Training in progress, step 1000

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bb067030f872fb2b70e06a73454240f478fe01ec627e1b1bfdc3d253c2fcd57
+oid sha256:1c953e09032d3a83a5cc7c9ef098d1e59f4182bae3fcfc2975fc69db9c359c7b
 size 967102729

test_whisper_finetuned.ipynb

@@ -2,51 +2,9 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "f7537db8beff4744b3555f4d360cb867",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Downloading data:   0%|          | 0.00/10.3G [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "0f469fd6738a484bafc3a42ff32bf21e",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Generating train split: 0 examples [00:00, ? examples/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "ec98f490c01240eb8f89d294a2c59dde",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Generating test split: 0 examples [00:00, ? examples/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
     {
      "name": "stdout",
      "output_type": "stream",
@@ -77,7 +35,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [
     {
@@ -107,24 +65,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 3,
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "909a04095ce84a70bb1cf0b693bfa843",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Downloading (…)rocessor_config.json:   0%|          | 0.00/185k [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
+   "outputs": [],
    "source": [
     "from transformers import WhisperFeatureExtractor\n",
     "\n",
@@ -133,107 +76,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "ac6c9f270ae44be7a07f3a2b2518a090",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Downloading (…)okenizer_config.json:   0%|          | 0.00/805 [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "c5ffc60826bb4582aef22999cd582ec1",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Downloading (…)olve/main/vocab.json:   0%|          | 0.00/836k [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "9aeafe7afc0241e296b4393281369665",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Downloading (…)/main/tokenizer.json:   0%|          | 0.00/2.48M [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "91ca2e2c0039401a95603600ccff5f1f",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Downloading (…)olve/main/merges.txt:   0%|          | 0.00/494k [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "67536c658ac64b96a09abf3f8e558533",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Downloading (…)main/normalizer.json:   0%|          | 0.00/52.7k [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "07d64b8f7c964df8b138f638629d84b7",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Downloading (…)in/added_tokens.json:   0%|          | 0.00/34.6k [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "c338b9a3ecb84de1b397a21489da4a2f",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Downloading (…)cial_tokens_map.json:   0%|          | 0.00/2.08k [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
     {
      "name": "stderr",
      "output_type": "stream",
@@ -250,7 +95,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [
     {
@@ -269,7 +114,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [
     {
@@ -287,7 +132,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -299,7 +144,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [
     {
