update model card README.md

.ipynb_checkpoints/Untitled-checkpoint.ipynb

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

README.md

@@ -0,0 +1,62 @@
+---
+tags:
+- generated_from_trainer
+metrics:
+- bleu
+model-index:
+- name: mBART_translator_json_all_2
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# mBART_translator_json_all_2
+
+This model is a fine-tuned version of [facebook/mbart-large-cc25](https://huggingface.co/facebook/mbart-large-cc25) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1595
+- Bleu: 76.137
+- Gen Len: 11.966
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Bleu    | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
+| 1.914         | 1.0   | 2908 | 0.7158          | 26.1202 | 44.2761 |
+| 0.948         | 2.0   | 5816 | 0.3113          | 74.3952 | 12.4625 |
+| 0.5552        | 3.0   | 8724 | 0.1595          | 76.137  | 11.966  |
+
+
+### Framework versions
+
+- Transformers 4.17.0
+- Pytorch 1.12.0
+- Datasets 1.18.3
+- Tokenizers 0.11.0

Untitled.ipynb

@@ -1,558 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "8f8a2b2c-8606-4217-85bf-b5e7b737acbd",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "3c797ac5-85bc-483e-82b1-331d8a10581c",
-   "metadata": {
-    "id": "X78SICZhiOU5"
-   },
-   "outputs": [
-    {
-     "ename": "AttributeError",
-     "evalue": "'collections.OrderedDict' object has no attribute 'to'",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[1;31mAttributeError\u001b[0m                            Traceback (most recent call last)",
-      "Input \u001b[1;32mIn [9]\u001b[0m, in \u001b[0;36m<cell line: 3>\u001b[1;34m()\u001b[0m\n\u001b[0;32m      1\u001b[0m model \u001b[38;5;241m=\u001b[39m torch\u001b[38;5;241m.\u001b[39mload(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mpytorch_model.bin\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[0;32m      2\u001b[0m device \u001b[38;5;241m=\u001b[39m torch\u001b[38;5;241m.\u001b[39mdevice(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcuda\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m----> 3\u001b[0m \u001b[43mmodel\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mto\u001b[49m(device)\n\u001b[0;32m      4\u001b[0m model\u001b[38;5;241m.\u001b[39meval()\n",
-      "\u001b[1;31mAttributeError\u001b[0m: 'collections.OrderedDict' object has no attribute 'to'"
-     ]
-    }
-   ],
-   "source": [
-    "model = torch.load('pytorch_model.bin')\n",
-    "device = torch.device(\"cuda\")\n",
-    "model.to(device)\n",
-    "model.eval()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "d738795b-24af-4194-ae57-d757fc2dbfb8",
-   "metadata": {
-    "id": "ZOitQbWQBUF0"
-   },
-   "source": [
-    "# Get the Score"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "b3613c9c-a5d3-44b3-947f-21ffad526c7d",
-   "metadata": {
-    "id": "Xm580mBbBhpe"
-   },
-   "outputs": [],
-   "source": [
-    "import torch"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "8b63ea65-0ce7-43f8-8799-9e73d776898e",
-   "metadata": {
-    "id": "IsCCLx1uBjcZ"
-   },
-   "outputs": [],
-   "source": [
-    "device = torch.device(\"cuda\") # if torch.cuda.is_available() else \"cpu\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "6ffcb2f2-fb2e-42f9-a16c-1b9b1cfdc32a",
-   "metadata": {
-    "colab": {
-     "base_uri": "https://localhost:8080/"
-    },
-    "id": "qBRxA4mTBke8",
-    "outputId": "75886e1c-cefd-432e-f681-dcc2ae268369"
-   },
-   "outputs": [
-    {
-     "ename": "NameError",
-     "evalue": "name 'model' is not defined",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[1;31mNameError\u001b[0m                                 Traceback (most recent call last)",
-      "Input \u001b[1;32mIn [3]\u001b[0m, in \u001b[0;36m<cell line: 1>\u001b[1;34m()\u001b[0m\n\u001b[1;32m----> 1\u001b[0m \u001b[43mmodel\u001b[49m\u001b[38;5;241m.\u001b[39mto(device)\n\u001b[0;32m      2\u001b[0m model\u001b[38;5;241m.\u001b[39meval()\n",
