: ignore[misc]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1510\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1511\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_call_impl\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1512\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1513\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0m_call_impl\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py\u001b[0m in \u001b[0;36m_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1518\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0m_global_backward_pre_hooks\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0m_global_backward_hooks\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1519\u001b[0m or _global_forward_hooks or _global_forward_pre_hooks):\n\u001b[0;32m-> 1520\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mforward_call\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1521\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1522\u001b[0m \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/torch/nn/modules/linear.py\u001b[0m in \u001b[0;36mforward\u001b[0;34m(self, input)\u001b[0m\n\u001b[1;32m 114\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 115\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0mforward\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0minput\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mTensor\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m->\u001b[0m \u001b[0mTensor\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 116\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mF\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mlinear\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0minput\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mweight\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mbias\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 117\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 118\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0mextra_repr\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m->\u001b[0m \u001b[0mstr\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;31mOutOfMemoryError\u001b[0m: CUDA out of memory. Tried to allocate 88.00 MiB. GPU 0 has a total capacity of 14.75 GiB of which 73.06 MiB is free. Process 7257 has 14.67 GiB memory in use. Of the allocated memory 14.29 GiB is allocated by PyTorch, and 263.18 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)" + ] + } + ] + }, + { + "cell_type": "markdown", + "source": [ + "### Infer the fine-tuned model" + ], + "metadata": { + "id": "PVNaC-xS5N40" + } + }, + { + "cell_type": "code", + "source": [ + "from llmtuner import ChatModel\n", + "chat_model = ChatModel(dict(\n", + " model_name_or_path=\"Qwen/Qwen1.5-0.5B-Chat\",\n", + " adapter_name_or_path=\"test_identity\",\n", + " finetuning_type=\"lora\",\n", + " template=\"qwen\",\n", + "))\n", + "messages = []\n", + "while True:\n", + " query = input(\"\\nUser: \")\n", + " if query.strip() == \"exit\":\n", + " break\n", + " if query.strip() == \"clear\":\n", + " messages = []\n", + " continue\n", + "\n", + " messages.append({\"role\": \"user\", \"content\": query})\n", + " print(\"Assistant: \", end=\"\", flush=True)\n", + " response = \"\"\n", + " for new_text in chat_model.stream_chat(messages):\n", + " print(new_text, end=\"\", flush=True)\n", + " response += new_text\n", + " print()\n", + " messages.append({\"role\": \"assistant\", \"content\": response})" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "oh8H9A_25SF9", + "outputId": "6730e9db-584a-4485-8b3b-c596749df84a" + }, + "execution_count": null, + "outputs": [ + { + "output_type": "stream", + "name": "stderr", + "text": [ + "[INFO|tokenization_utils_base.py:2046] 2024-03-02 12:03:09,835 >> loading file vocab.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen1.5-0.5B-Chat/snapshots/6c705984bb8b5591dd4e1a9e66e1a127965fd08d/vocab.json\n", + "[INFO|tokenization_utils_base.py:2046] 2024-03-02 12:03:09,837 >> loading file merges.txt from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen1.5-0.5B-Chat/snapshots/6c705984bb8b5591dd4e1a9e66e1a127965fd08d/merges.txt\n", + "[INFO|tokenization_utils_base.py:2046] 2024-03-02 12:03:09,839 >> loading file added_tokens.json from cache at None\n", + "[INFO|tokenization_utils_base.py:2046] 2024-03-02 12:03:09,841 >> loading file special_tokens_map.json from cache at None\n", + "[INFO|tokenization_utils_base.py:2046] 2024-03-02 12:03:09,843 >> loading file tokenizer_config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen1.5-0.5B-Chat/snapshots/6c705984bb8b5591dd4e1a9e66e1a127965fd08d/tokenizer_config.json\n", + "[INFO|tokenization_utils_base.py:2046] 2024-03-02 12:03:09,845 >> loading file tokenizer.