diff --git "a/Mamba_NLI_NLU.ipynb" "b/Mamba_NLI_NLU.ipynb"
new file mode 100644--- /dev/null
+++ "b/Mamba_NLI_NLU.ipynb"
@@ -0,0 +1,8951 @@
+{
+ "nbformat": 4,
+ "nbformat_minor": 0,
+ "metadata": {
+ "colab": {
+ "provenance": [],
+ "gpuType": "T4",
+ "collapsed_sections": [
+ "TOsxnf2GxSPP",
+ "IMupZZaKxV1-",
+ "dlmPjXCHxbRG",
+ "wC4RpyvKuQMM",
+ "BQGUd1oBuYOE",
+ "XgFakB63uhEa",
+ "CQLoRnN8ulw5",
+ "y1iQR7Viupdn",
+ "S0_uTR5jbd_y"
+ ]
+ },
+ "kernelspec": {
+ "name": "python3",
+ "display_name": "Python 3"
+ },
+ "language_info": {
+ "name": "python"
+ },
+ "accelerator": "GPU",
+ "widgets": {
+ "application/vnd.jupyter.widget-state+json": {
+ "b0037ea804754052a7ccee9fc200b9b2": {
+ "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_5383fef7471a4c1cb589b8787f550c9e",
+ "IPY_MODEL_d8804cab179c4b75949646a97cd2c449",
+ "IPY_MODEL_ec72bc3d05694095b094ddc7b19446ff"
+ ],
+ "layout": "IPY_MODEL_411da49080b641da81c4d38b22f274ce"
+ }
+ },
+ "5383fef7471a4c1cb589b8787f550c9e": {
+ "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_aee9b3f44600433985b889950f6f4ea8",
+ "placeholder": "",
+ "style": "IPY_MODEL_c6eb487f7ef946109ac3f42a47295c9b",
+ "value": "config.json: 100%"
+ }
+ },
+ "d8804cab179c4b75949646a97cd2c449": {
+ "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_82239355438e4e828008fc8c0595842a",
+ "max": 199,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_d3bc593a5dc441e0b0df6224fd65bcba",
+ "value": 199
+ }
+ },
+ "ec72bc3d05694095b094ddc7b19446ff": {
+ "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_0b42258e07974e5eb82ca3642499a0d0",
+ "placeholder": "",
+ "style": "IPY_MODEL_85407f7ff7ec4bfd851a76f7f5b610fc",
+ "value": " 199/199 [00:00<00:00, 15.3kB/s]"
+ }
+ },
+ "411da49080b641da81c4d38b22f274ce": {
+ "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
+ }
+ },
+ "aee9b3f44600433985b889950f6f4ea8": {
+ "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
+ }
+ },
+ "c6eb487f7ef946109ac3f42a47295c9b": {
+ "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": ""
+ }
+ },
+ "82239355438e4e828008fc8c0595842a": {
+ "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
+ }
+ },
+ "d3bc593a5dc441e0b0df6224fd65bcba": {
+ "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": ""
+ }
+ },
+ "0b42258e07974e5eb82ca3642499a0d0": {
+ "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
+ }
+ },
+ "85407f7ff7ec4bfd851a76f7f5b610fc": {
+ "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": ""
+ }
+ },
+ "832774cf2a8245829ed6ce775c6fc404": {
+ "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_f6a02dbfe5824ff4a5adba539277bfea",
+ "IPY_MODEL_ddadb9a42e774eff94c7f799c1d73ca0",
+ "IPY_MODEL_6ff246f616db4b39b9b95a5d69da69e3"
+ ],
+ "layout": "IPY_MODEL_39a6c048558e45d19fe888aeeacbb94c"
+ }
+ },
+ "f6a02dbfe5824ff4a5adba539277bfea": {
+ "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_9987a82c3caa4d75b27b3674bc683bbd",
+ "placeholder": "",
+ "style": "IPY_MODEL_eb246ae00fb941cb8ba785e97c2ad216",
+ "value": "pytorch_model.bin: 100%"
+ }
+ },
+ "ddadb9a42e774eff94c7f799c1d73ca0": {
+ "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_af6f74dc6bf24b5d984075c947409d72",
+ "max": 516618642,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_d82692dd1d1b49f1bb303ef5ac03f3e1",
+ "value": 516618642
+ }
+ },
+ "6ff246f616db4b39b9b95a5d69da69e3": {
+ "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_fdfba7a6ad0e4fc99ab9d96df7641f81",
+ "placeholder": "",
+ "style": "IPY_MODEL_57bf8324d4a5466580121ec5cb3c2e81",
+ "value": " 517M/517M [00:21<00:00, 22.7MB/s]"
+ }
+ },
+ "39a6c048558e45d19fe888aeeacbb94c": {
+ "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
+ }
+ },
+ "9987a82c3caa4d75b27b3674bc683bbd": {
+ "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
+ }
+ },
+ "eb246ae00fb941cb8ba785e97c2ad216": {
+ "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": ""
+ }
+ },
+ "af6f74dc6bf24b5d984075c947409d72": {
+ "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
+ }
+ },
+ "d82692dd1d1b49f1bb303ef5ac03f3e1": {
+ "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": ""
+ }
+ },
+ "fdfba7a6ad0e4fc99ab9d96df7641f81": {
+ "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
+ }
+ },
+ "57bf8324d4a5466580121ec5cb3c2e81": {
+ "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": ""
+ }
+ },
+ "759691faf9b544f28780bb75b10a9f6c": {
+ "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_24b574b637484cea93e94bdcd24b6458",
+ "IPY_MODEL_d7ca103ebbd44dd4a25f39597b021175",
+ "IPY_MODEL_8053285e39414e71ba5efc87f82769a8"
+ ],
+ "layout": "IPY_MODEL_a75ebc64fd3646dea8269ac628feec91"
+ }
+ },
+ "24b574b637484cea93e94bdcd24b6458": {
+ "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_59dd5c975c244a28997dae102da29094",
+ "placeholder": "",
+ "style": "IPY_MODEL_b6dbb69723cf4a179893656c4424e490",
+ "value": "tokenizer_config.json: 100%"
+ }
+ },
+ "d7ca103ebbd44dd4a25f39597b021175": {
+ "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_1bf82ba8430b4002bfdff0bb6268ab29",
+ "max": 156,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_81ea42372300473ab9e655ab509523a3",
+ "value": 156
+ }
+ },
+ "8053285e39414e71ba5efc87f82769a8": {
+ "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_66303ad5b1ea479fa89b5ab8517f2087",
+ "placeholder": "",
+ "style": "IPY_MODEL_564b6a7ab5054a1986e709838c7f9d70",
+ "value": " 156/156 [00:00<00:00, 17.4kB/s]"
+ }
+ },
+ "a75ebc64fd3646dea8269ac628feec91": {
+ "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
+ }
+ },
+ "59dd5c975c244a28997dae102da29094": {
+ "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
+ }
+ },
+ "b6dbb69723cf4a179893656c4424e490": {
+ "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": ""
+ }
+ },
+ "1bf82ba8430b4002bfdff0bb6268ab29": {
+ "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
+ }
+ },
+ "81ea42372300473ab9e655ab509523a3": {
+ "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": ""
+ }
+ },
+ "66303ad5b1ea479fa89b5ab8517f2087": {
+ "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
+ }
+ },
+ "564b6a7ab5054a1986e709838c7f9d70": {
+ "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": ""
+ }
+ },
+ "f798c29f3989498a92cd1503c8e74081": {
+ "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_343b0c62542d4f03837ffa1bf698411c",
+ "IPY_MODEL_37a9419c3002433b8911e59b3aa836a2",
+ "IPY_MODEL_bb3b1bf5f87a4fcfa8dbcc2ae6d8a25b"
+ ],
+ "layout": "IPY_MODEL_113cb61d327b43cd83e5a49ac86d0ce9"
+ }
+ },
+ "343b0c62542d4f03837ffa1bf698411c": {
+ "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_7dae014d0fe44407b41063065723beed",
+ "placeholder": "",
+ "style": "IPY_MODEL_3c81bc13902b440b80536e50171ee46f",
+ "value": "vocab.json: 100%"
+ }
+ },
+ "37a9419c3002433b8911e59b3aa836a2": {
+ "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_79d5c54978ec4813b874008d1478f57f",
+ "max": 1077392,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_7226a36f162e445d9de307b06b38b4ef",
+ "value": 1077392
+ }
+ },
+ "bb3b1bf5f87a4fcfa8dbcc2ae6d8a25b": {
+ "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_7a1d20eb8e4f41a3a907bad0bd20ab0e",
+ "placeholder": "",
+ "style": "IPY_MODEL_170188f3d113488abd6e543c55df1b47",
+ "value": " 1.08M/1.08M [00:00<00:00, 30.2MB/s]"
+ }
+ },
+ "113cb61d327b43cd83e5a49ac86d0ce9": {
+ "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
+ }
+ },
+ "7dae014d0fe44407b41063065723beed": {
+ "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
+ }
+ },
+ "3c81bc13902b440b80536e50171ee46f": {
+ "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": ""
+ }
+ },
+ "79d5c54978ec4813b874008d1478f57f": {
+ "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
+ }
+ },
+ "7226a36f162e445d9de307b06b38b4ef": {
+ "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": ""
+ }
+ },
+ "7a1d20eb8e4f41a3a907bad0bd20ab0e": {
+ "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
+ }
+ },
+ "170188f3d113488abd6e543c55df1b47": {
+ "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": ""
+ }
+ },
+ "250e830ac7744f2a98036336e7b2209d": {
+ "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_3b828f8df1aa451e85b1fd46af287f3f",
+ "IPY_MODEL_0f62bfbaeac5452dbc80db4e4f4602c7",
+ "IPY_MODEL_cc987c2d93b4490cad4f1d4b1651033f"
+ ],
+ "layout": "IPY_MODEL_52f35f0244d7447bac9d6c45caf3eddd"
+ }
+ },
+ "3b828f8df1aa451e85b1fd46af287f3f": {
+ "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_335b95d6a6234f88928354f7965c1848",
+ "placeholder": "",
+ "style": "IPY_MODEL_29d1c5a3160c4b748128dfd0969b4c0a",
+ "value": "merges.txt: 100%"
+ }
+ },
+ "0f62bfbaeac5452dbc80db4e4f4602c7": {
+ "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_d6427d07681a4cffb70d05804a6b3537",
+ "max": 456583,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_a63f8f572d854fb4978069dce27e4aba",
+ "value": 456583
+ }
+ },
+ "cc987c2d93b4490cad4f1d4b1651033f": {
+ "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_9abc05f2f42b490db11ffa60f5d738ad",
+ "placeholder": "",
+ "style": "IPY_MODEL_649b13622d974391be32dad91355f449",
+ "value": " 457k/457k [00:00<00:00, 37.8MB/s]"
+ }
+ },
+ "52f35f0244d7447bac9d6c45caf3eddd": {
+ "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
+ }
+ },
+ "335b95d6a6234f88928354f7965c1848": {
+ "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
+ }
+ },
+ "29d1c5a3160c4b748128dfd0969b4c0a": {
+ "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": ""
+ }
+ },
+ "d6427d07681a4cffb70d05804a6b3537": {
+ "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
+ }
+ },
+ "a63f8f572d854fb4978069dce27e4aba": {
+ "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": ""
+ }
+ },
+ "9abc05f2f42b490db11ffa60f5d738ad": {
+ "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
+ }
+ },
+ "649b13622d974391be32dad91355f449": {
+ "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": ""
+ }
+ },
+ "3aa1f8a964854593b26694ea2d1f499a": {
+ "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_4ae1cd49f9a14c069ea6e0928ae0bc15",
+ "IPY_MODEL_efd4bddaefa340d1a8bc7fd1ec3f3fb1",
+ "IPY_MODEL_fd103f1ddc2c4cc5a9ff898c949f0d2a"
+ ],
+ "layout": "IPY_MODEL_88014f62fd5d463787299be68a730c85"
+ }
+ },
+ "4ae1cd49f9a14c069ea6e0928ae0bc15": {
+ "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_523ce69c303d42a9b506f7e8d536acdd",
+ "placeholder": "",
+ "style": "IPY_MODEL_f3a906b9f250411cb14166849168d9ae",
+ "value": "tokenizer.json: 100%"
+ }
+ },
+ "efd4bddaefa340d1a8bc7fd1ec3f3fb1": {
+ "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_8fe8bac962664404816553cdf23a6854",
+ "max": 2113710,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_ac7a1903abc04f29aec7ca3ea41a4aed",
+ "value": 2113710
+ }
+ },
+ "fd103f1ddc2c4cc5a9ff898c949f0d2a": {
+ "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_e3373882cae543c79e944e2d3044887c",
+ "placeholder": "",
+ "style": "IPY_MODEL_701d936e338d4b8e8929656e0d830d66",
+ "value": " 2.11M/2.11M [00:00<00:00, 9.07MB/s]"
+ }
+ },
+ "88014f62fd5d463787299be68a730c85": {
+ "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
+ }
+ },
+ "523ce69c303d42a9b506f7e8d536acdd": {
+ "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
+ }
+ },
+ "f3a906b9f250411cb14166849168d9ae": {
+ "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": ""
+ }
+ },
+ "8fe8bac962664404816553cdf23a6854": {
+ "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
+ }
+ },
+ "ac7a1903abc04f29aec7ca3ea41a4aed": {
+ "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": ""
+ }
+ },
+ "e3373882cae543c79e944e2d3044887c": {
+ "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
+ }
+ },
+ "701d936e338d4b8e8929656e0d830d66": {
+ "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": ""
+ }
+ },
+ "7c588426535244139cb0b261eb1322bb": {
+ "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_e657136eeffc4c6db36649c427a7f7a1",
+ "IPY_MODEL_d792cd3291cc4837a73783dc8d3e840c",
+ "IPY_MODEL_4b460655df9646b5b6de2021945871c5"
+ ],
+ "layout": "IPY_MODEL_00d9a623b2414c94bd28466e79da2f2f"
+ }
+ },
+ "e657136eeffc4c6db36649c427a7f7a1": {
+ "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_1c51232afed8478090d191b3d18f9ba4",
+ "placeholder": "",
+ "style": "IPY_MODEL_28b2d5a2119b42f78318377cfc3b53c5",
+ "value": "special_tokens_map.json: 100%"
+ }
+ },
+ "d792cd3291cc4837a73783dc8d3e840c": {
+ "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_1e04d06db8f84b7abbb5d404d60ee2b1",
+ "max": 90,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_3c065f7cc3af470b8726ff75027c2fae",
+ "value": 90
+ }
+ },
+ "4b460655df9646b5b6de2021945871c5": {
+ "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_16ad8e9095a94200aded8c605c9e174d",
+ "placeholder": "",
+ "style": "IPY_MODEL_9410258eeebe401ca2a496eea21ed40f",
+ "value": " 90.0/90.0 [00:00<00:00, 9.67kB/s]"
+ }
+ },
+ "00d9a623b2414c94bd28466e79da2f2f": {
+ "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
+ }
+ },
+ "1c51232afed8478090d191b3d18f9ba4": {
+ "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
+ }
+ },