@@ -317,7 +162,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -331,7 +176,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -358,13 +203,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 11,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "a65c6a2e3f5d4d56bec901dbf14f2921",
+       "model_id": "0c3d689f889f4a71a6ffe0350727d7d7",
        "version_major": 2,
        "version_minor": 0
       },
@@ -378,7 +223,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "fe2de34ac35a415e8fb7661b41852c69",
+       "model_id": "f28073a5c15944e9a9c7da6c994fb3da",
        "version_major": 2,
        "version_minor": 0
       },
@@ -396,7 +241,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 12,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -409,13 +254,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 13,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "65b061edac6c4ef58f81cb8edec172e0",
+       "model_id": "a0ff361ac7824e87a1360eb36314f126",
        "version_major": 2,
        "version_minor": 0
       },
@@ -436,7 +281,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 14,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -475,7 +320,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 15,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -484,7 +329,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 25,
+   "execution_count": 16,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -495,24 +340,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 26,
+   "execution_count": 17,
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "a57f57bdfa4e4f1ba64458a6e381ebc1",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Downloading builder script:   0%|          | 0.00/5.60k [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
+   "outputs": [],
    "source": [
     "from evaluate import load\n",
     "cer_score = evaluate.load(\"cer\")"
@@ -550,7 +380,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 27,
+   "execution_count": 18,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -580,52 +410,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 28,
+   "execution_count": 19,
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "34f215d7229e419ba31b6db84d40dd4e",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Downloading (…)lve/main/config.json:   0%|          | 0.00/1.97k [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "9a10f9361120449ba5cec6baaf0064b3",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Downloading model.safetensors:   0%|          | 0.00/967M [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "37cb5f6cd0ec4c6c878d37afea648468",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Downloading (…)neration_config.json:   0%|          | 0.00/3.84k [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
+   "outputs": [],
    "source": [
     "from transformers import WhisperForConditionalGeneration\n",
     "\n",
@@ -634,7 +421,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 29,
+   "execution_count": 20,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -645,7 +432,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 30,
+   "execution_count": 21,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -677,7 +464,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 32,
+   "execution_count": 22,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -696,7 +483,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 33,
+   "execution_count": 23,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -705,41 +492,42 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 34,
