add the trained bert model

biobertALL_2epoch/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "dmis-lab/biobert-v1.1",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.24.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

biobertALL_2epoch/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e43d39cd8ab7b074dc264efadcc533c4a0bc8e25ed40e1169db91a0f1964908
+size 433318253

biobertALL_2epoch/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fd95089f8d96b6e2eb676380bfb0f2e152c0958f53795c9d26684f86a1b15cb
+size 3375

bluebertALL_2epoch/config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "bionlp/bluebert_pubmed_mimic_uncased_L-12_H-768_A-12",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.24.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

bluebertALL_2epoch/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5326fa9a67f154bfe9d9a1a9dbaedce7ff57e084db8d28807e519d8374a321e
+size 438006125

bluebertALL_2epoch/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acd211e3873a8f509ac9d21577c002397f9d5fb46c4f79660a9cd15e366c89db
+size 3375

clinicalbertALL_2epoch/config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "emilyalsentzer/Bio_ClinicalBERT",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.24.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

clinicalbertALL_2epoch/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2b8c199354cdf3606d28dc93e71670d25f1578ba67d01e0f34688ccb9ea193e
+size 433318253

clinicalbertALL_2epoch/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f405affa2b551e07a9d9af99be6aeb04f3b5cbe9c6f6527a18af82eecec495ee
+size 3375

pubmedbertALL_2epoch/config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.24.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

pubmedbertALL_2epoch/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c7f895c557f9748aab145e6f8e4f3727dfad0360ddd9482b607ec303a1e31d8
+size 438006125

pubmedbertALL_2epoch/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7b06c52d751e2b0e5bd6bc2e787ee7331e5f4b0793ca6f1a71fc878afea1cd4
+size 3375