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen1.5-0.5B-Chat/snapshots/6c705984bb8b5591dd4e1a9e66e1a127965fd08d/tokenizer.json\n", + "[WARNING|logging.py:314] 2024-03-02 12:03:10,117 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.\n", + "[INFO|configuration_utils.py:728] 2024-03-02 12:03:10,188 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen1.5-0.5B-Chat/snapshots/6c705984bb8b5591dd4e1a9e66e1a127965fd08d/config.json\n", + "[INFO|configuration_utils.py:791] 2024-03-02 12:03:10,191 >> Model config Qwen2Config {\n", + " \"_name_or_path\": \"Qwen/Qwen1.5-0.5B-Chat\",\n", + " \"architectures\": [\n", + " \"Qwen2ForCausalLM\"\n", + " ],\n", + " \"attention_dropout\": 0.0,\n", + " \"bos_token_id\": 151643,\n", + " \"eos_token_id\": 151645,\n", + " \"hidden_act\": \"silu\",\n", + " \"hidden_size\": 1024,\n", + " \"initializer_range\": 0.02,\n", + " \"intermediate_size\": 2816,\n", + " \"max_position_embeddings\": 32768,\n", + " \"max_window_layers\": 21,\n", + " \"model_type\": \"qwen2\",\n", + " \"num_attention_heads\": 16,\n", + " \"num_hidden_layers\": 24,\n", + " \"num_key_value_heads\": 16,\n", + " \"rms_norm_eps\": 1e-06,\n", + " \"rope_theta\": 1000000.0,\n", + " \"sliding_window\": 32768,\n", + " \"tie_word_embeddings\": true,\n", + " \"torch_dtype\": \"bfloat16\",\n", + " \"transformers_version\": \"4.38.1\",\n", + " \"use_cache\": true,\n", + " \"use_sliding_window\": false,\n", + " \"vocab_size\": 151936\n", + "}\n", + "\n", + "[INFO|modeling_utils.py:3257] 2024-03-02 12:03:10,196 >> loading weights file model.safetensors from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen1.5-0.5B-Chat/snapshots/6c705984bb8b5591dd4e1a9e66e1a127965fd08d/model.safetensors\n", + "[INFO|modeling_utils.py:1400] 2024-03-02 12:03:10,216 >> Instantiating Qwen2ForCausalLM model under default dtype torch.float16.\n", + "[INFO|configuration_utils.py:845] 2024-03-02 12:03:10,221 >> Generate config GenerationConfig {\n", + " \"bos_token_id\": 151643,\n", + " \"eos_token_id\": 151645\n", + "}\n", + "\n", + "[INFO|modeling_utils.py:3992] 2024-03-02 12:03:12,983 >> All model checkpoint weights were used when initializing Qwen2ForCausalLM.\n", + "\n", + "[INFO|modeling_utils.py:4000] 2024-03-02 12:03:12,984 >> All the weights of Qwen2ForCausalLM were initialized from the model checkpoint at Qwen/Qwen1.5-0.5B-Chat.\n", + "If your task is similar to the task the model of the checkpoint was trained on, you can already use Qwen2ForCausalLM for predictions without further training.\n", + "[INFO|configuration_utils.py:800] 2024-03-02 12:03:13,059 >> loading configuration file generation_config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen1.5-0.5B-Chat/snapshots/6c705984bb8b5591dd4e1a9e66e1a127965fd08d/generation_config.json\n", + "[INFO|configuration_utils.py:845] 2024-03-02 12:03:13,061 >> Generate config GenerationConfig {\n", + " \"bos_token_id\": 151643,\n", + " \"do_sample\": true,\n", + " \"eos_token_id\": [\n", + " 151645,\n", + " 151643\n", + " ],\n", + " \"pad_token_id\": 151643,\n", + " \"repetition_penalty\": 1.1,\n", + " \"top_p\": 0.8\n", + "}\n", + "\n" + ] + }, + { + "output_type": "stream", + "name": "stdout", + "text": [ + "03/02/2024 12:03:13 - INFO - llmtuner.model.adapter - Fine-tuning method: LoRA\n" + ] + }, + { + "output_type": "stream", + "name": "stderr", + "text": [ + "INFO:llmtuner.model.adapter:Fine-tuning method: LoRA\n" + ] + }, + { + "output_type": "stream", + "name": "stdout", + "text": [ + "03/02/2024 12:03:14 - INFO - llmtuner.model.adapter - Merged 1 adapter(s).\n" + ] + }, + { + "output_type": "stream", + "name": "stderr", + "text": [ + "INFO:llmtuner.model.adapter:Merged 1 adapter(s).\n" + ] + }, + { + "output_type": "stream", + "name": "stdout", + "text": [ + "03/02/2024 12:03:14 - INFO - llmtuner.model.adapter - Loaded adapter(s): test_identity\n" + ] + }, + { + "output_type": "stream", + "name": "stderr", + "text": [ + "INFO:llmtuner.model.adapter:Loaded adapter(s): test_identity\n" + ] + }, + { + "output_type": "stream", + "name": "stdout", + "text": [ + "03/02/2024 12:03:14 - INFO - llmtuner.model.loader - all params: 463987712\n" + ] + }, + { + "output_type": "stream", + "name": "stderr", + "text": [ + "INFO:llmtuner.model.loader:all params: 463987712\n" + ] + }, + { + "output_type": "stream", + "name": "stdout", + "text": [ + "03/02/2024 12:03:14 - INFO - llmtuner.data.template - Replace eos token: <|im_end|>\n" + ] + }, + { + "output_type": "stream", + "name": "stderr", + "text": [ + "INFO:llmtuner.data.template:Replace eos token: <|im_end|>\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n", + "User: hi\n", + "Assistant: Hello! How can I help you today?