add model

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

README.md

@@ -0,0 +1,75 @@
+---
+license: mit
+tags:
+- generated_from_trainer
+datasets:
+- renet
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model_index:
+- name: BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext-finetuned-renet
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: renet
+      type: renet
+    metric:
+      name: Accuracy
+      type: accuracy
+      value: 0.8640646029609691
+---
+
+<!-- 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. -->
+
+# BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext-finetuned-renet
+
+This model is a fine-tuned version of [microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext](https://huggingface.co/microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext) on the renet dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7226
+- Precision: 0.7799
+- Recall: 0.8211
+- F1: 0.8
+- Accuracy: 0.8641
+- Auc: 0.9325
+
+## 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: 16
+- eval_batch_size: 16
+- seed: 1
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.9.0.dev0
+- Pytorch 1.10.0.dev20210630+cu113
+- Datasets 1.8.0
+- Tokenizers 0.10.3

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "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": "4.9.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

eval_results.txt

@@ -0,0 +1,10 @@
+eval_loss = 0.7226132750511169
+eval_precision = 0.7799227799227799
+eval_recall = 0.8211382113821138
+eval_f1 = 0.8
+eval_accuracy = 0.8640646029609691
+eval_auc = 0.9324810652533084
+eval_runtime = 3.2791
+eval_samples_per_second = 226.589
+eval_steps_per_second = 14.333
+epoch = 5.0

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7483a95a256452553bc86eee50ce42561038dc3c428a38de8eaecf056253592
+size 438019245

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "name_or_path": "microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eab8d3c58121f92df787a314cf32b20b197226cd459298bd7de47388c1168dfc
+size 2799