metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- f1
- accuracy
base_model: bioformers/bioformer-litcovid
model-index:
- name: bioformer-LitCovid-v1.0
results: []
bioformer-LitCovid-v1.0
This model is a fine-tuned version of bioformers/bioformer-litcovid on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1191
- F1: 0.8969
- Roc Auc: 0.9366
- Accuracy: 0.7895
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|---|---|---|---|---|---|---|
| 0.1209 | 1.0 | 3120 | 0.1164 | 0.8921 | 0.9300 | 0.7863 |
| 0.1058 | 2.0 | 6240 | 0.1163 | 0.8909 | 0.9283 | 0.7825 |
| 0.0795 | 3.0 | 9360 | 0.1135 | 0.8963 | 0.9404 | 0.7881 |
| 0.0649 | 4.0 | 12480 | 0.1156 | 0.8989 | 0.9384 | 0.7953 |
| 0.0504 | 5.0 | 15600 | 0.1191 | 0.8969 | 0.9366 | 0.7895 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3