+ "28b2d5a2119b42f78318377cfc3b53c5": {
+ "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": ""
+ }
+ },
+ "1e04d06db8f84b7abbb5d404d60ee2b1": {
+ "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
+ }
+ },
+ "3c065f7cc3af470b8726ff75027c2fae": {
+ "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": ""
+ }
+ },
+ "16ad8e9095a94200aded8c605c9e174d": {
+ "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
+ }
+ },
+ "9410258eeebe401ca2a496eea21ed40f": {
+ "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": ""
+ }
+ },
+ "171ea990d8c14e6298a61c608b027b19": {
+ "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_e2d497249fd54e14a5f0fee864f20afa",
+ "IPY_MODEL_a8f5f3940d584d67afd3f43d2d408ceb",
+ "IPY_MODEL_b3a0a9a97c014f2fa844916e8443b570"
+ ],
+ "layout": "IPY_MODEL_e7cc9414135b4ea687b9cd91a00dd27f"
+ }
+ },
+ "e2d497249fd54e14a5f0fee864f20afa": {
+ "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_54fecadc4ceb487aa2db92367986539c",
+ "placeholder": "",
+ "style": "IPY_MODEL_89156885d0ee42a688352b9b2e6db0ff",
+ "value": "Generating train split: "
+ }
+ },
+ "a8f5f3940d584d67afd3f43d2d408ceb": {
+ "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_5bc5cb42d0d4492389fa88902567f1b1",
+ "max": 1,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_86d30f0a2d314fff9ed973089fd233f7",
+ "value": 1
+ }
+ },
+ "b3a0a9a97c014f2fa844916e8443b570": {
+ "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_76797c5e90504e5d906323bba3d47d37",
+ "placeholder": "",
+ "style": "IPY_MODEL_68a4634956b04059b4c45aee6fc0ad32",
+ "value": " 24432/0 [00:00<00:00, 203448.61 examples/s]"
+ }
+ },
+ "e7cc9414135b4ea687b9cd91a00dd27f": {
+ "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
+ }
+ },
+ "54fecadc4ceb487aa2db92367986539c": {
+ "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
+ }
+ },
+ "89156885d0ee42a688352b9b2e6db0ff": {
+ "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": ""
+ }
+ },
+ "5bc5cb42d0d4492389fa88902567f1b1": {
+ "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"
+ }
+ },
+ "86d30f0a2d314fff9ed973089fd233f7": {
+ "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": ""
+ }
+ },
+ "76797c5e90504e5d906323bba3d47d37": {
+ "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
+ }
+ },
+ "68a4634956b04059b4c45aee6fc0ad32": {
+ "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": ""
+ }
+ },
+ "89e7c2d90a2d43fb9cd5d21faad52b49": {
+ "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_4fa3c99c584b4e7cb73c8903a43f0a32",
+ "IPY_MODEL_f8d43e4272c84626bd1e80d977f53221",
+ "IPY_MODEL_c85095f6bbe04f5086d9e9bfdc1eea21"
+ ],
+ "layout": "IPY_MODEL_9122556aba9e4cbfae38038cddbab78c"
+ }
+ },
+ "4fa3c99c584b4e7cb73c8903a43f0a32": {
+ "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_fb1031904dd84eb5bb16330075d17083",
+ "placeholder": "",
+ "style": "IPY_MODEL_c972f967ffc041c887c54a91155ac62a",
+ "value": "Generating train split: "
+ }
+ },
+ "f8d43e4272c84626bd1e80d977f53221": {
+ "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_621aa6b2d1f74e849458de1751feca8e",
+ "max": 1,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_7fa1ac3de581419aaf9814aae03fa584",
+ "value": 1
+ }
+ },
+ "c85095f6bbe04f5086d9e9bfdc1eea21": {
+ "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_345522819e91495e821179e132cc0d93",
+ "placeholder": "",
+ "style": "IPY_MODEL_9856e98eb25a4b518964f9823a19fae8",
+ "value": " 6736/0 [00:00<00:00, 107967.10 examples/s]"
+ }
+ },
+ "9122556aba9e4cbfae38038cddbab78c": {
+ "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
+ }
+ },
+ "fb1031904dd84eb5bb16330075d17083": {
+ "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
+ }
+ },
+ "c972f967ffc041c887c54a91155ac62a": {
+ "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": ""
+ }
+ },
+ "621aa6b2d1f74e849458de1751feca8e": {
+ "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"
+ }
+ },
+ "7fa1ac3de581419aaf9814aae03fa584": {
+ "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": ""
+ }
+ },
+ "345522819e91495e821179e132cc0d93": {
+ "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
+ }
+ },
+ "9856e98eb25a4b518964f9823a19fae8": {
+ "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": ""
+ }
+ },
+ "6f4f9ee05cad4afa8d42b36fc40fcaee": {
+ "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_c807045c7f934d3ba0b5db6a480ca7ba",
+ "IPY_MODEL_2471e5d832844c2696e05dbc653ee199",
+ "IPY_MODEL_3401774f866f40728c19cdca5543c54c"
+ ],
+ "layout": "IPY_MODEL_615c4a27a9a742b2aaa33c0a91e37c3a"
+ }
+ },
+ "c807045c7f934d3ba0b5db6a480ca7ba": {
+ "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_45742c8298a64cb080b92522c71076d2",
+ "placeholder": "",
+ "style": "IPY_MODEL_fb37e8ac33ab460a8b14fd8294018a50",
+ "value": "Map: 100%"
+ }
+ },
+ "2471e5d832844c2696e05dbc653ee199": {
+ "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_f651fc657e2a45129a2a8d24325d7567",
+ "max": 24432,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_0f7f095700ba40bcb5b7e6850ab12b80",
+ "value": 24432
+ }
+ },
+ "3401774f866f40728c19cdca5543c54c": {
+ "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_bebbd131955a406d830b61f466576d2d",
+ "placeholder": "",
+ "style": "IPY_MODEL_10322f752019460ab4464eb1dfc0c495",
+ "value": " 24432/24432 [00:06<00:00, 5441.35 examples/s]"
+ }
+ },
+ "615c4a27a9a742b2aaa33c0a91e37c3a": {
+ "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
+ }
+ },
+ "45742c8298a64cb080b92522c71076d2": {
+ "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
+ }
+ },
+ "fb37e8ac33ab460a8b14fd8294018a50": {
+ "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": ""
+ }
+ },
+ "f651fc657e2a45129a2a8d24325d7567": {
+ "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
+ }
+ },
+ "0f7f095700ba40bcb5b7e6850ab12b80": {
+ "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": ""
+ }
+ },
+ "bebbd131955a406d830b61f466576d2d": {
+ "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
+ }
+ },
+ "10322f752019460ab4464eb1dfc0c495": {
+ "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": ""
+ }
+ },
+ "52e37a5d708647b4a5111148d1f23882": {
+ "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_a5be32f2f44543c7a2554fc9d3a3d491",
+ "IPY_MODEL_cf6347d7db544f4d9a304a98b08407b6",
+ "IPY_MODEL_6a8a5a05507c49ebaa05002971c17c66"
+ ],
+ "layout": "IPY_MODEL_32250a08aa324dee911c3ead39c4d858"
+ }
+ },
+ "a5be32f2f44543c7a2554fc9d3a3d491": {
+ "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_512b34bd1ab0422fa59b2edb803fd7fe",
+ "placeholder": "",
+ "style": "IPY_MODEL_8d1fd501e4ef45d2a79f6b12fecd2117",
+ "value": "Map: 100%"
+ }
+ },
+ "cf6347d7db544f4d9a304a98b08407b6": {
+ "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_11a2103bbd1f4c4aba51a7a8a8616ba0",
+ "max": 6736,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_ab7b8e3258f442fbbfbb5a1c4217a6b9",
+ "value": 6736
+ }
+ },
+ "6a8a5a05507c49ebaa05002971c17c66": {
+ "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_128f41897567498a99370d42a864df09",
+ "placeholder": "",
+ "style": "IPY_MODEL_1c22cbc2cc584295ab0619c503b1bc8c",
+ "value": " 6736/6736 [00:01<00:00, 5477.44 examples/s]"
+ }
+ },
+ "32250a08aa324dee911c3ead39c4d858": {
+ "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
+ }
+ },
+ "512b34bd1ab0422fa59b2edb803fd7fe": {
+ "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
+ }
+ },
+ "8d1fd501e4ef45d2a79f6b12fecd2117": {
+ "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": ""
+ }
+ },
+ "11a2103bbd1f4c4aba51a7a8a8616ba0": {
+ "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
+ }
+ },
+ "ab7b8e3258f442fbbfbb5a1c4217a6b9": {
+ "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": ""
+ }
+ },
+ "128f41897567498a99370d42a864df09": {
+ "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
+ }
+ },
+ "1c22cbc2cc584295ab0619c503b1bc8c": {
+ "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": ""
+ }
+ },
+ "5c5e3c6265904656b532c835fdb19ef4": {
+ "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_6e1cae0032d94e58b4868419e0bed506",
+ "IPY_MODEL_b2dfd1236ec64a928e7fc3f183b9e1c5",
+ "IPY_MODEL_2e9952452127450a8c2d7f58d5d92d89"
+ ],
+ "layout": "IPY_MODEL_cc7e759bdd0545ac8f3419c735fe5448"
+ }
+ },
+ "6e1cae0032d94e58b4868419e0bed506": {
+ "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_4783bf6aed4e46f4bdb56d3fb0e10eb1",
+ "placeholder": "",
+ "style": "IPY_MODEL_3420b3c222af410a9e086d03842a85af",
+ "value": "config.json: 100%"
+ }
+ },
+ "b2dfd1236ec64a928e7fc3f183b9e1c5": {
+ "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_78b851d587f140edb45c877192ef5112",
+ "max": 224,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_339ed21242d4441aa8116e1f66fef056",
+ "value": 224
+ }
+ },
+ "2e9952452127450a8c2d7f58d5d92d89": {
+ "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_ed419b0677e84dcbadd25b97170e63dc",
+ "placeholder": "",
+ "style": "IPY_MODEL_df6b224bdd3e46f4aacfc2d0f4c11a0b",
+ "value": " 224/224 [00:00<00:00, 23.5kB/s]"
+ }
+ },
+ "cc7e759bdd0545ac8f3419c735fe5448": {
+ "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
+ }
+ },
+ "4783bf6aed4e46f4bdb56d3fb0e10eb1": {
+ "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
+ }
+ },
+ "3420b3c222af410a9e086d03842a85af": {
+ "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": ""
+ }
+ },
+ "78b851d587f140edb45c877192ef5112": {
+ "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
+ }
+ },
+ "339ed21242d4441aa8116e1f66fef056": {
+ "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": ""
+ }
+ },
+ "ed419b0677e84dcbadd25b97170e63dc": {
+ "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
+ }
+ },
+ "df6b224bdd3e46f4aacfc2d0f4c11a0b": {
+ "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": ""
+ }
+ },
+ "d42ea7af636c4d5fb25b814e81dafa29": {
+ "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_c5287cecb88a4a518475813ba85913cc",
+ "IPY_MODEL_58d00e05e78e48aca0989d2e69af9e52",
+ "IPY_MODEL_4647fcbb28474fb6a9222aed10182389"
+ ],
+ "layout": "IPY_MODEL_e20e2a92c25342c8a30c785853111f05"
+ }
+ },
+ "c5287cecb88a4a518475813ba85913cc": {
+ "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_b805e658404d44abb0ca2f28f46b3de0",
+ "placeholder": "",
+ "style": "IPY_MODEL_20820b57aaed42908d1b3128351a7ecb",
+ "value": "pytorch_model.bin: 100%"
+ }
+ },
+ "58d00e05e78e48aca0989d2e69af9e52": {
+ "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_7e9eeacf8f0f4563aab51f39231d2400",
+ "max": 516640282,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_e823f2f705fc48db9ca5c9d32cdfdeb4",
+ "value": 516640282
+ }
+ },
+ "4647fcbb28474fb6a9222aed10182389": {
+ "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_3d287c0c32bc4042a16ce17e93d11406",
+ "placeholder": "",
+ "style": "IPY_MODEL_9cb3bda6951f4bba996c7eee8b4b4271",
+ "value": " 517M/517M [00:21<00:00, 21.9MB/s]"
+ }
+ },
+ "e20e2a92c25342c8a30c785853111f05": {
+ "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
+ }
+ },
+ "b805e658404d44abb0ca2f28f46b3de0": {
+ "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
+ }
+ },
+ "20820b57aaed42908d1b3128351a7ecb": {
+ "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": ""
+ }
+ },
+ "7e9eeacf8f0f4563aab51f39231d2400": {
+ "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
+ }
+ },
+ "e823f2f705fc48db9ca5c9d32cdfdeb4": {
+ "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": ""
+ }
+ },
+ "3d287c0c32bc4042a16ce17e93d11406": {
+ "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
+ }
+ },
+ "9cb3bda6951f4bba996c7eee8b4b4271": {
+ "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": ""
+ }
+ },
+ "9c77d36804314e3a940eb57137f204c7": {
+ "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_03a011f3362048aa8debd95221ba1642",
+ "IPY_MODEL_6bffd97d3244445097ca6a9b6172f291",
+ "IPY_MODEL_a51f5014f7754d8bbde6ca69e2372f68"
+ ],
+ "layout": "IPY_MODEL_da66b15a935a41d7b85c617d6b24f559"
+ }
+ },
+ "03a011f3362048aa8debd95221ba1642": {
+ "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_b2170bdb5abe4eb4bc8df9184c3934c5",
+ "placeholder": "",
+ "style": "IPY_MODEL_bd659d89b8924b1c8de21cbf7916af23",
+ "value": "tokenizer_config.json: 100%"
+ }
+ },
+ "6bffd97d3244445097ca6a9b6172f291": {
+ "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_3b34039631c549699fe540b5472700c8",
+ "max": 4876,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_6d243622262f4fb98da1ad459283e517",
+ "value": 4876
+ }
+ },
+ "a51f5014f7754d8bbde6ca69e2372f68": {
+ "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_976532cd16da499d9b5460a0d59615a1",
+ "placeholder": "",
+ "style": "IPY_MODEL_7e2753de494445088d21c76427484d73",
+ "value": " 4.88k/4.88k [00:00<00:00, 463kB/s]"
+ }
+ },
+ "da66b15a935a41d7b85c617d6b24f559": {
+ "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
+ }
+ },
+ "b2170bdb5abe4eb4bc8df9184c3934c5": {
+ "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
+ }
+ },
+ "bd659d89b8924b1c8de21cbf7916af23": {
+ "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": ""
+ }
+ },