+   "execution_count": 24,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "0303d20e3e2442dab77e2db5cc32f0bf",
+       "model_id": "e65ce3bc72904c3999b034bfeb8a12b6",
        "version_major": 2,
        "version_minor": 0
       },
       "text/plain": [
-       "  0%|          | 0/5000 [00:00<?, ?it/s]"
+       "  0%|          | 0/4000 [00:00<?, ?it/s]"
       ]
      },
      "metadata": {},
      "output_type": "display_data"
     },
     {
-     "ename": "OutOfMemoryError",
-     "evalue": "CUDA out of memory. Tried to allocate 6.44 GiB (GPU 0; 23.64 GiB total capacity; 16.89 GiB already allocated; 211.81 MiB free; 22.32 GiB reserved in total by PyTorch) If reserved memory is >> allocated memory try setting max_split_size_mb to avoid fragmentation.  See documentation for Memory Management and PYTORCH_CUDA_ALLOC_CONF",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mOutOfMemoryError\u001b[0m                          Traceback (most recent call last)",
-      "\u001b[1;32m/home/kwon/kwon/01_Coding/hmi/test_whisper_finetuned.ipynb 셀 25\u001b[0m line \u001b[0;36m1\n\u001b[0;32m----> <a href='vscode-notebook-cell:/home/kwon/kwon/01_Coding/hmi/test_whisper_finetuned.ipynb#X31sZmlsZQ%3D%3D?line=0'>1</a>\u001b[0m trainer\u001b[39m.\u001b[39;49mtrain()\n",
-      "File \u001b[0;32m~/anaconda3/envs/stt/lib/python3.8/site-packages/transformers/trainer.py:1582\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   1579\u001b[0m \u001b[39mtry\u001b[39;00m:\n\u001b[1;32m   1580\u001b[0m     \u001b[39m# Disable progress bars when uploading models during checkpoints to avoid polluting stdout\u001b[39;00m\n\u001b[1;32m   1581\u001b[0m     hf_hub_utils\u001b[39m.\u001b[39mdisable_progress_bars()\n\u001b[0;32m-> 1582\u001b[0m     \u001b[39mreturn\u001b[39;00m inner_training_loop(\n\u001b[1;32m   1583\u001b[0m         args\u001b[39m=\u001b[39;49margs,\n\u001b[1;32m   1584\u001b[0m         resume_from_checkpoint\u001b[39m=\u001b[39;49mresume_from_checkpoint,\n\u001b[1;32m   1585\u001b[0m         trial\u001b[39m=\u001b[39;49mtrial,\n\u001b[1;32m   1586\u001b[0m         ignore_keys_for_eval\u001b[39m=\u001b[39;49mignore_keys_for_eval,\n\u001b[1;32m   1587\u001b[0m     )\n\u001b[1;32m   1588\u001b[0m \u001b[39mfinally\u001b[39;00m:\n\u001b[1;32m   1589\u001b[0m     hf_hub_utils\u001b[39m.\u001b[39menable_progress_bars()\n",
-      "File \u001b[0;32m~/anaconda3/envs/stt/lib/python3.8/site-packages/transformers/trainer.py:1892\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   1889\u001b[0m     \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mcontrol \u001b[39m=\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mcallback_handler\u001b[39m.\u001b[39mon_step_begin(args, \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mstate, \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mcontrol)\n\u001b[1;32m   1891\u001b[0m \u001b[39mwith\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39maccelerator\u001b[39m.\u001b[39maccumulate(model):\n\u001b[0;32m-> 1892\u001b[0m     tr_loss_step \u001b[39m=\u001b[39m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mtraining_step(model, inputs)\n\u001b[1;32m   1894\u001b[0m \u001b[39mif\u001b[39;00m (\n\u001b[1;32m   1895\u001b[0m     args\u001b[39m.\u001b[39mlogging_nan_inf_filter\n\u001b[1;32m   1896\u001b[0m     \u001b[39mand\u001b[39;00m \u001b[39mnot\u001b[39;00m is_torch_tpu_available()\n\u001b[1;32m   1897\u001b[0m     \u001b[39mand\u001b[39;00m (torch\u001b[39m.\u001b[39misnan(tr_loss_step) \u001b[39mor\u001b[39;00m torch\u001b[39m.