metadata
license: mit
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: stbl_clinical_bert_ft_rs2
results: []
stbl_clinical_bert_ft_rs2
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: 0.0945
- F1: 0.9185
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 |
|---|---|---|---|---|
| 0.2719 | 1.0 | 101 | 0.0878 | 0.8458 |
| 0.0682 | 2.0 | 202 | 0.0678 | 0.8838 |
| 0.0321 | 3.0 | 303 | 0.0617 | 0.9041 |
| 0.0149 | 4.0 | 404 | 0.0709 | 0.9061 |
| 0.0097 | 5.0 | 505 | 0.0766 | 0.9114 |
| 0.0059 | 6.0 | 606 | 0.0803 | 0.9174 |
| 0.0035 | 7.0 | 707 | 0.0845 | 0.9160 |
| 0.0023 | 8.0 | 808 | 0.0874 | 0.9158 |
| 0.0016 | 9.0 | 909 | 0.0928 | 0.9188 |
| 0.0016 | 10.0 | 1010 | 0.0951 | 0.9108 |
| 0.0011 | 11.0 | 1111 | 0.0938 | 0.9178 |
| 0.0009 | 12.0 | 1212 | 0.0945 | 0.9185 |
Framework versions
- Transformers 4.22.1
- Pytorch 1.12.1+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1