metadata
library_name: transformers
base_model: dmis-lab/biobert-base-cased-v1.2
tags:
- generated_from_trainer
metrics:
- precision
- recall
model-index:
- name: lifechart-biobert-classifier-hptuning
results: []
lifechart-biobert-classifier-hptuning
This model is a fine-tuned version of dmis-lab/biobert-base-cased-v1.2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0893
- Macro F1: 0.7860
- Precision: 0.7904
- Recall: 0.7889
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: 2.387945549951255e-05
- train_batch_size: 8
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.007988632624643532
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Macro F1 | Precision | Recall |
|---|---|---|---|---|---|---|
| 1.5479 | 1.0 | 1641 | 0.8890 | 0.7486 | 0.7291 | 0.7857 |
| 0.6775 | 2.0 | 3282 | 0.9020 | 0.7831 | 0.7881 | 0.7877 |
| 0.4014 | 3.0 | 4923 | 0.9752 | 0.7728 | 0.7684 | 0.7851 |
| 0.2387 | 4.0 | 6564 | 1.0893 | 0.7860 | 0.7904 | 0.7889 |
Framework versions
- Transformers 4.55.4
- Pytorch 2.8.0+cu128
- Datasets 4.0.0
- Tokenizers 0.21.4