\u001b[39misinf(tr_loss_step))\n\u001b[1;32m   1898\u001b[0m ):\n\u001b[1;32m   1899\u001b[0m     \u001b[39m# if loss is nan or inf simply add the average of previous logged losses\u001b[39;00m\n\u001b[1;32m   1900\u001b[0m     tr_loss \u001b[39m+\u001b[39m\u001b[39m=\u001b[39m tr_loss \u001b[39m/\u001b[39m (\u001b[39m1\u001b[39m \u001b[39m+\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mstate\u001b[39m.\u001b[39mglobal_step \u001b[39m-\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_globalstep_last_logged)\n",
-      "File \u001b[0;32m~/anaconda3/envs/stt/lib/python3.8/site-packages/transformers/trainer.py:2787\u001b[0m, in \u001b[0;36mTrainer.training_step\u001b[0;34m(self, model, inputs)\u001b[0m\n\u001b[1;32m   2785\u001b[0m         scaled_loss\u001b[39m.\u001b[39mbackward()\n\u001b[1;32m   2786\u001b[0m \u001b[39melse\u001b[39;00m:\n\u001b[0;32m-> 2787\u001b[0m     \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49maccelerator\u001b[39m.\u001b[39;49mbackward(loss)\n\u001b[1;32m   2789\u001b[0m \u001b[39mreturn\u001b[39;00m loss\u001b[39m.\u001b[39mdetach() \u001b[39m/\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39margs\u001b[39m.\u001b[39mgradient_accumulation_steps\n",
-      "File \u001b[0;32m~/anaconda3/envs/stt/lib/python3.8/site-packages/accelerate/accelerator.py:1983\u001b[0m, in \u001b[0;36mAccelerator.backward\u001b[0;34m(self, loss, **kwargs)\u001b[0m\n\u001b[1;32m   1981\u001b[0m     \u001b[39mreturn\u001b[39;00m\n\u001b[1;32m   1982\u001b[0m \u001b[39melif\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mscaler \u001b[39mis\u001b[39;00m \u001b[39mnot\u001b[39;00m \u001b[39mNone\u001b[39;00m:\n\u001b[0;32m-> 1983\u001b[0m     \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mscaler\u001b[39m.\u001b[39;49mscale(loss)\u001b[39m.\u001b[39;49mbackward(\u001b[39m*\u001b[39;49m\u001b[39m*\u001b[39;49mkwargs)\n\u001b[1;32m   1984\u001b[0m \u001b[39melse\u001b[39;00m:\n\u001b[1;32m   1985\u001b[0m     loss\u001b[39m.\u001b[39mbackward(\u001b[39m*\u001b[39m\u001b[39m*\u001b[39mkwargs)\n",
-      "File \u001b[0;32m~/anaconda3/envs/stt/lib/python3.8/site-packages/torch/_tensor.py:487\u001b[0m, in \u001b[0;36mTensor.backward\u001b[0;34m(self, gradient, retain_graph, create_graph, inputs)\u001b[0m\n\u001b[1;32m    477\u001b[0m \u001b[39mif\u001b[39;00m has_torch_function_unary(\u001b[39mself\u001b[39m):\n\u001b[1;32m    478\u001b[0m     \u001b[39mreturn\u001b[39;00m handle_torch_function(\n\u001b[1;32m    479\u001b[0m         Tensor\u001b[39m.\u001b[39mbackward,\n\u001b[1;32m    480\u001b[0m         (\u001b[39mself\u001b[39m,),\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    485\u001b[0m         inputs\u001b[39m=\u001b[39minputs,\n\u001b[1;32m    486\u001b[0m     )\n\u001b[0;32m--> 487\u001b[0m torch\u001b[39m.\u001b[39;49mautograd\u001b[39m.\u001b[39;49mbackward(\n\u001b[1;32m    488\u001b[0m     \u001b[39mself\u001b[39;49m, gradient, retain_graph, create_graph, inputs\u001b[39m=\u001b[39;49minputs\n\u001b[1;32m    489\u001b[0m )\n",
