CeLLaTe-ner-bioformer16l-baseline
This model is a fine-tuned version of bioformers/bioformer-16l on the OTAR3088/CeLLaTe_V3.2_contracted_ent_IOB dataset. It achieves the following results on the evaluation set:
- Loss: 0.0636
- Precision: 0.8151
- Recall: 0.7415
- F1: 0.7766
- Accuracy: 0.9825
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: 3407
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.ADAMW_TORCH 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: 0.01
- num_epochs: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.2578 | 1.0 | 263 | 0.0759 | 0.5637 | 0.6534 | 0.6052 | 0.9716 |
| 0.0494 | 2.0 | 526 | 0.0644 | 0.7969 | 0.7142 | 0.7533 | 0.9817 |
| 0.0331 | 3.0 | 789 | 0.0635 | 0.8151 | 0.7415 | 0.7766 | 0.9825 |
| 0.0249 | 4.0 | 1052 | 0.0687 | 0.8192 | 0.7317 | 0.7730 | 0.9823 |
| 0.02 | 5.0 | 1315 | 0.0696 | 0.8031 | 0.7460 | 0.7735 | 0.9824 |
| 0.0157 | 6.0 | 1578 | 0.0744 | 0.8005 | 0.7321 | 0.7648 | 0.9820 |
Framework versions
- Transformers 4.48.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.2
- Tokenizers 0.21.0