diff --git "a/finetune.ipynb" "b/finetune.ipynb"
--- "a/finetune.ipynb"
+++ "b/finetune.ipynb"
@@ -1,4022 +1,403 @@
{
- "nbformat": 4,
- "nbformat_minor": 0,
- "metadata": {
- "kernelspec": {
- "name": "python3",
- "display_name": "Python 3"
- },
- "language_info": {
- "name": "python"
- },
- "accelerator": "GPU",
- "widgets": {
- "application/vnd.jupyter.widget-state+json": {
- "76eba77b0fc9499e9b4015393156153e": {
- "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_c42123767d4849ffbcdd48f09580ea13",
- "IPY_MODEL_e89f07c1f5744328b071f96a3bdc9532",
- "IPY_MODEL_da36c71ba5bc469eb32bde730c5038d3"
- ],
- "layout": "IPY_MODEL_6cc6b7c564fe48f086152c78f8a9a915"
- }
- },
- "c42123767d4849ffbcdd48f09580ea13": {
- "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_c6a3adfa76dd4bbd8cc5e75ee28ef3e8",
- "placeholder": "",
- "style": "IPY_MODEL_0c65f0e913b74de88ab712d65b9027f7",
- "value": "Downloading data files: 100%"
- }
- },
- "e89f07c1f5744328b071f96a3bdc9532": {
- "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_b07c7f3b6bc24f10821b88e254e88e43",
- "max": 1,
- "min": 0,
- "orientation": "horizontal",
- "style": "IPY_MODEL_42ea2834ee074029abe8cf8f9ff79a16",
- "value": 1
- }
- },
- "da36c71ba5bc469eb32bde730c5038d3": {
- "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_ec4205b0491a4f53ad1cba42689d59c4",
- "placeholder": "",
- "style": "IPY_MODEL_f8b9df09c8c54d53a22310e64e30772f",
- "value": " 1/1 [00:00<00:00, 39.39it/s]"
- }
- },
- "6cc6b7c564fe48f086152c78f8a9a915": {
- "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
- }
- },
- "c6a3adfa76dd4bbd8cc5e75ee28ef3e8": {
- "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
- }
- },
- "0c65f0e913b74de88ab712d65b9027f7": {
- "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": ""
- }
- },
- "b07c7f3b6bc24f10821b88e254e88e43": {
- "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
- }
- },
- "42ea2834ee074029abe8cf8f9ff79a16": {
- "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": ""
- }
- },
- "ec4205b0491a4f53ad1cba42689d59c4": {
- "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
- }
- },
- "f8b9df09c8c54d53a22310e64e30772f": {
- "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": ""
- }
- },
- "e69b8912d3384180842ff0ead6096803": {
- "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_550a2ef0612e4d8396462d1b1c43608d",
- "IPY_MODEL_f8d82b4d016f46ca8bab1a2fe591861e",
- "IPY_MODEL_975d908a1874425198e0d62ae884a3ef"
- ],
- "layout": "IPY_MODEL_152aa8231b3f4b7db4e6f27bb61065b9"
- }
- },
- "550a2ef0612e4d8396462d1b1c43608d": {
- "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_27b48982ae244c66bccd855e7e33a00d",
- "placeholder": "",
- "style": "IPY_MODEL_a896cb94d1fc4641ad224c7a9ca619b1",
- "value": "Extracting data files: 100%"
- }
- },
- "f8d82b4d016f46ca8bab1a2fe591861e": {
- "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_be5d02d7001a4a25a848d6b0c582b42b",
- "max": 1,
- "min": 0,
- "orientation": "horizontal",
- "style": "IPY_MODEL_609437910022418e83543fe6c3d16501",
- "value": 1
- }
- },
- "975d908a1874425198e0d62ae884a3ef": {
- "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_c3b5ef42dae64f95a2ef055db7e50fa8",
- "placeholder": "",
- "style": "IPY_MODEL_ee0f0aff0c254b82854d1a6f4b367161",
- "value": " 1/1 [00:01<00:00, 1.73s/it]"
- }
- },
- "152aa8231b3f4b7db4e6f27bb61065b9": {
- "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
- }
- },
- "27b48982ae244c66bccd855e7e33a00d": {
- "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
- }
- },
- "a896cb94d1fc4641ad224c7a9ca619b1": {
- "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": ""
- }
- },
- "be5d02d7001a4a25a848d6b0c582b42b": {
- "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
- }
- },
- "609437910022418e83543fe6c3d16501": {
- "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": ""
- }
- },
- "c3b5ef42dae64f95a2ef055db7e50fa8": {
- "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
- }
- },
- "ee0f0aff0c254b82854d1a6f4b367161": {
- "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": ""
- }
- },
- "fd90085d416440579f409cdd9b29e053": {
- "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_fdd55d56775a4641925fc88e43f946b8",
- "IPY_MODEL_a54ebe30a12b4c21b67b2f8d43aea2d3",
- "IPY_MODEL_6f041f053ff240cbbb52f6d117ebfcf1"
- ],
- "layout": "IPY_MODEL_b7d5f8aaee0047178661e58aa59433ee"
- }
- },
- "fdd55d56775a4641925fc88e43f946b8": {
- "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_563ca6cac1594ba0a7c168ee31ccc982",
- "placeholder": "",
- "style": "IPY_MODEL_e10e7830d1404baea72e81e0df295239",
- "value": "Generating train split: "
- }
- },
- "a54ebe30a12b4c21b67b2f8d43aea2d3": {
- "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": "info",
- "description": "",
- "description_tooltip": null,
- "layout": "IPY_MODEL_acc07aa077fd49d38d74e0e10fa3991a",
- "max": 1,
- "min": 0,
- "orientation": "horizontal",
- "style": "IPY_MODEL_441dfdd43ef0442894c19cad81a478db",
- "value": 1
- }
- },
- "6f041f053ff240cbbb52f6d117ebfcf1": {
- "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_9efe7ac9ee0946388eeb85f9a4603ffe",
- "placeholder": "",
- "style": "IPY_MODEL_ae9996dcefcf4cfc8ea2f7488629c5ec",
- "value": " 15011/0 [00:01<00:00, 14307.31 examples/s]"
- }
- },
- "b7d5f8aaee0047178661e58aa59433ee": {
- "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": "hidden",
- "width": null
- }
- },
- "563ca6cac1594ba0a7c168ee31ccc982": {
- "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
- }
- },
- "e10e7830d1404baea72e81e0df295239": {
- "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": ""
- }
- },
- "acc07aa077fd49d38d74e0e10fa3991a": {
- "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"
- }
- },
- "441dfdd43ef0442894c19cad81a478db": {
- "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": ""
- }
- },
- "9efe7ac9ee0946388eeb85f9a4603ffe": {
- "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
- }
- },
- "ae9996dcefcf4cfc8ea2f7488629c5ec": {
- "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": ""
- }
- },
- "db463b34f98c488e8282d7a59c421347": {
- "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_2ba524e48f35421c9afc9cc81e9ce3fb",
- "IPY_MODEL_1829c96471c64a03a4872e1b7a16551c",
- "IPY_MODEL_f639a121fab0407595ebdf04015d9267"
- ],
- "layout": "IPY_MODEL_fa5ff44ae5f64ce4bbf9b59e300b7ba3"
- }
- },
- "2ba524e48f35421c9afc9cc81e9ce3fb": {
- "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_e0d701b8c09744858db4fda6011b69df",
- "placeholder": "",
- "style": "IPY_MODEL_7ef61952e0f2463bad3dd1a814bfb95a",
- "value": "100%"
- }
- },
- "1829c96471c64a03a4872e1b7a16551c": {
- "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_75263b1d19ce4cb0b95cacb6138b6fcb",
- "max": 1,
- "min": 0,
- "orientation": "horizontal",
- "style": "IPY_MODEL_c3f35ce818e34b05b247fae76200c02e",
- "value": 1
- }
- },
- "f639a121fab0407595ebdf04015d9267": {
- "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_be8dddb19dde441da1193d5f8738413d",
- "placeholder": "",
- "style": "IPY_MODEL_4be8d304ddce49319488f20ab36e7f53",
- "value": " 1/1 [00:00<00:00, 22.58it/s]"
- }
- },
- "fa5ff44ae5f64ce4bbf9b59e300b7ba3": {
- "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
- }
- },
- "e0d701b8c09744858db4fda6011b69df": {
- "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
- }
- },
- "7ef61952e0f2463bad3dd1a814bfb95a": {
- "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": ""
- }
- },
- "75263b1d19ce4cb0b95cacb6138b6fcb": {
- "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
- }
- },
- "c3f35ce818e34b05b247fae76200c02e": {
- "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": ""
- }
- },
- "be8dddb19dde441da1193d5f8738413d": {
- "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
- }
- },
- "4be8d304ddce49319488f20ab36e7f53": {
- "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": ""
- }
- },
- "984896bacc39446091e2b6573facfa3e": {
- "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_f15179aad6ad44dfa2dfbd703dc7c319",
- "IPY_MODEL_f92c68902b984e648337da7e63fcc775",
- "IPY_MODEL_5ce279d7dca74e55acae1c70efae6cd5"
- ],
- "layout": "IPY_MODEL_b187d889a6654fd7ad948d66a8bce197"
- }
- },
- "f15179aad6ad44dfa2dfbd703dc7c319": {
- "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_e131a64ebaa84a809754b3c762525c37",
- "placeholder": "",
- "style": "IPY_MODEL_72819a3c606c41f19d1493539d64aff5",
- "value": "Downloading (…)lve/main/config.json: 100%"
- }
- },
- "f92c68902b984e648337da7e63fcc775": {
- "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_6761867d6e2b415b932bebd33a3144f3",
- "max": 506,
- "min": 0,
- "orientation": "horizontal",
- "style": "IPY_MODEL_72c9aa3bb9614dfc8f316bc45a3455a0",
- "value": 506
- }
- },
- "5ce279d7dca74e55acae1c70efae6cd5": {
- "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_58e5e895215d4910b55d8cbe1417a111",
- "placeholder": "",
- "style": "IPY_MODEL_b6bad7f690c54cb5814d09081e306393",
- "value": " 506/506 [00:00<00:00, 31.8kB/s]"
- }
- },
- "b187d889a6654fd7ad948d66a8bce197": {
- "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
- }
- },
- "e131a64ebaa84a809754b3c762525c37": {
- "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
- }
- },
- "72819a3c606c41f19d1493539d64aff5": {
- "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": ""
- }
- },
- "6761867d6e2b415b932bebd33a3144f3": {
- "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
- }
- },
- "72c9aa3bb9614dfc8f316bc45a3455a0": {
- "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": ""
- }
- },
- "58e5e895215d4910b55d8cbe1417a111": {
- "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
- }
- },
- "b6bad7f690c54cb5814d09081e306393": {
- "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": ""
- }
- },
