metadata
license: mit
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: stbl_clinical_bert_ft_rs6
results: []
stbl_clinical_bert_ft_rs6
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: 0.0876
- F1: 0.9177
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 12
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| 0.2778 | 1.0 | 101 | 0.0871 | 0.8482 |
| 0.066 | 2.0 | 202 | 0.0700 | 0.8892 |
| 0.031 | 3.0 | 303 | 0.0657 | 0.9053 |
| 0.0152 | 4.0 | 404 | 0.0716 | 0.9057 |
| 0.0099 | 5.0 | 505 | 0.0717 | 0.9105 |
| 0.0049 | 6.0 | 606 | 0.0807 | 0.9145 |
| 0.0042 | 7.0 | 707 | 0.0796 | 0.9140 |
| 0.0028 | 8.0 | 808 | 0.0833 | 0.9140 |
| 0.002 | 9.0 | 909 | 0.0836 | 0.9141 |
| 0.0013 | 10.0 | 1010 | 0.0866 | 0.9177 |
| 0.0011 | 11.0 | 1111 | 0.0867 | 0.9178 |
| 0.001 | 12.0 | 1212 | 0.0876 | 0.9177 |
Framework versions
- Transformers 4.22.1
- Pytorch 1.12.1+cu113
- Datasets 2.5.1
- Tokenizers 0.12.1