-      "\u001b[1;31mNameError\u001b[0m: name 'model' is not defined"
-     ]
-    }
-   ],
-   "source": [
-    "model.to(device)\n",
-    "model.eval()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "id": "c956811c-b2e6-4601-b737-1fd09d49cc3c",
-   "metadata": {
-    "id": "y7eiuqiJB8mW",
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "from torch.utils.data import Dataset, DataLoader\n",
-    "\n",
-    "class DatasetRetriever(Dataset):\n",
-    "    def __init__(self, features):\n",
-    "        super(DatasetRetriever, self).__init__()\n",
-    "        self.features = features\n",
-    "\n",
-    "    def __len__(self):\n",
-    "        return len(self.features)\n",
-    "    \n",
-    "    def __getitem__(self, index):   \n",
-    "        feature = self.features[index]\n",
-    "        max_target_length = 50\n",
-    "        embedding = tokenizer(feature, max_length=max_target_length, truncation=True)\n",
-    "        # embedding = tokenizer(feature, truncation=True, max_length=512, return_attention_mask=False, return_token_type_ids=False)\n",
-    "        return {'input_ids' : embedding['input_ids']}"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 13,
-   "id": "e01fe9fe-4b44-4730-aa13-6b59f6811c4d",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "903\n"
-     ]
-    }
-   ],
-   "source": [
-    "import pandas as pd\n",
-    "original = pd.read_csv(\"./DeepLoading/Slang/slang_dataframe.csv\")\n",
-    "print(len(original))  "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "id": "3b36ede5-546e-4b89-9b0f-c942224fb6b2",
-   "metadata": {
-    "id": "0YJZuvMCYYUg"
-   },
-   "outputs": [],
-   "source": [
-    "test_slang, test_answer = [], []\n",
-    "for i in range(100):\n",
-    "    test_slang.append(original['slang'][i])\n",
-    "    test_answer.append(original['standard'][i])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 15,
-   "id": "a5e50a50-ce56-41f2-918e-9516e3162f73",
-   "metadata": {
-    "id": "Ffd1xDXsCBMU"
-   },
-   "outputs": [],
-   "source": [
-    "test_dataset = DatasetRetriever(test_slang)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 16,
-   "id": "67a2e271-4d04-42c9-8c8b-0fd554aa0ea0",
-   "metadata": {
-    "colab": {
-     "base_uri": "https://localhost:8080/"
-    },
-    "id": "xQDf51qIYkeu",
-    "outputId": "547c9f14-b31d-4e0e-f68c-ae03dceeeedd"
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "<__main__.DatasetRetriever at 0x1e9dd5ceee0>"
-      ]
-     },
-     "execution_count": 16,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "test_dataset"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 17,
-   "id": "949de28e-8f30-4494-8eb8-b406eb7acec7",
-   "metadata": {
-    "id": "Fs5W7QapCC5y"
-   },
-   "outputs": [],
-   "source": [
-    "from transformers import DataCollatorForSeq2Seq\n",
-    "data_collator = DataCollatorForSeq2Seq(tokenizer, model=model)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 18,
-   "id": "258a1ba2-08c3-43b3-8016-ea5adce470de",
-   "metadata": {
-    "id": "j7J8i2k9CI0o"
-   },
-   "outputs": [],
-   "source": [
-    "collator = DataCollatorForSeq2Seq(tokenizer, model)\n",
-    "\n",
-    "test_loader = DataLoader(\n",
-    "    test_dataset,\n",
-    "    batch_size=4, \n",
-    "    shuffle=False,\n",
-    "    collate_fn=collator,\n",
-    "    num_workers=1)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 19,
-   "id": "02ffd5ae-bc39-4f6c-ab71-c3b346cdf51a",
-   "metadata": {
-    "colab": {
-     "base_uri": "https://localhost:8080/"
-    },
-    "id": "1YEoF7QUnsab",
-    "outputId": "d4417fc2-4827-4a9e-b196-82fb99f68006"
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "<torch.utils.data.dataloader.DataLoader at 0x1e9de53adc0>"
-      ]
-     },
-     "execution_count": 19,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "test_loader"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 20,
-   "id": "0354a617-a667-49b5-a9cd-cad56c9e7f38",