- "ae3921fcb8e44862a42031f284f608c3": {
- "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_aaac19cd3f524821a656ceffa57fb337",
- "IPY_MODEL_a77af2c0771b4a20b42dade07c40021c",
- "IPY_MODEL_7e5ced10225544399add5e68dda80595"
- ],
- "layout": "IPY_MODEL_ccf73891ca1941ca8b77c87ba84058f8"
- }
- },
- "aaac19cd3f524821a656ceffa57fb337": {
- "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_bfc1e1979f0741a09e6c9f4181ae88e7",
- "placeholder": "",
- "style": "IPY_MODEL_8ce25329fdf04a6e8c4ad8097975111e",
- "value": "Downloading pytorch_model.bin: 100%"
- }
- },
- "a77af2c0771b4a20b42dade07c40021c": {
- "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_479d18fc0f9448a49b07b93ac608ae1d",
- "max": 6853038093,
- "min": 0,
- "orientation": "horizontal",
- "style": "IPY_MODEL_85ffc3306cb4474aa5bfac22f6356352",
- "value": 6853038093
- }
- },
- "7e5ced10225544399add5e68dda80595": {
- "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_0d5765bde1fa470eb087df5fe1e45e56",
- "placeholder": "",
- "style": "IPY_MODEL_6873f0a521cd4e4390563e27046c1aa6",
- "value": " 6.85G/6.85G [00:35<00:00, 230MB/s]"
- }
- },
- "ccf73891ca1941ca8b77c87ba84058f8": {
- "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
- }
- },
- "bfc1e1979f0741a09e6c9f4181ae88e7": {
- "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
- }
- },
- "8ce25329fdf04a6e8c4ad8097975111e": {
- "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": ""
- }
- },
- "479d18fc0f9448a49b07b93ac608ae1d": {
- "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
- }
- },
- "85ffc3306cb4474aa5bfac22f6356352": {
- "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": ""
- }
- },
- "0d5765bde1fa470eb087df5fe1e45e56": {
- "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
- }
- },
- "6873f0a521cd4e4390563e27046c1aa6": {
- "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": ""
- }
- },
- "0832a0aa65ac4f70ba2f303f9b867d25": {
- "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_436e9deafae04955a13f2ff0fc0e6348",
- "IPY_MODEL_83427a912e3740008c0a7ffb9d20a1bd",
- "IPY_MODEL_084f196c105c4c428253e0ce6dce8a21"
- ],
- "layout": "IPY_MODEL_403990397a4041abb8aff7bdcc5d8e8a"
- }
- },
- "436e9deafae04955a13f2ff0fc0e6348": {
- "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_f957482962954f03b383d7c4f93c7b04",
- "placeholder": "",
- "style": "IPY_MODEL_19a731496867404b8888986f3d9c83ef",
- "value": "Downloading (…)neration_config.json: 100%"
- }
- },
- "83427a912e3740008c0a7ffb9d20a1bd": {
- "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_e0b09d3aa9ae4719bcdfad8e75ad86c5",
- "max": 137,
- "min": 0,
- "orientation": "horizontal",
- "style": "IPY_MODEL_9d41c197843644858919a396dc927936",
- "value": 137
- }
- },
- "084f196c105c4c428253e0ce6dce8a21": {
- "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_67f9f877dee04d538ffbe2de6c4dd181",
- "placeholder": "",
- "style": "IPY_MODEL_001bb332cdb94a0c96dd2a322ff8718f",
- "value": " 137/137 [00:00<00:00, 9.29kB/s]"
- }
- },
- "403990397a4041abb8aff7bdcc5d8e8a": {
- "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
- }
- },
- "f957482962954f03b383d7c4f93c7b04": {
- "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
- }
- },
- "19a731496867404b8888986f3d9c83ef": {
- "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": ""
- }
- },
- "e0b09d3aa9ae4719bcdfad8e75ad86c5": {
- "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
- }
- },
- "9d41c197843644858919a396dc927936": {
- "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": ""
- }
- },
- "67f9f877dee04d538ffbe2de6c4dd181": {
- "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
- }
- },
- "001bb332cdb94a0c96dd2a322ff8718f": {
- "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": ""
- }
- },
- "310970764a4a4c9382e2334a4abbbd77": {
- "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_2cd59f5acc4948988814eb9b3d909aed",
- "IPY_MODEL_8939309032ca4787a9d3c7b54b889926",
- "IPY_MODEL_fcd31f8d1e5a482d9267ab63fd723e86"
- ],
- "layout": "IPY_MODEL_2d126272a4284ba9af39de65e9680fc8"
- }
- },
- "2cd59f5acc4948988814eb9b3d909aed": {
- "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_d8a0e85fa9fc4a9291f9303861fc9efc",
- "placeholder": "",
- "style": "IPY_MODEL_d21f1cfb275b4bb38baf7022665e0208",
- "value": "Map: 100%"
- }
- },
- "8939309032ca4787a9d3c7b54b889926": {
- "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": "",
- "description": "",
- "description_tooltip": null,
- "layout": "IPY_MODEL_81e25933b9af43a492a6da4a5e3560f6",
- "max": 15011,
- "min": 0,
- "orientation": "horizontal",
- "style": "IPY_MODEL_5fe27494333b4e07a632769696744210",
- "value": 15011
- }
- },
- "fcd31f8d1e5a482d9267ab63fd723e86": {
- "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_35ca13104a3e4263a192889362dbc05e",
- "placeholder": "",
- "style": "IPY_MODEL_85ae96c237754c4db014e5c09898e162",
- "value": " 14994/15011 [00:44<00:00, 638.52 examples/s]"
- }
- },
- "2d126272a4284ba9af39de65e9680fc8": {
- "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": "hidden",
- "width": null
- }
- },
- "d8a0e85fa9fc4a9291f9303861fc9efc": {
- "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
- }
- },
- "d21f1cfb275b4bb38baf7022665e0208": {
- "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": ""
- }
- },
- "81e25933b9af43a492a6da4a5e3560f6": {
- "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
- }
- },
- "5fe27494333b4e07a632769696744210": {
- "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": ""
- }
- },
- "35ca13104a3e4263a192889362dbc05e": {
- "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
- }
- },
- "85ae96c237754c4db014e5c09898e162": {
- "model_module": "@jupyter-widgets/controls",
- "model_name": "DescriptionStyleModel",
- "model_module_version": "1.5.0",
- "state": {
- "_model_module": "@jupyter-widgets/controls",
- "_model_module_version": "1.5.0",
- "_model_name": "DescriptionStyleModel",
- "_view_count": null,
- "_view_module": "@jupyter-widgets/base",
- "_view_module_version": "1.2.0",
- "_view_name": "StyleView",
- "description_width": ""
- }
- }
- }
- }
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "Gzg8SopX8EWH"
+ },
+ "source": [
+ "# Alpaca OpenLLaMa 3B LoRA"
+ ]
},
- "cells": [
- {
- "cell_type": "code",
- "execution_count": 1,
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "YSW4FUQPwIYu",
- "outputId": "421da5b9-be5e-4661-bf98-6c57fbf1f6fd"
- },
- "outputs": [
- {
- "output_type": "stream",
- "name": "stdout",
- "text": [
- "Cloning into 'alpaca-lora'...\n",
- "remote: Enumerating objects: 607, done.\u001b[K\n",
- "remote: Counting objects: 100% (51/51), done.\u001b[K\n",
- "remote: Compressing objects: 100% (32/32), done.\u001b[K\n",
- "remote: Total 607 (delta 28), reused 33 (delta 19), pack-reused 556\u001b[K\n",
- "Receiving objects: 100% (607/607), 27.78 MiB | 5.67 MiB/s, done.\n",
- "Resolving deltas: 100% (360/360), done.\n"
- ]
- }
- ],
- "source": [
- "!git clone https://github.com/tloen/alpaca-lora.git"
- ]
- },
- {
- "cell_type": "markdown",
- "source": [
- "# Alpaca OpenLLaMa 3B LoRA"
- ],
- "metadata": {
- "id": "Gzg8SopX8EWH"
- }
- },
- {
- "cell_type": "code",
- "source": [
- "%cd alpaca-lora/"
- ],
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "s1xm2uERx_st",
- "outputId": "c77b42e1-202b-45ac-aa2c-3fdf2bcde155"
- },
- "execution_count": 2,
- "outputs": [
- {
- "output_type": "stream",
- "name": "stdout",
- "text": [
- "/content/alpaca-lora\n"
- ]
- }
- ]
- },
- {
- "cell_type": "code",
- "source": [
- "!pip install -q datasets loralib sentencepiece\n",
- "\n",
- "!pip install -q git+https://github.com/huggingface/transformers.git\n",
- "!pip install -q git+https://github.com/huggingface/peft.git"
- ],
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "JCB9UzMVwsSM",
- "outputId": "7f0688e4-f360-4da6-a4d3-0d59d4135649"
- },
- "execution_count": 5,
- "outputs": [
- {
- "output_type": "stream",
- "name": "stdout",
- "text": [
- " Installing build dependencies ... \u001b[?25l\u001b[?25hdone\n",
- " Getting requirements to build wheel ... \u001b[?25l\u001b[?25hdone\n",
- " Preparing metadata (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
- "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.3/1.3 MB\u001b[0m \u001b[31m39.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
- "\u001b[?25h Building wheel for transformers (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
- " Installing build dependencies ... \u001b[?25l\u001b[?25hdone\n",
- " Getting requirements to build wheel ... \u001b[?25l\u001b[?25hdone\n",
- " Preparing metadata (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n"
- ]
- }
- ]
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
},
- {
- "cell_type": "code",
- "source": [
- "!pip install bitsandbytes"
- ],
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "qCnXTszZxE2T",
- "outputId": "e619573c-3ac2-4ac3-bed5-caab57d00f9a"
- },
- "execution_count": 6,
- "outputs": [
- {
- "output_type": "stream",
- "name": "stdout",
- "text": [
- "Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n",
- "Collecting bitsandbytes\n",
- " Downloading bitsandbytes-0.39.0-py3-none-any.whl (92.2 MB)\n",
- "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m92.2/92.2 MB\u001b[0m \u001b[31m6.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
- "\u001b[?25hInstalling collected packages: bitsandbytes\n",
- "Successfully installed bitsandbytes-0.39.0\n"
- ]
- }
- ]
- },
- {
- "cell_type": "code",
- "source": [
- "from google.colab import drive\n",
- "drive.mount('/content/drive')"
- ],
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/"
- },
- "id": "NyxvpDjcrUvv",
- "outputId": "abe581a2-70ce-4956-b3dd-593fa4f3d8ef"
- },
- "execution_count": 8,
- "outputs": [
- {
