metadata
license: mit
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: Bio_ClinicalBERT_fold_1_binary_v1
results: []
Bio_ClinicalBERT_fold_1_binary_v1
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: 1.7063
- F1: 0.8114
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
- num_epochs: 25
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| No log | 1.0 | 288 | 0.4168 | 0.7949 |
| 0.3981 | 2.0 | 576 | 0.4124 | 0.8137 |
| 0.3981 | 3.0 | 864 | 0.6691 | 0.8002 |
| 0.1779 | 4.0 | 1152 | 0.8402 | 0.8122 |
| 0.1779 | 5.0 | 1440 | 0.9786 | 0.8007 |
| 0.082 | 6.0 | 1728 | 1.0425 | 0.7981 |
| 0.0332 | 7.0 | 2016 | 1.2070 | 0.8006 |
| 0.0332 | 8.0 | 2304 | 1.3305 | 0.8028 |
| 0.0149 | 9.0 | 2592 | 1.4515 | 0.8009 |
| 0.0149 | 10.0 | 2880 | 1.3826 | 0.8160 |
| 0.01 | 11.0 | 3168 | 1.5267 | 0.7963 |
| 0.01 | 12.0 | 3456 | 1.5158 | 0.8112 |
| 0.0084 | 13.0 | 3744 | 1.5919 | 0.7998 |
| 0.0027 | 14.0 | 4032 | 1.6206 | 0.8060 |
| 0.0027 | 15.0 | 4320 | 1.6861 | 0.8014 |
| 0.0061 | 16.0 | 4608 | 1.6660 | 0.8001 |
| 0.0061 | 17.0 | 4896 | 1.5061 | 0.8054 |
| 0.0133 | 18.0 | 5184 | 1.5813 | 0.8025 |
| 0.0133 | 19.0 | 5472 | 1.6314 | 0.7968 |
| 0.0032 | 20.0 | 5760 | 1.6282 | 0.8117 |
| 0.0007 | 21.0 | 6048 | 1.6378 | 0.8153 |
| 0.0007 | 22.0 | 6336 | 1.6710 | 0.8033 |
| 0.0018 | 23.0 | 6624 | 1.6999 | 0.8066 |
| 0.0018 | 24.0 | 6912 | 1.7045 | 0.8109 |
| 0.0001 | 25.0 | 7200 | 1.7063 | 0.8114 |
Framework versions
- Transformers 4.21.0
- Pytorch 1.12.0+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1