metadata
library_name: transformers
base_model: dmis-lab/biobert-v1.1
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: biobert-v1.1-finetuned-medmcqa-2024-11-25-T16-21-48
results: []
biobert-v1.1-finetuned-medmcqa-2024-11-25-T16-21-48
This model is a fine-tuned version of dmis-lab/biobert-v1.1 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0952
- Accuracy: 0.6190
- F1: 0.6142
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: 0.000159
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 1.0926 | 0.9978 | 57 | 1.0952 | 0.6190 | 0.6142 |
| 0.8087 | 1.9956 | 114 | 0.8597 | 0.5952 | 0.6151 |
| 0.5811 | 2.9934 | 171 | 0.8742 | 0.6190 | 0.6371 |
| 0.368 | 3.9912 | 228 | 1.3578 | 0.5714 | 0.5839 |
| 0.1739 | 4.9891 | 285 | 1.6110 | 0.5952 | 0.6032 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.5.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3