- "output_type": "stream",
- "name": "stdout",
- "text": [
- "Mounted at /content/drive\n"
- ]
- }
- ]
+ "id": "YSW4FUQPwIYu",
+ "outputId": "421da5b9-be5e-4661-bf98-6c57fbf1f6fd"
+ },
+ "outputs": [],
+ "source": [
+ "!git clone https://github.com/tloen/alpaca-lora.git"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
},
- {
- "cell_type": "markdown",
- "source": [
- "## Data Check"
- ],
- "metadata": {
- "id": "9w0aSCzhxxQf"
- }
+ "id": "s1xm2uERx_st",
+ "outputId": "c77b42e1-202b-45ac-aa2c-3fdf2bcde155"
+ },
+ "outputs": [],
+ "source": [
+ "%cd alpaca-lora/"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
},
- {
- "cell_type": "code",
- "source": [
- "from datasets import load_dataset\n",
- "from transformers import LlamaTokenizer\n",
- "\n",
- "\n",
- "tokenizer = LlamaTokenizer.from_pretrained(\"openlm-research/open_llama_3b_600bt_preview\", add_eos_token=True)\n",
- "tokenizer.pad_token = tokenizer.eos_token\n",
- "tokenizer.pad_token_id = tokenizer.eos_token_id\n",
- "\n",
- "data = load_dataset(\"json\", data_files=\"/content/drive/MyDrive/alpaca-data.json\")\n",
- "\n",
- "\n",
- "def generate_prompt(data_point):\n",
- " # sorry about the formatting disaster gotta move fast\n",
- " if data_point[\"input\"]:\n",
- " return f\"\"\"Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.\n",
- "\n",
- "### Instruction:\n",
- "{data_point[\"instruction\"]}\n",
- "\n",
- "### Input:\n",
- "{data_point[\"input\"]}\n",
- "\n",
- "### Response:\n",
- "{data_point[\"output\"]}\"\"\"\n",
- " else:\n",
- " return f\"\"\"Below is an instruction that describes a task. Write a response that appropriately completes the request.\n",
- "\n",
- "### Instruction:\n",
- "{data_point[\"instruction\"]}\n",
- "\n",
- "### Response:\n",
- "{data_point[\"output\"]}\"\"\""
- ],
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/",
- "height": 150,
- "referenced_widgets": [
- "76eba77b0fc9499e9b4015393156153e",
- "c42123767d4849ffbcdd48f09580ea13",
- "e89f07c1f5744328b071f96a3bdc9532",
- "da36c71ba5bc469eb32bde730c5038d3",
- "6cc6b7c564fe48f086152c78f8a9a915",
- "c6a3adfa76dd4bbd8cc5e75ee28ef3e8",
- "0c65f0e913b74de88ab712d65b9027f7",
- "b07c7f3b6bc24f10821b88e254e88e43",
- "42ea2834ee074029abe8cf8f9ff79a16",
- "ec4205b0491a4f53ad1cba42689d59c4",
- "f8b9df09c8c54d53a22310e64e30772f",
- "e69b8912d3384180842ff0ead6096803",
- "550a2ef0612e4d8396462d1b1c43608d",
- "f8d82b4d016f46ca8bab1a2fe591861e",
- "975d908a1874425198e0d62ae884a3ef",
- "152aa8231b3f4b7db4e6f27bb61065b9",
- "27b48982ae244c66bccd855e7e33a00d",
- "a896cb94d1fc4641ad224c7a9ca619b1",
- "be5d02d7001a4a25a848d6b0c582b42b",
- "609437910022418e83543fe6c3d16501",
- "c3b5ef42dae64f95a2ef055db7e50fa8",
- "ee0f0aff0c254b82854d1a6f4b367161",
- "fd90085d416440579f409cdd9b29e053",
- "fdd55d56775a4641925fc88e43f946b8",
- "a54ebe30a12b4c21b67b2f8d43aea2d3",
- "6f041f053ff240cbbb52f6d117ebfcf1",
- "b7d5f8aaee0047178661e58aa59433ee",
- "563ca6cac1594ba0a7c168ee31ccc982",
- "e10e7830d1404baea72e81e0df295239",
- "acc07aa077fd49d38d74e0e10fa3991a",
- "441dfdd43ef0442894c19cad81a478db",
- "9efe7ac9ee0946388eeb85f9a4603ffe",
- "ae9996dcefcf4cfc8ea2f7488629c5ec",
- "db463b34f98c488e8282d7a59c421347",
- "2ba524e48f35421c9afc9cc81e9ce3fb",
- "1829c96471c64a03a4872e1b7a16551c",
- "f639a121fab0407595ebdf04015d9267",
- "fa5ff44ae5f64ce4bbf9b59e300b7ba3",
- "e0d701b8c09744858db4fda6011b69df",
- "7ef61952e0f2463bad3dd1a814bfb95a",
- "75263b1d19ce4cb0b95cacb6138b6fcb",
- "c3f35ce818e34b05b247fae76200c02e",
- "be8dddb19dde441da1193d5f8738413d",
- "4be8d304ddce49319488f20ab36e7f53"
- ]
- },
- "id": "OdgRTo5YxyRL",
- "outputId": "e6e64014-796b-4fa9-9635-3cb29f2dab7d"
- },
- "execution_count": 9,
- "outputs": [
- {
- "output_type": "stream",
- "name": "stdout",
- "text": [
- "Downloading and preparing dataset json/default to /root/.cache/huggingface/datasets/json/default-e726d3f1eee28f16/0.0.0/e347ab1c932092252e717ff3f949105a4dd28b27e842dd53157d2f72e276c2e4...\n"
- ]
- },
- {
- "output_type": "display_data",
- "data": {
- "text/plain": [
- "Downloading data files: 0%| | 0/1 [00:00"
- ],
- "text/html": [
- "\n",
- " \n",
- " \n",
- "
\n",
- " [ 3/119 01:48 < 3:29:02, 0.01 it/s, Epoch 0.02/1]\n",
- "
\n",
- " \n",
- " \n",
- " | Step | \n",
- " Training Loss | \n",
- "
\n",
- " \n",
- " \n",
- " \n",
- " | 1 | \n",
- " 2.421700 | \n",
- "
\n",
- " \n",
- "
"
- ]
- },
- "metadata": {}
- },
- {
- "output_type": "display_data",
- "data": {
- "text/plain": [
- "\u001b[31m╭─\u001b[0m\u001b[31m──────────────────────────────\u001b[0m\u001b[31m \u001b[0m\u001b[1;31mTraceback \u001b[0m\u001b[1;2;31m(most recent call last)\u001b[0m\u001b[31m \u001b[0m\u001b[31m───────────────────────────────\u001b[0m\u001b[31m─╮\u001b[0m\n",
- "\u001b[31m│\u001b[0m in \u001b[92m\u001b[0m:\u001b[94m27\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2;33m/usr/local/lib/python3.10/dist-packages/transformers/\u001b[0m\u001b[1;33mtrainer.py\u001b[0m:\u001b[94m1696\u001b[0m in \u001b[92mtrain\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m1693 \u001b[0m\u001b[2m│ │ \u001b[0minner_training_loop = find_executable_batch_size( \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m1694 \u001b[0m\u001b[2m│ │ │ \u001b[0m\u001b[96mself\u001b[0m._inner_training_loop, \u001b[96mself\u001b[0m._train_batch_size, args.auto_find_batch_size \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m1695 \u001b[0m\u001b[2m│ │ \u001b[0m) \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m❱ \u001b[0m1696 \u001b[2m│ │ \u001b[0m\u001b[94mreturn\u001b[0m inner_training_loop( \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m1697 \u001b[0m\u001b[2m│ │ │ \u001b[0margs=args, \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m1698 \u001b[0m\u001b[2m│ │ │ \u001b[0mresume_from_checkpoint=resume_from_checkpoint, \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m1699 \u001b[0m\u001b[2m│ │ │ \u001b[0mtrial=trial, \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2;33m/usr/local/lib/python3.10/dist-packages/transformers/\u001b[0m\u001b[1;33mtrainer.py\u001b[0m:\u001b[94m1973\u001b[0m in \u001b[92m_inner_training_loop\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m1970 \u001b[0m\u001b[2m│ │ │ │ │ \u001b[0m\u001b[94mwith\u001b[0m model.no_sync(): \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m1971 \u001b[0m\u001b[2m│ │ │ │ │ │ \u001b[0mtr_loss_step = \u001b[96mself\u001b[0m.training_step(model, inputs) \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m1972 \u001b[0m\u001b[2m│ │ │ │ \u001b[0m\u001b[94melse\u001b[0m: \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m❱ \u001b[0m1973 \u001b[2m│ │ │ │ │ \u001b[0mtr_loss_step = \u001b[96mself\u001b[0m.training_step(model, inputs) \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m1974 \u001b[0m\u001b[2m│ │ │ │ \u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m1975 \u001b[0m\u001b[2m│ │ │ │ \u001b[0m\u001b[94mif\u001b[0m ( \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m1976 \u001b[0m\u001b[2m│ │ │ │ │ \u001b[0margs.logging_nan_inf_filter \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2;33m/usr/local/lib/python3.10/dist-packages/transformers/\u001b[0m\u001b[1;33mtrainer.py\u001b[0m:\u001b[94m2787\u001b[0m in \u001b[92mtraining_step\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m2784 \u001b[0m\u001b[2m│ │ │ \u001b[0m\u001b[94mreturn\u001b[0m loss_mb.reduce_mean().detach().to(\u001b[96mself\u001b[0m.args.device) \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m2785 \u001b[0m\u001b[2m│ │ \u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m2786 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[94mwith\u001b[0m \u001b[96mself\u001b[0m.compute_loss_context_manager(): \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m❱ \u001b[0m2787 \u001b[2m│ │ │ \u001b[0mloss = \u001b[96mself\u001b[0m.compute_loss(model, inputs) \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m2788 \u001b[0m\u001b[2m│ │ \u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m2789 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[94mif\u001b[0m \u001b[96mself\u001b[0m.args.n_gpu > \u001b[94m1\u001b[0m: \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m2790 \u001b[0m\u001b[2m│ │ │ \u001b[0mloss = loss.mean() \u001b[2m# mean() to average on multi-gpu parallel training\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2;33m/usr/local/lib/python3.10/dist-packages/transformers/\u001b[0m\u001b[1;33mtrainer.py\u001b[0m:\u001b[94m2819\u001b[0m in \u001b[92mcompute_loss\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m2816 \u001b[0m\u001b[2m│ │ │ \u001b[0mlabels = inputs.pop(\u001b[33m\"\u001b[0m\u001b[33mlabels\u001b[0m\u001b[33m\"\u001b[0m) \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m2817 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[94melse\u001b[0m: \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m2818 \u001b[0m\u001b[2m│ │ │ \u001b[0mlabels = \u001b[94mNone\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m❱ \u001b[0m2819 \u001b[2m│ │ \u001b[0moutputs = model(**inputs) \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m2820 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[2m# Save past state if it exists\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m2821 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[2m# TODO: this needs to be fixed and made cleaner later.