ranking_responses.ipynb

@@ -0,0 +1,406 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# import the package\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "import datasets\n",
+    "import evaluate\n",
+    "from datasets import DatasetDict, Dataset\n",
+    "from transformers import AutoTokenizer, Trainer, BertForSequenceClassification\n",
+    "import torch\n",
+    "from accelerate import Accelerator"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Attention:  \n",
+    "\n",
+    "This file is used to ranking the response. It will calculate the probability for each sample_answer and return the most probability one and the index of it.  \n",
+    "\n",
+    "The file only contains answers to one question is recommended or we need to split the dataframe manually.\n",
+    "\n",
+    "The input of the function is the path of the file and the file of the pretrained model and corresponding tokenizer."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# load the data\n",
+    "\n",
+    "path = 'C:/Users/cxz55/Desktop/UCL/term2/COMP087/cw/data_nlp_porject' #!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!\n",
+    "file_name = 'five_responses.csv' #!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!\n",
+    "\n",
+    "def load_data(path,file_name):\n",
+    "\n",
+    "    path = '/'.join([path,file_name])\n",
+    "    test_response = pd.read_csv(path)\n",
+    "    return test_response"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Some weights of BertForSequenceClassification were not initialized from the model checkpoint at dmis-lab/biobert-v1.1 and are newly initialized: ['classifier.bias', 'classifier.weight']\n",
+      "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
+     ]
+    }
+   ],
+   "source": [
+    "# give the model and corresponfing tokenizer\n",
+    "\n",
+    "# the base models we used are:\n",
+    "# \"emilyalsentzer/Bio_ClinicalBERT\"     \n",
+    "# \"dmis-lab/biobert-v1.1\"\n",
+    "# \"microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext\"\n",
+    "# \"allenai/scibert_scivocab_uncased\"\n",
+    "# \"bionlp/bluebert_pubmed_mimic_uncased_L-12_H-768_A-12\"\n",
+    "\n",
+    "# model_name = 'dmis-lab/biobert-v1.1' #!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!\n",
+    "# model = BertForSequenceClassification.from_pretrained(model_name, num_labels=2)\n",
+    "\n",
+    "# tokenizer_name = 'dmis-lab/biobert-v1.1' #!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!\n",
+    "# tokenizer = AutoTokenizer.from_pretrained(tokenizer_name)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# def tokenize_function(data):\n",
+    "#     return tokenizer(data['Question'],data['Answer'],padding='max_length',truncation=True,max_length=128)\n",
+    "\n",
+    "# def compute_metrics(eval_preds):\n",
+    "#   metric = evaluate.load(\"accuracy\")\n",
+    "#   x,y = eval_preds\n",
+    "#   preds = np.argmax(x, -1)\n",
+    "#   return metric.compute(predictions=preds, references=y)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# # add device\n",
+    "# accelerator = Accelerator()\n",
+    "# device = accelerator.device"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# build the model\n",
+    "# trainer = Trainer(\n",
+    "#     model=model.to(device),\n",
+    "#     # args=training_args,\n",
+    "#     # data_collator=data_collator,\n",
+    "#     tokenizer=tokenizer,\n",
+    "#     compute_metrics=compute_metrics,\n",
+    "# )"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# # dealing with data: from dataframe transform into DatasetDict\n",
+    "# data_set = load_data(path,file_name)\n",
+    "# data_dict = Dataset.from_pandas(data_set)\n",
+    "# data_dict_token = data_dict.map(tokenize_function, batched=8)\n",
+    "# # make prediction\n",
+    "# prediction = trainer.predict(data_dict_token)\n",
+    "# logits = torch.tensor(prediction.predictions)\n",
+    "# prob = torch.softmax(logits,dim=1)\n",
+    "# right_prob = prob[:,1]\n",
+    "# prob_list = right_prob.tolist()\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def prob_position(path, file_name, model_name,tokenizer_name):\n",
+    "\n",
+    "    # the list of model name:\n",
+    "    # the base models we used are:\n",
+    "    # \"emilyalsentzer/Bio_ClinicalBERT\"     \n",
+    "    # \"dmis-lab/biobert-v1.1\"\n",
+    "    # \"microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext\"\n",
+    "    # \"allenai/scibert_scivocab_uncased\"\n",
+    "    # \"bionlp/bluebert_pubmed_mimic_uncased_L-12_H-768_A-12\"\n",
+    "\n",
+    "    model = BertForSequenceClassification.from_pretrained(model_name, num_labels=2)\n",
+    "    tokenizer = AutoTokenizer.from_pretrained(tokenizer_name)\n",
+    "\n",
+    "    # define the tokenizing map and the metrics\n",
+    "    def tokenize_function(data):\n",
+    "        return tokenizer(data['Question'],data['Answer'],padding='max_length',truncation=True,max_length=128)\n",
+    "    def compute_metrics(eval_preds):\n",
+    "        metric = evaluate.load(\"accuracy\")\n",
+    "        x,y = eval_preds\n",