+ "3b34039631c549699fe540b5472700c8": {
+ "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
+ }
+ },
+ "6d243622262f4fb98da1ad459283e517": {
+ "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": ""
+ }
+ },
+ "976532cd16da499d9b5460a0d59615a1": {
+ "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
+ }
+ },
+ "7e2753de494445088d21c76427484d73": {
+ "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": ""
+ }
+ },
+ "1abce180e6b140f1a583570be9665ef8": {
+ "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_6c14b22a4ed94997a3f2f77dca0b1ba6",
+ "IPY_MODEL_343aa7bae39c4fe3aa075dc4d9d784f7",
+ "IPY_MODEL_87a9e1a745814e2bb09eb0b6ea06692b"
+ ],
+ "layout": "IPY_MODEL_97c866b7064b4247bc58bd6a8815673b"
+ }
+ },
+ "6c14b22a4ed94997a3f2f77dca0b1ba6": {
+ "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_b7e52f5ea0974cbaac7cec56f14d6aa6",
+ "placeholder": "",
+ "style": "IPY_MODEL_b7e0ccf9041d47168cad50fdd8f52732",
+ "value": "tokenizer.json: 100%"
+ }
+ },
+ "343aa7bae39c4fe3aa075dc4d9d784f7": {
+ "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_75d0f70e54bd4dbca085aa20211385b6",
+ "max": 3564576,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_d3522bc1535f49ea946aa93d4bff9658",
+ "value": 3564576
+ }
+ },
+ "87a9e1a745814e2bb09eb0b6ea06692b": {
+ "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_3fc97002c3ad4f05bcb21931574f1e1c",
+ "placeholder": "",
+ "style": "IPY_MODEL_552557ce23f345e2ba640553f030ed2a",
+ "value": " 3.56M/3.56M [00:01<00:00, 3.38MB/s]"
+ }
+ },
+ "97c866b7064b4247bc58bd6a8815673b": {
+ "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
+ }
+ },
+ "b7e52f5ea0974cbaac7cec56f14d6aa6": {
+ "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
+ }
+ },
+ "b7e0ccf9041d47168cad50fdd8f52732": {
+ "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": ""
+ }
+ },
+ "75d0f70e54bd4dbca085aa20211385b6": {
+ "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
+ }
+ },
+ "d3522bc1535f49ea946aa93d4bff9658": {
+ "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": ""
+ }
+ },
+ "3fc97002c3ad4f05bcb21931574f1e1c": {
+ "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
+ }
+ },
+ "552557ce23f345e2ba640553f030ed2a": {
+ "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": ""
+ }
+ },
+ "166903568d6b49a5a325b719ca259938": {
+ "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_237be64d5ac44aa6b4e29bc881978ab4",
+ "IPY_MODEL_f17b7a136c8f49f28d5545c5a736c515",
+ "IPY_MODEL_3d6ff50f90374649ab4406bac5d3b58a"
+ ],
+ "layout": "IPY_MODEL_2d63a035addf4e7aa2de636560348ca2"
+ }
+ },
+ "237be64d5ac44aa6b4e29bc881978ab4": {
+ "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_aaf897a858f84417bd26b2b4f181dd0f",
+ "placeholder": "",
+ "style": "IPY_MODEL_26ba3e21bc9c478e9c66f755841614fb",
+ "value": "special_tokens_map.json: 100%"
+ }
+ },
+ "f17b7a136c8f49f28d5545c5a736c515": {
+ "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_06ea3adf62b14d8aab9f7cf9d59ff2c1",
+ "max": 473,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_bec39de5540c4fb4b1a5ee019a4b27ac",
+ "value": 473
+ }
+ },
+ "3d6ff50f90374649ab4406bac5d3b58a": {
+ "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_be2a0b5623a149aabf8953bd6044b439",
+ "placeholder": "",
+ "style": "IPY_MODEL_cbb2c111ad5042aa89615de84a298c45",
+ "value": " 473/473 [00:00<00:00, 40.8kB/s]"
+ }
+ },
+ "2d63a035addf4e7aa2de636560348ca2": {
+ "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
+ }
+ },
+ "aaf897a858f84417bd26b2b4f181dd0f": {
+ "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
+ }
+ },
+ "26ba3e21bc9c478e9c66f755841614fb": {
+ "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": ""
+ }
+ },
+ "06ea3adf62b14d8aab9f7cf9d59ff2c1": {
+ "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
+ }
+ },
+ "bec39de5540c4fb4b1a5ee019a4b27ac": {
+ "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": ""
+ }
+ },
+ "be2a0b5623a149aabf8953bd6044b439": {
+ "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
+ }
+ },
+ "cbb2c111ad5042aa89615de84a298c45": {
+ "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": ""
+ }
+ },
+ "872da9be814e462eb85887e1bc6b9f61": {
+ "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_8d20cfef24e94f94863544503fd00d38",
+ "IPY_MODEL_6aacfe74d4d843a397509f0db6347f0d",
+ "IPY_MODEL_5a70162130704ee0a404b77fbf8cde1f"
+ ],
+ "layout": "IPY_MODEL_aa046179941e46639987c7427061d861"
+ }
+ },
+ "8d20cfef24e94f94863544503fd00d38": {
+ "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_b0ccad64b5cf40d0bd386af183bc2b7f",
+ "placeholder": "",
+ "style": "IPY_MODEL_1d48d9fab2fe45bd8f131417a1faba8b",
+ "value": "Generating train split: "
+ }
+ },
+ "6aacfe74d4d843a397509f0db6347f0d": {
+ "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_eeaf84cf79cc42eb8a0cc5bfb7386fe1",
+ "max": 1,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_68ace37ad114467389b34d04b1e71242",
+ "value": 1
+ }
+ },
+ "5a70162130704ee0a404b77fbf8cde1f": {
+ "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_2d2b7db7c9074ad69dc76771f0676b9a",
+ "placeholder": "",
+ "style": "IPY_MODEL_28d88ac5589844c2afe80f7ab42e7689",
+ "value": " 6736/0 [00:00<00:00, 99330.01 examples/s]"
+ }
+ },
+ "aa046179941e46639987c7427061d861": {
+ "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
+ }
+ },
+ "b0ccad64b5cf40d0bd386af183bc2b7f": {
+ "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
+ }
+ },
+ "1d48d9fab2fe45bd8f131417a1faba8b": {
+ "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": ""
+ }
+ },
+ "eeaf84cf79cc42eb8a0cc5bfb7386fe1": {
+ "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"
+ }
+ },
+ "68ace37ad114467389b34d04b1e71242": {
+ "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": ""
+ }
+ },
+ "2d2b7db7c9074ad69dc76771f0676b9a": {
+ "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
+ }
+ },
+ "28d88ac5589844c2afe80f7ab42e7689": {
+ "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": ""
+ }
+ },
+ "a0c2974e5cda47a296db704cc9d9f27a": {
+ "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_2006b5b3252f43cbbc2b58dd91e471d9",
+ "IPY_MODEL_d941077b54974b8eb10a6dc473071398",
+ "IPY_MODEL_4f060e080e884f5c932b7b4c3e5c6aab"
+ ],
+ "layout": "IPY_MODEL_60076a60a2f846d1acae57c57c3f42e6"
+ }
+ },
+ "2006b5b3252f43cbbc2b58dd91e471d9": {
+ "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_47afdb97dd13457ca0d9a0f277e704db",
+ "placeholder": "",
+ "style": "IPY_MODEL_6545fc938d444bce8441a8b4e1ab9fb1",
+ "value": "Map: 100%"
+ }
+ },
+ "d941077b54974b8eb10a6dc473071398": {
+ "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_68925d06ceee482992dd8e7498b75371",
+ "max": 6736,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_a2292d7034a34cd4ad69a76d94f26e49",
+ "value": 6736
+ }
+ },
+ "4f060e080e884f5c932b7b4c3e5c6aab": {
+ "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_eff01e9452304c7d8695b9621ccc6c70",
+ "placeholder": "",
+ "style": "IPY_MODEL_0a567306a4df43e8a16fe980406282f6",
+ "value": " 6736/6736 [00:01<00:00, 5871.16 examples/s]"
+ }
+ },
+ "60076a60a2f846d1acae57c57c3f42e6": {
+ "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
+ }
+ },
+ "47afdb97dd13457ca0d9a0f277e704db": {
+ "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
+ }
+ },
+ "6545fc938d444bce8441a8b4e1ab9fb1": {
+ "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": ""
+ }
+ },
+ "68925d06ceee482992dd8e7498b75371": {
+ "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
+ }
+ },
+ "a2292d7034a34cd4ad69a76d94f26e49": {
+ "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": ""
+ }
+ },
+ "eff01e9452304c7d8695b9621ccc6c70": {
+ "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
+ }
+ },
+ "0a567306a4df43e8a16fe980406282f6": {
+ "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": ""
+ }
+ },
+ "8e6ac4b384854f76b7c30300a712487a": {
+ "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_bbfafe1b96444939b6c4954b9d58e1be",
+ "IPY_MODEL_4c54dd50f9424759b5ca084860f05775",
+ "IPY_MODEL_32e83caf09df42dab004dd54e00eea26"
+ ],
+ "layout": "IPY_MODEL_7cecd2053eef46eab654190ec1f3fabf"
+ }
+ },
+ "bbfafe1b96444939b6c4954b9d58e1be": {
+ "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_fe10948b9463448898e10f4bc8a8d07c",
+ "placeholder": "",
+ "style": "IPY_MODEL_230107d8cfb34b908df9a1485262551f",
+ "value": "Downloading builder script: 100%"
+ }
+ },
+ "4c54dd50f9424759b5ca084860f05775": {
+ "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_bed1f1b099a3487db9734674a31b0482",
+ "max": 4203,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_c787e80ceabd4b269e3e4759785537d2",
+ "value": 4203
+ }
+ },
+ "32e83caf09df42dab004dd54e00eea26": {
+ "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_5285591888604113a28ecdeec98a8409",
+ "placeholder": "",
+ "style": "IPY_MODEL_3ee0892a94c245e884ae8a669b26aae0",
+ "value": " 4.20k/4.20k [00:00<00:00, 435kB/s]"
+ }
+ },
+ "7cecd2053eef46eab654190ec1f3fabf": {
+ "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
+ }
+ },
+ "fe10948b9463448898e10f4bc8a8d07c": {
+ "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
+ }
+ },
+ "230107d8cfb34b908df9a1485262551f": {
+ "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": ""
+ }
+ },
+ "bed1f1b099a3487db9734674a31b0482": {
+ "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
+ }
+ },
+ "c787e80ceabd4b269e3e4759785537d2": {
+ "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": ""
+ }
+ },
+ "5285591888604113a28ecdeec98a8409": {
+ "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
+ }
+ },
+ "3ee0892a94c245e884ae8a669b26aae0": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ }
+ }
+ }
+ },
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "source": [
+ "# Mamba NLI Classifier\n",
+ "\n",
+ "This project fine-tunes a Mamba SSM model for binary natural language inference (entailment vs. non-entailment). \n",
+ "Final model: [patrickmlml/mamba_nli_ensemble](https://huggingface.co/patrickmlml/mamba_nli_ensemble)\n",
+ "\n",
+ "## Code Overview\n",
+ "\n",
+ "- `MambaTextClassification`: Wraps Mamba with a classification head.\n",
+ "- `MambaTrainer`: Custom Hugging Face `Trainer`.\n",
+ "- Tokenization via `EleutherAI/gpt-neox-20b`.\n",
+ "- Input: premise + hypothesis (tokenized together).\n",
+ "- Metrics: accuracy and Matthews correlation coefficient (MCC).\n",
+ "\n",
+ "## Running\n",
+ "\n",
+ "1. Add CSV datasets in `NLI/train.csv`, `NLI/dev.csv` (or add NLI.zip), and `test.csv`.\n",
+ "2. Install dependencies.\n",
+ "3. Train the model: \n",
+ " `trainer.train()`\n",
+ "4. Save or load model from: \n",
+ " `patrickmlml/mamba_nli_ensemble`\n",
+ "\n",
+ "## Attribution\n",
+ "\n",
+ "- Code and ideas from: \n",
+ " - [Mamba SSM](https://github.com/state-spaces/mamba) \n",
+ " - [Mamba for Sequence Classification](https://github.com/getorca/mamba_for_sequence_classification) \n",
+ " - [arXiv:2312.00752](https://arxiv.org/pdf/2312.00752)\n",
+ "- Tokenizer: [EleutherAI/gpt-neox-20b](https://huggingface.co/EleutherAI/gpt-neox-20b)\n",
+ "- Pretrained model: [state-spaces/mamba-130m](https://huggingface.co/state-spaces/mamba-130m)\n",
+ "- Trained model: [patrickmlml/mamba_nli_ensemble](https://huggingface.co/patrickmlml/mamba_nli_ensemble)\n"
+ ],
+ "metadata": {
+ "id": "0XNRLF_gikfC"
+ }
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "# Libraries and Environment"
+ ],
+ "metadata": {
+ "id": "IMupZZaKxV1-"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "!unzip -qo NLI.zip"
+ ],
+ "metadata": {
+ "id": "1USVSyb042ij"
+ },
+ "execution_count": 25,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 5,
+ "metadata": {
+ "id": "m2bccYSsVTza",
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "outputId": "7ce1a36b-4caa-4332-f78f-0b43e2c796c0",
+ "collapsed": true
+ },
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "unzip: cannot find or open NLI.zip, NLI.zip.zip or NLI.zip.ZIP.\n",
+ "Collecting datasets\n",
+ " Downloading datasets-3.5.0-py3-none-any.whl.metadata (19 kB)\n",
+ "Collecting evaluate\n",
+ " Downloading evaluate-0.4.3-py3-none-any.whl.metadata (9.2 kB)\n",
+ "Requirement already satisfied: accelerate in /usr/local/lib/python3.11/dist-packages (1.5.2)\n",
+ "Collecting optuna\n",
+ " Downloading optuna-4.2.1-py3-none-any.whl.metadata (17 kB)\n",
+ "Requirement already satisfied: filelock in /usr/local/lib/python3.11/dist-packages (from datasets) (3.18.0)\n",
+ "Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.11/dist-packages (from datasets) (2.0.2)\n",
+ "Requirement already satisfied: pyarrow>=15.0.0 in /usr/local/lib/python3.11/dist-packages (from datasets) (18.1.0)\n",
+ "Collecting dill<0.3.9,>=0.3.0 (from datasets)\n",
+ " Downloading dill-0.3.8-py3-none-any.whl.metadata (10 kB)\n",
+ "Requirement already satisfied: pandas in /usr/local/lib/python3.11/dist-packages (from datasets) (2.2.2)\n",
+ "Requirement already satisfied: requests>=2.32.2 in /usr/local/lib/python3.11/dist-packages (from datasets) (2.32.3)\n",