\n", + "\n", + "User: who are you\n", + "Assistant: I am NAME, an AI assistant developed by AUTHOR. I am here to help you with your queries and provide you with the best possible responses.\n", + "\n", + "User: give three tips for staying healthy\n", + "Assistant: 1. Stay hydrated: Drink plenty of water throughout the day to stay hydrated and keep your body functioning at its best.\n", + "2. Exercise regularly: Exercise is one of the best ways to stay healthy. Aim for at least 30 minutes of moderate-intensity exercise most days of the week.\n", + "3. Eat a healthy diet: Eating a balanced and nutritious diet is crucial for maintaining good health. Focus on whole, unprocessed foods, plenty of fruits, vegetables, and lean proteins.\n", + "\n", + "User: exit\n" + ] + } + ] + }, + { + "cell_type": "markdown", + "source": [ + "### Merge LoRA weights" + ], + "metadata": { + "id": "flmc2i3Z7Bl7" + } + }, + { + "cell_type": "code", + "source": [ + "from llmtuner import export_model\n", + "export_model(dict(\n", + " model_name_or_path=\"mistralai/Mistral-7B-v0.1\",\n", + " adapter_name_or_path=\"Artples/LAI-Paca-7b\",\n", + " finetuning_type=\"lora\",\n", + " template=\"mistral\",\n", + " export_dir=\"test_exported\",\n", + " export_hub_model_id=\"Artples/LAI-Paca-7b-Merged\",\n", + "))" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 1000, + "referenced_widgets": [ + "775689b53d674875af95dacb5a804c1d", + "83ac0f982b664dd7ab1bf4003b649f7c", + "93385c2627614f39a8cdaef41770d5dc", + "6a68f4f93136476ba5dda0240ca5239a", + "a52bd50efc7c4a51ba349df39ca8934e", + "4c3db643b3cf49ba8faba63e21d1aa42", + "c1b46640ed8f453292dde7f7bc0be403", + "f45df54413f543caa78f8f44474d600c", + "957f211021b043d0a8da929b5b3e92c4", + "63b452a4cbc546f0a6f956e2a5f5c0b9", + "5f7f24bf6b0b4797b019e8122d37fffe", + "2542ffb4be9846888c31c3b28d1fc8ee", + "36125ba0485d4736896dbe41b5332273", + "55a3d7ba21984835b0ccbeacb00cd74b", + "ce80e04267264ca295383372b23d756e", + "8bd42cd71c55476dbc94e4e3b1cbcf67", + "a928892a06694dd09e61b2c6db9707b3", + "422a58f5fa7646ed9003810b846d7868", + "feff6dd972f842bf99c7f907971175a1", + "8428dd401aac4812af6de9a840f3fbc8", + "c54bf007b00143b4b21232d940043adc", + "f05412ea9aca4e158fc02755ca47f1b2", + "818c371aa671498397a3a4c16e737f07", + "b8707b2d77314eadba4ff5d77d12fead", + "36c8c7b46fa74ea191e1b863b6b67773", + "61ee25e87bbe4e8abcab805c97f3ac68", + "facd485690bd4aaab13fef6568fb03ae", + "78a7c76072bd4090976ddc2b7de874d8", + "9e1ac20517484497ae9a0ea565093858", + "03684e6c259f46c684efe940626be82c", + "8ca6e75fec51431eb1934c29c6c1b45f", + "f7b4a6ea97c641cbbef74f26bbe132e1", + "3c6097f3850a4e7bb282ac4cfd0a5db3" + ] + }, + "id": "g0fVaJsj7GC-", + "outputId": "1c670ce5-1661-484c-8b69-14842cd83220" + }, + "execution_count": null, + "outputs": [ + { + "output_type": "stream", + "name": "stderr", + "text": [ + "[INFO|tokenization_utils_base.py:2046] 2024-04-07 15:22:20,992 >> loading file tokenizer.model from cache at /root/.cache/huggingface/hub/models--mistralai--Mistral-7B-v0.1/snapshots/26bca36bde8333b5d7f72e9ed20ccda6a618af24/tokenizer.model\n", + "[INFO|tokenization_utils_base.py:2046] 2024-04-07 15:22:20,993 >> loading file added_tokens.json from cache at None\n", + "[INFO|tokenization_utils_base.py:2046] 2024-04-07 15:22:20,996 >> loading file special_tokens_map.json from cache at /root/.cache/huggingface/hub/models--mistralai--Mistral-7B-v0.1/snapshots/26bca36bde8333b5d7f72e9ed20ccda6a618af24/special_tokens_map.json\n", + "[INFO|tokenization_utils_base.py:2046] 2024-04-07 15:22:20,998 >> loading file tokenizer_config.json from cache at /root/.cache/huggingface/hub/models--mistralai--Mistral-7B-v0.1/snapshots/26bca36bde8333b5d7f72e9ed20ccda6a618af24/tokenizer_config.json\n", + "[INFO|tokenization_utils_base.py:2046] 2024-04-07 15:22:20,999 >> loading file tokenizer.json from cache at /root/.cache/huggingface/hub/models--mistralai--Mistral-7B-v0.1/snapshots/26bca36bde8333b5d7f72e9ed20ccda6a618af24/tokenizer.json\n" + ] + }, + { + "output_type": "stream", + "name": "stdout", + "text": [ + "04/07/2024 15:22:21 - INFO - llmtuner.data.template - Add pad token: \n" + ] + }, + { + "output_type": "stream", + "name": "stderr", + "text": [ + "INFO:llmtuner.data.template:Add pad token: \n", + "[INFO|configuration_utils.py:728] 2024-04-07 15:22:21,159 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--mistralai--Mistral-7B-v0.1/snapshots/26bca36bde8333b5d7f72e9ed20ccda6a618af24/config.json\n", + "[INFO|configuration_utils.py:791] 2024-04-07 15:22:21,161 >> Model config MistralConfig {\n", + " \"_name_or_path\": \"mistralai/Mistral-7B-v0.1\",\n", + " \"architectures\": [\n", + " \"MistralForCausalLM\"\n", + " ],\n", + " \"attention_dropout\": 0.0,\n", + " \"bos_token_id\": 1,\n", + " \"eos_token_id\": 2,\n", + " \"hidden_act\": \"silu\",\n", + " \"hidden_size\": 4096,\n", + " \"initializer_range\": 0.02,\n", + " \"intermediate_size\": 14336,\n", + " \"max_position_embeddings\": 32768,\n", + " \"model_type\": \"mistral\",\n", + " \"num_attention_heads\": 32,\n", + " \"num_hidden_layers\": 32,\n", + " \"num_key_value_heads\": 8,\n", + " \"rms_norm_eps\": 1e-05,\n", + " \"rope_theta\": 10000.0,\n", + " \"sliding_window\": 4096,\n", + " \"tie_word_embeddings\": false,\n", + " \"torch_dtype\": \"bfloat16\",\n", + " \"transformers_version\": \"4.38.2\",\n", + " \"use_cache\": true,\n", + " \"vocab_size\": 32000\n", + "}\n", + "\n" + ] + }, + { + "output_type": "stream", + "name": "stdout", + "text": [ + "04/07/2024 15:22:21 - INFO - llmtuner.model.patcher - Using KV cache for faster generation.\n" + ] + }, + { + "output_type": "stream", + "name": "stderr", + "text": [ + "INFO:llmtuner.model.patcher:Using KV cache for faster generation.\n", + "[INFO|modeling_utils.py:3257] 2024-04-07 15:22:21,169 >> loading weights file model.safetensors from cache at /root/.cache/huggingface/hub/models--mistralai--Mistral-7B-v0.1/snapshots/26bca36bde8333b5d7f72e9ed20ccda6a618af24/model.safetensors.index.json\n", + "[INFO|modeling_utils.py:1400] 2024-04-07 15:22:21,173 >> Instantiating MistralForCausalLM model under default dtype torch.float16.\n", + "[INFO|configuration_utils.py:845] 2024-04-07 15:22:21,176 >> Generate config GenerationConfig {\n", + " \"bos_token_id\": 1,\n", + " \"eos_token_id\": 2\n", + "}\n", + "\n", + "/usr/local/lib/python3.10/dist-packages/accelerate/utils/modeling.py:1363: UserWarning: Current model requires 536875008 bytes of buffer for offloaded layers, which seems does not fit any GPU's remaining memory. If you are experiencing a OOM later, please consider using offload_buffers=True.\n", + " warnings.warn(\n" + ] + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "Loading checkpoint shards: 0%| | 0/2 [00:00> All model checkpoint weights were used when initializing MistralForCausalLM.\n", + "\n", + "[INFO|modeling_utils.py:4000] 2024-04-07 15:23:06,331 >> All the weights of MistralForCausalLM were initialized from the model checkpoint at mistralai/Mistral-7B-v0.1.\n", + "If your task is similar to the task the model of the checkpoint was trained on, you can already use MistralForCausalLM for predictions without further training.\n", + "[INFO|configuration_utils.py:800] 2024-04-07 15:23:06,435 >> loading configuration file generation_config.json from cache at /root/.cache/huggingface/hub/models--mistralai--Mistral-7B-v0.1/snapshots/26bca36bde8333b5d7f72e9ed20ccda6a618af24/generation_config.json\n", + "[INFO|configuration_utils.py:845] 2024-04-07 15:23:06,438 >> Generate config GenerationConfig {\n", + " \"bos_token_id\": 1,\n", + " \"eos_token_id\": 2\n", + "}\n", + "\n", + "WARNING:root:Some parameters are on the meta device device because they were offloaded to the cpu and disk.\n" + ] + }, + { + "output_type": "stream", + "name": "stdout", + "text": [ + "04/07/2024 15:23:06 - INFO - llmtuner.model.adapter - Fine-tuning method: LoRA\n" + ] + }, + { + "output_type": "stream", + "name": "stderr", + "text": [ + "INFO:llmtuner.model.adapter:Fine-tuning method: LoRA\n" + ] + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "adapter_config.json: 0%| | 0.00/728 [00:00\u001b[0m in \u001b[0;36m\u001b[0;34m()\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0mllmtuner\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mexport_model\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m export_model(dict(\n\u001b[0m\u001b[1;32m 3\u001b[0m \u001b[0mmodel_name_or_path\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m\"mistralai/Mistral-7B-v0.1\"\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 4\u001b[0m \u001b[0madapter_name_or_path\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m\"Artples/LAI-Paca-7b\"\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 