-      "File \u001b[0;32m~/anaconda3/envs/stt/lib/python3.8/site-packages/torch/autograd/__init__.py:197\u001b[0m, in \u001b[0;36mbackward\u001b[0;34m(tensors, grad_tensors, retain_graph, create_graph, grad_variables, inputs)\u001b[0m\n\u001b[1;32m    192\u001b[0m     retain_graph \u001b[39m=\u001b[39m create_graph\n\u001b[1;32m    194\u001b[0m \u001b[39m# The reason we repeat same the comment below is that\u001b[39;00m\n\u001b[1;32m    195\u001b[0m \u001b[39m# some Python versions print out the first line of a multi-line function\u001b[39;00m\n\u001b[1;32m    196\u001b[0m \u001b[39m# calls in the traceback and some print out the last line\u001b[39;00m\n\u001b[0;32m--> 197\u001b[0m Variable\u001b[39m.\u001b[39;49m_execution_engine\u001b[39m.\u001b[39;49mrun_backward(  \u001b[39m# Calls into the C++ engine to run the backward pass\u001b[39;49;00m\n\u001b[1;32m    198\u001b[0m     tensors, grad_tensors_, retain_graph, create_graph, inputs,\n\u001b[1;32m    199\u001b[0m     allow_unreachable\u001b[39m=\u001b[39;49m\u001b[39mTrue\u001b[39;49;00m, accumulate_grad\u001b[39m=\u001b[39;49m\u001b[39mTrue\u001b[39;49;00m)\n",
-      "File \u001b[0;32m~/anaconda3/envs/stt/lib/python3.8/site-packages/torch/autograd/function.py:267\u001b[0m, in \u001b[0;36mBackwardCFunction.apply\u001b[0;34m(self, *args)\u001b[0m\n\u001b[1;32m    263\u001b[0m     \u001b[39mraise\u001b[39;00m \u001b[39mRuntimeError\u001b[39;00m(\u001b[39m\"\u001b[39m\u001b[39mImplementing both \u001b[39m\u001b[39m'\u001b[39m\u001b[39mbackward\u001b[39m\u001b[39m'\u001b[39m\u001b[39m and \u001b[39m\u001b[39m'\u001b[39m\u001b[39mvjp\u001b[39m\u001b[39m'\u001b[39m\u001b[39m for a custom \u001b[39m\u001b[39m\"\u001b[39m\n\u001b[1;32m    264\u001b[0m                        \u001b[39m\"\u001b[39m\u001b[39mFunction is not allowed. You should only implement one \u001b[39m\u001b[39m\"\u001b[39m\n\u001b[1;32m    265\u001b[0m                        \u001b[39m\"\u001b[39m\u001b[39mof them.\u001b[39m\u001b[39m\"\u001b[39m)\n\u001b[1;32m    266\u001b[0m user_fn \u001b[39m=\u001b[39m vjp_fn \u001b[39mif\u001b[39;00m vjp_fn \u001b[39mis\u001b[39;00m \u001b[39mnot\u001b[39;00m Function\u001b[39m.\u001b[39mvjp \u001b[39melse\u001b[39;00m backward_fn\n\u001b[0;32m--> 267\u001b[0m \u001b[39mreturn\u001b[39;00m user_fn(\u001b[39mself\u001b[39;49m, \u001b[39m*\u001b[39;49margs)\n",
-      "File \u001b[0;32m~/anaconda3/envs/stt/lib/python3.8/site-packages/torch/utils/checkpoint.py:157\u001b[0m, in \u001b[0;36mCheckpointFunction.backward\u001b[0;34m(ctx, *args)\u001b[0m\n\u001b[1;32m    153\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mlen\u001b[39m(outputs_with_grad) \u001b[39m==\u001b[39m \u001b[39m0\u001b[39m:\n\u001b[1;32m    154\u001b[0m     \u001b[39mraise\u001b[39;00m \u001b[39mRuntimeError\u001b[39;00m(\n\u001b[1;32m    155\u001b[0m         \u001b[39m\"\u001b[39m\u001b[39mnone of output has requires_grad=True,\u001b[39m\u001b[39m\"\u001b[39m\n\u001b[1;32m    156\u001b[0m         \u001b[39m\"\u001b[39m\u001b[39m this checkpoint() is not necessary\u001b[39m\u001b[39m\"\u001b[39m)\n\u001b[0;32m--> 157\u001b[0m torch\u001b[39m.\u001b[39;49mautograd\u001b[39m.\u001b[39;49mbackward(outputs_with_grad, args_with_grad)\n\u001b[1;32m    158\u001b[0m grads \u001b[39m=\u001b[39m \u001b[39mtuple\u001b[39m(inp\u001b[39m.\u001b[39mgrad \u001b[39mif\u001b[39;00m \u001b[39misinstance\u001b[39m(inp, torch\u001b[39m.\u001b[39mTensor) \u001b[39melse\u001b[39;00m \u001b[39mNone\u001b[39;00m\n\u001b[1;32m    159\u001b[0m               \u001b[39mfor\u001b[39;00m inp \u001b[39min\u001b[39;00m detached_inputs)\n\u001b[1;32m    161\u001b[0m \u001b[39mreturn\u001b[39;00m (\u001b[39mNone\u001b[39;00m, \u001b[39mNone\u001b[39;00m) \u001b[39m+\u001b[39m grads\n",