-   "metadata": {
-    "id": "o4k2lYoOCOX8"
-   },
-   "outputs": [],
-   "source": [
-    "from tqdm import tqdm\n",
-    "\n",
-    "def get_prediction(text):\n",
-    "    embeddings = tokenizer(text, max_length=256, return_attention_mask=False, return_token_type_ids=False, return_tensors='pt')\n",
-    "    embeddings.to(device)\n",
-    "    output = model.generate(**embeddings, max_length=256, bos_token_id=tokenizer.cls_token_id, eos_token_id=tokenizer.sep_token_id)[0, 0:-1].cpu()\n",
-    "    return tokenizer.decode(output[1:])\n",
-    "\n",
-    "def get_predictions(data):\n",
-    "    # inputs = processor(batch[\"speech\"], sampling_rate=16000, return_tensors=\"pt\", padding=\"longest\")\n",
-    "    result = []\n",
-    "    for batch in tqdm(data):\n",
-    "        batch = {key: value.to(device) for key, value in batch.items()}\n",
-    "        print(batch)\n",
-    "        output = model.generate(batch['input_ids'], max_length=256).cpu()\n",
-    "        try:\n",
-    "            outputs = [tokenizer.decode(item[2:item.tolist().index(tokenizer.sep_token_id)]) for item in output]\n",
-    "        except ValueError:\n",
-    "            outputs = [tokenizer.decode(item[2:]) for item in output]\n",
-    "        result.extend(outputs)\n",
-    "    return result"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 21,
-   "id": "338b3ed5-0f39-4a4d-896e-1ffb258c6223",
-   "metadata": {
-    "colab": {
-     "base_uri": "https://localhost:8080/"
-    },
-    "id": "zSRHHADHCRC0",
-    "outputId": "bb0f0d98-260f-4d1b-d81b-6e3c5902bcc6"
-   },
-   "outputs": [],
-   "source": [
-    "# embeddings = tokenizer(\"5층에서 3개월째 구조대 기다리고 있는데 탈출할 기미가 안보여. 언제까지 존버해야 될지 모르겠지만 익절을 해 독기로 버틴다. 그래도 점점 오르고 있는 추세니까 해볼만 해.\", return_attention_mask=False, return_token_type_ids=False, return_tensors='pt')\n",
-    "# print(embeddings)\n",
-    "# embeddings.to(device)\n",
-    "# output = model.generate(**embeddings, max_length=256, bos_token_id=tokenizer.cls_token_id, eos_token_id=tokenizer.sep_token_id)[0, 0:-1].cpu()\n",
-    "# print(output)\n",
-    "# print(tokenizer.decode(output[1:]))"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 22,
-   "id": "e065f9b3-5f8b-4ce1-bf94-9a7de422658c",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "print\n"
-     ]
-    }
-   ],
-   "source": [
-    "print(\"print\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 23,
-   "id": "0882dd65-260a-4728-9ce3-9138f70e6b15",
-   "metadata": {
-    "id": "iUfIalpvgMAw"
-   },
-   "outputs": [
-    {
-     "ename": "NameError",
-     "evalue": "name 'train' is not defined",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[1;31mNameError\u001b[0m                                 Traceback (most recent call last)",
-      "Input \u001b[1;32mIn [23]\u001b[0m, in \u001b[0;36m<cell line: 1>\u001b[1;34m()\u001b[0m\n\u001b[1;32m----> 1\u001b[0m train \u001b[38;5;241m=\u001b[39m \u001b[43mtrain\u001b[49m\u001b[38;5;241m.\u001b[39mdrop([\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mUnnamed: 0\u001b[39m\u001b[38;5;124m'\u001b[39m], axis \u001b[38;5;241m=\u001b[39m \u001b[38;5;241m1\u001b[39m)\n",
-      "\u001b[1;31mNameError\u001b[0m: name 'train' is not defined"
-     ]
-    }
-   ],
-   "source": [
-    "train = train.drop(['Unnamed: 0'], axis = 1)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "b5794321-bec2-41da-bfac-6d656cfc2db9",
-   "metadata": {
-    "colab": {
-     "base_uri": "https://localhost:8080/"
-    },
-    "id": "Enk7jC6AC1BM",
-    "outputId": "ccc150d4-907f-4833-a3fa-b4c795fd4a26"
-   },
-   "outputs": [],
-   "source": [
-    "rnd_num = []\n",
-    "for i in range(30):\n",
-    "    rnd_num.append(random.randint(0, len(train)))\n",
-    "print(rnd_num)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "fca0a6ae-1d1e-4949-93e1-70c47c7fd1e8",
-   "metadata": {
-    "colab": {
-     "base_uri": "https://localhost:8080/"
-    },
