End of training

fine-tune-whisper-non-streaming-fleurs-ms.ipynb

@@ -1162,7 +1162,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 23,
    "id": "ee8b7b8e-1c9a-4d77-9137-1778a629e6de",
    "metadata": {
     "id": "ee8b7b8e-1c9a-4d77-9137-1778a629e6de"
@@ -1191,8 +1191,8 @@
        "\n",
        "    <div>\n",
        "      \n",
-       "      <progress value='1001' max='5000' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
-       "      [1001/5000 1:09:54 < 4:39:51, 0.24 it/s, Epoch 10.75/54]\n",
+       "      <progress value='1137' max='5000' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
+       "      [1137/5000 1:25:51 < 4:52:12, 0.22 it/s, Epoch 12.21/54]\n",
        "    </div>\n",
        "    <table border=\"1\" class=\"dataframe\">\n",
        "  <thead>\n",
@@ -1200,17 +1200,18 @@
        "      <th>Step</th>\n",
        "      <th>Training Loss</th>\n",
        "      <th>Validation Loss</th>\n",
+       "      <th>Wer</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
+       "    <tr>\n",
+       "      <td>1000</td>\n",
+       "      <td>0.001500</td>\n",
+       "      <td>0.332360</td>\n",
+       "      <td>15.645336</td>\n",
+       "    </tr>\n",
        "  </tbody>\n",
-       "</table><p>\n",
-       "    <div>\n",
-       "      \n",
-       "      <progress value='83' max='94' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
-       "      [83/94 04:51 < 00:39, 0.28 it/s]\n",
-       "    </div>\n",
-       "    "
+       "</table><p>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -1226,7 +1227,25 @@
       "The following columns in the evaluation set don't have a corresponding argument in `WhisperForConditionalGeneration.forward` and have been ignored: input_length. If input_length are not expected by `WhisperForConditionalGeneration.forward`,  you can safely ignore this message.\n",
       "***** Running Evaluation *****\n",
       "  Num examples = 749\n",
-      "  Batch size = 8\n"
+      "  Batch size = 8\n",
+      "Saving model checkpoint to ./checkpoint-1000\n",
+      "Configuration saved in ./checkpoint-1000/config.json\n",
+      "Model weights saved in ./checkpoint-1000/pytorch_model.bin\n",
+      "Feature extractor saved in ./checkpoint-1000/preprocessor_config.json\n",
+      "Feature extractor saved in ./preprocessor_config.json\n"
+     ]
+    },
+    {
+     "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[23], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mtrainer\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mtrain\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[0;32m~/whisper/lib/python3.8/site-packages/transformers/trainer.py:1535\u001b[0m, in \u001b[0;36mTrainer.train\u001b[0;34m(self, resume_from_checkpoint, trial, ignore_keys_for_eval, **kwargs)\u001b[0m\n\u001b[1;32m   1530\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mmodel_wrapped \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mmodel\n\u001b[1;32m   1532\u001b[0m inner_training_loop \u001b[38;5;241m=\u001b[39m find_executable_batch_size(\n\u001b[1;32m   1533\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_inner_training_loop, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_train_batch_size, args\u001b[38;5;241m.\u001b[39mauto_find_batch_size\n\u001b[1;32m   1534\u001b[0m )\n\u001b[0;32m-> 1535\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43minner_training_loop\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   1536\u001b[0m \u001b[43m    \u001b[49m\u001b[43margs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1537\u001b[0m \u001b[43m    \u001b[49m\u001b[43mresume_from_checkpoint\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mresume_from_checkpoint\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1538\u001b[0m \u001b[43m    \u001b[49m\u001b[43mtrial\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtrial\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1539\u001b[0m \u001b[43m    \u001b[49m\u001b[43mignore_keys_for_eval\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mignore_keys_for_eval\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1540\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[0;32m~/whisper/lib/python3.8/site-packages/transformers/trainer.py:1785\u001b[0m, in \u001b[0;36mTrainer._inner_training_loop\u001b[0;34m(self, batch_size, args, resume_from_checkpoint, trial, ignore_keys_for_eval)\u001b[0m\n\u001b[1;32m   1782\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m   1783\u001b[0m     tr_loss_step \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mtraining_step(model, inputs)\n\u001b[0;32m-> 1785\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m (\n\u001b[1;32m   1786\u001b[0m     args\u001b[38;5;241m.\u001b[39mlogging_nan_inf_filter\n\u001b[1;32m   1787\u001b[0m     \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m is_torch_tpu_available()\n\u001b[1;32m   1788\u001b[0m     \u001b[38;5;129;01mand\u001b[39;00m (torch\u001b[38;5;241m.\u001b[39misnan(tr_loss_step) \u001b[38;5;129;01mor\u001b[39;00m torch\u001b[38;5;241m.\u001b[39misinf(tr_loss_step))\n\u001b[1;32m   1789\u001b[0m ):\n\u001b[1;32m   1790\u001b[0m     \u001b[38;5;66;03m# if loss is nan or inf simply add the average of previous logged losses\u001b[39;00m\n\u001b[1;32m   1791\u001b[0m     tr_loss \u001b[38;5;241m+\u001b[39m\u001b[38;5;241m=\u001b[39m tr_loss \u001b[38;5;241m/\u001b[39m (\u001b[38;5;241m1\u001b[39m \u001b[38;5;241m+\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mstate\u001b[38;5;241m.\u001b[39mglobal_step \u001b[38;5;241m-\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_globalstep_last_logged)\n\u001b[1;32m   1792\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n",
+      "\u001b[0;31mKeyboardInterrupt\u001b[0m: "
      ]
     }
    ],
@@ -1246,7 +1265,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 24,
    "id": "c704f91e-241b-48c9-b8e0-f0da396a9663",
    "metadata": {
     "id": "c704f91e-241b-48c9-b8e0-f0da396a9663"
@@ -1260,7 +1279,7 @@
     "    \"model_name\": \"Whisper Small MS - FLEURS\",  # a 'pretty' name for your model\n",
     "    \"finetuned_from\": \"openai/whisper-small\",\n",
     "    \"tasks\": \"automatic-speech-recognition\",\n",
-    "    \"tags\": \"whisper-event\",\n",
+    "    \"tags\": [\"whisper-event\", \"incomplete\"],\n",
     "}"
    ]
   },
@@ -1281,7 +1300,18 @@
    "metadata": {
     "id": "d7030622-caf7-4039-939b-6195cdaa2585"
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Saving model checkpoint to ./\n",
+      "Configuration saved in ./config.json\n",
+      "Model weights saved in ./pytorch_model.bin\n",
+      "Feature extractor saved in ./preprocessor_config.json\n"
+     ]
+    }
+   ],
    "source": [
     "trainer.push_to_hub(**kwargs)"
    ]

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80ecaa4afa57b3eabd3082c922b776df470a7da84f8e7ab71afdbd22321b7c4b
+oid sha256:dcc04218f31af574bfbde70d73250344da004bfa40593e65c10ae8984db558eb
 size 967102601

runs/Dec11_09-38-31_DANDAN/events.out.tfevents.1670722725.DANDAN.10984.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebf73a5f26128a891db7a8345514f6bdf0c6d2979874b6f9cb65dc62a8dea419
-size 10861
+oid sha256:7610414f37504b1b4057dd1cb351805a3020f7eb06db524f404a4cbeb20d34af
+size 11646