+    "        preds = np.argmax(x, -1)\n",
+    "        return metric.compute(predictions=preds, references=y)\n",
+    "\n",
+    "    # add device\n",
+    "    accelerator = Accelerator()\n",
+    "    device = accelerator.device\n",
+    "\n",
+    "    # build trainer\n",
+    "    trainer = Trainer(\n",
+    "        model=model.to(device),\n",
+    "        # args=training_args,\n",
+    "        # data_collator=data_collator,\n",
+    "        tokenizer=tokenizer,\n",
+    "        compute_metrics=compute_metrics,\n",
+    "    )\n",
+    "\n",
+    "    # dealing with data: from dataframe transform into DatasetDict\n",
+    "    data_set = load_data(path,file_name)\n",
+    "    data_dict = Dataset.from_pandas(data_set)\n",
+    "    data_dict_token = data_dict.map(tokenize_function, batched=8)\n",
+    "    \n",
+    "    # make prediction\n",
+    "    prediction = trainer.predict(data_dict_token)\n",
+    "\n",
+    "    # transform it into probability\n",
+    "    logits = torch.tensor(prediction.predictions)\n",
+    "    prob = torch.softmax(logits,dim=1)\n",
+    "\n",
+    "    # the probability the answer is correct\n",
+    "    right_prob = prob[:,1]\n",
+    "    prob_list = right_prob.tolist()\n",
+    "\n",
+    "    max_value = max(prob_list)\n",
+    "    max_index = prob_list.index(max_value) + 1\n",
+    "\n",
+    "    print(f'\\n##############RESULT####################\\nThe index of the most proper answer is: {max_index}\\nThe probability it is correct is: {max_value}')\n",
+    "\n",
+    "    return max_value,max_index"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "loading configuration file config.json from cache at C:\\Users\\cxz55/.cache\\huggingface\\hub\\models--dmis-lab--biobert-v1.1\\snapshots\\551ca18efd7f052c8dfa0b01c94c2a8e68bc5488\\config.json\n",
+      "Model config BertConfig {\n",
+      "  \"architectures\": [\n",
+      "    \"BertModel\"\n",
+      "  ],\n",
+      "  \"attention_probs_dropout_prob\": 0.1,\n",
+      "  \"classifier_dropout\": null,\n",
+      "  \"gradient_checkpointing\": false,\n",
+      "  \"hidden_act\": \"gelu\",\n",
+      "  \"hidden_dropout_prob\": 0.1,\n",
+      "  \"hidden_size\": 768,\n",
+      "  \"initializer_range\": 0.02,\n",
+      "  \"intermediate_size\": 3072,\n",
+      "  \"layer_norm_eps\": 1e-12,\n",
+      "  \"max_position_embeddings\": 512,\n",
+      "  \"model_type\": \"bert\",\n",
+      "  \"num_attention_heads\": 12,\n",
+      "  \"num_hidden_layers\": 12,\n",
+      "  \"pad_token_id\": 0,\n",
+      "  \"position_embedding_type\": \"absolute\",\n",
+      "  \"transformers_version\": \"4.24.0\",\n",
+      "  \"type_vocab_size\": 2,\n",
+      "  \"use_cache\": true,\n",
+      "  \"vocab_size\": 28996\n",
+      "}\n",
+      "\n",
+      "loading weights file pytorch_model.bin from cache at C:\\Users\\cxz55/.cache\\huggingface\\hub\\models--dmis-lab--biobert-v1.1\\snapshots\\551ca18efd7f052c8dfa0b01c94c2a8e68bc5488\\pytorch_model.bin\n",
+      "All model checkpoint weights were used when initializing BertForSequenceClassification.\n",
+      "\n",
+      "Some weights of BertForSequenceClassification were not initialized from the model checkpoint at dmis-lab/biobert-v1.1 and are newly initialized: ['classifier.bias', 'classifier.weight']\n",
+      "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n",
+      "loading configuration file config.json from cache at C:\\Users\\cxz55/.cache\\huggingface\\hub\\models--dmis-lab--biobert-v1.1\\snapshots\\551ca18efd7f052c8dfa0b01c94c2a8e68bc5488\\config.json\n",
+      "Model config BertConfig {\n",
+      "  \"_name_or_path\": \"dmis-lab/biobert-v1.1\",\n",
+      "  \"architectures\": [\n",
+      "    \"BertModel\"\n",
+      "  ],\n",
+      "  \"attention_probs_dropout_prob\": 0.1,\n",
+      "  \"classifier_dropout\": null,\n",
+      "  \"gradient_checkpointing\": false,\n",
+      "  \"hidden_act\": \"gelu\",\n",
+      "  \"hidden_dropout_prob\": 0.1,\n",
+      "  \"hidden_size\": 768,\n",
+      "  \"initializer_range\": 0.02,\n",
+      "  \"intermediate_size\": 3072,\n",
+      "  \"layer_norm_eps\": 1e-12,\n",
+      "  \"max_position_embeddings\": 512,\n",
+      "  \"model_type\": \"bert\",\n",
+      "  \"num_attention_heads\": 12,\n",
+      "  \"num_hidden_layers\": 12,\n",
+      "  \"pad_token_id\": 0,\n",
+      "  \"position_embedding_type\": \"absolute\",\n",
+      "  \"transformers_version\": \"4.24.0\",\n",
+      "  \"type_vocab_size\": 2,\n",
+      "  \"use_cache\": true,\n",
+      "  \"vocab_size\": 28996\n",
+      "}\n",
+      "\n",
+      "loading file vocab.txt from cache at C:\\Users\\cxz55/.cache\\huggingface\\hub\\models--dmis-lab--biobert-v1.1\\snapshots\\551ca18efd7f052c8dfa0b01c94c2a8e68bc5488\\vocab.txt\n",
+      "loading file tokenizer.json from cache at None\n",
+      "loading file added_tokens.json from cache at None\n",
+      "loading file special_tokens_map.json from cache at C:\\Users\\cxz55/.cache\\huggingface\\hub\\models--dmis-lab--biobert-v1.1\\snapshots\\551ca18efd7f052c8dfa0b01c94c2a8e68bc5488\\special_tokens_map.json\n",