\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m2822 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[94mif\u001b[0m \u001b[96mself\u001b[0m.args.past_index >= \u001b[94m0\u001b[0m: \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2;33m/usr/local/lib/python3.10/dist-packages/torch/nn/modules/\u001b[0m\u001b[1;33mmodule.py\u001b[0m:\u001b[94m1501\u001b[0m in \u001b[92m_call_impl\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m1498 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[94mif\u001b[0m \u001b[95mnot\u001b[0m (\u001b[96mself\u001b[0m._backward_hooks \u001b[95mor\u001b[0m \u001b[96mself\u001b[0m._backward_pre_hooks \u001b[95mor\u001b[0m \u001b[96mself\u001b[0m._forward_hooks \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m1499 \u001b[0m\u001b[2m│ │ │ │ \u001b[0m\u001b[95mor\u001b[0m _global_backward_pre_hooks \u001b[95mor\u001b[0m _global_backward_hooks \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m1500 \u001b[0m\u001b[2m│ │ │ │ \u001b[0m\u001b[95mor\u001b[0m _global_forward_hooks \u001b[95mor\u001b[0m _global_forward_pre_hooks): \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m❱ \u001b[0m1501 \u001b[2m│ │ │ \u001b[0m\u001b[94mreturn\u001b[0m forward_call(*args, **kwargs) \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m1502 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[2m# Do not call functions when jit is used\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m1503 \u001b[0m\u001b[2m│ │ \u001b[0mfull_backward_hooks, non_full_backward_hooks = [], [] \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m1504 \u001b[0m\u001b[2m│ │ \u001b[0mbackward_pre_hooks = [] \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2;33m/usr/local/lib/python3.10/dist-packages/peft/\u001b[0m\u001b[1;33mpeft_model.py\u001b[0m:\u001b[94m686\u001b[0m in \u001b[92mforward\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m 683 \u001b[0m\u001b[2m│ \u001b[0m): \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m 684 \u001b[0m\u001b[2m│ │ \u001b[0mpeft_config = \u001b[96mself\u001b[0m.active_peft_config \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m 685 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[94mif\u001b[0m \u001b[95mnot\u001b[0m \u001b[96misinstance\u001b[0m(peft_config, PromptLearningConfig): \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m❱ \u001b[0m 686 \u001b[2m│ │ │ \u001b[0m\u001b[94mreturn\u001b[0m \u001b[96mself\u001b[0m.base_model( \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m 687 \u001b[0m\u001b[2m│ │ │ │ \u001b[0minput_ids=input_ids, \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m 688 \u001b[0m\u001b[2m│ │ │ │ \u001b[0mattention_mask=attention_mask, \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m 689 \u001b[0m\u001b[2m│ │ │ │ \u001b[0minputs_embeds=inputs_embeds, \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2;33m/usr/local/lib/python3.10/dist-packages/torch/nn/modules/\u001b[0m\u001b[1;33mmodule.py\u001b[0m:\u001b[94m1501\u001b[0m in \u001b[92m_call_impl\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m1498 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[94mif\u001b[0m \u001b[95mnot\u001b[0m (\u001b[96mself\u001b[0m._backward_hooks \u001b[95mor\u001b[0m \u001b[96mself\u001b[0m._backward_pre_hooks \u001b[95mor\u001b[0m \u001b[96mself\u001b[0m._forward_hooks \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m1499 \u001b[0m\u001b[2m│ │ │ │ \u001b[0m\u001b[95mor\u001b[0m _global_backward_pre_hooks \u001b[95mor\u001b[0m _global_backward_hooks \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m1500 \u001b[0m\u001b[2m│ │ │ │ \u001b[0m\u001b[95mor\u001b[0m _global_forward_hooks \u001b[95mor\u001b[0m _global_forward_pre_hooks): \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m❱ \u001b[0m1501 \u001b[2m│ │ │ \u001b[0m\u001b[94mreturn\u001b[0m forward_call(*args, **kwargs) \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m1502 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[2m# Do not call functions when jit is used\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m1503 \u001b[0m\u001b[2m│ │ \u001b[0mfull_backward_hooks, non_full_backward_hooks = [], [] \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m1504 \u001b[0m\u001b[2m│ │ \u001b[0mbackward_pre_hooks = [] \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2;33m/usr/local/lib/python3.10/dist-packages/accelerate/\u001b[0m\u001b[1;33mhooks.py\u001b[0m:\u001b[94m165\u001b[0m in \u001b[92mnew_forward\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m162 \u001b[0m\u001b[2m│ │ │ \u001b[0m\u001b[94mwith\u001b[0m torch.no_grad(): \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m163 \u001b[0m\u001b[2m│ │ │ │ \u001b[0moutput = old_forward(*args, **kwargs) \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m164 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[94melse\u001b[0m: \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m❱ \u001b[0m165 \u001b[2m│ │ │ \u001b[0moutput = old_forward(*args, **kwargs) \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m166 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[94mreturn\u001b[0m module._hf_hook.post_forward(module, output) \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m167 \u001b[0m\u001b[2m│ \u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m168 \u001b[0m\u001b[2m│ \u001b[0mmodule.forward = new_forward \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2;33m/usr/local/lib/python3.10/dist-packages/transformers/models/llama/\u001b[0m\u001b[1;33mmodeling_llama.py\u001b[0m:\u001b[94m687\u001b[0m in \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[92mforward\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m684 \u001b[0m\u001b[2m│ │ \u001b[0mreturn_dict = return_dict \u001b[94mif\u001b[0m return_dict \u001b[95mis\u001b[0m \u001b[95mnot\u001b[0m \u001b[94mNone\u001b[0m \u001b[94melse\u001b[0m \u001b[96mself\u001b[0m.config.use_return \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m685 \u001b[0m\u001b[2m│ │ \u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m686 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[2m# decoder outputs consists of (dec_features, layer_state, dec_hidden, dec_attn)\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m❱ \u001b[0m687 \u001b[2m│ │ \u001b[0moutputs = \u001b[96mself\u001b[0m.model( \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m688 \u001b[0m\u001b[2m│ │ │ \u001b[0minput_ids=input_ids, \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m689 \u001b[0m\u001b[2m│ │ │ \u001b[0mattention_mask=attention_mask, \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m690 \u001b[0m\u001b[2m│ │ │ \u001b[0mposition_ids=position_ids, \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2;33m/usr/local/lib/python3.10/dist-packages/torch/nn/modules/\u001b[0m\u001b[1;33mmodule.py\u001b[0m:\u001b[94m1501\u001b[0m in \u001b[92m_call_impl\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m1498 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[94mif\u001b[0m \u001b[95mnot\u001b[0m (\u001b[96mself\u001b[0m._backward_hooks \u001b[95mor\u001b[0m \u001b[96mself\u001b[0m._backward_pre_hooks \u001b[95mor\u001b[0m \u001b[96mself\u001b[0m._forward_hooks \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m1499 \u001b[0m\u001b[2m│ │ │ │ \u001b[0m\u001b[95mor\u001b[0m _global_backward_pre_hooks \u001b[95mor\u001b[0m _global_backward_hooks \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m1500 \u001b[0m\u001b[2m│ │ │ │ \u001b[0m\u001b[95mor\u001b[0m _global_forward_hooks \u001b[95mor\u001b[0m _global_forward_pre_hooks): \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m❱ \u001b[0m1501 \u001b[2m│ │ │ \u001b[0m\u001b[94mreturn\u001b[0m forward_call(*args, **kwargs) \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m1502 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[2m# Do not call functions when jit is used\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m1503 \u001b[0m\u001b[2m│ │ \u001b[0mfull_backward_hooks, non_full_backward_hooks = [], [] \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m1504 \u001b[0m\u001b[2m│ │ \u001b[0mbackward_pre_hooks = [] \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2;33m/usr/local/lib/python3.10/dist-packages/accelerate/\u001b[0m\u001b[1;33mhooks.py\u001b[0m:\u001b[94m165\u001b[0m in \u001b[92mnew_forward\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m162 \u001b[0m\u001b[2m│ │ │ \u001b[0m\u001b[94mwith\u001b[0m torch.no_grad(): \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m163 \u001b[0m\u001b[2m│ │ │ │ \u001b[0moutput = old_forward(*args, **kwargs) \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m164 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[94melse\u001b[0m: \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m❱ \u001b[0m165 \u001b[2m│ │ │ \u001b[0moutput = old_forward(*args, **kwargs) \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m166 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[94mreturn\u001b[0m module._hf_hook.post_forward(module, output) \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m167 \u001b[0m\u001b[2m│ \u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m168 \u001b[0m\u001b[2m│ \u001b[0mmodule.forward = new_forward \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2;33m/usr/local/lib/python3.10/dist-packages/transformers/models/llama/\u001b[0m\u001b[1;33mmodeling_llama.py\u001b[0m:\u001b[94m569\u001b[0m in \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[92mforward\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m566 \u001b[0m\u001b[2m│ │ │ │ │ \u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m567 \u001b[0m\u001b[2m│ │ │ │ │ \u001b[0m\u001b[94mreturn\u001b[0m custom_forward \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m568 \u001b[0m\u001b[2m│ │ │ │ \u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m❱ \u001b[0m569 \u001b[2m│ │ │ │ \u001b[0mlayer_outputs = torch.utils.checkpoint.checkpoint( \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m570 \u001b[0m\u001b[2m│ │ │ │ │ \u001b[0mcreate_custom_forward(decoder_layer), \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m571 \u001b[0m\u001b[2m│ │ │ │ │ \u001b[0mhidden_states, \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m572 \u001b[0m\u001b[2m│ │ │ │ │ \u001b[0mattention_mask, \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2;33m/usr/local/lib/python3.10/dist-packages/torch/utils/\u001b[0m\u001b[1;33mcheckpoint.py\u001b[0m:\u001b[94m249\u001b[0m in \u001b[92mcheckpoint\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m246 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[94mraise\u001b[0m \u001b[96mValueError\u001b[0m(\u001b[33m\"\u001b[0m\u001b[33mUnexpected keyword arguments: \u001b[0m\u001b[33m\"\u001b[0m + \u001b[33m\"\u001b[0m\u001b[33m,\u001b[0m\u001b[33m\"\u001b[0m.join(arg \u001b[94mfor\u001b[0m arg \u001b[95min\u001b[0m kwar \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m247 \u001b[0m\u001b[2m│ \u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m248 \u001b[0m\u001b[2m│ \u001b[0m\u001b[94mif\u001b[0m use_reentrant: \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m❱ \u001b[0m249 \u001b[2m│ │ \u001b[0m\u001b[94mreturn\u001b[0m CheckpointFunction.apply(function, preserve, *args) \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m250 \u001b[0m\u001b[2m│ \u001b[0m\u001b[94melse\u001b[0m: \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m251 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[94mreturn\u001b[0m _checkpoint_without_reentrant( \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m252 \u001b[0m\u001b[2m│ │ │ \u001b[0mfunction, \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2;33m/usr/local/lib/python3.10/dist-packages/torch/autograd/\u001b[0m\u001b[1;33mfunction.py\u001b[0m:\u001b[94m506\u001b[0m in \u001b[92mapply\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m503 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[94mif\u001b[0m \u001b[95mnot\u001b[0m torch._C._are_functorch_transforms_active(): \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m504 \u001b[0m\u001b[2m│ │ │ \u001b[0m\u001b[2m# See NOTE: [functorch vjp and autograd interaction]\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m505 \u001b[0m\u001b[2m│ │ │ \u001b[0margs = _functorch.utils.unwrap_dead_wrappers(args) \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m❱ \u001b[0m506 \u001b[2m│ │ │ \u001b[0m\u001b[94mreturn\u001b[0m \u001b[96msuper\u001b[0m().apply(*args, **kwargs) \u001b[2m# type: ignore[misc]\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m507 \u001b[0m\u001b[2m│ │ \u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m508 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[94mif\u001b[0m \u001b[96mcls\u001b[0m.setup_context == _SingleLevelFunction.setup_context: \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m509 \u001b[0m\u001b[2m│ │ │ \u001b[0m\u001b[94mraise\u001b[0m \u001b[96mRuntimeError\u001b[0m( \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2;33m/usr/local/lib/python3.10/dist-packages/torch/utils/\u001b[0m\u001b[1;33mcheckpoint.py\u001b[0m:\u001b[94m107\u001b[0m in \u001b[92mforward\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m104 \u001b[0m\u001b[2m│ │ \u001b[0mctx.save_for_backward(*tensor_inputs) \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m105 \u001b[0m\u001b[2m│ │ \u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m106 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[94mwith\u001b[0m torch.no_grad(): \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m❱ \u001b[0m107 \u001b[2m│ │ │ \u001b[0moutputs = run_function(*args) \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m108 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[94mreturn\u001b[0m outputs \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m109 \u001b[0m\u001b[2m│ \u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m110 \u001b[0m\u001b[2m│ \u001b[0m\u001b[1;95m@staticmethod\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2;33m/usr/local/lib/python3.10/dist-packages/transformers/models/llama/\u001b[0m\u001b[1;33mmodeling_llama.py\u001b[0m:\u001b[94m565\u001b[0m in \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[92mcustom_forward\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m562 \u001b[0m\u001b[2m│ │ │ │ \u001b[0m\u001b[94mdef\u001b[0m \u001b[92mcreate_custom_forward\u001b[0m(module): \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m563 \u001b[0m\u001b[2m│ │ │ │ │ \u001b[0m\u001b[94mdef\u001b[0m \u001b[92mcustom_forward\u001b[0m(*inputs): \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m564 \u001b[0m\u001b[2m│ │ │ │ │ │ \u001b[0m\u001b[2m# None for past_key_value\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m❱ \u001b[0m565 \u001b[2m│ │ │ │ │ │ \u001b[0m\u001b[94mreturn\u001b[0m module(*inputs, output_attentions, \u001b[94mNone\u001b[0m) \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m566 \u001b[0m\u001b[2m│ │ │ │ │ \u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m567 \u001b[0m\u001b[2m│ │ │ │ │ \u001b[0m\u001b[94mreturn\u001b[0m custom_forward \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m568 \u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2;33m/usr/local/lib/python3.10/dist-packages/torch/nn/modules/\u001b[0m\u001b[1;33mmodule.py\u001b[0m:\u001b[94m1501\u001b[0m in \u001b[92m_call_impl\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m1498 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[94mif\u001b[0m \u001b[95mnot\u001b[0m (\u001b[96mself\u001b[0m._backward_hooks \u001b[95mor\u001b[0m \u001b[96mself\u001b[0m._backward_pre_hooks \u001b[95mor\u001b[0m \u001b[96mself\u001b[0m._forward_hooks \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m1499 \u001b[0m\u001b[2m│ │ │ │ \u001b[0m\u001b[95mor\u001b[0m _global_backward_pre_hooks \u001b[95mor\u001b[0m _global_backward_hooks \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m1500 \u001b[0m\u001b[2m│ │ │ │ \u001b[0m\u001b[95mor\u001b[0m _global_forward_hooks \u001b[95mor\u001b[0m _global_forward_pre_hooks): \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m❱ \u001b[0m1501 \u001b[2m│ │ │ \u001b[0m\u001b[94mreturn\u001b[0m forward_call(*args, **kwargs) \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m1502 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[2m# Do not call functions when jit is used\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m1503 \u001b[0m\u001b[2m│ │ \u001b[0mfull_backward_hooks, non_full_backward_hooks = [], [] \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m1504 \u001b[0m\u001b[2m│ │ \u001b[0mbackward_pre_hooks = [] \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2;33m/usr/local/lib/python3.10/dist-packages/accelerate/\u001b[0m\u001b[1;33mhooks.py\u001b[0m:\u001b[94m165\u001b[0m in \u001b[92mnew_forward\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m162 \u001b[0m\u001b[2m│ │ │ \u001b[0m\u001b[94mwith\u001b[0m torch.no_grad(): \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m163 \u001b[0m\u001b[2m│ │ │ │ \u001b[0moutput = old_forward(*args, **kwargs) \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m164 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[94melse\u001b[0m: \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m❱ \u001b[0m165 \u001b[2m│ │ │ \u001b[0moutput = old_forward(*args, **kwargs) \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m166 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[94mreturn\u001b[0m module._hf_hook.post_forward(module, output) \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m167 \u001b[0m\u001b[2m│ \u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m168 \u001b[0m\u001b[2m│ \u001b[0mmodule.forward = new_forward \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2;33m/usr/local/lib/python3.10/dist-packages/transformers/models/llama/\u001b[0m\u001b[1;33mmodeling_llama.py\u001b[0m:\u001b[94m292\u001b[0m in \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[92mforward\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m289 \u001b[0m\u001b[2m│ │ \u001b[0mhidden_states = \u001b[96mself\u001b[0m.input_layernorm(hidden_states) \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m290 \u001b[0m\u001b[2m│ │ \u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m291 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[2m# Self Attention\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m❱ \u001b[0m292 \u001b[2m│ │ \u001b[0mhidden_states, self_attn_weights, present_key_value = \u001b[96mself\u001b[0m.self_attn( \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m293 \u001b[0m\u001b[2m│ │ │ \u001b[0mhidden_states=hidden_states, \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m294 \u001b[0m\u001b[2m│ │ │ \u001b[0mattention_mask=attention_mask, \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m295 \u001b[0m\u001b[2m│ │ │ \u001b[0mposition_ids=position_ids, \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2;33m/usr/local/lib/python3.10/dist-packages/torch/nn/modules/\u001b[0m\u001b[1;33mmodule.py\u001b[0m:\u001b[94m1501\u001b[0m in \u001b[92m_call_impl\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m1498 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[94mif\u001b[0m \u001b[95mnot\u001b[0m (\u001b[96mself\u001b[0m._backward_hooks \u001b[95mor\u001b[0m \u001b[96mself\u001b[0m._backward_pre_hooks \u001b[95mor\u001b[0m \u001b[96mself\u001b[0m._forward_hooks \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m1499 \u001b[0m\u001b[2m│ │ │ │ \u001b[0m\u001b[95mor\u001b[0m _global_backward_pre_hooks \u001b[95mor\u001b[0m _global_backward_hooks \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m1500 \u001b[0m\u001b[2m│ │ │ │ \u001b[0m\u001b[95mor\u001b[0m _global_forward_hooks \u001b[95mor\u001b[0m _global_forward_pre_hooks): \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m❱ \u001b[0m1501 \u001b[2m│ │ │ \u001b[0m\u001b[94mreturn\u001b[0m forward_call(*args, **kwargs) \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m1502 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[2m# Do not call functions when jit is used\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m1503 \u001b[0m\u001b[2m│ │ \u001b[0mfull_backward_hooks, non_full_backward_hooks = [], [] \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m1504 \u001b[0m\u001b[2m│ │ \u001b[0mbackward_pre_hooks = [] \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2;33m/usr/local/lib/python3.10/dist-packages/accelerate/\u001b[0m\u001b[1;33mhooks.py\u001b[0m:\u001b[94m165\u001b[0m in \u001b[92mnew_forward\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m162 \u001b[0m\u001b[2m│ │ │ \u001b[0m\u001b[94mwith\u001b[0m torch.no_grad(): \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m163 \u001b[0m\u001b[2m│ │ │ │ \u001b[0moutput = old_forward(*args, **kwargs) \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m164 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[94melse\u001b[0m: \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m❱ \u001b[0m165 \u001b[2m│ │ │ \u001b[0moutput = old_forward(*args, **kwargs) \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m166 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[94mreturn\u001b[0m module._hf_hook.post_forward(module, output) \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m167 \u001b[0m\u001b[2m│ \u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m168 \u001b[0m\u001b[2m│ \u001b[0mmodule.forward = new_forward \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2;33m/usr/local/lib/python3.10/dist-packages/transformers/models/llama/\u001b[0m\u001b[1;33mmodeling_llama.py\u001b[0m:\u001b[94m194\u001b[0m in \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[92mforward\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m191 \u001b[0m\u001b[2m│ \u001b[0m) -> Tuple[torch.Tensor, Optional[torch.Tensor], Optional[Tuple[torch.Tensor]]]: \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m192 \u001b[0m\u001b[2m│ │ \u001b[0mbsz, q_len, _ = hidden_states.size() \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m193 \u001b[0m\u001b[2m│ │ \u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m❱ \u001b[0m194 \u001b[2m│ │ \u001b[0mquery_states = \u001b[96mself\u001b[0m.q_proj(hidden_states).view(bsz, q_len, \u001b[96mself\u001b[0m.num_heads, \u001b[96mself\u001b[0m. \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m195 \u001b[0m\u001b[2m│ │ \u001b[0mkey_states = \u001b[96mself\u001b[0m.k_proj(hidden_states).view(bsz, q_len, \u001b[96mself\u001b[0m.num_heads, \u001b[96mself\u001b[0m.he \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m196 \u001b[0m\u001b[2m│ │ \u001b[0mvalue_states = \u001b[96mself\u001b[0m.v_proj(hidden_states).view(bsz, q_len, \u001b[96mself\u001b[0m.num_heads, \u001b[96mself\u001b[0m. \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m197 \u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2;33m/usr/local/lib/python3.10/dist-packages/torch/nn/modules/\u001b[0m\u001b[1;33mmodule.py\u001b[0m:\u001b[94m1501\u001b[0m in \u001b[92m_call_impl\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m1498 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[94mif\u001b[0m \u001b[95mnot\u001b[0m (\u001b[96mself\u001b[0m._backward_hooks \u001b[95mor\u001b[0m \u001b[96mself\u001b[0m._backward_pre_hooks \u001b[95mor\u001b[0m \u001b[96mself\u001b[0m._forward_hooks \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m1499 \u001b[0m\u001b[2m│ │ │ │ \u001b[0m\u001b[95mor\u001b[0m _global_backward_pre_hooks \u001b[95mor\u001b[0m _global_backward_hooks \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m1500 \u001b[0m\u001b[2m│ │ │ │ \u001b[0m\u001b[95mor\u001b[0m _global_forward_hooks \u001b[95mor\u001b[0m _global_forward_pre_hooks): \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m❱ \u001b[0m1501 \u001b[2m│ │ │ \u001b[0m\u001b[94mreturn\u001b[0m forward_call(*args, **kwargs) \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m1502 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[2m# Do not call functions when jit is used\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m1503 \u001b[0m\u001b[2m│ │ \u001b[0mfull_backward_hooks, non_full_backward_hooks = [], [] \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m1504 \u001b[0m\u001b[2m│ │ \u001b[0mbackward_pre_hooks = [] \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2;33m/usr/local/lib/python3.10/dist-packages/peft/tuners/\u001b[0m\u001b[1;33mlora.py\u001b[0m:\u001b[94m709\u001b[0m in \u001b[92mforward\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m706 \u001b[0m\u001b[2m│ │ │ \u001b[0m\u001b[96mself\u001b[0m.active_adapter = adapter_name \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m707 \u001b[0m\u001b[2m│ │ \u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m708 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[94mdef\u001b[0m \u001b[92mforward\u001b[0m(\u001b[96mself\u001b[0m, x: torch.Tensor): \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m❱ \u001b[0m709 \u001b[2m│ │ │ \u001b[0mresult = \u001b[96msuper\u001b[0m().forward(x) \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m710 \u001b[0m\u001b[2m│ │ │ \u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m711 \u001b[0m\u001b[2m│ │ │ \u001b[0m\u001b[94mif\u001b[0m \u001b[96mself\u001b[0m.disable_adapters \u001b[95mor\u001b[0m \u001b[96mself\u001b[0m.active_adapter \u001b[95mnot\u001b[0m \u001b[95min\u001b[0m \u001b[96mself\u001b[0m.lora_A.keys(): \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m712 \u001b[0m\u001b[2m│ │ │ │ \u001b[0m\u001b[94mreturn\u001b[0m result \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2;33m/usr/local/lib/python3.10/dist-packages/bitsandbytes/nn/\u001b[0m\u001b[1;33mmodules.py\u001b[0m:\u001b[94m388\u001b[0m in \u001b[92mforward\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m385 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[94mif\u001b[0m \u001b[96mself\u001b[0m.bias \u001b[95mis\u001b[0m \u001b[95mnot\u001b[0m \u001b[94mNone\u001b[0m \u001b[95mand\u001b[0m \u001b[96mself\u001b[0m.bias.dtype != x.dtype: \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m386 \u001b[0m\u001b[2m│ │ │ \u001b[0m\u001b[96mself\u001b[0m.bias.data = \u001b[96mself\u001b[0m.bias.data.to(x.dtype) \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m387 \u001b[0m\u001b[2m│ │ \u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m❱ \u001b[0m388 \u001b[2m│ │ \u001b[0mout = bnb.matmul(x, \u001b[96mself\u001b[0m.weight, bias=\u001b[96mself\u001b[0m.bias, state=\u001b[96mself\u001b[0m.state) \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m389 \u001b[0m\u001b[2m│ │ \u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m390 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[94mif\u001b[0m \u001b[95mnot\u001b[0m \u001b[96mself\u001b[0m.state.has_fp16_weights: \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m391 \u001b[0m\u001b[2m│ │ │ \u001b[0m\u001b[94mif\u001b[0m \u001b[96mself\u001b[0m.state.CB \u001b[95mis\u001b[0m \u001b[95mnot\u001b[0m \u001b[94mNone\u001b[0m \u001b[95mand\u001b[0m \u001b[96mself\u001b[0m.state.CxB \u001b[95mis\u001b[0m \u001b[95mnot\u001b[0m \u001b[94mNone\u001b[0m: \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2;33m/usr/local/lib/python3.10/dist-packages/bitsandbytes/autograd/\u001b[0m\u001b[1;33m_functions.py\u001b[0m:\u001b[94m559\u001b[0m in \u001b[92mmatmul\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m556 \u001b[0m\u001b[2m│ \u001b[0mstate = state \u001b[95mor\u001b[0m MatmulLtState() \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m557 \u001b[0m\u001b[2m│ \u001b[0m\u001b[94mif\u001b[0m threshold > \u001b[94m0.0\u001b[0m: \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m558 \u001b[0m\u001b[2m│ │ \u001b[0mstate.threshold = threshold \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m❱ \u001b[0m559 \u001b[2m│ \u001b[0m\u001b[94mreturn\u001b[0m MatMul8bitLt.apply(A, B, out, bias, state) \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m560 \u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m561 \u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m562 \u001b[0m\u001b[94mdef\u001b[0m \u001b[92mmatmul_4bit\u001b[0m(A: tensor, B: tensor, quant_state: List, out: tensor = \u001b[94mNone\u001b[0m, bias=\u001b[94mNone\u001b[0m): \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2;33m/usr/local/lib/python3.10/dist-packages/torch/autograd/\u001b[0m\u001b[1;33mfunction.py\u001b[0m:\u001b[94m506\u001b[0m in \u001b[92mapply\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m503 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[94mif\u001b[0m \u001b[95mnot\u001b[0m torch._C._are_functorch_transforms_active(): \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m504 \u001b[0m\u001b[2m│ │ │ \u001b[0m\u001b[2m# See NOTE: [functorch vjp and autograd interaction]\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m505 \u001b[0m\u001b[2m│ │ │ \u001b[0margs = _functorch.utils.unwrap_dead_wrappers(args) \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m❱ \u001b[0m506 \u001b[2m│ │ │ \u001b[0m\u001b[94mreturn\u001b[0m \u001b[96msuper\u001b[0m().apply(*args, **kwargs) \u001b[2m# type: ignore[misc]\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m507 \u001b[0m\u001b[2m│ │ \u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m508 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[94mif\u001b[0m \u001b[96mcls\u001b[0m.setup_context == _SingleLevelFunction.setup_context: \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m509 \u001b[0m\u001b[2m│ │ │ \u001b[0m\u001b[94mraise\u001b[0m \u001b[96mRuntimeError\u001b[0m( \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2;33m/usr/local/lib/python3.10/dist-packages/bitsandbytes/autograd/\u001b[0m\u001b[1;33m_functions.py\u001b[0m:\u001b[94m323\u001b[0m in \u001b[92mforward\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m320 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[2m# 1. Quantize A\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m321 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[94mif\u001b[0m \u001b[96mlen\u001b[0m(A.shape) == \u001b[94m3\u001b[0m: \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m322 \u001b[0m\u001b[2m│ │ │ \u001b[0mA = A.view(-\u001b[94m1\u001b[0m, A.shape[-\u001b[94m1\u001b[0m]).contiguous() \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m❱ \u001b[0m323 \u001b[2m│ │ \u001b[0mCA, CAt, SCA, SCAt, coo_tensorA = F.double_quant(A.to(torch.float16), threshold= \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m324 \u001b[0m\u001b[2m│ │ \u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m325 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[94mif\u001b[0m state.threshold > \u001b[94m0.0\u001b[0m \u001b[95mand\u001b[0m coo_tensorA \u001b[95mis\u001b[0m \u001b[95mnot\u001b[0m \u001b[94mNone\u001b[0m: \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m326 \u001b[0m\u001b[2m│ │ │ \u001b[0m\u001b[94mif\u001b[0m state.has_fp16_weights: \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2;33m/usr/local/lib/python3.10/dist-packages/bitsandbytes/\u001b[0m\u001b[1;33mfunctional.py\u001b[0m:\u001b[94m2029\u001b[0m in \u001b[92mdouble_quant\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m2026 \u001b[0m\u001b[2m│ │ │ │ \u001b[0mct.c_int32(rows), \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m2027 \u001b[0m\u001b[2m│ │ │ │ \u001b[0mct.c_int32(cols), \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m2028 \u001b[0m\u001b[2m│ │ │ \u001b[0m) \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m❱ \u001b[0m2029 \u001b[2m│ │ │ \u001b[0mval, idx = torch.sort(coo_tensor.rowidx) \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m2030 \u001b[0m\u001b[2m│ │ │ \u001b[0mcoo_tensor.rowidx = val \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m2031 \u001b[0m\u001b[2m│ │ │ \u001b[0mcoo_tensor.colidx = coo_tensor.colidx[idx] \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m2032 \u001b[0m\u001b[2m│ │ │ \u001b[0mcoo_tensor.values = coo_tensor.values[idx] \u001b[31m│\u001b[0m\n",
- "\u001b[31m╰──────────────────────────────────────────────────────────────────────────────────────────────────╯\u001b[0m\n",
- "\u001b[1;91mKeyboardInterrupt\u001b[0m\n"
- ],
- "text/html": [
- "╭─────────────────────────────── Traceback (most recent call last) ────────────────────────────────╮\n",
- "│ in <cell line: 27>:27 │\n",
- "│ │\n",
- "│ /usr/local/lib/python3.10/dist-packages/transformers/trainer.py:1696 in train │\n",
- "│ │\n",
- "│ 1693 │ │ inner_training_loop = find_executable_batch_size( │\n",
- "│ 1694 │ │ │ self._inner_training_loop, self._train_batch_size, args.auto_find_batch_size │\n",
- "│ 1695 │ │ ) │\n",
- "│ ❱ 1696 │ │ return inner_training_loop( │\n",
- "│ 1697 │ │ │ args=args, │\n",
- "│ 1698 │ │ │ resume_from_checkpoint=resume_from_checkpoint, │\n",
- "│ 1699 │ │ │ trial=trial, │\n",
- "│ │\n",
- "│ /usr/local/lib/python3.10/dist-packages/transformers/trainer.py:1973 in _inner_training_loop │\n",
- "│ │\n",
- "│ 1970 │ │ │ │ │ with model.no_sync(): │\n",
- "│ 1971 │ │ │ │ │ │ tr_loss_step = self.training_step(model, inputs) │\n",
- "│ 1972 │ │ │ │ else: │\n",
- "│ ❱ 1973 │ │ │ │ │ tr_loss_step = self.training_step(model, inputs) │\n",
- "│ 1974 │ │ │ │ │\n",
- "│ 1975 │ │ │ │ if ( │\n",
- "│ 1976 │ │ │ │ │ args.logging_nan_inf_filter │\n",
- "│ │\n",
- "│ /usr/local/lib/python3.10/dist-packages/transformers/trainer.py:2787 in training_step │\n",
- "│ │\n",
- "│ 2784 │ │ │ return loss_mb.reduce_mean().detach().to(self.args.device) │\n",
- "│ 2785 │ │ │\n",
- "│ 2786 │ │ with self.compute_loss_context_manager(): │\n",
- "│ ❱ 2787 │ │ │ loss = self.compute_loss(model, inputs) │\n",
- "│ 2788 │ │ │\n",
- "│ 2789 │ │ if self.args.n_gpu > 1: │\n",
- "│ 2790 │ │ │ loss = loss.mean() # mean() to average on multi-gpu parallel training │\n",
- "│ │\n",
- "│ /usr/local/lib/python3.10/dist-packages/transformers/trainer.py:2819 in compute_loss │\n",
- "│ │\n",
- "│ 2816 │ │ │ labels = inputs.pop(\"labels\") │\n",
- "│ 2817 │ │ else: │\n",
- "│ 2818 │ │ │ labels = None │\n",
- "│ ❱ 2819 │ │ outputs = model(**inputs) │\n",
- "│ 2820 │ │ # Save past state if it exists │\n",
- "│ 2821 │ │ # TODO: this needs to be fixed and made cleaner later. │\n",
- "│ 2822 │ │ if self.args.past_index >= 0: │\n",
- "│ │\n",
- "│ /usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py:1501 in _call_impl │\n",
- "│ │\n",
- "│ 1498 │ │ if not (self._backward_hooks or self._backward_pre_hooks or self._forward_hooks │\n",
- "│ 1499 │ │ │ │ or _global_backward_pre_hooks or _global_backward_hooks │\n",
- "│ 1500 │ │ │ │ or _global_forward_hooks or _global_forward_pre_hooks): │\n",
- "│ ❱ 1501 │ │ │ return forward_call(*args, **kwargs) │\n",
- "│ 1502 │ │ # Do not call functions when jit is used │\n",
- "│ 1503 │ │ full_backward_hooks, non_full_backward_hooks = [], [] │\n",
- "│ 1504 │ │ backward_pre_hooks = [] │\n",
- "│ │\n",
- "│ /usr/local/lib/python3.10/dist-packages/peft/peft_model.py:686 in forward │\n",
- "│ │\n",
- "│ 683 │ ): │\n",
- "│ 684 │ │ peft_config = self.active_peft_config │\n",
- "│ 685 │ │ if not isinstance(peft_config, PromptLearningConfig): │\n",
- "│ ❱ 686 │ │ │ return self.base_model( │\n",
- "│ 687 │ │ │ │ input_ids=input_ids, │\n",
- "│ 688 │ │ │ │ attention_mask=attention_mask, │\n",
- "│ 689 │ │ │ │ inputs_embeds=inputs_embeds, │\n",
- "│ │\n",
- "│ /usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py:1501 in _call_impl │\n",
- "│ │\n",
- "│ 1498 │ │ if not (self._backward_hooks or self._backward_pre_hooks or self._forward_hooks │\n",
- "│ 1499 │ │ │ │ or _global_backward_pre_hooks or _global_backward_hooks │\n",
- "│ 1500 │ │ │ │ or _global_forward_hooks or _global_forward_pre_hooks): │\n",
- "│ ❱ 1501 │ │ │ return forward_call(*args, **kwargs) │\n",
- "│ 1502 │ │ # Do not call functions when jit is used │\n",
- "│ 1503 │ │ full_backward_hooks, non_full_backward_hooks = [], [] │\n",
- "│ 1504 │ │ backward_pre_hooks = [] │\n",
- "│ │\n",
- "│ /usr/local/lib/python3.10/dist-packages/accelerate/hooks.py:165 in new_forward │\n",
- "│ │\n",
- "│ 162 │ │ │ with torch.no_grad(): │\n",
- "│ 163 │ │ │ │ output = old_forward(*args, **kwargs) │\n",
- "│ 164 │ │ else: │\n",
- "│ ❱ 165 │ │ │ output = old_forward(*args, **kwargs) │\n",
- "│ 166 │ │ return module._hf_hook.post_forward(module, output) │\n",
- "│ 167 │ │\n",
- "│ 168 │ module.forward = new_forward │\n",
- "│ │\n",
- "│ /usr/local/lib/python3.10/dist-packages/transformers/models/llama/modeling_llama.py:687 in │\n",
- "│ forward │\n",
- "│ │\n",
- "│ 684 │ │ return_dict = return_dict if return_dict is not None else self.config.use_return │\n",
- "│ 685 │ │ │\n",
- "│ 686 │ │ # decoder outputs consists of (dec_features, layer_state, dec_hidden, dec_attn) │\n",
- "│ ❱ 687 │ │ outputs = self.model( │\n",
- "│ 688 │ │ │ input_ids=input_ids, │\n",
- "│ 689 │ │ │ attention_mask=attention_mask, │\n",
- "│ 690 │ │ │ position_ids=position_ids, │\n",
- "│ │\n",
- "│ /usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py:1501 in _call_impl │\n",
- "│ │\n",
- "│ 1498 │ │ if not (self._backward_hooks or self._backward_pre_hooks or self._forward_hooks │\n",
- "│ 1499 │ │ │ │ or _global_backward_pre_hooks or _global_backward_hooks │\n",
- "│ 1500 │ │ │ │ or _global_forward_hooks or _global_forward_pre_hooks): │\n",
- "│ ❱ 1501 │ │ │ return forward_call(*args, **kwargs) │\n",
- "│ 1502 │ │ # Do not call functions when jit is used │\n",
- "│ 1503 │ │ full_backward_hooks, non_full_backward_hooks = [], [] │\n",
- "│ 1504 │ │ backward_pre_hooks = [] │\n",
- "│ │\n",
- "│ /usr/local/lib/python3.10/dist-packages/accelerate/hooks.py:165 in new_forward │\n",
- "│ │\n",
- "│ 162 │ │ │ with torch.no_grad(): │\n",
- "│ 163 │ │ │ │ output = old_forward(*args, **kwargs) │\n",
- "│ 164 │ │ else: │\n",
- "│ ❱ 165 │ │ │ output = old_forward(*args, **kwargs) │\n",
- "│ 166 │ │ return module._hf_hook.post_forward(module, output) │\n",
- "│ 167 │ │\n",
- "│ 168 │ module.forward = new_forward │\n",
- "│ │\n",
- "│ /usr/local/lib/python3.10/dist-packages/transformers/models/llama/modeling_llama.py:569 in │\n",
- "│ forward │\n",
- "│ │\n",
- "│ 566 │ │ │ │ │ │\n",
- "│ 567 │ │ │ │ │ return custom_forward │\n",
- "│ 568 │ │ │ │ │\n",
- "│ ❱ 569 │ │ │ │ layer_outputs = torch.utils.checkpoint.checkpoint( │\n",
- "│ 570 │ │ │ │ │ create_custom_forward(decoder_layer), │\n",
- "│ 571 │ │ │ │ │ hidden_states, │\n",
- "│ 572 │ │ │ │ │ attention_mask, │\n",
- "│ │\n",
- "│ /usr/local/lib/python3.10/dist-packages/torch/utils/checkpoint.py:249 in checkpoint │\n",
- "│ │\n",
- "│ 246 │ │ raise ValueError(\"Unexpected keyword arguments: \" + \",\".join(arg for arg in kwar │\n",
- "│ 247 │ │\n",
- "│ 248 │ if use_reentrant: │\n",
- "│ ❱ 249 │ │ return CheckpointFunction.apply(function, preserve, *args) │\n",
- "│ 250 │ else: │\n",
- "│ 251 │ │ return _checkpoint_without_reentrant( │\n",
- "│ 252 │ │ │ function, │\n",
- "│ │\n",
- "│ /usr/local/lib/python3.10/dist-packages/torch/autograd/function.py:506 in apply │\n",
- "│ │\n",
- "│ 503 │ │ if not torch._C._are_functorch_transforms_active(): │\n",
