Upload folder using huggingface_hub

.ipynb_checkpoints/Untitled-checkpoint.ipynb

@@ -0,0 +1,6 @@
+{
+ "cells": [],
+ "metadata": {},
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

Untitled.ipynb

@@ -0,0 +1,107 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "4c32f546-78f9-4108-bba9-0fe6836ce21c",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "415c79a4df3e404ea2efb3fec933343c",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "VBox(children=(HTML(value='<center> <img\\nsrc=https://huggingface.co/front/assets/huggingface_logo-noborder.sv…"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "ename": "KeyboardInterrupt",
+     "evalue": "",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
+      "Cell \u001b[0;32mIn[6], line 22\u001b[0m\n\u001b[1;32m     20\u001b[0m \u001b[38;5;66;03m# Upload\u001b[39;00m\n\u001b[1;32m     21\u001b[0m api \u001b[38;5;241m=\u001b[39m HfApi()\n\u001b[0;32m---> 22\u001b[0m \u001b[43mapi\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mupload_folder\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m     23\u001b[0m \u001b[43m    \u001b[49m\u001b[43mfolder_path\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mMODEL_PATH\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m     24\u001b[0m \u001b[43m    \u001b[49m\u001b[43mrepo_id\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrepo_id\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m     25\u001b[0m \u001b[43m    \u001b[49m\u001b[43mrepo_type\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mmodel\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\n\u001b[1;32m     26\u001b[0m \u001b[43m)\u001b[49m\n\u001b[1;32m     28\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m✅ Model uploaded to: https://huggingface.co/\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mrepo_id\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m)\n",
+      "File \u001b[0;32m/usr/local/lib/python3.11/dist-packages/huggingface_hub/utils/_validators.py:118\u001b[0m, in \u001b[0;36mvalidate_hf_hub_args.<locals>._inner_fn\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m    115\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m check_use_auth_token:\n\u001b[1;32m    116\u001b[0m     kwargs \u001b[38;5;241m=\u001b[39m smoothly_deprecate_use_auth_token(fn_name\u001b[38;5;241m=\u001b[39mfn\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m, has_token\u001b[38;5;241m=\u001b[39mhas_token, kwargs\u001b[38;5;241m=\u001b[39mkwargs)\n\u001b[0;32m--> 118\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfn\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[0;32m/usr/local/lib/python3.11/dist-packages/huggingface_hub/hf_api.py:1208\u001b[0m, in \u001b[0;36mfuture_compatible.<locals>._inner\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1205\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mrun_as_future(fn, \u001b[38;5;28mself\u001b[39m, \u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[1;32m   1207\u001b[0m \u001b[38;5;66;03m# Otherwise, call the function normally\u001b[39;00m\n\u001b[0;32m-> 1208\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfn\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[0;32m/usr/local/lib/python3.11/dist-packages/huggingface_hub/hf_api.py:4565\u001b[0m, in \u001b[0;36mHfApi.upload_folder\u001b[0;34m(self, repo_id, folder_path, path_in_repo, commit_message, commit_description, token, repo_type, revision, create_pr, parent_commit, allow_patterns, ignore_patterns, delete_patterns, multi_commits, multi_commits_verbose, run_as_future)\u001b[0m\n\u001b[1;32m   4555\u001b[0m ignore_patterns \u001b[38;5;241m+\u001b[39m\u001b[38;5;241m=\u001b[39m IGNORE_GIT_FOLDER_PATTERNS\n\u001b[1;32m   4557\u001b[0m delete_operations \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_prepare_upload_folder_deletions(\n\u001b[1;32m   4558\u001b[0m     repo_id\u001b[38;5;241m=\u001b[39mrepo_id,\n\u001b[1;32m   4559\u001b[0m     repo_type\u001b[38;5;241m=\u001b[39mrepo_type,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m   4563\u001b[0m     delete_patterns\u001b[38;5;241m=\u001b[39mdelete_patterns,\n\u001b[1;32m   4564\u001b[0m )\n\u001b[0;32m-> 4565\u001b[0m add_operations \u001b[38;5;241m=\u001b[39m \u001b[43m_prepare_upload_folder_additions\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   4566\u001b[0m \u001b[43m    \u001b[49m\u001b[43mfolder_path\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   4567\u001b[0m \u001b[43m    \u001b[49m\u001b[43mpath_in_repo\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   4568\u001b[0m \u001b[43m    \u001b[49m\u001b[43mallow_patterns\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mallow_patterns\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   4569\u001b[0m \u001b[43m    \u001b[49m\u001b[43mignore_patterns\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mignore_patterns\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   4570\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   4572\u001b[0m \u001b[38;5;66;03m# Optimize operations: if some files will be overwritten, we don't need to delete them first\u001b[39;00m\n\u001b[1;32m   4573\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(add_operations) \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m0\u001b[39m:\n",
