|
--- |
|
license: bsd-3-clause |
|
base_model: LongSafari/hyenadna-large-1m-seqlen-hf |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- accuracy |
|
model-index: |
|
- name: hyenadna-large-1m-seqlen-hf_ft_BioS74_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-large-1m-seqlen-hf_ft_BioS74_1kbpHG19_DHSs_H3K27AC |
|
|
|
This model is a fine-tuned version of [LongSafari/hyenadna-large-1m-seqlen-hf](https://huggingface.co/LongSafari/hyenadna-large-1m-seqlen-hf) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4539 |
|
- F1 Score: 0.8085 |
|
- Precision: 0.7851 |
|
- Recall: 0.8332 |
|
- Accuracy: 0.7933 |
|
- Auc: 0.8657 |
|
- Prc: 0.8552 |
|
|
|
## 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 | |
|
|:-------------:|:------:|:-----:|:---------------:|:--------:|:---------:|:------:|:--------:|:------:|:------:| |
|
| 0.5457 | 0.1314 | 500 | 0.5130 | 0.7789 | 0.7681 | 0.7901 | 0.7652 | 0.8248 | 0.7983 | |
|
| 0.5285 | 0.2629 | 1000 | 0.5064 | 0.7851 | 0.7822 | 0.7880 | 0.7741 | 0.8339 | 0.8177 | |
|
| 0.5192 | 0.3943 | 1500 | 0.5260 | 0.7687 | 0.7852 | 0.7529 | 0.7628 | 0.8313 | 0.8174 | |
|
| 0.4935 | 0.5258 | 2000 | 0.5067 | 0.7964 | 0.7532 | 0.8448 | 0.7739 | 0.8342 | 0.8097 | |
|
| 0.4776 | 0.6572 | 2500 | 0.4999 | 0.8050 | 0.7410 | 0.8810 | 0.7765 | 0.8392 | 0.8221 | |
|
| 0.5066 | 0.7886 | 3000 | 0.4872 | 0.7978 | 0.7484 | 0.8543 | 0.7733 | 0.8429 | 0.8282 | |
|
| 0.4927 | 0.9201 | 3500 | 0.5143 | 0.8023 | 0.7509 | 0.8614 | 0.7778 | 0.8327 | 0.8071 | |
|
| 0.5076 | 1.0515 | 4000 | 0.5345 | 0.7476 | 0.8154 | 0.6901 | 0.7560 | 0.8443 | 0.8294 | |
|
| 0.4967 | 1.1830 | 4500 | 0.5013 | 0.7991 | 0.7147 | 0.9061 | 0.7615 | 0.8367 | 0.8181 | |
|
| 0.4905 | 1.3144 | 5000 | 0.4846 | 0.8055 | 0.7496 | 0.8704 | 0.7799 | 0.8461 | 0.8328 | |
|
| 0.4872 | 1.4458 | 5500 | 0.4887 | 0.7939 | 0.7888 | 0.7991 | 0.7828 | 0.8523 | 0.8405 | |
|
| 0.4734 | 1.5773 | 6000 | 0.5150 | 0.7924 | 0.7739 | 0.8117 | 0.7773 | 0.8460 | 0.8268 | |
|
| 0.4699 | 1.7087 | 6500 | 0.4917 | 0.7764 | 0.8120 | 0.7438 | 0.7757 | 0.8520 | 0.8421 | |
|
| 0.4632 | 1.8402 | 7000 | 0.5059 | 0.7860 | 0.8026 | 0.7700 | 0.7804 | 0.8508 | 0.8396 | |
|
| 0.4774 | 1.9716 | 7500 | 0.4994 | 0.8069 | 0.7269 | 0.9066 | 0.7728 | 0.8515 | 0.8323 | |
|
| 0.4709 | 2.1030 | 8000 | 0.4750 | 0.7944 | 0.7932 | 0.7956 | 0.7844 | 0.8555 | 0.8470 | |
|
| 0.4608 | 2.2345 | 8500 | 0.4694 | 0.7985 | 0.7901 | 0.8071 | 0.7867 | 0.8572 | 0.8476 | |
|
| 0.4626 | 2.3659 | 9000 | 0.4691 | 0.7997 | 0.7963 | 0.8031 | 0.7894 | 0.8592 | 0.8507 | |
|
| 0.4476 | 2.4974 | 9500 | 0.4661 | 0.8109 | 0.7818 | 0.8423 | 0.7944 | 0.8584 | 0.8398 | |
|
| 0.4618 | 2.6288 | 10000 | 0.4752 | 0.7986 | 0.8068 | 0.7906 | 0.7912 | 0.8634 | 0.8559 | |
|
| 0.453 | 2.7603 | 10500 | 0.4660 | 0.7966 | 0.7966 | 0.7966 | 0.7870 | 0.8590 | 0.8488 | |
|
| 0.4482 | 2.8917 | 11000 | 0.4639 | 0.8018 | 0.7970 | 0.8066 | 0.7912 | 0.8615 | 0.8514 | |
|
| 0.4421 | 3.0231 | 11500 | 0.4728 | 0.8128 | 0.7755 | 0.8538 | 0.7941 | 0.8611 | 0.8490 | |
|
| 0.4359 | 3.1546 | 12000 | 0.4647 | 0.8094 | 0.7707 | 0.8523 | 0.7899 | 0.8604 | 0.8509 | |
|
| 0.4339 | 3.2860 | 12500 | 0.4843 | 0.8012 | 0.8018 | 0.8006 | 0.7920 | 0.8671 | 0.8615 | |
|
| 0.4415 | 3.4175 | 13000 | 0.4764 | 0.8080 | 0.7279 | 0.9081 | 0.7741 | 0.8621 | 0.8557 | |
|
| 0.4336 | 3.5489 | 13500 | 0.4627 | 0.8056 | 0.7823 | 0.8302 | 0.7902 | 0.8637 | 0.8560 | |
|
| 0.4446 | 3.6803 | 14000 | 0.4539 | 0.8085 | 0.7851 | 0.8332 | 0.7933 | 0.8657 | 0.8552 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.42.3 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.19.0 |
|
|
