metadata
license: mit
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: stbl_clinical_bert_ft_rs10
results: []
stbl_clinical_bert_ft_rs10
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: 0.0846
- F1: 0.9297
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 |
|---|---|---|---|---|
| 0.2834 | 1.0 | 101 | 0.0930 | 0.8446 |
| 0.0669 | 2.0 | 202 | 0.0732 | 0.8938 |
| 0.033 | 3.0 | 303 | 0.0676 | 0.9119 |
| 0.0168 | 4.0 | 404 | 0.0703 | 0.9219 |
| 0.0084 | 5.0 | 505 | 0.0742 | 0.9245 |
| 0.006 | 6.0 | 606 | 0.0772 | 0.9252 |
| 0.0033 | 7.0 | 707 | 0.0844 | 0.9239 |
| 0.0023 | 8.0 | 808 | 0.0855 | 0.9272 |
| 0.0019 | 9.0 | 909 | 0.0843 | 0.9296 |
| 0.0013 | 10.0 | 1010 | 0.0878 | 0.9262 |
| 0.0012 | 11.0 | 1111 | 0.0857 | 0.9266 |
| 0.0008 | 12.0 | 1212 | 0.0846 | 0.9297 |
Framework versions
- Transformers 4.22.2
- Pytorch 1.12.1+cu113
- Datasets 2.5.1
- Tokenizers 0.12.1