+ "Requirement already satisfied: tqdm>=4.66.3 in /usr/local/lib/python3.11/dist-packages (from datasets) (4.67.1)\n",
+ "Collecting xxhash (from datasets)\n",
+ " Downloading xxhash-3.5.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (12 kB)\n",
+ "Collecting multiprocess<0.70.17 (from datasets)\n",
+ " Downloading multiprocess-0.70.16-py311-none-any.whl.metadata (7.2 kB)\n",
+ "Collecting fsspec<=2024.12.0,>=2023.1.0 (from fsspec[http]<=2024.12.0,>=2023.1.0->datasets)\n",
+ " Downloading fsspec-2024.12.0-py3-none-any.whl.metadata (11 kB)\n",
+ "Requirement already satisfied: aiohttp in /usr/local/lib/python3.11/dist-packages (from datasets) (3.11.14)\n",
+ "Requirement already satisfied: huggingface-hub>=0.24.0 in /usr/local/lib/python3.11/dist-packages (from datasets) (0.29.3)\n",
+ "Requirement already satisfied: packaging in /usr/local/lib/python3.11/dist-packages (from datasets) (24.2)\n",
+ "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.11/dist-packages (from datasets) (6.0.2)\n",
+ "Requirement already satisfied: psutil in /usr/local/lib/python3.11/dist-packages (from accelerate) (5.9.5)\n",
+ "Requirement already satisfied: torch>=2.0.0 in /usr/local/lib/python3.11/dist-packages (from accelerate) (2.6.0+cu124)\n",
+ "Requirement already satisfied: safetensors>=0.4.3 in /usr/local/lib/python3.11/dist-packages (from accelerate) (0.5.3)\n",
+ "Collecting alembic>=1.5.0 (from optuna)\n",
+ " Downloading alembic-1.15.2-py3-none-any.whl.metadata (7.3 kB)\n",
+ "Collecting colorlog (from optuna)\n",
+ " Downloading colorlog-6.9.0-py3-none-any.whl.metadata (10 kB)\n",
+ "Requirement already satisfied: sqlalchemy>=1.4.2 in /usr/local/lib/python3.11/dist-packages (from optuna) (2.0.39)\n",
+ "Requirement already satisfied: Mako in /usr/lib/python3/dist-packages (from alembic>=1.5.0->optuna) (1.1.3)\n",
+ "Requirement already satisfied: typing-extensions>=4.12 in /usr/local/lib/python3.11/dist-packages (from alembic>=1.5.0->optuna) (4.12.2)\n",
+ "Requirement already satisfied: aiohappyeyeballs>=2.3.0 in /usr/local/lib/python3.11/dist-packages (from aiohttp->datasets) (2.6.1)\n",
+ "Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.11/dist-packages (from aiohttp->datasets) (1.3.2)\n",
+ "Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.11/dist-packages (from aiohttp->datasets) (25.3.0)\n",
+ "Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.11/dist-packages (from aiohttp->datasets) (1.5.0)\n",
+ "Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.11/dist-packages (from aiohttp->datasets) (6.2.0)\n",
+ "Requirement already satisfied: propcache>=0.2.0 in /usr/local/lib/python3.11/dist-packages (from aiohttp->datasets) (0.3.0)\n",
+ "Requirement already satisfied: yarl<2.0,>=1.17.0 in /usr/local/lib/python3.11/dist-packages (from aiohttp->datasets) (1.18.3)\n",
+ "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.11/dist-packages (from requests>=2.32.2->datasets) (3.4.1)\n",
+ "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.11/dist-packages (from requests>=2.32.2->datasets) (3.10)\n",
+ "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.11/dist-packages (from requests>=2.32.2->datasets) (2.3.0)\n",
+ "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.11/dist-packages (from requests>=2.32.2->datasets) (2025.1.31)\n",
+ "Requirement already satisfied: greenlet!=0.4.17 in /usr/local/lib/python3.11/dist-packages (from sqlalchemy>=1.4.2->optuna) (3.1.1)\n",
+ "Requirement already satisfied: networkx in /usr/local/lib/python3.11/dist-packages (from torch>=2.0.0->accelerate) (3.4.2)\n",
+ "Requirement already satisfied: jinja2 in /usr/local/lib/python3.11/dist-packages (from torch>=2.0.0->accelerate) (3.1.6)\n",
+ "Collecting nvidia-cuda-nvrtc-cu12==12.4.127 (from torch>=2.0.0->accelerate)\n",
+ " Downloading nvidia_cuda_nvrtc_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n",
+ "Collecting nvidia-cuda-runtime-cu12==12.4.127 (from torch>=2.0.0->accelerate)\n",
+ " Downloading nvidia_cuda_runtime_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n",
+ "Collecting nvidia-cuda-cupti-cu12==12.4.127 (from torch>=2.0.0->accelerate)\n",
+ " Downloading nvidia_cuda_cupti_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.6 kB)\n",
+ "Collecting nvidia-cudnn-cu12==9.1.0.70 (from torch>=2.0.0->accelerate)\n",
+ " Downloading nvidia_cudnn_cu12-9.1.0.70-py3-none-manylinux2014_x86_64.whl.metadata (1.6 kB)\n",
+ "Collecting nvidia-cublas-cu12==12.4.5.8 (from torch>=2.0.0->accelerate)\n",
+ " Downloading nvidia_cublas_cu12-12.4.5.8-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n",
+ "Collecting nvidia-cufft-cu12==11.2.1.3 (from torch>=2.0.0->accelerate)\n",
+ " Downloading nvidia_cufft_cu12-11.2.1.3-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n",
+ "Collecting nvidia-curand-cu12==10.3.5.147 (from torch>=2.0.0->accelerate)\n",
+ " Downloading nvidia_curand_cu12-10.3.5.147-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n",
+ "Collecting nvidia-cusolver-cu12==11.6.1.9 (from torch>=2.0.0->accelerate)\n",
+ " Downloading nvidia_cusolver_cu12-11.6.1.9-py3-none-manylinux2014_x86_64.whl.metadata (1.6 kB)\n",
+ "Collecting nvidia-cusparse-cu12==12.3.1.170 (from torch>=2.0.0->accelerate)\n",
+ " Downloading nvidia_cusparse_cu12-12.3.1.170-py3-none-manylinux2014_x86_64.whl.metadata (1.6 kB)\n",
+ "Requirement already satisfied: nvidia-cusparselt-cu12==0.6.2 in /usr/local/lib/python3.11/dist-packages (from torch>=2.0.0->accelerate) (0.6.2)\n",
+ "Requirement already satisfied: nvidia-nccl-cu12==2.21.5 in /usr/local/lib/python3.11/dist-packages (from torch>=2.0.0->accelerate) (2.21.5)\n",
+ "Requirement already satisfied: nvidia-nvtx-cu12==12.4.127 in /usr/local/lib/python3.11/dist-packages (from torch>=2.0.0->accelerate) (12.4.127)\n",
+ "Collecting nvidia-nvjitlink-cu12==12.4.127 (from torch>=2.0.0->accelerate)\n",
+ " Downloading nvidia_nvjitlink_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n",
+ "Requirement already satisfied: triton==3.2.0 in /usr/local/lib/python3.11/dist-packages (from torch>=2.0.0->accelerate) (3.2.0)\n",
+ "Requirement already satisfied: sympy==1.13.1 in /usr/local/lib/python3.11/dist-packages (from torch>=2.0.0->accelerate) (1.13.1)\n",
+ "Requirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.11/dist-packages (from sympy==1.13.1->torch>=2.0.0->accelerate) (1.3.0)\n",
+ "Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.11/dist-packages (from pandas->datasets) (2.8.2)\n",
+ "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.11/dist-packages (from pandas->datasets) (2025.1)\n",
+ "Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.11/dist-packages (from pandas->datasets) (2025.1)\n",
+ "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.11/dist-packages (from python-dateutil>=2.8.2->pandas->datasets) (1.17.0)\n",
+ "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.11/dist-packages (from jinja2->torch>=2.0.0->accelerate) (3.0.2)\n",
+ "Downloading datasets-3.5.0-py3-none-any.whl (491 kB)\n",
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m491.2/491.2 kB\u001b[0m \u001b[31m30.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hDownloading evaluate-0.4.3-py3-none-any.whl (84 kB)\n",
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m84.0/84.0 kB\u001b[0m \u001b[31m8.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hDownloading optuna-4.2.1-py3-none-any.whl (383 kB)\n",
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m383.6/383.6 kB\u001b[0m \u001b[31m30.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hDownloading alembic-1.15.2-py3-none-any.whl (231 kB)\n",
+ "\u001b[2K \u001b[90m━━━━━━���━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m231.9/231.9 kB\u001b[0m \u001b[31m22.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hDownloading dill-0.3.8-py3-none-any.whl (116 kB)\n",
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m116.3/116.3 kB\u001b[0m \u001b[31m11.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hDownloading fsspec-2024.12.0-py3-none-any.whl (183 kB)\n",
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m183.9/183.9 kB\u001b[0m \u001b[31m18.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hDownloading multiprocess-0.70.16-py311-none-any.whl (143 kB)\n",
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m143.5/143.5 kB\u001b[0m \u001b[31m12.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hDownloading nvidia_cublas_cu12-12.4.5.8-py3-none-manylinux2014_x86_64.whl (363.4 MB)\n",
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m363.4/363.4 MB\u001b[0m \u001b[31m4.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hDownloading nvidia_cuda_cupti_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl (13.8 MB)\n",
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m13.8/13.8 MB\u001b[0m \u001b[31m97.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hDownloading nvidia_cuda_nvrtc_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl (24.6 MB)\n",
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m24.6/24.6 MB\u001b[0m \u001b[31m87.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hDownloading nvidia_cuda_runtime_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl (883 kB)\n",
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m883.7/883.7 kB\u001b[0m \u001b[31m56.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hDownloading nvidia_cudnn_cu12-9.1.0.70-py3-none-manylinux2014_x86_64.whl (664.8 MB)\n",
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m664.8/664.8 MB\u001b[0m \u001b[31m2.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hDownloading nvidia_cufft_cu12-11.2.1.3-py3-none-manylinux2014_x86_64.whl (211.5 MB)\n",
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m211.5/211.5 MB\u001b[0m \u001b[31m5.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hDownloading nvidia_curand_cu12-10.3.5.147-py3-none-manylinux2014_x86_64.whl (56.3 MB)\n",
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m56.3/56.3 MB\u001b[0m \u001b[31m12.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hDownloading nvidia_cusolver_cu12-11.6.1.9-py3-none-manylinux2014_x86_64.whl (127.9 MB)\n",
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m127.9/127.9 MB\u001b[0m \u001b[31m7.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hDownloading nvidia_cusparse_cu12-12.3.1.170-py3-none-manylinux2014_x86_64.whl (207.5 MB)\n",
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m207.5/207.5 MB\u001b[0m \u001b[31m5.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hDownloading nvidia_nvjitlink_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl (21.1 MB)\n",
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m21.1/21.1 MB\u001b[0m \u001b[31m98.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hDownloading colorlog-6.9.0-py3-none-any.whl (11 kB)\n",
+ "Downloading xxhash-3.5.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (194 kB)\n",
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m194.8/194.8 kB\u001b[0m \u001b[31m18.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hInstalling collected packages: xxhash, nvidia-nvjitlink-cu12, nvidia-curand-cu12, nvidia-cufft-cu12, nvidia-cuda-runtime-cu12, nvidia-cuda-nvrtc-cu12, nvidia-cuda-cupti-cu12, nvidia-cublas-cu12, fsspec, dill, colorlog, nvidia-cusparse-cu12, nvidia-cudnn-cu12, multiprocess, alembic, optuna, nvidia-cusolver-cu12, datasets, evaluate\n",
+ " Attempting uninstall: nvidia-nvjitlink-cu12\n",
+ " Found existing installation: nvidia-nvjitlink-cu12 12.5.82\n",
+ " Uninstalling nvidia-nvjitlink-cu12-12.5.82:\n",
+ " Successfully uninstalled nvidia-nvjitlink-cu12-12.5.82\n",
+ " Attempting uninstall: nvidia-curand-cu12\n",
+ " Found existing installation: nvidia-curand-cu12 10.3.6.82\n",
+ " Uninstalling nvidia-curand-cu12-10.3.6.82:\n",
+ " Successfully uninstalled nvidia-curand-cu12-10.3.6.82\n",
+ " Attempting uninstall: nvidia-cufft-cu12\n",
+ " Found existing installation: nvidia-cufft-cu12 11.2.3.61\n",
+ " Uninstalling nvidia-cufft-cu12-11.2.3.61:\n",
+ " Successfully uninstalled nvidia-cufft-cu12-11.2.3.61\n",
+ " Attempting uninstall: nvidia-cuda-runtime-cu12\n",
+ " Found existing installation: nvidia-cuda-runtime-cu12 12.5.82\n",
+ " Uninstalling nvidia-cuda-runtime-cu12-12.5.82:\n",
+ " Successfully uninstalled nvidia-cuda-runtime-cu12-12.5.82\n",
+ " Attempting uninstall: nvidia-cuda-nvrtc-cu12\n",
+ " Found existing installation: nvidia-cuda-nvrtc-cu12 12.5.82\n",
+ " Uninstalling nvidia-cuda-nvrtc-cu12-12.5.82:\n",
+ " Successfully uninstalled nvidia-cuda-nvrtc-cu12-12.5.82\n",
+ " Attempting uninstall: nvidia-cuda-cupti-cu12\n",
+ " Found existing installation: nvidia-cuda-cupti-cu12 12.5.82\n",
+ " Uninstalling nvidia-cuda-cupti-cu12-12.5.82:\n",
+ " Successfully uninstalled nvidia-cuda-cupti-cu12-12.5.82\n",
+ " Attempting uninstall: nvidia-cublas-cu12\n",
+ " Found existing installation: nvidia-cublas-cu12 12.5.3.2\n",
+ " Uninstalling nvidia-cublas-cu12-12.5.3.2:\n",