+      "File \u001b[0;32m/usr/local/lib/python3.11/dist-packages/huggingface_hub/hf_api.py:8265\u001b[0m, in \u001b[0;36m_prepare_upload_folder_additions\u001b[0;34m(folder_path, path_in_repo, allow_patterns, ignore_patterns)\u001b[0m\n\u001b[1;32m   8262\u001b[0m \u001b[38;5;66;03m# Filter files and return\u001b[39;00m\n\u001b[1;32m   8263\u001b[0m \u001b[38;5;66;03m# Patterns are applied on the path relative to `folder_path`. `path_in_repo` is prefixed after the filtering.\u001b[39;00m\n\u001b[1;32m   8264\u001b[0m prefix \u001b[38;5;241m=\u001b[39m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mpath_in_repo\u001b[38;5;241m.\u001b[39mstrip(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m/\u001b[39m\u001b[38;5;124m'\u001b[39m)\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m/\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m path_in_repo \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m-> 8265\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43m[\u001b[49m\n\u001b[1;32m   8266\u001b[0m \u001b[43m    \u001b[49m\u001b[43mCommitOperationAdd\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   8267\u001b[0m \u001b[43m        \u001b[49m\u001b[43mpath_or_fileobj\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrelpath_to_abspath\u001b[49m\u001b[43m[\u001b[49m\u001b[43mrelpath\u001b[49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\u001b[43m  \u001b[49m\u001b[38;5;66;43;03m# absolute path on disk\u001b[39;49;00m\n\u001b[1;32m   8268\u001b[0m \u001b[43m        \u001b[49m\u001b[43mpath_in_repo\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mprefix\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m+\u001b[39;49m\u001b[43m \u001b[49m\u001b[43mrelpath\u001b[49m\u001b[43m,\u001b[49m\u001b[43m  \u001b[49m\u001b[38;5;66;43;03m# \"absolute\" path in repo\u001b[39;49;00m\n\u001b[1;32m   8269\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   8270\u001b[0m \u001b[43m    \u001b[49m\u001b[38;5;28;43;01mfor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mrelpath\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mfilter_repo_objects\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   8271\u001b[0m \u001b[43m        \u001b[49m\u001b[43mrelpath_to_abspath\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mkeys\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mallow_patterns\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mallow_patterns\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mignore_patterns\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mignore_patterns\u001b[49m\n\u001b[1;32m   8272\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   8273\u001b[0m \u001b[43m\u001b[49m\u001b[43m]\u001b[49m\n",
+      "File \u001b[0;32m/usr/local/lib/python3.11/dist-packages/huggingface_hub/hf_api.py:8266\u001b[0m, in \u001b[0;36m<listcomp>\u001b[0;34m(.0)\u001b[0m\n\u001b[1;32m   8262\u001b[0m \u001b[38;5;66;03m# Filter files and return\u001b[39;00m\n\u001b[1;32m   8263\u001b[0m \u001b[38;5;66;03m# Patterns are applied on the path relative to `folder_path`. `path_in_repo` is prefixed after the filtering.\u001b[39;00m\n\u001b[1;32m   8264\u001b[0m prefix \u001b[38;5;241m=\u001b[39m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mpath_in_repo\u001b[38;5;241m.\u001b[39mstrip(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m/\u001b[39m\u001b[38;5;124m'\u001b[39m)\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m/\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m path_in_repo \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m   8265\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m [\n\u001b[0;32m-> 8266\u001b[0m     \u001b[43mCommitOperationAdd\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   8267\u001b[0m \u001b[43m        \u001b[49m\u001b[43mpath_or_fileobj\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrelpath_to_abspath\u001b[49m\u001b[43m[\u001b[49m\u001b[43mrelpath\u001b[49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\u001b[43m  \u001b[49m\u001b[38;5;66;43;03m# absolute path on disk\u001b[39;49;00m\n\u001b[1;32m   8268\u001b[0m \u001b[43m        \u001b[49m\u001b[43mpath_in_repo\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mprefix\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m+\u001b[39;49m\u001b[43m \u001b[49m\u001b[43mrelpath\u001b[49m\u001b[43m,\u001b[49m\u001b[43m  \u001b[49m\u001b[38;5;66;43;03m# \"absolute\" path in repo\u001b[39;49;00m\n\u001b[1;32m   8269\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   8270\u001b[0m     \u001b[38;5;28;01mfor\u001b[39;00m relpath \u001b[38;5;129;01min\u001b[39;00m filter_repo_objects(\n\u001b[1;32m   8271\u001b[0m         relpath_to_abspath\u001b[38;5;241m.