cer

README.md

@@ -0,0 +1,67 @@
+---
+license: mit
+base_model: emilyalsentzer/Bio_ClinicalBERT
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: Bio_ClinicalBERT
+ 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. -->
+
+# Bio_ClinicalBERT
+
+This model is a fine-tuned version of [emilyalsentzer/Bio_ClinicalBERT](https://huggingface.co/emilyalsentzer/Bio_ClinicalBERT) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1917
+- Precision: 0.9240
+- Recall: 0.8625
+- F1: 0.8922
+- Accuracy: 0.9299
+
+## 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: 0.0002
+- 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
+- lr_scheduler_warmup_ratio: 0.2
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.001 | 1.0 | 4841 | 0.1917 | 0.9240 | 0.8625 | 0.8922 | 0.9299 |
+
+
+### Framework versions
+
+- Transformers 4.37.0
+- Pytorch 2.1.2
+- Datasets 2.1.0
+- Tokenizers 0.15.1

config.json

@@ -0,0 +1,35 @@
+{
+ "_name_or_path": "emilyalsentzer/Bio_ClinicalBERT",
+ "architectures": [
+ "BertForTokenClassification"
+ ],
+ "attention_probs_dropout_prob": 0.1,
+ "classifier_dropout": null,
+ "hidden_act": "gelu",
+ "hidden_dropout_prob": 0.1,
+ "hidden_size": 768,
+ "id2label": {
+ "0": "O",
+ "1": "B-clinical_entity",
+ "2": "I-clinical_entity"
+ },
+ "initializer_range": 0.02,
+ "intermediate_size": 3072,
+ "label2id": {
+ "B-clinical_entity": 1,
+ "I-clinical_entity": 2,
+ "O": 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",
+ "torch_dtype": "float32",
+ "transformers_version": "4.37.0",
+ "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 sha256:66700e066b7e1f9c3adf3d8b8b02e9948be38704266c845d6dbb037edc10ec21
+size 430911284

runs/Feb27_14-42-18_b93fc8ba8ca9/events.out.tfevents.1709044942.b93fc8ba8ca9.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db318f2fa2bdd7bb403c15eb9bea3b9d30b04a0dea0bade4726b5138afdf42c4
+size 6728

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": 512,
+ "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 sha256:55a6d6ba97253a7873bcdc5cad5246cba46af68c957149649b6c3c1f86c6a8ce
+size 4728