|
--- |
|
license: cc-by-nc-sa-4.0 |
|
base_model: InstaDeepAI/nucleotide-transformer-500m-1000g |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- accuracy |
|
model-index: |
|
- name: nucleotide-transformer-500m-1000g_ft_BioS45_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. --> |
|
|
|
# nucleotide-transformer-500m-1000g_ft_BioS45_1kbpHG19_DHSs_H3K27AC |
|
|
|
This model is a fine-tuned version of [InstaDeepAI/nucleotide-transformer-500m-1000g](https://huggingface.co/InstaDeepAI/nucleotide-transformer-500m-1000g) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.0165 |
|
- F1 Score: 0.8158 |
|
- Precision: 0.8524 |
|
- Recall: 0.7823 |
|
- Accuracy: 0.8157 |
|
- Auc: 0.9011 |
|
- Prc: 0.8977 |
|
|
|
## 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 | |
|
|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:--------:|:------:|:------:| |
|
| 0.529 | 0.2103 | 500 | 0.4367 | 0.8252 | 0.7590 | 0.9040 | 0.8002 | 0.8862 | 0.8840 | |
|
| 0.4486 | 0.4207 | 1000 | 0.4420 | 0.8333 | 0.7765 | 0.8992 | 0.8124 | 0.8919 | 0.8853 | |
|
| 0.4422 | 0.6310 | 1500 | 0.4717 | 0.8330 | 0.7471 | 0.9411 | 0.8031 | 0.8979 | 0.8959 | |
|
| 0.4313 | 0.8414 | 2000 | 0.4178 | 0.8375 | 0.7597 | 0.9331 | 0.8111 | 0.9063 | 0.9030 | |
|
| 0.4131 | 1.0517 | 2500 | 0.5239 | 0.8404 | 0.8380 | 0.8427 | 0.8330 | 0.9017 | 0.8967 | |
|
| 0.3597 | 1.2621 | 3000 | 0.4806 | 0.8418 | 0.7864 | 0.9056 | 0.8225 | 0.9018 | 0.8987 | |
|
| 0.3415 | 1.4724 | 3500 | 0.6284 | 0.8061 | 0.8790 | 0.7444 | 0.8132 | 0.9047 | 0.9046 | |
|
| 0.3372 | 1.6828 | 4000 | 0.4651 | 0.8314 | 0.8355 | 0.8274 | 0.8250 | 0.9039 | 0.9042 | |
|
| 0.3294 | 1.8931 | 4500 | 0.5134 | 0.8382 | 0.7631 | 0.9298 | 0.8128 | 0.9023 | 0.9040 | |
|
| 0.2382 | 2.1035 | 5000 | 0.8833 | 0.8245 | 0.8289 | 0.8202 | 0.8178 | 0.8980 | 0.8988 | |
|
| 0.1741 | 2.3138 | 5500 | 1.0165 | 0.8158 | 0.8524 | 0.7823 | 0.8157 | 0.9011 | 0.8977 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.42.3 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.19.0 |
|
|