\u001b[39mkeys(), allow_patterns\u001b[38;5;241m=\u001b[39mallow_patterns, ignore_patterns\u001b[38;5;241m=\u001b[39mignore_patterns\n\u001b[1;32m   8272\u001b[0m     )\n\u001b[1;32m   8273\u001b[0m ]\n",
+      "File \u001b[0;32m<string>:5\u001b[0m, in \u001b[0;36m__init__\u001b[0;34m(self, path_in_repo, path_or_fileobj)\u001b[0m\n",
+      "File \u001b[0;32m/usr/local/lib/python3.11/dist-packages/huggingface_hub/_commit_api.py:183\u001b[0m, in \u001b[0;36mCommitOperationAdd.__post_init__\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    181\u001b[0m \u001b[38;5;66;03m# Compute \"upload_info\" attribute\u001b[39;00m\n\u001b[1;32m    182\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mpath_or_fileobj, \u001b[38;5;28mstr\u001b[39m):\n\u001b[0;32m--> 183\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mupload_info \u001b[38;5;241m=\u001b[39m \u001b[43mUploadInfo\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfrom_path\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mpath_or_fileobj\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    184\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mpath_or_fileobj, \u001b[38;5;28mbytes\u001b[39m):\n\u001b[1;32m    185\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mupload_info \u001b[38;5;241m=\u001b[39m UploadInfo\u001b[38;5;241m.\u001b[39mfrom_bytes(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mpath_or_fileobj)\n",
+      "File \u001b[0;32m/usr/local/lib/python3.11/dist-packages/huggingface_hub/lfs.py:82\u001b[0m, in \u001b[0;36mUploadInfo.from_path\u001b[0;34m(cls, path)\u001b[0m\n\u001b[1;32m     80\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m io\u001b[38;5;241m.\u001b[39mopen(path, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mrb\u001b[39m\u001b[38;5;124m\"\u001b[39m) \u001b[38;5;28;01mas\u001b[39;00m file:\n\u001b[1;32m     81\u001b[0m     sample \u001b[38;5;241m=\u001b[39m file\u001b[38;5;241m.\u001b[39mpeek(\u001b[38;5;241m512\u001b[39m)[:\u001b[38;5;241m512\u001b[39m]\n\u001b[0;32m---> 82\u001b[0m     sha \u001b[38;5;241m=\u001b[39m \u001b[43msha_fileobj\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfile\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m     83\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mcls\u001b[39m(size\u001b[38;5;241m=\u001b[39msize, sha256\u001b[38;5;241m=\u001b[39msha, sample\u001b[38;5;241m=\u001b[39msample)\n",
+      "File \u001b[0;32m/usr/local/lib/python3.11/dist-packages/huggingface_hub/utils/sha.py:25\u001b[0m, in \u001b[0;36msha_fileobj\u001b[0;34m(fileobj, chunk_size)\u001b[0m\n\u001b[1;32m     23\u001b[0m \u001b[38;5;28;01mwhile\u001b[39;00m \u001b[38;5;28;01mTrue\u001b[39;00m:\n\u001b[1;32m     24\u001b[0m     chunk \u001b[38;5;241m=\u001b[39m fileobj\u001b[38;5;241m.\u001b[39mread(chunk_size)\n\u001b[0;32m---> 25\u001b[0m     sha\u001b[38;5;241m.\u001b[39mupdate(chunk)\n\u001b[1;32m     26\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m chunk:\n\u001b[1;32m     27\u001b[0m         \u001b[38;5;28;01mbreak\u001b[39;00m\n",
+      "\u001b[0;31mKeyboardInterrupt\u001b[0m: "
+     ]
+    }
+   ],
+   "source": [
+    "#!/usr/bin/env python3\n",
+    "\"\"\"Upload ELECTRA model to HuggingFace Hub\"\"\"\n",
+    "\n",
+    "from huggingface_hub import HfApi, create_repo, login\n",
+    "import os\n",
+    "\n",
+    "# Config\n",
+    "USERNAME = \"pasindubg\"  # Change this!\n",
+    "REPO_NAME = \"singlish-electra-joint\"\n",
+    "MODEL_PATH = \"/notebooks/electra-model/joint_electra\"\n",
+    "\n",
+    "# Login (will prompt for token)\n",
+    "login()\n",
+    "\n",
+    "# Create repo\n",
+    "repo_id = f\"{USERNAME}/{REPO_NAME}\"\n",
+    "create_repo(repo_id, repo_type=\"model\", exist_ok=True)\n",
+    "print(f\"✅ Created repo: {repo_id}\")\n",
+    "\n",
+    "# Upload\n",
+    "api = HfApi()\n",
+    "api.upload_folder(\n",
+    "    folder_path=MODEL_PATH,\n",
+    "    repo_id=repo_id,\n",
+    "    repo_type=\"model\"\n",
+    ")\n",
+    "\n",
+    "print(f\"✅ Model uploaded to: https://huggingface.co/{repo_id}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f65d7be7-5e42-4aed-9d53-1526e8655e2b",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