- "│ 504 │ │ │ # See NOTE: [functorch vjp and autograd interaction] │\n",
- "│ 505 │ │ │ args = _functorch.utils.unwrap_dead_wrappers(args) │\n",
- "│ ❱ 506 │ │ │ return super().apply(*args, **kwargs) # type: ignore[misc] │\n",
- "│ 507 │ │ │\n",
- "│ 508 │ │ if cls.setup_context == _SingleLevelFunction.setup_context: │\n",
- "│ 509 │ │ │ raise RuntimeError( │\n",
- "│ │\n",
- "│ /usr/local/lib/python3.10/dist-packages/torch/utils/checkpoint.py:107 in forward │\n",
- "│ │\n",
- "│ 104 │ │ ctx.save_for_backward(*tensor_inputs) │\n",
- "│ 105 │ │ │\n",
- "│ 106 │ │ with torch.no_grad(): │\n",
- "│ ❱ 107 │ │ │ outputs = run_function(*args) │\n",
- "│ 108 │ │ return outputs │\n",
- "│ 109 │ │\n",
- "│ 110 │ @staticmethod │\n",
- "│ │\n",
- "│ /usr/local/lib/python3.10/dist-packages/transformers/models/llama/modeling_llama.py:565 in │\n",
- "│ custom_forward │\n",
- "│ │\n",
- "│ 562 │ │ │ │ def create_custom_forward(module): │\n",
- "│ 563 │ │ │ │ │ def custom_forward(*inputs): │\n",
- "│ 564 │ │ │ │ │ │ # None for past_key_value │\n",
- "│ ❱ 565 │ │ │ │ │ │ return module(*inputs, output_attentions, None) │\n",
- "│ 566 │ │ │ │ │ │\n",
- "│ 567 │ │ │ │ │ return custom_forward │\n",
- "│ 568 │\n",
- "│ │\n",
- "│ /usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py:1501 in _call_impl │\n",
- "│ │\n",
- "│ 1498 │ │ if not (self._backward_hooks or self._backward_pre_hooks or self._forward_hooks │\n",
- "│ 1499 │ │ │ │ or _global_backward_pre_hooks or _global_backward_hooks │\n",
- "│ 1500 │ │ │ │ or _global_forward_hooks or _global_forward_pre_hooks): │\n",
- "│ ❱ 1501 │ │ │ return forward_call(*args, **kwargs) │\n",
- "│ 1502 │ │ # Do not call functions when jit is used │\n",
- "│ 1503 │ │ full_backward_hooks, non_full_backward_hooks = [], [] │\n",
- "│ 1504 │ │ backward_pre_hooks = [] │\n",
- "│ │\n",
- "│ /usr/local/lib/python3.10/dist-packages/accelerate/hooks.py:165 in new_forward │\n",
- "│ │\n",
- "│ 162 │ │ │ with torch.no_grad(): │\n",
- "│ 163 │ │ │ │ output = old_forward(*args, **kwargs) │\n",
- "│ 164 │ │ else: │\n",
- "│ ❱ 165 │ │ │ output = old_forward(*args, **kwargs) │\n",
- "│ 166 │ │ return module._hf_hook.post_forward(module, output) │\n",
- "│ 167 │ │\n",
- "│ 168 │ module.forward = new_forward │\n",
- "│ │\n",
- "│ /usr/local/lib/python3.10/dist-packages/transformers/models/llama/modeling_llama.py:292 in │\n",
- "│ forward │\n",
- "│ │\n",
- "│ 289 │ │ hidden_states = self.input_layernorm(hidden_states) │\n",
- "│ 290 │ │ │\n",
- "│ 291 │ │ # Self Attention │\n",
- "│ ❱ 292 │ │ hidden_states, self_attn_weights, present_key_value = self.self_attn( │\n",
- "│ 293 │ │ │ hidden_states=hidden_states, │\n",
- "│ 294 │ │ │ attention_mask=attention_mask, │\n",
- "│ 295 │ │ │ position_ids=position_ids, │\n",
- "│ │\n",
- "│ /usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py:1501 in _call_impl │\n",
- "│ │\n",
- "│ 1498 │ │ if not (self._backward_hooks or self._backward_pre_hooks or self._forward_hooks │\n",
- "│ 1499 │ │ │ │ or _global_backward_pre_hooks or _global_backward_hooks │\n",
- "│ 1500 │ │ │ │ or _global_forward_hooks or _global_forward_pre_hooks): │\n",
- "│ ❱ 1501 │ │ │ return forward_call(*args, **kwargs) │\n",
- "│ 1502 │ │ # Do not call functions when jit is used │\n",
- "│ 1503 │ │ full_backward_hooks, non_full_backward_hooks = [], [] │\n",
- "│ 1504 │ │ backward_pre_hooks = [] │\n",
- "│ │\n",
- "│ /usr/local/lib/python3.10/dist-packages/accelerate/hooks.py:165 in new_forward │\n",
- "│ │\n",
- "│ 162 │ │ │ with torch.no_grad(): │\n",
- "│ 163 │ │ │ │ output = old_forward(*args, **kwargs) │\n",
- "│ 164 │ │ else: │\n",
- "│ ❱ 165 │ │ │ output = old_forward(*args, **kwargs) │\n",
- "│ 166 │ │ return module._hf_hook.post_forward(module, output) │\n",
- "│ 167 │ │\n",
- "│ 168 │ module.forward = new_forward │\n",
- "│ │\n",
- "│ /usr/local/lib/python3.10/dist-packages/transformers/models/llama/modeling_llama.py:194 in │\n",
- "│ forward │\n",
- "│ │\n",
- "│ 191 │ ) -> Tuple[torch.Tensor, Optional[torch.Tensor], Optional[Tuple[torch.Tensor]]]: │\n",
- "│ 192 │ │ bsz, q_len, _ = hidden_states.size() │\n",
- "│ 193 │ │ │\n",
- "│ ❱ 194 │ │ query_states = self.q_proj(hidden_states).view(bsz, q_len, self.num_heads, self. │\n",
- "│ 195 │ │ key_states = self.k_proj(hidden_states).view(bsz, q_len, self.num_heads, self.he │\n",
- "│ 196 │ │ value_states = self.v_proj(hidden_states).view(bsz, q_len, self.num_heads, self. │\n",
- "│ 197 │\n",
- "│ │\n",
- "│ /usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py:1501 in _call_impl │\n",
- "│ │\n",
- "│ 1498 │ │ if not (self._backward_hooks or self._backward_pre_hooks or self._forward_hooks │\n",
- "│ 1499 │ │ │ │ or _global_backward_pre_hooks or _global_backward_hooks │\n",
- "│ 1500 │ │ │ │ or _global_forward_hooks or _global_forward_pre_hooks): │\n",
- "│ ❱ 1501 │ │ │ return forward_call(*args, **kwargs) │\n",
- "│ 1502 │ │ # Do not call functions when jit is used │\n",
- "│ 1503 │ │ full_backward_hooks, non_full_backward_hooks = [], [] │\n",
- "│ 1504 │ │ backward_pre_hooks = [] │\n",
- "│ │\n",
- "│ /usr/local/lib/python3.10/dist-packages/peft/tuners/lora.py:709 in forward │\n",
- "│ │\n",
- "│ 706 │ │ │ self.active_adapter = adapter_name │\n",
- "│ 707 │ │ │\n",
- "│ 708 │ │ def forward(self, x: torch.Tensor): │\n",
- "│ ❱ 709 │ │ │ result = super().forward(x) │\n",
- "│ 710 │ │ │ │\n",
- "│ 711 │ │ │ if self.disable_adapters or self.active_adapter not in self.lora_A.keys(): │\n",
- "│ 712 │ │ │ │ return result │\n",
- "│ │\n",
- "│ /usr/local/lib/python3.10/dist-packages/bitsandbytes/nn/modules.py:388 in forward │\n",
- "│ │\n",
- "│ 385 │ │ if self.bias is not None and self.bias.dtype != x.dtype: │\n",
- "│ 386 │ │ │ self.bias.data = self.bias.data.to(x.dtype) │\n",
- "│ 387 │ │ │\n",
- "│ ❱ 388 │ │ out = bnb.matmul(x, self.weight, bias=self.bias, state=self.state) │\n",
- "│ 389 │ │ │\n",
- "│ 390 │ │ if not self.state.has_fp16_weights: │\n",
- "│ 391 │ │ │ if self.state.CB is not None and self.state.CxB is not None: │\n",
- "│ │\n",
- "│ /usr/local/lib/python3.10/dist-packages/bitsandbytes/autograd/_functions.py:559 in matmul │\n",
- "│ │\n",
- "│ 556 │ state = state or MatmulLtState() │\n",
- "│ 557 │ if threshold > 0.0: │\n",
- "│ 558 │ │ state.threshold = threshold │\n",
- "│ ❱ 559 │ return MatMul8bitLt.apply(A, B, out, bias, state) │\n",
- "│ 560 │\n",
- "│ 561 │\n",
- "│ 562 def matmul_4bit(A: tensor, B: tensor, quant_state: List, out: tensor = None, bias=None): │\n",
- "│ │\n",
- "│ /usr/local/lib/python3.10/dist-packages/torch/autograd/function.py:506 in apply │\n",
- "│ │\n",
- "│ 503 │ │ if not torch._C._are_functorch_transforms_active(): │\n",
- "│ 504 │ │ │ # See NOTE: [functorch vjp and autograd interaction] │\n",
- "│ 505 │ │ │ args = _functorch.utils.unwrap_dead_wrappers(args) │\n",
- "│ ❱ 506 │ │ │ return super().apply(*args, **kwargs) # type: ignore[misc] │\n",
- "│ 507 │ │ │\n",
- "│ 508 │ │ if cls.setup_context == _SingleLevelFunction.setup_context: │\n",
- "│ 509 │ │ │ raise RuntimeError( │\n",
- "│ │\n",
- "│ /usr/local/lib/python3.10/dist-packages/bitsandbytes/autograd/_functions.py:323 in forward │\n",
- "│ │\n",
- "│ 320 │ │ # 1. Quantize A │\n",
- "│ 321 │ │ if len(A.shape) == 3: │\n",
- "│ 322 │ │ │ A = A.view(-1, A.shape[-1]).contiguous() │\n",
- "│ ❱ 323 │ │ CA, CAt, SCA, SCAt, coo_tensorA = F.double_quant(A.to(torch.float16), threshold= │\n",
- "│ 324 │ │ │\n",
- "│ 325 │ │ if state.threshold > 0.0 and coo_tensorA is not None: │\n",
- "│ 326 │ │ │ if state.has_fp16_weights: │\n",
- "│ │\n",
- "│ /usr/local/lib/python3.10/dist-packages/bitsandbytes/functional.py:2029 in double_quant │\n",
- "│ │\n",
- "│ 2026 │ │ │ │ ct.c_int32(rows), │\n",
- "│ 2027 │ │ │ │ ct.c_int32(cols), │\n",
- "│ 2028 │ │ │ ) │\n",
- "│ ❱ 2029 │ │ │ val, idx = torch.sort(coo_tensor.rowidx) │\n",
- "│ 2030 │ │ │ coo_tensor.rowidx = val │\n",
- "│ 2031 │ │ │ coo_tensor.colidx = coo_tensor.colidx[idx] │\n",
- "│ 2032 │ │ │ coo_tensor.values = coo_tensor.values[idx] │\n",
- "╰──────────────────────────────────────────────────────────────────────────────────────────────────╯\n",
- "KeyboardInterrupt\n",
- " \n"
- ]
- },
- "metadata": {}
- }
- ]
- }
- ]
+ "id": "kWP89TPIwRkK",
+ "outputId": "fb4d3012-795b-46c2-90a0-f72fc8185a11"
+ },
+ "outputs": [],
+ "source": [
+ "data = data.shuffle().map(\n",
+ " lambda data_point: tokenizer(\n",
+ " generate_prompt(data_point),\n",
+ " truncation=True,\n",
+ " max_length=CUTOFF_LEN,\n",
+ " padding=\"max_length\",\n",
+ " )\n",
+ ")\n",
+ "\n",
+ "trainer = transformers.Trainer(\n",
+ " model=model,\n",
+ " train_dataset=data[\"train\"],\n",
+ " args=transformers.TrainingArguments(\n",
+ " per_device_train_batch_size=MICRO_BATCH_SIZE,\n",
+ " gradient_accumulation_steps=GRADIENT_ACCUMULATION_STEPS,\n",
+ " warmup_steps=100,\n",
+ " num_train_epochs=EPOCHS,\n",
+ " learning_rate=LEARNING_RATE,\n",
+ " fp16=True,\n",
+ " logging_steps=1,\n",
+ " output_dir=\"lora-alpaca\",\n",
+ " save_total_limit=3,\n",
+ " ),\n",
+ " data_collator=transformers.DataCollatorForLanguageModeling(tokenizer, mlm=False),\n",
+ ")\n",
+ "model.config.use_cache = False\n",
+ "trainer.train(resume_from_checkpoint=False)\n",
+ "\n",
+ "model.save_pretrained(\"lora-alpaca\")\n",
+ "\n",
+ "!cp -rv lora-alpaca /content/drive/MyDrive/"
+ ]
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "Python 3 (ipykernel)",
+ "language": "python",
+ "name": "python3"
+ },
+ "language_info": {
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 3
+ },
+ "file_extension": ".py",
+ "mimetype": "text/x-python",
+ "name": "python",
+ "nbconvert_exporter": "python",
+ "pygments_lexer": "ipython3",
+ "version": "3.11.3"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 1
}
|