+      "loading file tokenizer_config.json from cache at C:\\Users\\cxz55/.cache\\huggingface\\hub\\models--dmis-lab--biobert-v1.1\\snapshots\\551ca18efd7f052c8dfa0b01c94c2a8e68bc5488\\tokenizer_config.json\n",
+      "loading configuration file config.json from cache at C:\\Users\\cxz55/.cache\\huggingface\\hub\\models--dmis-lab--biobert-v1.1\\snapshots\\551ca18efd7f052c8dfa0b01c94c2a8e68bc5488\\config.json\n",
+      "Model config BertConfig {\n",
+      "  \"_name_or_path\": \"dmis-lab/biobert-v1.1\",\n",
+      "  \"architectures\": [\n",
+      "    \"BertModel\"\n",
+      "  ],\n",
+      "  \"attention_probs_dropout_prob\": 0.1,\n",
+      "  \"classifier_dropout\": null,\n",
+      "  \"gradient_checkpointing\": false,\n",
+      "  \"hidden_act\": \"gelu\",\n",
+      "  \"hidden_dropout_prob\": 0.1,\n",
+      "  \"hidden_size\": 768,\n",
+      "  \"initializer_range\": 0.02,\n",
+      "  \"intermediate_size\": 3072,\n",
+      "  \"layer_norm_eps\": 1e-12,\n",
+      "  \"max_position_embeddings\": 512,\n",
+      "  \"model_type\": \"bert\",\n",
+      "  \"num_attention_heads\": 12,\n",
+      "  \"num_hidden_layers\": 12,\n",
+      "  \"pad_token_id\": 0,\n",
+      "  \"position_embedding_type\": \"absolute\",\n",
+      "  \"transformers_version\": \"4.24.0\",\n",
+      "  \"type_vocab_size\": 2,\n",
+      "  \"use_cache\": true,\n",
+      "  \"vocab_size\": 28996\n",
+      "}\n",
+      "\n",
+      "loading configuration file config.json from cache at C:\\Users\\cxz55/.cache\\huggingface\\hub\\models--dmis-lab--biobert-v1.1\\snapshots\\551ca18efd7f052c8dfa0b01c94c2a8e68bc5488\\config.json\n",
+      "Model config BertConfig {\n",
+      "  \"_name_or_path\": \"dmis-lab/biobert-v1.1\",\n",
+      "  \"architectures\": [\n",
+      "    \"BertModel\"\n",
+      "  ],\n",
+      "  \"attention_probs_dropout_prob\": 0.1,\n",
+      "  \"classifier_dropout\": null,\n",
+      "  \"gradient_checkpointing\": false,\n",
+      "  \"hidden_act\": \"gelu\",\n",
+      "  \"hidden_dropout_prob\": 0.1,\n",
+      "  \"hidden_size\": 768,\n",
+      "  \"initializer_range\": 0.02,\n",
+      "  \"intermediate_size\": 3072,\n",
+      "  \"layer_norm_eps\": 1e-12,\n",
+      "  \"max_position_embeddings\": 512,\n",
+      "  \"model_type\": \"bert\",\n",
+      "  \"num_attention_heads\": 12,\n",
+      "  \"num_hidden_layers\": 12,\n",
+      "  \"pad_token_id\": 0,\n",
+      "  \"position_embedding_type\": \"absolute\",\n",
+      "  \"transformers_version\": \"4.24.0\",\n",
+      "  \"type_vocab_size\": 2,\n",
+      "  \"use_cache\": true,\n",
+      "  \"vocab_size\": 28996\n",
+      "}\n",
+      "\n",
+      "No `TrainingArguments` passed, using `output_dir=tmp_trainer`.\n",
+      "PyTorch: setting up devices\n",
+      "The default value for the training argument `--report_to` will change in v5 (from all installed integrations to none). In v5, you will need to use `--report_to all` to get the same behavior as now. You should start updating your code and make this info disappear :-).\n",
+      "The following columns in the test set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: Unnamed: 0, Context, Label, Question, Answer. If Unnamed: 0, Context, Label, Question, Answer are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.\n",
+      "***** Running Prediction *****\n",
+      "  Num examples = 300\n",
+      "  Batch size = 8\n",
+      "You're using a BertTokenizerFast tokenizer. Please note that with a fast tokenizer, using the `__call__` method is faster than using a method to encode the text followed by a call to the `pad` method to get a padded encoding.\n",
+      "100%|██████████| 38/38 [00:01<00:00, 25.79it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "##############RESULT####################\n",
+      "The index of the most proper answer is: 54\n",
+      "The probability it is correct is: 0.6013683676719666\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "(0.6013683676719666, 54)"
+      ]
+     },
+     "execution_count": 30,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "prob_position(path,file_name,\"dmis-lab/biobert-v1.1\",\"dmis-lab/biobert-v1.1\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "pytorch",
+   "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": "3.8.5 (default, Sep  3 2020, 21:29:08) [MSC v.1916 64 bit (AMD64)]"
+  },
+  "orig_nbformat": 4,
+  "vscode": {
+   "interpreter": {
+    "hash": "9cf8428aa180ee23632ed7df20f7a595edda7c60e668686876baf89d702ea1cf"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

scibertALL_2epoch/config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "allenai/scibert_scivocab_uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.24.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31090
+}

scibertALL_2epoch/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:861ed4e280274cc8cfddc100a4b77a755a7d9b9f7567c26a38eac8d5648a0c46
+size 439751021

scibertALL_2epoch/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ceac58d3a6093ccf62847cb3bcd606ae1d98eac1594624c7b8a81c4f324d251
+size 3375