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-5pct-2024-12-03-T09-43-29
results: []
biobert-v1.1-finetuned-medmcqa-5pct-2024-12-03-T09-43-29
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: 1.2074
- Accuracy: 0.5532
- F1: 0.5543
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: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.7328 | 0.9974 | 285 | 0.9662 | 0.5398 | 0.5408 |
| 0.5829 | 1.9987 | 571 | 0.9861 | 0.5520 | 0.5529 |
| 0.2838 | 2.9930 | 855 | 1.2074 | 0.5532 | 0.5543 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.5.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3