best_model/discriminator/config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "joint_electra/checkpoints/step_195000/discriminator",
+  "architectures": [
+    "ElectraModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 128,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 256,
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30000
+}

best_model/discriminator/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9a9e54b2d91aebb6377040712a78513ec7612c1a738b048f9d3f0a8d546c498
+size 53686760

best_model/discriminator/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

best_model/discriminator/tokenizer_config.json

@@ -0,0 +1,52 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "[UNK]"
+}

best_model/discriminator_head.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5200dce144e77ae3af08b31581ae2355f588609907ca01ffa06a1f065a3354b
+size 3674

best_model/generator/config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "joint_electra/checkpoints/step_195000/generator",
+  "architectures": [
+    "ElectraForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 768,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 256,
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30000
+}

best_model/generator/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ee8fc843687cd53cfcf5dea98d00f4a5b469f63a808f3db2177a0c0869f4e72
+size 133381168

best_model/generator/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

best_model/generator/tokenizer_config.json

@@ -0,0 +1,52 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "[UNK]"
+}

best_model/training_history.json

@@ -0,0 +1,15 @@
+{
+  "epochs": [
+    1
+  ],
+  "total_losses": [
+    26.839805470152086
+  ],
+  "gen_losses": [
+    4.150190665201886
+  ],
+  "disc_losses": [
+    0.4537922960495262
+  ],
+  "best_loss": 26.839805470152086
+}

best_model/training_state.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ffda0e223350dca578ea44ab95bfac6f9824e3b358042d74cd1c04bd5c00e25
+size 374397856

checkpoints/epoch_1/discriminator/config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "joint_electra/checkpoints/step_195000/discriminator",
+  "architectures": [
+    "ElectraModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 128,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 256,
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30000
+}

checkpoints/epoch_1/discriminator/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9a9e54b2d91aebb6377040712a78513ec7612c1a738b048f9d3f0a8d546c498
+size 53686760

checkpoints/epoch_1/discriminator/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoints/epoch_1/discriminator/tokenizer_config.json