-    "id": "Lm1dGSuXCU8I",
-    "outputId": "21f3feaa-90e8-47d4-b2b7-2f581d9e4d7f"
-   },
-   "outputs": [],
-   "source": [
-    "for i in range(5):\n",
-    "    print(\"original:   \", slang[i])\n",
-    "    print(\"answer:     \", standard[i])\n",
-    "    print(\"prediction: \", get_prediction(slang[i]) , \"\\n\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 24,
-   "id": "0455c8b4-3606-4d25-89e4-27d290f47930",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import random as rand \n",
-    "random_num = []\n",
-    "for i in range(100):\n",
-    "    num = rand.randint(0, len(original))\n",
-    "    random_num.append(num)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 26,
-   "id": "ec73f1f9-dd5f-4f21-a118-b4fd50428e48",
-   "metadata": {
-    "colab": {
-     "base_uri": "https://localhost:8080/"
-    },
-    "id": "lfjfmq5JZ6X_",
-    "outputId": "a6cf8c09-4eba-49f9-9fe5-ba25dcf7c65d"
-   },
-   "outputs": [],
-   "source": [
-    "prediction = []\n",
-    "for i in range(10):\n",
-    "    prediction.append(get_prediction(original['slang'][i]))"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 28,
-   "id": "3386b8ae-71ea-4e9c-8a92-4ce2ef6a0bcb",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "시험기간에 스카가서 나는 폰으로 유튜브 봤는데 주위에서 다들 열공하는 모습에 현타옴 앞으로 나도 열심히 해야겠어.\n",
-      "하교 시간에 초등학교 앞을 지나가니까 그 잠깐 사이에 급식체를 원없이 들을 수 있었어.\n",
-      "버스에서 급식충들이 자기들끼리 시끄럽게 떠드는 소리에 머리가 지끈거렸어.\n",
-      "일주일 내내 약속이 있다니. 너 정말 인싸구나.\n",
-      "같이 놀 친구가 없어서 이번 수학여행을 갈지 말지 고민이야， 나는 아무래도 아싸인가봐.\n",
-      "이번에 쟤가 전교 1등이라고 했지? 공부도 잘하는데 인기도 많고 진짜 엄친아인 것 같아.\n",
-      "어쩔 수 없다. 이렇게 된 이상 이번 시험은 조삼모사 전략으로 갈게， 우리 평균만 넘자.\n",
-      "올해 사망년이라 진로 걱정도 많고 취업 걱정도 많아서 힘들어. 아무 걱정 없던 새내기 때로 돌아가고 싶다.\n",
-      "생명과학 교양 첫 수업이었는데 국어국문학과인 나는 도저히 무슨 소리인지 하나도 모르겠어서 정말 문송했어.\n",
-      "이번 중간고사에서 역대급으로 어려웠는데 올백이 나왔다고? 믿기지가 않아.\n"
-     ]
-    }
-   ],
-   "source": [
-    "for i in range(10):\n",
-    "    print(original['slang'][i])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "2c59bf28-dba7-4d09-a7a4-de31b0cc8d03",
-   "metadata": {
-    "colab": {
-     "base_uri": "https://localhost:8080/"
-    },
-    "id": "4316coIrCt8U",
-    "outputId": "f5fdaccf-6c88-49f2-de2b-f738d557371f"
-   },
-   "outputs": [],
-   "source": [
-    "import nltk\n",
-    "\n",
-    "BLEUscore_sum = []\n",
-    "order = 0 \n",
-    "for i in random_num:\n",
-    "    hypothesis = prediction[order]\n",
-    "    reference = original['standard'][i]\n",
-    "    BLEU = nltk.translate.bleu_score.sentence_bleu([reference], hypothesis)\n",
-    "    BLEUscore_sum.append(BLEU)\n",
-    "    order += 1 "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "a7c2760a-e3b2-4f58-b304-b169875b675e",
-   "metadata": {
-    "colab": {
-     "base_uri": "https://localhost:8080/"
-    },
-    "id": "go5ElXjlCvtm",
-    "outputId": "4aff6690-f5e5-41e2-98e8-73d25f2bd0d9",
-    "scrolled": true
-   },
-   "outputs": [],
-   "source": [
-    "avg = sum(BLEUscore_sum, 0.0) / len(BLEUscore_sum)\n",
-    "print(\"테스트 데이터셋 BLEU 스코어: \", avg)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "d1cd78f9-fe66-47d1-9168-874888d72786",
-   "metadata": {
-    "colab": {
-     "base_uri": "https://localhost:8080/"
-    },
-    "id": "m9BtsCieiciv",
-    "outputId": "6fd739a6-e012-47d7-f425-a5ac0139ab61",
-    "scrolled": true
-   },
-   "outputs": [],
-   "source": [
-    "order = 0\n",
-    "for i in random_num:\n",
-    "    print(\"original:   \", original['slang'][i])\n",
-    "    print(\"answer:     \", original['standard'][i])\n",
-    "    print(\"prediction: \", prediction[order] , \"\\n\")\n",
-    "    order += 1"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "4e4f1064-a7b5-43ef-adb0-ec2821d0b22c",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "fb06b3d8-3046-44c5-b0af-bdcfd7a70b23",
-   "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": "3.9.13"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}