+ " Successfully uninstalled nvidia-cublas-cu12-12.5.3.2\n",
+ " Attempting uninstall: fsspec\n",
+ " Found existing installation: fsspec 2025.3.0\n",
+ " Uninstalling fsspec-2025.3.0:\n",
+ " Successfully uninstalled fsspec-2025.3.0\n",
+ " Attempting uninstall: nvidia-cusparse-cu12\n",
+ " Found existing installation: nvidia-cusparse-cu12 12.5.1.3\n",
+ " Uninstalling nvidia-cusparse-cu12-12.5.1.3:\n",
+ " Successfully uninstalled nvidia-cusparse-cu12-12.5.1.3\n",
+ " Attempting uninstall: nvidia-cudnn-cu12\n",
+ " Found existing installation: nvidia-cudnn-cu12 9.3.0.75\n",
+ " Uninstalling nvidia-cudnn-cu12-9.3.0.75:\n",
+ " Successfully uninstalled nvidia-cudnn-cu12-9.3.0.75\n",
+ " Attempting uninstall: nvidia-cusolver-cu12\n",
+ " Found existing installation: nvidia-cusolver-cu12 11.6.3.83\n",
+ " Uninstalling nvidia-cusolver-cu12-11.6.3.83:\n",
+ " Successfully uninstalled nvidia-cusolver-cu12-11.6.3.83\n",
+ "\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n",
+ "gcsfs 2025.3.0 requires fsspec==2025.3.0, but you have fsspec 2024.12.0 which is incompatible.\u001b[0m\u001b[31m\n",
+ "\u001b[0mSuccessfully installed alembic-1.15.2 colorlog-6.9.0 datasets-3.5.0 dill-0.3.8 evaluate-0.4.3 fsspec-2024.12.0 multiprocess-0.70.16 nvidia-cublas-cu12-12.4.5.8 nvidia-cuda-cupti-cu12-12.4.127 nvidia-cuda-nvrtc-cu12-12.4.127 nvidia-cuda-runtime-cu12-12.4.127 nvidia-cudnn-cu12-9.1.0.70 nvidia-cufft-cu12-11.2.1.3 nvidia-curand-cu12-10.3.5.147 nvidia-cusolver-cu12-11.6.1.9 nvidia-cusparse-cu12-12.3.1.170 nvidia-nvjitlink-cu12-12.4.127 optuna-4.2.1 xxhash-3.5.0\n",
+ "Collecting causal-conv1d\n",
+ " Downloading causal_conv1d-1.5.0.post8.tar.gz (9.4 kB)\n",
+ " Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
+ "Requirement already satisfied: torch in /usr/local/lib/python3.11/dist-packages (from causal-conv1d) (2.6.0+cu124)\n",
+ "Requirement already satisfied: packaging in /usr/local/lib/python3.11/dist-packages (from causal-conv1d) (24.2)\n",
+ "Collecting ninja (from causal-conv1d)\n",
+ " Downloading ninja-1.11.1.4-py3-none-manylinux_2_12_x86_64.manylinux2010_x86_64.whl.metadata (5.0 kB)\n",
+ "Requirement already satisfied: filelock in /usr/local/lib/python3.11/dist-packages (from torch->causal-conv1d) (3.18.0)\n",
+ "Requirement already satisfied: typing-extensions>=4.10.0 in /usr/local/lib/python3.11/dist-packages (from torch->causal-conv1d) (4.12.2)\n",
+ "Requirement already satisfied: networkx in /usr/local/lib/python3.11/dist-packages (from torch->causal-conv1d) (3.4.2)\n",
+ "Requirement already satisfied: jinja2 in /usr/local/lib/python3.11/dist-packages (from torch->causal-conv1d) (3.1.6)\n",
+ "Requirement already satisfied: fsspec in /usr/local/lib/python3.11/dist-packages (from torch->causal-conv1d) (2024.12.0)\n",
+ "Requirement already satisfied: nvidia-cuda-nvrtc-cu12==12.4.127 in /usr/local/lib/python3.11/dist-packages (from torch->causal-conv1d) (12.4.127)\n",
+ "Requirement already satisfied: nvidia-cuda-runtime-cu12==12.4.127 in /usr/local/lib/python3.11/dist-packages (from torch->causal-conv1d) (12.4.127)\n",
+ "Requirement already satisfied: nvidia-cuda-cupti-cu12==12.4.127 in /usr/local/lib/python3.11/dist-packages (from torch->causal-conv1d) (12.4.127)\n",
+ "Requirement already satisfied: nvidia-cudnn-cu12==9.1.0.70 in /usr/local/lib/python3.11/dist-packages (from torch->causal-conv1d) (9.1.0.70)\n",
+ "Requirement already satisfied: nvidia-cublas-cu12==12.4.5.8 in /usr/local/lib/python3.11/dist-packages (from torch->causal-conv1d) (12.4.5.8)\n",
+ "Requirement already satisfied: nvidia-cufft-cu12==11.2.1.3 in /usr/local/lib/python3.11/dist-packages (from torch->causal-conv1d) (11.2.1.3)\n",
+ "Requirement already satisfied: nvidia-curand-cu12==10.3.5.147 in /usr/local/lib/python3.11/dist-packages (from torch->causal-conv1d) (10.3.5.147)\n",
+ "Requirement already satisfied: nvidia-cusolver-cu12==11.6.1.9 in /usr/local/lib/python3.11/dist-packages (from torch->causal-conv1d) (11.6.1.9)\n",
+ "Requirement already satisfied: nvidia-cusparse-cu12==12.3.1.170 in /usr/local/lib/python3.11/dist-packages (from torch->causal-conv1d) (12.3.1.170)\n",
+ "Requirement already satisfied: nvidia-cusparselt-cu12==0.6.2 in /usr/local/lib/python3.11/dist-packages (from torch->causal-conv1d) (0.6.2)\n",
+ "Requirement already satisfied: nvidia-nccl-cu12==2.21.5 in /usr/local/lib/python3.11/dist-packages (from torch->causal-conv1d) (2.21.5)\n",
+ "Requirement already satisfied: nvidia-nvtx-cu12==12.4.127 in /usr/local/lib/python3.11/dist-packages (from torch->causal-conv1d) (12.4.127)\n",
+ "Requirement already satisfied: nvidia-nvjitlink-cu12==12.4.127 in /usr/local/lib/python3.11/dist-packages (from torch->causal-conv1d) (12.4.127)\n",
+ "Requirement already satisfied: triton==3.2.0 in /usr/local/lib/python3.11/dist-packages (from torch->causal-conv1d) (3.2.0)\n",
+ "Requirement already satisfied: sympy==1.13.1 in /usr/local/lib/python3.11/dist-packages (from torch->causal-conv1d) (1.13.1)\n",
+ "Requirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.11/dist-packages (from sympy==1.13.1->torch->causal-conv1d) (1.3.0)\n",
+ "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.11/dist-packages (from jinja2->torch->causal-conv1d) (3.0.2)\n",
+ "Downloading ninja-1.11.1.4-py3-none-manylinux_2_12_x86_64.manylinux2010_x86_64.whl (422 kB)\n",
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m422.8/422.8 kB\u001b[0m \u001b[31m28.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hBuilding wheels for collected packages: causal-conv1d\n",
+ " Building wheel for causal-conv1d (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
+ " Created wheel for causal-conv1d: filename=causal_conv1d-1.5.0.post8-cp311-cp311-linux_x86_64.whl size=103984203 sha256=f1bff4a48017e4a1b2f18a84b3d881df7de2cff8cc9dbbc0c53c9d5df233359b\n",
+ " Stored in directory: /root/.cache/pip/wheels/ba/be/7d/2b11e629de32101f0801e2c62d5a26ff09802c391561a3e3eb\n",
+ "Successfully built causal-conv1d\n",
+ "Installing collected packages: ninja, causal-conv1d\n",
+ "Successfully installed causal-conv1d-1.5.0.post8 ninja-1.11.1.4\n",
+ "Collecting mamba-ssm\n",
+ " Downloading mamba_ssm-2.2.4.tar.gz (91 kB)\n",
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m91.8/91.8 kB\u001b[0m \u001b[31m9.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25h 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",
+ "Requirement already satisfied: torch in /usr/local/lib/python3.11/dist-packages (from mamba-ssm) (2.6.0+cu124)\n",
+ "Requirement already satisfied: ninja in /usr/local/lib/python3.11/dist-packages (from mamba-ssm) (1.11.1.4)\n",
+ "Requirement already satisfied: einops in /usr/local/lib/python3.11/dist-packages (from mamba-ssm) (0.8.1)\n",
+ "Requirement already satisfied: transformers in /usr/local/lib/python3.11/dist-packages (from mamba-ssm) (4.50.0)\n",
+ "Requirement already satisfied: packaging in /usr/local/lib/python3.11/dist-packages (from mamba-ssm) (24.2)\n",
+ "Requirement already satisfied: setuptools>=61.0.0 in /usr/local/lib/python3.11/dist-packages (from mamba-ssm) (75.1.0)\n",
+ "Requirement already satisfied: filelock in /usr/local/lib/python3.11/dist-packages (from torch->mamba-ssm) (3.18.0)\n",
+ "Requirement already satisfied: typing-extensions>=4.10.0 in /usr/local/lib/python3.11/dist-packages (from torch->mamba-ssm) (4.12.2)\n",
+ "Requirement already satisfied: networkx in /usr/local/lib/python3.11/dist-packages (from torch->mamba-ssm) (3.4.2)\n",
+ "Requirement already satisfied: jinja2 in /usr/local/lib/python3.11/dist-packages (from torch->mamba-ssm) (3.1.6)\n",
+ "Requirement already satisfied: fsspec in /usr/local/lib/python3.11/dist-packages (from torch->mamba-ssm) (2024.12.0)\n",
+ "Requirement already satisfied: nvidia-cuda-nvrtc-cu12==12.4.127 in /usr/local/lib/python3.11/dist-packages (from torch->mamba-ssm) (12.4.127)\n",
+ "Requirement already satisfied: nvidia-cuda-runtime-cu12==12.4.127 in /usr/local/lib/python3.11/dist-packages (from torch->mamba-ssm) (12.4.127)\n",
+ "Requirement already satisfied: nvidia-cuda-cupti-cu12==12.4.127 in /usr/local/lib/python3.11/dist-packages (from torch->mamba-ssm) (12.4.127)\n",
+ "Requirement already satisfied: nvidia-cudnn-cu12==9.1.0.70 in /usr/local/lib/python3.11/dist-packages (from torch->mamba-ssm) (9.1.0.70)\n",
+ "Requirement already satisfied: nvidia-cublas-cu12==12.4.5.8 in /usr/local/lib/python3.11/dist-packages (from torch->mamba-ssm) (12.4.5.8)\n",
+ "Requirement already satisfied: nvidia-cufft-cu12==11.2.1.3 in /usr/local/lib/python3.11/dist-packages (from torch->mamba-ssm) (11.2.1.3)\n",
+ "Requirement already satisfied: nvidia-curand-cu12==10.3.5.147 in /usr/local/lib/python3.11/dist-packages (from torch->mamba-ssm) (10.3.5.147)\n",
+ "Requirement already satisfied: nvidia-cusolver-cu12==11.6.1.9 in /usr/local/lib/python3.11/dist-packages (from torch->mamba-ssm) (11.6.1.9)\n",
+ "Requirement already satisfied: nvidia-cusparse-cu12==12.3.1.170 in /usr/local/lib/python3.11/dist-packages (from torch->mamba-ssm) (12.3.1.170)\n",
+ "Requirement already satisfied: nvidia-cusparselt-cu12==0.6.2 in /usr/local/lib/python3.11/dist-packages (from torch->mamba-ssm) (0.6.2)\n",
+ "Requirement already satisfied: nvidia-nccl-cu12==2.21.5 in /usr/local/lib/python3.11/dist-packages (from torch->mamba-ssm) (2.21.5)\n",
+ "Requirement already satisfied: nvidia-nvtx-cu12==12.4.127 in /usr/local/lib/python3.11/dist-packages (from torch->mamba-ssm) (12.4.127)\n",
+ "Requirement already satisfied: nvidia-nvjitlink-cu12==12.4.127 in /usr/local/lib/python3.11/dist-packages (from torch->mamba-ssm) (12.4.127)\n",
+ "Requirement already satisfied: triton==3.2.0 in /usr/local/lib/python3.11/dist-packages (from torch->mamba-ssm) (3.2.0)\n",
+ "Requirement already satisfied: sympy==1.13.1 in /usr/local/lib/python3.11/dist-packages (from torch->mamba-ssm) (1.13.1)\n",
+ "Requirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.11/dist-packages (from sympy==1.13.1->torch->mamba-ssm) (1.3.0)\n",
+ "Requirement already satisfied: huggingface-hub<1.0,>=0.26.0 in /usr/local/lib/python3.11/dist-packages (from transformers->mamba-ssm) (0.29.3)\n",
+ "Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.11/dist-packages (from transformers->mamba-ssm) (2.0.2)\n",
+ "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.11/dist-packages (from transformers->mamba-ssm) (6.0.2)\n",
+ "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.11/dist-packages (from transformers->mamba-ssm) (2024.11.6)\n",
+ "Requirement already satisfied: requests in /usr/local/lib/python3.11/dist-packages (from transformers->mamba-ssm) (2.32.3)\n",
+ "Requirement already satisfied: tokenizers<0.22,>=0.21 in /usr/local/lib/python3.11/dist-packages (from transformers->mamba-ssm) (0.21.1)\n",
+ "Requirement already satisfied: safetensors>=0.4.3 in /usr/local/lib/python3.11/dist-packages (from transformers->mamba-ssm) (0.5.3)\n",
+ "Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.11/dist-packages (from transformers->mamba-ssm) (4.67.1)\n",
+ "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.11/dist-packages (from jinja2->torch->mamba-ssm) (3.0.2)\n",
+ "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.11/dist-packages (from requests->transformers->mamba-ssm) (3.4.1)\n",
+ "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.11/dist-packages (from requests->transformers->mamba-ssm) (3.10)\n",
+ "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.11/dist-packages (from requests->transformers->mamba-ssm) (2.3.0)\n",
+ "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.11/dist-packages (from requests->transformers->mamba-ssm) (2025.1.31)\n",
+ "Building wheels for collected packages: mamba-ssm\n",
+ " Building wheel for mamba-ssm (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
+ " Created wheel for mamba-ssm: filename=mamba_ssm-2.2.4-cp311-cp311-linux_x86_64.whl size=323672993 sha256=8a0be01153fa30727a9e69024fbe061eb92c7ba4416d2049c5fc3107ed91d852\n",
+ " Stored in directory: /root/.cache/pip/wheels/2a/5e/64/cfcb5dfe4f854944456e031c34953dc872af1ad7c206145d4a\n",
+ "Successfully built mamba-ssm\n",
+ "Installing collected packages: mamba-ssm\n",
+ "Successfully installed mamba-ssm-2.2.4\n",
+ "Requirement already satisfied: huggingface_hub in /usr/local/lib/python3.11/dist-packages (0.29.3)\n",
+ "Requirement already satisfied: filelock in /usr/local/lib/python3.11/dist-packages (from huggingface_hub) (3.18.0)\n",
+ "Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.11/dist-packages (from huggingface_hub) (2024.12.0)\n",
+ "Requirement already satisfied: packaging>=20.9 in /usr/local/lib/python3.11/dist-packages (from huggingface_hub) (24.2)\n",
+ "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.11/dist-packages (from huggingface_hub) (6.0.2)\n",
+ "Requirement already satisfied: requests in /usr/local/lib/python3.11/dist-packages (from huggingface_hub) (2.32.3)\n",
