NHS-dmis-binary-random

README.md

@@ -0,0 +1,67 @@
+---
+base_model: dmis-lab/biobert-base-cased-v1.2
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- precision
+- recall
+- f1
+model-index:
+- name: NHS-dmis-binary
+ 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. -->
+
+# NHS-dmis-binary
+
+This model is a fine-tuned version of [dmis-lab/biobert-base-cased-v1.2](https://huggingface.co/dmis-lab/biobert-base-cased-v1.2) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4752
+- Accuracy: 0.8158
+- Precision: 0.8102
+- Recall: 0.8064
+- F1: 0.8081
+
+## 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: 6
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
+| 0.0543 | 1.0 | 397 | 0.3985 | 0.8240 | 0.8232 | 0.8089 | 0.8141 |
+| 0.1033 | 2.0 | 794 | 0.4902 | 0.7817 | 0.7913 | 0.7996 | 0.7811 |
+| 2.162 | 3.0 | 1191 | 0.4752 | 0.8158 | 0.8102 | 0.8064 | 0.8081 |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,34 @@
+{
+ "_name_or_path": "dmis-lab/biobert-base-cased-v1.2",
+ "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": "4.38.2",
+ "type_vocab_size": 2,
+ "use_cache": true,
+ "vocab_size": 28996
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:866d942fc37e4f0fb426378bf1c6eb924c534579565114a87d6e7be874dddaca
+size 433270768

runs/Mar26_05-56-06_d4944df8337e/events.out.tfevents.1711432568.d4944df8337e.190.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13181cb335da1e4a46d1189865daddbc2bf62661262447026d021681012b97d6
+size 257629

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
+ },
+ "100": {
+ "content": "[UNK]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "101": {
+ "content": "[CLS]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "102": {
+ "content": "[SEP]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "103": {
+ "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:ab3c0161f4b663e8ad8f4a8e7b79e2f909256b84d9333819e6ef45935c4a7908
+size 4920