output
This model is a fine-tuned version of zhihan1996/DNA_bert_6 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3879
- Accuracy: 0.8612
- Precision: 0.9154
- Recall: 0.8240
- F1: 0.8673
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: 16
- eval_batch_size: 16
- seed: 0
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.4958 | 0.46 | 500 | 0.4749 | 0.7831 | 0.7303 | 0.9606 | 0.8298 |
| 0.3928 | 0.93 | 1000 | 0.4086 | 0.8207 | 0.7717 | 0.9574 | 0.8546 |
| 0.3319 | 1.39 | 1500 | 0.3467 | 0.8635 | 0.8664 | 0.8891 | 0.8776 |
| 0.3036 | 1.85 | 2000 | 0.3176 | 0.8702 | 0.8717 | 0.8960 | 0.8836 |
| 0.2383 | 2.31 | 2500 | 0.3403 | 0.8707 | 0.8901 | 0.8728 | 0.8814 |
| 0.2189 | 2.78 | 3000 | 0.3879 | 0.8612 | 0.9154 | 0.8240 | 0.8673 |
Framework versions
- Transformers 4.27.4
- Pytorch 2.0.0+cu118
- Tokenizers 0.13.3