+ "Requirement already satisfied: tqdm>=4.42.1 in /usr/local/lib/python3.11/dist-packages (from huggingface_hub) (4.67.1)\n",
+ "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.11/dist-packages (from huggingface_hub) (4.12.2)\n",
+ "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.11/dist-packages (from requests->huggingface_hub) (3.4.1)\n",
+ "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.11/dist-packages (from requests->huggingface_hub) (3.10)\n",
+ "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.11/dist-packages (from requests->huggingface_hub) (2.3.0)\n",
+ "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.11/dist-packages (from requests->huggingface_hub) (2025.1.31)\n"
+ ]
+ }
+ ],
+ "source": [
+ "# install packages and unzip datasets\n",
+ "!pip install datasets evaluate accelerate optuna\n",
+ "!pip install causal-conv1d\n",
+ "!pip install mamba-ssm\n",
+ "!pip install --upgrade huggingface_hub"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "# slightly hacky method for gpu compatibility\n",
+ "!export LC_ALL=\"en_US.UTF-8\"\n",
+ "!export LD_LIBRARY_PATH=\"/usr/lib64-nvidia\"\n",
+ "!export LIBRARY_PATH=\"/usr/local/cuda/lib64/stubs\"\n",
+ "!ldconfig /usr/lib64-nvidia"
+ ],
+ "metadata": {
+ "collapsed": true,
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "2qmFp0EpxANa",
+ "outputId": "3ee01976-979d-4859-e0f2-7fccbb8eb5df"
+ },
+ "execution_count": 6,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "/sbin/ldconfig.real: /usr/local/lib/libtbb.so.12 is not a symbolic link\n",
+ "\n",
+ "/sbin/ldconfig.real: /usr/local/lib/libur_loader.so.0 is not a symbolic link\n",
+ "\n",
+ "/sbin/ldconfig.real: /usr/local/lib/libur_adapter_opencl.so.0 is not a symbolic link\n",
+ "\n",
+ "/sbin/ldconfig.real: /usr/local/lib/libtbbbind_2_0.so.3 is not a symbolic link\n",
+ "\n",
+ "/sbin/ldconfig.real: /usr/local/lib/libhwloc.so.15 is not a symbolic link\n",
+ "\n",
+ "/sbin/ldconfig.real: /usr/local/lib/libtbbbind.so.3 is not a symbolic link\n",
+ "\n",
+ "/sbin/ldconfig.real: /usr/local/lib/libtcm_debug.so.1 is not a symbolic link\n",
+ "\n",
+ "/sbin/ldconfig.real: /usr/local/lib/libtbbmalloc.so.2 is not a symbolic link\n",
+ "\n",
+ "/sbin/ldconfig.real: /usr/local/lib/libur_adapter_level_zero.so.0 is not a symbolic link\n",
+ "\n",
+ "/sbin/ldconfig.real: /usr/local/lib/libtbbmalloc_proxy.so.2 is not a symbolic link\n",
+ "\n",
+ "/sbin/ldconfig.real: /usr/local/lib/libumf.so.0 is not a symbolic link\n",
+ "\n",
+ "/sbin/ldconfig.real: /usr/local/lib/libtbbbind_2_5.so.3 is not a symbolic link\n",
+ "\n",
+ "/sbin/ldconfig.real: /usr/local/lib/libtcm.so.1 is not a symbolic link\n",
+ "\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "# import all necessary libraries\n",
+ "import os\n",
+ "import random\n",
+ "import json\n",
+ "import torch\n",
+ "import torch.nn as nn\n",
+ "from collections import namedtuple\n",
+ "from dataclasses import dataclass, field, asdict\n",
+ "from mamba_ssm.models.mixer_seq_simple import MambaLMHeadModel\n",
+ "from mamba_ssm.utils.hf import load_config_hf, load_state_dict_hf\n",
+ "\n",
+ "import evaluate\n",
+ "import numpy as np\n",
+ "import pandas as pd\n",
+ "from datasets import load_dataset\n",
+ "from transformers import Trainer\n",
+ "from transformers import AutoTokenizer, TrainingArguments\n",
+ "\n",
+ "from huggingface_hub import login, HfApi, notebook_login\n",
+ "import os\n",
+ "import json\n",
+ "from google.colab import userdata\n",
+ "HF_TOKEN=userdata.get('HF_TOKEN_WRITE')\n",
+ "login(token=HF_TOKEN)"
+ ],
+ "metadata": {
+ "id": "mHOT9sURxGCw"
+ },
+ "execution_count": 7,
+ "outputs": []
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "# Training"
+ ],
+ "metadata": {
+ "id": "OCRRIkPxxivI"
+ }
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "## References and Overview"
+ ],
+ "metadata": {
+ "id": "TOsxnf2GxSPP"
+ }
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "https://github.com/state-spaces/mamba\n",
+ "\n",
+ "https://huggingface.co/state-spaces?sort_models=created#models\n",
+ "\n",
+ "https://github.com/getorca/mamba_for_sequence_classification\n",
+ "\n",
+ "https://arxiv.org/pdf/2312.00752"
+ ],
+ "metadata": {
+ "id": "agsMILlIXaCf"
+ }
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "1. **Tokenization and Input Formatting:** \n",
+ " - **Tokenize:** Break down both the premise and hypothesis into individual tokens. \n",
+ " - **Special Delimiter:** Insert a special token (like [SEP] or a custom delimiter) between the premise and hypothesis to clearly separate them. \n",
+ " - **Padding/Truncation:** Adjust the sequence lengths to ensure consistency across your dataset.\n",
+ "\n",
+ "2. **Embedding:** \n",
+ " - **Convert Tokens:** Map each token to a dense vector using either pre-trained embeddings (e.g., GloVe) or embeddings learned during training.\n",
+ "\n",
+ "3. **Passing Through the Pretrained Mamba SSM:** \n",
+ " - **Input to SSM:** Feed the concatenated and embedded sequence (premise + delimiter + hypothesis) into the pretrained Mamba SSM. \n",
+ " - **Contextual Representations:** The SSM outputs a sequence of contextualized token representations, where each token's vector now reflects the context of the entire input.\n",
+ "\n",
+ "4. **Aggregation of Token-wise Outputs:** \n",
+ " - **Fixed-Size Representation:** Aggregate the token-level outputs into a single vector that summarizes the sequence. \n",
+ " - **Pooling Methods:** You might use mean pooling, max pooling, or simply select the representation corresponding to a special token (similar to BERT’s [CLS] token).\n",
+ "\n",
+ "5. **Classification Head:** \n",
+ " - **Fully Connected Layers:** Pass the aggregated representation through one or more linear layers that serve as a classification head. \n",
+ " - **Activation Function:** Apply an activation function (e.g., softmax for multiclass, sigmoid for binary classification) to convert the raw logits into probabilities.\n",
+ "\n",
+ "6. **Prediction:** \n",
+ " - **Binary Decision:** Based on the output probabilities, determine whether the hypothesis is entailed by the premise (entailment vs. non-entailment). \n",
+ " - **Training:** Fine-tune the entire model (both the pretrained Mamba SSM and the classification head) on your NLI dataset using a suitable loss function like cross-entropy loss.\n"
+ ],
+ "metadata": {
+ "id": "OidUHyT0ZHXt"
+ }
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "## Custom Mamba Classes"
+ ],
+ "metadata": {
+ "id": "dlmPjXCHxbRG"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "# define model config\n",
+ "@dataclass\n",
+ "class MambaConfig:\n",
+ " d_model: int = 2560\n",
+ " d_intermediate: int = 0 # from error when loading pretrained\n",
+ " n_layer: int = 64\n",
+ " vocab_size: int = 50277\n",
+ " ssm_cfg: dict = field(default_factory=dict)\n",
+ " attn_layer_idx = []\n",
+ " attn_cfg = {}\n",
+ " rms_norm: bool = True\n",
+ " residual_in_fp32: bool = True\n",
+ " fused_add_norm: bool = True\n",
+ " pad_vocab_size_multiple: int = 8\n",
+ " tie_embeddings = True\n",
+ "\n",
+ " def to_json_string(self):\n",
+ " return json.dumps(asdict(self))\n",
+ "\n",
+ " def to_dict(self):\n",
+ " return asdict(self)"
+ ],
+ "metadata": {
+ "id": "t51d_k_Mxepp"
+ },
+ "execution_count": 26,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "# use a linear layer to classify d_model dimensions into num_classes classes\n",
+ "# https://arxiv.org/pdf/2312.00752 source for \"improved recipe\"\n",
+ "class MambaClassificationHead(nn.Module):\n",
+ " def __init__(self, d_model, num_classes, **kwargs):\n",
+ " super(MambaClassificationHead, self).__init__()\n",
+ " self.classification_head = nn.Linear(d_model, num_classes, **kwargs)\n",
+ "\n",
+ " def forward(self, hidden_states):\n",
+ " return self.classification_head(hidden_states)"
+ ],
+ "metadata": {
+ "id": "KFB0E_JgyC5q"
+ },
+ "execution_count": 27,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "# define our custom version of Mamba for text classification\n",
+ "class MambaTextClassification(MambaLMHeadModel):\n",
+ " def __init__(\n",
+ " self,\n",
+ " config: MambaConfig,\n",
+ " initializer_cfg=None,\n",
+ " device=None,\n",
+ " dtype=None,\n",
+ " ) -> None:\n",
+ " super().__init__(config, initializer_cfg, device, dtype)\n",
+ "\n",
+ " # create a classifier head with d_model embedding dimensions and 2 classes (binary)\n",
+ " self.classification_head = MambaClassificationHead(d_model=config.d_model, num_classes=2)\n",
+ "\n",
+ " del self.lm_head\n",
+ "\n",
+ " def forward(self, input_ids, attention_mask=None, labels=None):\n",
+ " # pass input_ids through the original model to get hidden_states.\n",
+ " hidden_states = self.backbone(input_ids)\n",
+ "\n",
+ " # take the average of hidden_states in the second dimension to create a representative [CLS] feature\n",
+ " mean_hidden_states = hidden_states.mean(dim=1)\n",
+ "\n",
+ " # pass mean_hidden_states through the classifier to get logits.\n",
+ " logits = self.classification_head(mean_hidden_states)\n",
+ "\n",
+ " if labels is None:\n",
+ " ClassificationOutput = namedtuple(\"ClassificationOutput\", [\"logits\"])\n",
+ " return ClassificationOutput(logits=logits)\n",
+ " else:\n",
+ " ClassificationOutput = namedtuple(\"ClassificationOutput\", [\"loss\", \"logits\"])\n",
+ "\n",
+ " # use the CrossEntropyLoss loss function to calculate the loss\n",
+ " loss_fct = nn.CrossEntropyLoss()\n",
+ " loss = loss_fct(logits, labels)\n",
+ "\n",
+ " return ClassificationOutput(loss=loss, logits=logits)\n",
+ "\n",
+ " def predict(self, text, tokenizer, id2label=None):\n",
+ " input_ids = torch.tensor(tokenizer(text)['input_ids'], device='cuda')[None]\n",
+ " with torch.no_grad():\n",
+ " logits = self.forward(input_ids).logits[0]\n",
+ " label = np.argmax(logits.cpu().numpy())\n",
+ "\n",
+ " if id2label is not None:\n",
+ " return id2label[label]\n",
+ " else:\n",
+ " return label\n",
+ "\n",
+ " @classmethod\n",
+ " def from_pretrained(cls, pretrained_model_name, device=None, dtype=None, **kwargs):\n",
+ " # load configuration from previously trained model\n",
+ " config_data = load_config_hf(pretrained_model_name)\n",
+ " config = MambaConfig(**config_data)\n",
+ "\n",
+ " # Iiitialize the model from the configuration and pass it to the desired device and data type\n",
+ " model = cls(config, device=device, dtype=dtype, **kwargs)\n",
+ "\n",
+ " # load the previously trained model state.\n",
+ " model_state_dict = load_state_dict_hf(pretrained_model_name, device=device, dtype=dtype)\n",
+ " model.load_state_dict(model_state_dict, strict=False)\n",
+ "\n",
+ " # print out the newly initialized embedding parameters\n",
+ " print(\"Newly initialized embedding:\", set(model.state_dict().keys()) - set(model_state_dict.keys()))\n",
+ " return model"
+ ],
+ "metadata": {
+ "id": "emSRPdjLyjYl"
+ },
+ "execution_count": 28,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "# define a MambaTrainer subclass that inherits from the Trainer class\n",
+ "class MambaTrainer(Trainer):\n",
+ "\n",
+ " # Define a compute_loss function to compute the loss function during training.\n",
+ " def compute_loss(self, model, inputs, return_outputs=False, **kwargs):\n",
+ " # Get input_ids and labels from inputs.\n",
+ " input_ids = inputs.pop(\"input_ids\")\n",
+ " labels = inputs.pop('labels')\n",
+ "\n",
+ " # Call the model's forward function with input_ids and labels to get the results.\n",
+ " outputs = model(input_ids=input_ids, labels=labels)\n",
+ "\n",
+ " # Get the loss value from the model's output.\n",
+ " loss = outputs.loss\n",
+ "\n",
+ " # Return both loss and outputs if return_outputs is True, otherwise return only loss.\n",
+ " return (loss, outputs) if return_outputs else loss\n",
+ "\n",
+ " # Define a save_model function to save the model during training.\n",
+ " def save_model(self, output_dir = None, _internal_call = False):\n",
+ " # Check if the save directory is not specified, use the default directory from the 'args' argument.\n",
+ " if output_dir is None:\n",
+ " output_dir = self.args.output_dir\n",
+ "\n",
+ " # If the output directory does not exist, create it.\n",
+ " if not os.path.exists(output_dir):\n",
+ " os.makedirs(output_dir)\n",
+ "\n",
+ " # Save the state of the PyTorch model to the file 'pytorch_model.bin' in the output directory.\n",
+ " torch.save(self.model.state_dict(), f\"{output_dir}/pytorch_model.bin\")\n",
+ "\n",
+ " # Save the state of the tokenizer to the output directory.\n",
+ " self.tokenizer.save_pretrained(output_dir)\n",
+ "\n",
+ " # Save the model configuration to the file 'config.json' in the output directory.\n",
+ " with open(f'{output_dir}/config.json', 'w') as f:\n",
+ " json.dump(self.model.config.to_dict(), f)"
+ ],
+ "metadata": {
+ "id": "-PDzsHG12z8k"
+ },
+ "execution_count": 29,
+ "outputs": []
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "## Load Model and Tokenizer"
+ ],
+ "metadata": {
