metadata
license: cc0-1.0
base_model: bionlp/bluebert_pubmed_mimic_uncased_L-12_H-768_A-12
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: BlueBERT_CRAFT_NER
results: []
BlueBERT_CRAFT_NER
This model is a fine-tuned version of bionlp/bluebert_pubmed_mimic_uncased_L-12_H-768_A-12 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1403
- Precision: 0.8067
- Recall: 0.7909
- F1: 0.7987
- Accuracy: 0.9633
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 347 | 0.1578 | 0.7663 | 0.7662 | 0.7662 | 0.9562 |
| 0.2328 | 2.0 | 695 | 0.1396 | 0.7927 | 0.7994 | 0.7961 | 0.9620 |
| 0.0645 | 3.0 | 1041 | 0.1403 | 0.8067 | 0.7909 | 0.7987 | 0.9633 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.0
- Tokenizers 0.15.0