5\u001b[0m \u001b[0mfinetuning_type\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m\"lora\"\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/llmtuner/train/tuner.py\u001b[0m in \u001b[0;36mexport_model\u001b[0;34m(args)\u001b[0m\n\u001b[1;32m 55\u001b[0m \u001b[0mtokenizer\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mload_tokenizer\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmodel_args\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 56\u001b[0m \u001b[0mget_template_and_fix_tokenizer\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtokenizer\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdata_args\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtemplate\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 57\u001b[0;31m \u001b[0mmodel\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mload_model\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtokenizer\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmodel_args\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfinetuning_args\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;31m# must after fixing tokenizer to resize vocab\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 58\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 59\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mgetattr\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmodel\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m\"quantization_method\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mand\u001b[0m \u001b[0mmodel_args\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0madapter_name_or_path\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/llmtuner/model/loader.py\u001b[0m in \u001b[0;36mload_model\u001b[0;34m(tokenizer, model_args, finetuning_args, is_trainable, add_valuehead)\u001b[0m\n\u001b[1;32m 91\u001b[0m \u001b[0mregister_autoclass\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mconfig\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmodel\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtokenizer\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 92\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 93\u001b[0;31m \u001b[0mmodel\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0minit_adapter\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmodel\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmodel_args\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfinetuning_args\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mis_trainable\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 94\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 95\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0madd_valuehead\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/llmtuner/model/adapter.py\u001b[0m in \u001b[0;36minit_adapter\u001b[0;34m(model, model_args, finetuning_args, is_trainable)\u001b[0m\n\u001b[1;32m 108\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 109\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0madapter\u001b[0m \u001b[0;32min\u001b[0m \u001b[0madapter_to_merge\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 110\u001b[0;31m model: \"LoraModel\" = PeftModel.from_pretrained(\n\u001b[0m\u001b[1;32m 111\u001b[0m \u001b[0mmodel\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0madapter\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0moffload_folder\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mmodel_args\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0moffload_folder\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 112\u001b[0m )\n", + "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/peft/peft_model.py\u001b[0m in \u001b[0;36mfrom_pretrained\u001b[0;34m(cls, model, model_id, adapter_name, is_trainable, config, **kwargs)\u001b[0m\n\u001b[1;32m 354\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 355\u001b[0m \u001b[0mmodel\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mMODEL_TYPE_TO_PEFT_MODEL_MAPPING\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mconfig\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtask_type\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmodel\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mconfig\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0madapter_name\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 356\u001b[0;31m \u001b[0mmodel\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mload_adapter\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmodel_id\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0madapter_name\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mis_trainable\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mis_trainable\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 357\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mmodel\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 358\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/peft/peft_model.py\u001b[0m in \u001b[0;36mload_adapter\u001b[0;34m(self, model_id, adapter_name, is_trainable, **kwargs)\u001b[0m\n\u001b[1;32m 725\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0madd_adapter\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0madapter_name\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mpeft_config\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 726\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 727\u001b[0;31m \u001b[0madapters_weights\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mload_peft_weights\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmodel_id\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdevice\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mtorch_device\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mhf_hub_download_kwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 728\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 729\u001b[0m \u001b[0;31m# load the weights into the model\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/peft/utils/save_and_load.py\u001b[0m in \u001b[0;36mload_peft_weights\u001b[0;34m(model_id, device, **hf_hub_download_kwargs)\u001b[0m\n\u001b[1;32m 324\u001b[0m \u001b[0madapters_weights\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0msafe_load_file\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfilename\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdevice\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m\"cpu\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 325\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 326\u001b[0;31m \u001b[0madapters_weights\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0msafe_load_file\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfilename\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdevice\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mdevice\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 327\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 328\u001b[0m \u001b[0madapters_weights\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtorch\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mload\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfilename\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmap_location\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mtorch\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdevice\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdevice\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.10/dist-packages/safetensors/torch.py\u001b[0m in \u001b[0;36mload_file\u001b[0;34m(filename, device)\u001b[0m\n\u001b[1;32m 308\u001b[0m \u001b[0;32mwith\u001b[0m \u001b[0msafe_open\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfilename\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mframework\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m\"pt\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdevice\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mdevice\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mf\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 309\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mk\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mkeys\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 310\u001b[0;31m \u001b[0mresult\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mk\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_tensor\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mk\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 311\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mresult\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 312\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;31mOutOfMemoryError\u001b[0m: CUDA out of memory. Tried to allocate 2.00 MiB. GPU 0 has a total capacity of 14.75 GiB of which 1.06 MiB is free. Process 7257 has 14.74 GiB memory in use. Of the allocated memory 14.36 GiB is allocated by PyTorch, and 263.37 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)" + ] + } + ] + } + ] +} \ No newline at end of file