+ "id": "wC4RpyvKuQMM"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "# load the Mamba model from the pretrained model\n",
+ "model = MambaTextClassification.from_pretrained(\"state-spaces/mamba-130m\")\n",
+ "model.to(\"cuda\")\n",
+ "\n",
+ "# load the Mamba model tokenizer (used for Mamba pretraining)\n",
+ "tokenizer = AutoTokenizer.from_pretrained(\"EleutherAI/gpt-neox-20b\")\n",
+ "tokenizer.pad_token_id = tokenizer.eos_token_id"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 0,
+ "referenced_widgets": [
+ "b0037ea804754052a7ccee9fc200b9b2",
+ "5383fef7471a4c1cb589b8787f550c9e",
+ "d8804cab179c4b75949646a97cd2c449",
+ "ec72bc3d05694095b094ddc7b19446ff",
+ "411da49080b641da81c4d38b22f274ce",
+ "aee9b3f44600433985b889950f6f4ea8",
+ "c6eb487f7ef946109ac3f42a47295c9b",
+ "82239355438e4e828008fc8c0595842a",
+ "d3bc593a5dc441e0b0df6224fd65bcba",
+ "0b42258e07974e5eb82ca3642499a0d0",
+ "85407f7ff7ec4bfd851a76f7f5b610fc",
+ "832774cf2a8245829ed6ce775c6fc404",
+ "f6a02dbfe5824ff4a5adba539277bfea",
+ "ddadb9a42e774eff94c7f799c1d73ca0",
+ "6ff246f616db4b39b9b95a5d69da69e3",
+ "39a6c048558e45d19fe888aeeacbb94c",
+ "9987a82c3caa4d75b27b3674bc683bbd",
+ "eb246ae00fb941cb8ba785e97c2ad216",
+ "af6f74dc6bf24b5d984075c947409d72",
+ "d82692dd1d1b49f1bb303ef5ac03f3e1",
+ "fdfba7a6ad0e4fc99ab9d96df7641f81",
+ "57bf8324d4a5466580121ec5cb3c2e81",
+ "759691faf9b544f28780bb75b10a9f6c",
+ "24b574b637484cea93e94bdcd24b6458",
+ "d7ca103ebbd44dd4a25f39597b021175",
+ "8053285e39414e71ba5efc87f82769a8",
+ "a75ebc64fd3646dea8269ac628feec91",
+ "59dd5c975c244a28997dae102da29094",
+ "b6dbb69723cf4a179893656c4424e490",
+ "1bf82ba8430b4002bfdff0bb6268ab29",
+ "81ea42372300473ab9e655ab509523a3",
+ "66303ad5b1ea479fa89b5ab8517f2087",
+ "564b6a7ab5054a1986e709838c7f9d70",
+ "f798c29f3989498a92cd1503c8e74081",
+ "343b0c62542d4f03837ffa1bf698411c",
+ "37a9419c3002433b8911e59b3aa836a2",
+ "bb3b1bf5f87a4fcfa8dbcc2ae6d8a25b",
+ "113cb61d327b43cd83e5a49ac86d0ce9",
+ "7dae014d0fe44407b41063065723beed",
+ "3c81bc13902b440b80536e50171ee46f",
+ "79d5c54978ec4813b874008d1478f57f",
+ "7226a36f162e445d9de307b06b38b4ef",
+ "7a1d20eb8e4f41a3a907bad0bd20ab0e",
+ "170188f3d113488abd6e543c55df1b47",
+ "250e830ac7744f2a98036336e7b2209d",
+ "3b828f8df1aa451e85b1fd46af287f3f",
+ "0f62bfbaeac5452dbc80db4e4f4602c7",
+ "cc987c2d93b4490cad4f1d4b1651033f",
+ "52f35f0244d7447bac9d6c45caf3eddd",
+ "335b95d6a6234f88928354f7965c1848",
+ "29d1c5a3160c4b748128dfd0969b4c0a",
+ "d6427d07681a4cffb70d05804a6b3537",
+ "a63f8f572d854fb4978069dce27e4aba",
+ "9abc05f2f42b490db11ffa60f5d738ad",
+ "649b13622d974391be32dad91355f449",
+ "3aa1f8a964854593b26694ea2d1f499a",
+ "4ae1cd49f9a14c069ea6e0928ae0bc15",
+ "efd4bddaefa340d1a8bc7fd1ec3f3fb1",
+ "fd103f1ddc2c4cc5a9ff898c949f0d2a",
+ "88014f62fd5d463787299be68a730c85",
+ "523ce69c303d42a9b506f7e8d536acdd",
+ "f3a906b9f250411cb14166849168d9ae",
+ "8fe8bac962664404816553cdf23a6854",
+ "ac7a1903abc04f29aec7ca3ea41a4aed",
+ "e3373882cae543c79e944e2d3044887c",
+ "701d936e338d4b8e8929656e0d830d66",
+ "7c588426535244139cb0b261eb1322bb",
+ "e657136eeffc4c6db36649c427a7f7a1",
+ "d792cd3291cc4837a73783dc8d3e840c",
+ "4b460655df9646b5b6de2021945871c5",
+ "00d9a623b2414c94bd28466e79da2f2f",
+ "1c51232afed8478090d191b3d18f9ba4",
+ "28b2d5a2119b42f78318377cfc3b53c5",
+ "1e04d06db8f84b7abbb5d404d60ee2b1",
+ "3c065f7cc3af470b8726ff75027c2fae",
+ "16ad8e9095a94200aded8c605c9e174d",
+ "9410258eeebe401ca2a496eea21ed40f"
+ ]
+ },
+ "id": "UgwsiuMtzoIo",
+ "outputId": "2cd32d8e-a037-46e5-fa00-b2ecb443fe42"
+ },
+ "execution_count": 30,
+ "outputs": [
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/plain": [
+ "config.json: 0%| | 0.00/199 [00:00"
+ ],
+ "text/html": [
+ "\n",
+ " \n",
+ " \n",
+ "
\n",
+ " [30540/30540 1:17:36, Epoch 5/5]\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | Epoch | \n",
+ " Training Loss | \n",
+ " Validation Loss | \n",
+ " Accuracy | \n",
+ " Mcc | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " | 1 | \n",
+ " 0.476900 | \n",
+ " 0.605887 | \n",
+ " 0.808321 | \n",
+ " 0.616186 | \n",
+ "
\n",
+ " \n",
+ " | 2 | \n",
+ " 0.336500 | \n",
+ " 0.752999 | \n",
+ " 0.823180 | \n",
+ " 0.645671 | \n",
+ "
\n",
+ " \n",
+ " | 3 | \n",
+ " 0.174400 | \n",
+ " 0.692573 | \n",
+ " 0.848440 | \n",
+ " 0.696585 | \n",
+ "
\n",
+ " \n",
+ " | 4 | \n",
+ " 0.008400 | \n",
+ " 0.920146 | \n",
+ " 0.843982 | \n",
+ " 0.687377 | \n",
+ "
\n",
+ " \n",
+ " | 5 | \n",
+ " 0.000100 | \n",
+ " 1.003138 | \n",
+ " 0.846954 | \n",
+ " 0.693309 | \n",
+ "
\n",
+ " \n",
+ "
"
+ ]
+ },
+ "metadata": {}
+ },
+ {
+ "output_type": "stream",
+ "name": "stderr",
+ "text": [
+ "Trainer.tokenizer is now deprecated. You should use Trainer.processing_class instead.\n",
+ "Trainer.tokenizer is now deprecated. You should use Trainer.processing_class instead.\n",
+ "Trainer.tokenizer is now deprecated. You should use Trainer.processing_class instead.\n",
+ "Trainer.tokenizer is now deprecated. You should use Trainer.processing_class instead.\n",
+ "Trainer.tokenizer is now deprecated. You should use Trainer.processing_class instead.\n"
+ ]
+ },
+ {
+ "output_type": "execute_result",
+ "data": {
+ "text/plain": [
+ "TrainOutput(global_step=30540, training_loss=0.2358197668629472, metrics={'train_runtime': 4661.9881, 'train_samples_per_second': 26.203, 'train_steps_per_second': 6.551, 'total_flos': 0.0, 'train_loss': 0.2358197668629472, 'epoch': 5.0})"
+ ]
+ },
+ "metadata": {},
+ "execution_count": 39
+ }
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "## Save Model and Dev Predictions"
+ ],
+ "metadata": {
+ "id": "y1iQR7Viupdn"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "# save the trained model locally, to upload to huggingface manually\n",
+ "model.save_pretrained(\"mamba_nli_ensemble\")\n",
+ "tokenizer.save_pretrained(\"mamba_nli_ensemble\")\n",
+ "\n",
+ "!zip -r mamba_nli_ensemble.zip mamba_nli_ensemble\n",
+ "from google.colab import files\n",
+ "files.download(\"mamba_nli_ensemble.zip\")"
+ ],
+ "metadata": {
+ "id": "mWVVCgwkLuzW",
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 312
+ },
+ "outputId": "90f84583-0af9-4f1d-8c9e-7219944093e4"
+ },
+ "execution_count": 40,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ " adding: mamba_nli_ensemble/ (stored 0%)\n",
+ " adding: mamba_nli_ensemble/special_tokens_map.json (deflated 75%)\n",
+ " adding: mamba_nli_ensemble/tokenizer_config.json (deflated 92%)\n",
+ " adding: mamba_nli_ensemble/checkpoint-6108/ (stored 0%)\n",
+ " adding: mamba_nli_ensemble/checkpoint-6108/scheduler.pt (deflated 56%)\n",
+ " adding: mamba_nli_ensemble/checkpoint-6108/special_tokens_map.json (deflated 75%)\n",
+ " adding: mamba_nli_ensemble/checkpoint-6108/tokenizer_config.json (deflated 92%)\n",
+ " adding: mamba_nli_ensemble/checkpoint-6108/pytorch_model.bin (deflated 7%)\n",
+ " adding: mamba_nli_ensemble/checkpoint-6108/tokenizer.json (deflated 81%)\n",
+ " adding: mamba_nli_ensemble/checkpoint-6108/config.json (deflated 32%)\n",
+ " adding: mamba_nli_ensemble/checkpoint-6108/optimizer.pt (deflated 23%)\n",
+ " adding: mamba_nli_ensemble/checkpoint-6108/rng_state.pth (deflated 25%)\n",
+ " adding: mamba_nli_ensemble/checkpoint-6108/trainer_state.json (deflated 76%)\n",
+ " adding: mamba_nli_ensemble/pytorch_model.bin (deflated 7%)\n",
+ " adding: mamba_nli_ensemble/tokenizer.json (deflated 81%)\n",
+ " adding: mamba_nli_ensemble/config.json (deflated 39%)\n"
+ ]
+ },
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/plain": [
+ ""
+ ],
+ "application/javascript": [
+ "\n",
+ " async function download(id, filename, size) {\n",
+ " if (!google.colab.kernel.accessAllowed) {\n",
+ " return;\n",
+ " }\n",
+ " const div = document.createElement('div');\n",
+ " const label = document.createElement('label');\n",
+ " label.textContent = `Downloading \"${filename}\": `;\n",
+ " div.appendChild(label);\n",
+ " const progress = document.createElement('progress');\n",
+ " progress.max = size;\n",
+ " div.appendChild(progress);\n",
+ " document.body.appendChild(div);\n",
+ "\n",
+ " const buffers = [];\n",
+ " let downloaded = 0;\n",
+ "\n",
+ " const channel = await google.colab.kernel.comms.open(id);\n",
+ " // Send a message to notify the kernel that we're ready.\n",
+ " channel.send({})\n",
+ "\n",
+ " for await (const message of channel.messages) {\n",
+ " // Send a message to notify the kernel that we're ready.\n",
+ " channel.send({})\n",
+ " if (message.buffers) {\n",
+ " for (const buffer of message.buffers) {\n",
+ " buffers.push(buffer);\n",
+ " downloaded += buffer.byteLength;\n",
+ " progress.value = downloaded;\n",
+ " }\n",
+ " }\n",
+ " }\n",
+ " const blob = new Blob(buffers, {type: 'application/binary'});\n",
+ " const a = document.createElement('a');\n",
+ " a.href = window.URL.createObjectURL(blob);\n",
+ " a.download = filename;\n",
+ " div.appendChild(a);\n",
+ " a.click();\n",
+ " div.remove();\n",
+ " }\n",
+ " "
+ ]
+ },
+ "metadata": {}
+ },
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/plain": [
+ ""
+ ],
+ "application/javascript": [
+ "download(\"download_8d468879-adbc-40a5-a05b-04b979f4d52d\", \"mamba_nli_ensemble.zip\", 1757902243)"
+ ]
+ },
+ "metadata": {}
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "# make predictions on validation dataset\n",
+ "outputs = trainer.predict(dev_dataset)\n",
+ "print(outputs.metrics)\n",
+ "\n",
+ "# process predictions to .csv.predict.zip file\n",
+ "preds = outputs.predictions\n",
+ "predicted_class = np.argmax(preds, axis=1)\n",
+ "\n",
+ "df = pd.DataFrame({'prediction': predicted_class})\n",
+ "df.to_csv(\"predictions.csv.predict\", index=False)\n",
+ "!zip -r predictions.csv.predict.zip predictions.csv.predict\n",
+ "from google.colab import files\n",
+ "files.download(\"predictions.csv.predict.zip\")"
+ ],
+ "metadata": {
+ "id": "iKt48_a94vu6",
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 54
+ },
+ "outputId": "903ce700-e6c7-4537-ce3c-ffab0bf78d2d"
+ },
+ "execution_count": 41,
+ "outputs": [
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/plain": [
+ ""
+ ],
+ "text/html": []
+ },
+ "metadata": {}
+ },
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "{'test_loss': 0.5712032318115234, 'test_accuracy': 0.8249703087885986, 'test_mcc': 0.6494663772050464, 'test_runtime': 53.2421, 'test_samples_per_second': 126.516, 'test_steps_per_second': 7.907}\n",
+ "updating: predictions.csv.predict (deflated 90%)\n"
+ ]
+ },
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/plain": [
+ ""
+ ],
+ "application/javascript": [
+ "\n",
+ " async function download(id, filename, size) {\n",
+ " if (!google.colab.kernel.accessAllowed) {\n",
+ " return;\n",
+ " }\n",
+ " const div = document.createElement('div');\n",
+ " const label = document.createElement('label');\n",
+ " label.textContent = `Downloading \"${filename}\": `;\n",
+ " div.appendChild(label);\n",
+ " const progress = document.createElement('progress');\n",
+ " progress.max = size;\n",
+ " div.appendChild(progress);\n",
+ " document.body.appendChild(div);\n",
+ "\n",
+ " const buffers = [];\n",
+ " let downloaded = 0;\n",
+ "\n",
+ " const channel = await google.colab.kernel.comms.open(id);\n",
+ " // Send a message to notify the kernel that we're ready.\n",
+ " channel.send({})\n",
+ "\n",
+ " for await (const message of channel.messages) {\n",
+ " // Send a message to notify the kernel that we're ready.\n",
+ " channel.send({})\n",
+ " if (message.buffers) {\n",
+ " for (const buffer of message.buffers) {\n",
+ " buffers.push(buffer);\n",
+ " downloaded += buffer.byteLength;\n",
+ " progress.value = downloaded;\n",
+ " }\n",
+ " }\n",
+ " }\n",
+ " const blob = new Blob(buffers, {type: 'application/binary'});\n",
+ " const a = document.createElement('a');\n",
+ " a.href = window.URL.createObjectURL(blob);\n",
+ " a.download = filename;\n",
+ " div.appendChild(a);\n",
+ " a.click();\n",
+ " div.remove();\n",
+ " }\n",
+ " "
+ ]
+ },
+ "metadata": {}
+ },
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/plain": [
+ ""
+ ],
+ "application/javascript": [
+ "download(\"download_bc4ae04d-82c5-4107-bce5-384a89696227\", \"predictions.csv.predict.zip\", 1541)"
+ ]
+ },
+ "metadata": {}
+ }
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "# Demo"
+ ],
+ "metadata": {
+ "id": "-yPpFCpexlp6"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "FILE_PATH = \"test.csv\"\n",
+ "MODEL_HF_REPO = \"patrickmlml/mamba_nli_ensemble\""
+ ],
+ "metadata": {
+ "id": "GGq8iwEry9CT"
+ },
+ "execution_count": 9,
+ "outputs": []
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "## Custom Mamba Classes"
+ ],
+ "metadata": {
+ "id": "UL-jDECUylez"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "# define model config\n",
+ "@dataclass\n",
+ "class MambaConfig:\n",
+ " d_model: int = 2560\n",
+ " d_intermediate: int = 0 # from error when loading pretrained\n",
+ " n_layer: int = 64\n",
+ " vocab_size: int = 50277\n",
+ " ssm_cfg: dict = field(default_factory=dict)\n",
+ " attn_layer_idx = []\n",