@@ -0,0 +1,52 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "[UNK]"
+}

checkpoints/epoch_1/discriminator_head.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5200dce144e77ae3af08b31581ae2355f588609907ca01ffa06a1f065a3354b
+size 3674

checkpoints/epoch_1/generator/config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "joint_electra/checkpoints/step_195000/generator",
+  "architectures": [
+    "ElectraForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 768,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 256,
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30000
+}

checkpoints/epoch_1/generator/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ee8fc843687cd53cfcf5dea98d00f4a5b469f63a808f3db2177a0c0869f4e72
+size 133381168

checkpoints/epoch_1/generator/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoints/epoch_1/generator/tokenizer_config.json

@@ -0,0 +1,52 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "[UNK]"
+}

checkpoints/epoch_1/training_history.json

@@ -0,0 +1,15 @@
+{
+  "epochs": [
+    1
+  ],
+  "total_losses": [
+    26.839805470152086
+  ],
+  "gen_losses": [
+    4.150190665201886
+  ],
+  "disc_losses": [
+    0.4537922960495262
+  ],
+  "best_loss": 26.839805470152086
+}

checkpoints/epoch_1/training_state.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ffda0e223350dca578ea44ab95bfac6f9824e3b358042d74cd1c04bd5c00e25
+size 374397856

checkpoints/epoch_2/discriminator/config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "joint_electra/checkpoints/step_345000/discriminator",
+  "architectures": [
+    "ElectraModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 128,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 256,
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30000
+}

checkpoints/epoch_2/discriminator/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:260ae5ecc92a8a8df321bf49604e22e0f266792e86fd4c7757379c6c667ec0f5
+size 53686760

checkpoints/epoch_2/discriminator/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoints/epoch_2/discriminator/tokenizer_config.json

@@ -0,0 +1,52 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "[UNK]"
+}

checkpoints/epoch_2/discriminator_head.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03b4e2a19251a666a14e9b5f3d0e3407921daac698726c34cad45015c6a21abe
+size 3674

checkpoints/epoch_2/generator/config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "joint_electra/checkpoints/step_345000/generator",
+  "architectures": [
+    "ElectraForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 768,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 256,
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30000
+}

checkpoints/epoch_2/generator/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:406bc595610b318cfbc49a128e5b29a8f5ff7a6701c35c0aa01f8501fbcedb78
+size 133381168

checkpoints/epoch_2/generator/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoints/epoch_2/generator/tokenizer_config.json

@@ -0,0 +1,52 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "[UNK]"
+}

checkpoints/epoch_2/training_history.json

@@ -0,0 +1,19 @@
+{
+  "epochs": [
+    1,
+    2
+  ],
+  "total_losses": [
+    26.839805470152086,
+    27.0937718378346
+  ],
+  "gen_losses": [
+    4.150190665201886,
+    3.966244459467499
+  ],
+  "disc_losses": [
+    0.4537922960495262,
+    0.4625505475584797
+  ],
+  "best_loss": 26.839805470152086
+}

checkpoints/epoch_2/training_state.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c55ff6d32387f2730be54d7f29cbd6b9ae29eac35b6f3d8943891b8da549fb32
+size 374397856

checkpoints/epoch_3/discriminator/config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "joint_electra/checkpoints/step_525000/discriminator",
+  "architectures": [
+    "ElectraModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 128,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 256,
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30000
+}

checkpoints/epoch_3/discriminator/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e13e5bf69401740edfedc9f36e4d73bf96765762cf5cdfe8bcb7202a70605893
+size 53686760

checkpoints/epoch_3/discriminator/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoints/epoch_3/discriminator/tokenizer_config.json

@@ -0,0 +1,52 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "[UNK]"
+}

checkpoints/epoch_3/discriminator_head.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c390ee921f6e0bab9d26d63972e161393700f056e0ec8685ec109d7aff836f55
+size 3674

checkpoints/epoch_3/generator/config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "joint_electra/checkpoints/step_525000/generator",
+  "architectures": [
+    "ElectraForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 768,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 256,
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30000
+}

checkpoints/epoch_3/generator/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72cf5f7afc8ca6efb755e4254f3d5122d7c50a636c0fa7d2b3efd9e786293d5f
+size 133381168

checkpoints/epoch_3/generator/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}