End of training

README.md

@@ -0,0 +1,69 @@
+---
+license: mit
+base_model: microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- precision
+- recall
+- f1
+model-index:
+- name: test
+ 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. -->
+
+# test
+
+This model is a fine-tuned version of [microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract](https://huggingface.co/microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4018
+- Accuracy: 0.8207
+- Precision: 0.8202
+- Recall: 0.8207
+- F1: 0.8202
+
+## 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: 3e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 4
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
+| 0.4749 | 1.0 | 417 | 0.4018 | 0.8207 | 0.8202 | 0.8207 | 0.8202 |
+| 0.0976 | 2.0 | 834 | 0.4443 | 0.8189 | 0.8234 | 0.8189 | 0.8197 |
+| 0.0061 | 3.0 | 1251 | 0.7378 | 0.8213 | 0.8233 | 0.8213 | 0.8219 |
+| 0.3159 | 4.0 | 1668 | 0.9154 | 0.8094 | 0.8092 | 0.8094 | 0.8092 |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.15.0
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,34 @@
+{
+ "_name_or_path": "microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract",
+ "architectures": [
+ "BertForSequenceClassification"
+ ],
+ "attention_probs_dropout_prob": 0.1,
+ "classifier_dropout": null,
+ "hidden_act": "gelu",
+ "hidden_dropout_prob": 0.1,
+ "hidden_size": 768,
+ "id2label": {
+ "0": "the paper is not a primary experimental study in rare disease or the study is not directly investigating the natural history of a disease",
+ "1": "its primary contribution centers on observing the time course of a rare disease"
+ },
+ "initializer_range": 0.02,
+ "intermediate_size": 3072,
+ "label2id": {
+ "its primary contribution centers on observing the time course of a rare disease": 1,
+ "the paper is not a primary experimental study in rare disease or the study is not directly investigating the natural history of a disease": 0
+ },
+ "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": "4.35.2",
+ "type_vocab_size": 2,
+ "use_cache": true,
+ "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98a33ce0ed4378275ab49f8e83ea579e2190e46aa2278b19174adbfcd265eee4
+size 437958648

runs/Dec18_18-03-50_7f2d725bb68d/events.out.tfevents.1702922631.7f2d725bb68d.967.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:715ff991888daf49b0f4d65540ee0bef90d91a36cd5fe915681cc37fd19ee053
+size 5468

runs/Dec18_18-04-37_7f2d725bb68d/events.out.tfevents.1702922684.7f2d725bb68d.967.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c4e022a77cbfaf3eb9f5d34ca11dc56cb9d7d31f3c094fbfc8c2c4c7b86947b
+size 268483

runs/Dec18_18-04-37_7f2d725bb68d/events.out.tfevents.1702924161.7f2d725bb68d.967.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a16f77cbe8880329a041afcc670959f4927ecf1cd726a16a1d1ff24d6d1fdfdf
+size 560

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+ "cls_token": "[CLS]",
+ "mask_token": "[MASK]",
+ "pad_token": "[PAD]",
+ "sep_token": "[SEP]",
+ "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+ "added_tokens_decoder": {
+ "0": {
+ "content": "[PAD]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "1": {
+ "content": "[UNK]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "2": {
+ "content": "[CLS]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "3": {
+ "content": "[SEP]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "4": {
+ "content": "[MASK]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ }
+ },
+ "clean_up_tokenization_spaces": true,
+ "cls_token": "[CLS]",
+ "do_basic_tokenize": true,
+ "do_lower_case": true,
+ "mask_token": "[MASK]",
+ "model_max_length": 1000000000000000019884624838656,
+ "never_split": null,
+ "pad_token": "[PAD]",
+ "sep_token": "[SEP]",
+ "strip_accents": null,
+ "tokenize_chinese_chars": true,
+ "tokenizer_class": "BertTokenizer",
+ "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f739c4c37b8ce47c8f6a8429d0b9611948aa21788db0f76e7977fe117d243f99
+size 4536