metadata
library_name: transformers
base_model: dmis-lab/biobert-base-cased-v1.2
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
model-index:
- name: ade_biobert_output
results: []
ade_biobert_output
This model is a fine-tuned version of dmis-lab/biobert-base-cased-v1.2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4138
- Precision: 0.8945
- Recall: 0.8822
- F1: 0.8853
- Recall Positive: 0.8887
- Recall Negative: 0.8798
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: 5e-05
- train_batch_size: 4
- eval_batch_size: 4
- 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_steps: 500
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Recall Positive | Recall Negative |
|---|---|---|---|---|---|---|---|---|
| 0.4983 | 0.1063 | 500 | 0.5789 | 0.8609 | 0.7602 | 0.7700 | 0.9858 | 0.6640 |
| 0.4389 | 0.2126 | 1000 | 0.6829 | 0.8700 | 0.8639 | 0.8547 | 0.6031 | 0.9751 |
| 0.5353 | 0.3189 | 1500 | 0.4000 | 0.8974 | 0.8903 | 0.8922 | 0.8862 | 0.8921 |
| 0.6367 | 0.4253 | 2000 | 0.6262 | 0.4915 | 0.7011 | 0.5779 | 0.0 | 1.0 |
| 0.623 | 0.5316 | 2500 | 0.6189 | 0.4915 | 0.7011 | 0.5779 | 0.0 | 1.0 |
| 0.6653 | 0.6379 | 3000 | 0.6122 | 0.4915 | 0.7011 | 0.5779 | 0.0 | 1.0 |
Framework versions
- Transformers 4.55.0
- Pytorch 2.8.0
- Datasets 4.0.0
- Tokenizers 0.21.4