|
--- |
|
license: bsd-3-clause |
|
base_model: LongSafari/hyenadna-small-32k-seqlen-hf |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- accuracy |
|
model-index: |
|
- name: hyenadna-small-32k-seqlen-hf_ft_BioS73_1kbpHG19_DHSs_H3K27AC |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# hyenadna-small-32k-seqlen-hf_ft_BioS73_1kbpHG19_DHSs_H3K27AC |
|
|
|
This model is a fine-tuned version of [LongSafari/hyenadna-small-32k-seqlen-hf](https://huggingface.co/LongSafari/hyenadna-small-32k-seqlen-hf) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4833 |
|
- F1 Score: 0.8364 |
|
- Precision: 0.8120 |
|
- Recall: 0.8624 |
|
- Accuracy: 0.8200 |
|
- Auc: 0.8967 |
|
- Prc: 0.8849 |
|
|
|
## 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: 1e-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: 20 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | F1 Score | Precision | Recall | Accuracy | Auc | Prc | |
|
|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:--------:|:------:|:------:| |
|
| 0.481 | 0.1864 | 500 | 0.4460 | 0.8302 | 0.7734 | 0.8959 | 0.8043 | 0.8756 | 0.8562 | |
|
| 0.4329 | 0.3727 | 1000 | 0.4339 | 0.8343 | 0.8056 | 0.8652 | 0.8166 | 0.8840 | 0.8728 | |
|
| 0.4273 | 0.5591 | 1500 | 0.4282 | 0.8317 | 0.8105 | 0.8541 | 0.8155 | 0.8879 | 0.8797 | |
|
| 0.4207 | 0.7454 | 2000 | 0.4154 | 0.8442 | 0.7975 | 0.8966 | 0.8233 | 0.8906 | 0.8784 | |
|
| 0.4072 | 0.9318 | 2500 | 0.4407 | 0.8344 | 0.8149 | 0.8547 | 0.8189 | 0.8893 | 0.8806 | |
|
| 0.3884 | 1.1182 | 3000 | 0.4272 | 0.8471 | 0.7887 | 0.9148 | 0.8237 | 0.8936 | 0.8821 | |
|
| 0.3692 | 1.3045 | 3500 | 0.4085 | 0.8412 | 0.8148 | 0.8694 | 0.8248 | 0.8956 | 0.8854 | |
|
| 0.3814 | 1.4909 | 4000 | 0.3987 | 0.8379 | 0.8210 | 0.8554 | 0.8233 | 0.8977 | 0.8878 | |
|
| 0.3628 | 1.6772 | 4500 | 0.4825 | 0.8441 | 0.8040 | 0.8883 | 0.8248 | 0.8972 | 0.8885 | |
|
| 0.3816 | 1.8636 | 5000 | 0.4157 | 0.8482 | 0.8041 | 0.8973 | 0.8286 | 0.8944 | 0.8817 | |
|
| 0.3462 | 2.0499 | 5500 | 0.4931 | 0.8302 | 0.8431 | 0.8177 | 0.8215 | 0.8970 | 0.8868 | |
|
| 0.338 | 2.2363 | 6000 | 0.4842 | 0.8464 | 0.7970 | 0.9022 | 0.8252 | 0.8941 | 0.8802 | |
|
| 0.3356 | 2.4227 | 6500 | 0.4493 | 0.8434 | 0.8034 | 0.8876 | 0.8241 | 0.8896 | 0.8750 | |
|
| 0.3416 | 2.6090 | 7000 | 0.4466 | 0.8478 | 0.7920 | 0.9120 | 0.8252 | 0.8902 | 0.8744 | |
|
| 0.3339 | 2.7954 | 7500 | 0.4833 | 0.8364 | 0.8120 | 0.8624 | 0.8200 | 0.8967 | 0.8849 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.42.3 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.19.0 |
|
|