-      "File \u001b[0;32m~/anaconda3/envs/stt/lib/python3.8/site-packages/torch/autograd/__init__.py:197\u001b[0m, in \u001b[0;36mbackward\u001b[0;34m(tensors, grad_tensors, retain_graph, create_graph, grad_variables, inputs)\u001b[0m\n\u001b[1;32m    192\u001b[0m     retain_graph \u001b[39m=\u001b[39m create_graph\n\u001b[1;32m    194\u001b[0m \u001b[39m# The reason we repeat same the comment below is that\u001b[39;00m\n\u001b[1;32m    195\u001b[0m \u001b[39m# some Python versions print out the first line of a multi-line function\u001b[39;00m\n\u001b[1;32m    196\u001b[0m \u001b[39m# calls in the traceback and some print out the last line\u001b[39;00m\n\u001b[0;32m--> 197\u001b[0m Variable\u001b[39m.\u001b[39;49m_execution_engine\u001b[39m.\u001b[39;49mrun_backward(  \u001b[39m# Calls into the C++ engine to run the backward pass\u001b[39;49;00m\n\u001b[1;32m    198\u001b[0m     tensors, grad_tensors_, retain_graph, create_graph, inputs,\n\u001b[1;32m    199\u001b[0m     allow_unreachable\u001b[39m=\u001b[39;49m\u001b[39mTrue\u001b[39;49;00m, accumulate_grad\u001b[39m=\u001b[39;49m\u001b[39mTrue\u001b[39;49;00m)\n",
-      "\u001b[0;31mOutOfMemoryError\u001b[0m: CUDA out of memory. Tried to allocate 6.44 GiB (GPU 0; 23.64 GiB total capacity; 16.89 GiB already allocated; 211.81 MiB free; 22.32 GiB reserved in total by PyTorch) If reserved memory is >> allocated memory try setting max_split_size_mb to avoid fragmentation.  See documentation for Memory Management and PYTORCH_CUDA_ALLOC_CONF"
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'loss': 2.0528, 'learning_rate': 4.4e-07, 'epoch': 0.02}\n",
+      "{'loss': 1.6367, 'learning_rate': 9.400000000000001e-07, 'epoch': 0.04}\n",
+      "{'loss': 1.2439, 'learning_rate': 1.44e-06, 'epoch': 0.05}\n",
+      "{'loss': 0.7302, 'learning_rate': 1.94e-06, 'epoch': 0.07}\n",
+      "{'loss': 0.5361, 'learning_rate': 2.4400000000000004e-06, 'epoch': 0.09}\n",
+      "{'loss': 0.4687, 'learning_rate': 2.9400000000000002e-06, 'epoch': 0.11}\n",
+      "{'loss': 0.4293, 'learning_rate': 3.44e-06, 'epoch': 0.13}\n",
+      "{'loss': 0.3663, 'learning_rate': 3.94e-06, 'epoch': 0.14}\n",
+      "{'loss': 0.3301, 'learning_rate': 4.440000000000001e-06, 'epoch': 0.16}\n",
+      "{'loss': 0.3001, 'learning_rate': 4.94e-06, 'epoch': 0.18}\n",
+      "{'loss': 0.2242, 'learning_rate': 5.4400000000000004e-06, 'epoch': 0.2}\n",
+      "{'loss': 0.2262, 'learning_rate': 5.94e-06, 'epoch': 0.22}\n",
+      "{'loss': 0.2143, 'learning_rate': 6.440000000000001e-06, 'epoch': 0.23}\n",
+      "{'loss': 0.2019, 'learning_rate': 6.9400000000000005e-06, 'epoch': 0.25}\n",
+      "{'loss': 0.1992, 'learning_rate': 7.440000000000001e-06, 'epoch': 0.27}\n"
      ]
     }
    ],
@@ -755,10 +543,10 @@
    "outputs": [],
    "source": [
     "kwargs = {\n",
-    "    \"dataset_tags\": \"mozilla-foundation/common_voice_11_0\",\n",
+    "    \"dataset_tags\": \"kresnik/zeroth_korean\",\n",
     "    \"dataset\": \"zeroth_korean\",  # a 'pretty' name for the training dataset\n",
-    "    \"language\": \"hi\",\n",
-    "    \"model_name\": \"Whisper Small Hi - Sanchit Gandhi\",  # a 'pretty' name for your model\n",
+    "    \"language\": \"ko\",\n",
+    "    \"model_name\": \"Whisper Small Ko\",  # a 'pretty' name for your model\n",
     "    \"finetuned_from\": \"openai/whisper-small\",\n",
     "    \"tasks\": \"automatic-speech-recognition\",\n",
     "    \"tags\": \"whisper-event\",\n",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cddb675e1cf557b1a6326846a2385741c669e6a0d34dee3f65cc9f58add729e4
+oid sha256:62c514187e98b3a26a315cb738cd44d24e71b91b83d22b4b6e336329fe80abf2
 size 4155