Bio_ClinicalBERT_top10
This model is a fine-tuned version of emilyalsentzer/Bio_ClinicalBERT on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6042
- Precision Macro: 0.1276
- Recall Macro: 0.1184
- F1 Macro: 0.1128
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: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.3
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision Macro | Recall Macro | F1 Macro |
|---|---|---|---|---|---|---|
| 1.7839 | 1.0 | 789 | 0.6753 | 0.4515 | 0.0693 | 0.0589 |
| 0.6437 | 2.0 | 1578 | 0.6079 | 0.2880 | 0.1048 | 0.0924 |
| 0.6113 | 3.0 | 2367 | 0.5901 | 0.2078 | 0.1224 | 0.1111 |
| 0.5795 | 4.0 | 3156 | 0.5922 | 0.3373 | 0.1149 | 0.1229 |
| 0.5736 | 5.0 | 3945 | 0.5790 | 0.2145 | 0.1066 | 0.1089 |
| 0.5457 | 6.0 | 4734 | 0.5966 | 0.1133 | 0.1301 | 0.1179 |
| 0.5175 | 7.0 | 5523 | 0.6042 | 0.1276 | 0.1184 | 0.1128 |
Framework versions
- Transformers 4.34.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.6.dev0
- Tokenizers 0.14.0