+ " attn_cfg = {}\n",
+ " rms_norm: bool = True\n",
+ " residual_in_fp32: bool = True\n",
+ " fused_add_norm: bool = True\n",
+ " pad_vocab_size_multiple: int = 8\n",
+ " tie_embeddings = True\n",
+ "\n",
+ " def to_json_string(self):\n",
+ " return json.dumps(asdict(self))\n",
+ "\n",
+ " def to_dict(self):\n",
+ " return asdict(self)"
+ ],
+ "metadata": {
+ "id": "ZjJ7B8hMylez"
+ },
+ "execution_count": 10,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "# use a linear layer to classify d_model dimensions into num_classes classes\n",
+ "# https://arxiv.org/pdf/2312.00752 source for \"improved recipe\"\n",
+ "class MambaClassificationHead(nn.Module):\n",
+ " def __init__(self, d_model, num_classes, **kwargs):\n",
+ " super(MambaClassificationHead, self).__init__()\n",
+ " self.classification_head = nn.Linear(d_model, num_classes, **kwargs)\n",
+ "\n",
+ " def forward(self, hidden_states):\n",
+ " return self.classification_head(hidden_states)"
+ ],
+ "metadata": {
+ "id": "LVZDQONWylez"
+ },
+ "execution_count": 11,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "# define our custom version of Mamba for text classification\n",
+ "class MambaTextClassification(MambaLMHeadModel):\n",
+ " def __init__(\n",
+ " self,\n",
+ " config: MambaConfig,\n",
+ " initializer_cfg=None,\n",
+ " device=None,\n",
+ " dtype=None,\n",
+ " ) -> None:\n",
+ " super().__init__(config, initializer_cfg, device, dtype)\n",
+ "\n",
+ " # create a classifier head with d_model embedding dimensions and 2 classes (binary)\n",
+ " self.classification_head = MambaClassificationHead(d_model=config.d_model, num_classes=2)\n",
+ "\n",
+ " del self.lm_head\n",
+ "\n",
+ " def forward(self, input_ids, attention_mask=None, labels=None):\n",
+ " # pass input_ids through the original model to get hidden_states.\n",
+ " hidden_states = self.backbone(input_ids)\n",
+ "\n",
+ " # take the average of hidden_states in the second dimension to create a representative [CLS] feature\n",
+ " mean_hidden_states = hidden_states.mean(dim=1)\n",
+ "\n",
+ " # pass mean_hidden_states through the classifier to get logits.\n",
+ " logits = self.classification_head(mean_hidden_states)\n",
+ "\n",
+ " if labels is None:\n",
+ " ClassificationOutput = namedtuple(\"ClassificationOutput\", [\"logits\"])\n",
+ " return ClassificationOutput(logits=logits)\n",
+ " else:\n",
+ " ClassificationOutput = namedtuple(\"ClassificationOutput\", [\"loss\", \"logits\"])\n",
+ "\n",
+ " # use the CrossEntropyLoss loss function to calculate the loss\n",
+ " loss_fct = nn.CrossEntropyLoss()\n",
+ " loss = loss_fct(logits, labels)\n",
+ "\n",
+ " return ClassificationOutput(loss=loss, logits=logits)\n",
+ "\n",
+ " def predict(self, text, tokenizer, id2label=None):\n",
+ " input_ids = torch.tensor(tokenizer(text)['input_ids'], device='cuda')[None]\n",
+ " with torch.no_grad():\n",
+ " logits = self.forward(input_ids).logits[0]\n",
+ " label = np.argmax(logits.cpu().numpy())\n",
+ "\n",
+ " if id2label is not None:\n",
+ " return id2label[label]\n",
+ " else:\n",
+ " return label\n",
+ "\n",
+ " @classmethod\n",
+ " def from_pretrained(cls, pretrained_model_name, device=None, dtype=None, **kwargs):\n",
+ " # load configuration from previously trained model\n",
+ " config_data = load_config_hf(pretrained_model_name)\n",
+ " config = MambaConfig(**config_data)\n",
+ "\n",
+ " # Iiitialize the model from the configuration and pass it to the desired device and data type\n",
+ " model = cls(config, device=device, dtype=dtype, **kwargs)\n",
+ "\n",
+ " # load the previously trained model state.\n",
+ " model_state_dict = load_state_dict_hf(pretrained_model_name, device=device, dtype=dtype)\n",
+ " model.load_state_dict(model_state_dict, strict=False)\n",
+ "\n",
+ " # print out the newly initialized embedding parameters\n",
+ " print(\"Newly initialized embedding:\", set(model.state_dict().keys()) - set(model_state_dict.keys()))\n",
+ " return model"
+ ],
+ "metadata": {
+ "id": "sgG6HjMTylez"
+ },
+ "execution_count": 12,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "# define a MambaTrainer subclass that inherits from the Trainer class\n",
+ "class MambaTrainer(Trainer):\n",
+ "\n",
+ " # Define a compute_loss function to compute the loss function during training.\n",
+ " def compute_loss(self, model, inputs, return_outputs=False, **kwargs):\n",
+ " # Get input_ids and labels from inputs.\n",
+ " input_ids = inputs.pop(\"input_ids\")\n",
+ " labels = inputs.pop('labels')\n",
+ "\n",
+ " # Call the model's forward function with input_ids and labels to get the results.\n",
+ " outputs = model(input_ids=input_ids, labels=labels)\n",
+ "\n",
+ " # Get the loss value from the model's output.\n",
+ " loss = outputs.loss\n",
+ "\n",
+ " # Return both loss and outputs if return_outputs is True, otherwise return only loss.\n",
+ " return (loss, outputs) if return_outputs else loss\n",
+ "\n",
+ " # Define a save_model function to save the model during training.\n",
+ " def save_model(self, output_dir = None, _internal_call = False):\n",
+ " # Check if the save directory is not specified, use the default directory from the 'args' argument.\n",
+ " if output_dir is None:\n",
+ " output_dir = self.args.output_dir\n",
+ "\n",
+ " # If the output directory does not exist, create it.\n",
+ " if not os.path.exists(output_dir):\n",
+ " os.makedirs(output_dir)\n",
+ "\n",
+ " # Save the state of the PyTorch model to the file 'pytorch_model.bin' in the output directory.\n",
+ " torch.save(self.model.state_dict(), f\"{output_dir}/pytorch_model.bin\")\n",
+ "\n",
+ " # Save the state of the tokenizer to the output directory.\n",
+ " self.tokenizer.save_pretrained(output_dir)\n",
+ "\n",
+ " # Save the model configuration to the file 'config.json' in the output directory.\n",
+ " with open(f'{output_dir}/config.json', 'w') as f:\n",
+ " json.dump(self.model.config.to_dict(), f)"
+ ],
+ "metadata": {
+ "id": "J6f3AJmQyle0"
+ },
+ "execution_count": 13,
+ "outputs": []
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "## Load Model and Tokenizer"
+ ],
+ "metadata": {
+ "id": "X57GVYKCyxhE"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "from transformers import GPTNeoXTokenizerFast\n",
+ "# load the Mamba model from the pretrained model\n",
+ "model = MambaTextClassification.from_pretrained(MODEL_HF_REPO)\n",
+ "model.to(\"cuda\")\n",
+ "\n",
+ "# load the Mamba model tokenizer (used for Mamba pretraining)\n",
+ "tokenizer = GPTNeoXTokenizerFast.from_pretrained(MODEL_HF_REPO)\n",
+ "tokenizer.pad_token_id = tokenizer.eos_token_id"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "referenced_widgets": [
+ "5c5e3c6265904656b532c835fdb19ef4",
+ "6e1cae0032d94e58b4868419e0bed506",
+ "b2dfd1236ec64a928e7fc3f183b9e1c5",
+ "2e9952452127450a8c2d7f58d5d92d89",
+ "cc7e759bdd0545ac8f3419c735fe5448",
+ "4783bf6aed4e46f4bdb56d3fb0e10eb1",
+ "3420b3c222af410a9e086d03842a85af",
+ "78b851d587f140edb45c877192ef5112",
+ "339ed21242d4441aa8116e1f66fef056",
+ "ed419b0677e84dcbadd25b97170e63dc",
+ "df6b224bdd3e46f4aacfc2d0f4c11a0b",
+ "d42ea7af636c4d5fb25b814e81dafa29",
+ "c5287cecb88a4a518475813ba85913cc",
+ "58d00e05e78e48aca0989d2e69af9e52",
+ "4647fcbb28474fb6a9222aed10182389",
+ "e20e2a92c25342c8a30c785853111f05",
+ "b805e658404d44abb0ca2f28f46b3de0",
+ "20820b57aaed42908d1b3128351a7ecb",
+ "7e9eeacf8f0f4563aab51f39231d2400",
+ "e823f2f705fc48db9ca5c9d32cdfdeb4",
+ "3d287c0c32bc4042a16ce17e93d11406",
+ "9cb3bda6951f4bba996c7eee8b4b4271",
+ "9c77d36804314e3a940eb57137f204c7",
+ "03a011f3362048aa8debd95221ba1642",
+ "6bffd97d3244445097ca6a9b6172f291",
+ "a51f5014f7754d8bbde6ca69e2372f68",
+ "da66b15a935a41d7b85c617d6b24f559",
+ "b2170bdb5abe4eb4bc8df9184c3934c5",
+ "bd659d89b8924b1c8de21cbf7916af23",
+ "3b34039631c549699fe540b5472700c8",
+ "6d243622262f4fb98da1ad459283e517",
+ "976532cd16da499d9b5460a0d59615a1",
+ "7e2753de494445088d21c76427484d73",
+ "1abce180e6b140f1a583570be9665ef8",
+ "6c14b22a4ed94997a3f2f77dca0b1ba6",
+ "343aa7bae39c4fe3aa075dc4d9d784f7",
+ "87a9e1a745814e2bb09eb0b6ea06692b",
+ "97c866b7064b4247bc58bd6a8815673b",
+ "b7e52f5ea0974cbaac7cec56f14d6aa6",
+ "b7e0ccf9041d47168cad50fdd8f52732",
+ "75d0f70e54bd4dbca085aa20211385b6",
+ "d3522bc1535f49ea946aa93d4bff9658",
+ "3fc97002c3ad4f05bcb21931574f1e1c",
+ "552557ce23f345e2ba640553f030ed2a",
+ "166903568d6b49a5a325b719ca259938",
+ "237be64d5ac44aa6b4e29bc881978ab4",
+ "f17b7a136c8f49f28d5545c5a736c515",
+ "3d6ff50f90374649ab4406bac5d3b58a",
+ "2d63a035addf4e7aa2de636560348ca2",
+ "aaf897a858f84417bd26b2b4f181dd0f",
+ "26ba3e21bc9c478e9c66f755841614fb",
+ "06ea3adf62b14d8aab9f7cf9d59ff2c1",
+ "bec39de5540c4fb4b1a5ee019a4b27ac",
+ "be2a0b5623a149aabf8953bd6044b439",
+ "cbb2c111ad5042aa89615de84a298c45"
+ ],
+ "height": 195
+ },
+ "outputId": "839ea567-7b5c-47f8-c17d-03f1e7c818af",
+ "id": "YaeKwrHbyxhF"
+ },
+ "execution_count": 14,
+ "outputs": [
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/plain": [
+ "config.json: 0%| | 0.00/224 [00:00"
+ ],
+ "text/html": []
+ },
+ "metadata": {}
+ },
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "Evaluation Metrics: {'test_loss': 0.8145957589149475, 'test_model_preparation_time': 0.016, 'test_accuracy': 0.8230403800475059, 'test_runtime': 57.9113, 'test_samples_per_second': 116.316, 'test_steps_per_second': 14.539}\n"
+ ]
+ },
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/plain": [
+ ""
+ ],
+ "application/javascript": [
+ "\n",
+ " async function download(id, filename, size) {\n",
+ " if (!google.colab.kernel.accessAllowed) {\n",
+ " return;\n",
+ " }\n",
+ " const div = document.createElement('div');\n",
+ " const label = document.createElement('label');\n",
+ " label.textContent = `Downloading \"${filename}\": `;\n",
+ " div.appendChild(label);\n",
+ " const progress = document.createElement('progress');\n",
+ " progress.max = size;\n",
+ " div.appendChild(progress);\n",
+ " document.body.appendChild(div);\n",
+ "\n",
+ " const buffers = [];\n",
+ " let downloaded = 0;\n",
+ "\n",
+ " const channel = await google.colab.kernel.comms.open(id);\n",
+ " // Send a message to notify the kernel that we're ready.\n",
+ " channel.send({})\n",
+ "\n",
+ " for await (const message of channel.messages) {\n",
+ " // Send a message to notify the kernel that we're ready.\n",
+ " channel.send({})\n",
+ " if (message.buffers) {\n",
+ " for (const buffer of message.buffers) {\n",
+ " buffers.push(buffer);\n",
+ " downloaded += buffer.byteLength;\n",
+ " progress.value = downloaded;\n",
+ " }\n",
+ " }\n",
+ " }\n",
+ " const blob = new Blob(buffers, {type: 'application/binary'});\n",
+ " const a = document.createElement('a');\n",
+ " a.href = window.URL.createObjectURL(blob);\n",
+ " a.download = filename;\n",
+ " div.appendChild(a);\n",
+ " a.click();\n",
+ " div.remove();\n",
+ " }\n",
+ " "
+ ]
+ },
+ "metadata": {}
+ },
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/plain": [
+ ""
+ ],
+ "application/javascript": [
+ "download(\"download_b3c46d0e-ee46-47b5-a428-63df28ffa261\", \"predictions.csv\", 13483)"
+ ]
+ },
+ "metadata": {}
+ },
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "updating: predictions.csv.predict (deflated 90%)\n"
+ ]
+ },
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/plain": [
+ ""
+ ],
+ "application/javascript": [
+ "\n",
+ " async function download(id, filename, size) {\n",
+ " if (!google.colab.kernel.accessAllowed) {\n",
+ " return;\n",
+ " }\n",
+ " const div = document.createElement('div');\n",
+ " const label = document.createElement('label');\n",
+ " label.textContent = `Downloading \"${filename}\": `;\n",
+ " div.appendChild(label);\n",
+ " const progress = document.createElement('progress');\n",
+ " progress.max = size;\n",
+ " div.appendChild(progress);\n",
+ " document.body.appendChild(div);\n",
+ "\n",
+ " const buffers = [];\n",
+ " let downloaded = 0;\n",
+ "\n",
+ " const channel = await google.colab.kernel.comms.open(id);\n",
+ " // Send a message to notify the kernel that we're ready.\n",
+ " channel.send({})\n",
+ "\n",
+ " for await (const message of channel.messages) {\n",
+ " // Send a message to notify the kernel that we're ready.\n",
+ " channel.send({})\n",
+ " if (message.buffers) {\n",
+ " for (const buffer of message.buffers) {\n",
+ " buffers.push(buffer);\n",
+ " downloaded += buffer.byteLength;\n",
+ " progress.value = downloaded;\n",
+ " }\n",
+ " }\n",
+ " }\n",
+ " const blob = new Blob(buffers, {type: 'application/binary'});\n",
+ " const a = document.createElement('a');\n",
+ " a.href = window.URL.createObjectURL(blob);\n",
+ " a.download = filename;\n",
+ " div.appendChild(a);\n",
+ " a.click();\n",
+ " div.remove();\n",
+ " }\n",
+ " "
+ ]
+ },
+ "metadata": {}
+ },
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/plain": [
+ ""
+ ],
+ "application/javascript": [
+ "download(\"download_2387decd-c617-4ecf-bbe4-75130e38b78a\", \"predictions.csv.predict.zip\", 1535)"
+ ]
+ },
+ "metadata": {}
+ }
+ ]
+ }
+ ]
+}
\ No newline at end of file