|
--- |
|
license: apache-2.0 |
|
base_model: ctheodoris/Geneformer |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- accuracy |
|
model-index: |
|
- name: Geneformer_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. --> |
|
|
|
# Geneformer_ft_BioS74_1kbpHG19_DHSs_H3K27AC |
|
|
|
This model is a fine-tuned version of [ctheodoris/Geneformer](https://huggingface.co/ctheodoris/Geneformer) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.5809 |
|
- F1 Score: 0.7069 |
|
- Precision: 0.7107 |
|
- Recall: 0.7032 |
|
- Accuracy: 0.6947 |
|
- Auc: 0.7638 |
|
- Prc: 0.7611 |
|
|
|
## 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 | |
|
|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:--------:|:------:|:------:| |
|
| 0.6934 | 0.1314 | 500 | 0.6908 | 0.6505 | 0.5332 | 0.8338 | 0.5309 | 0.5321 | 0.5544 | |
|
| 0.692 | 0.2629 | 1000 | 0.6811 | 0.5043 | 0.6257 | 0.4224 | 0.5653 | 0.6063 | 0.6190 | |
|
| 0.6783 | 0.3943 | 1500 | 0.6729 | 0.4941 | 0.6808 | 0.3877 | 0.5843 | 0.6381 | 0.6423 | |
|
| 0.6617 | 0.5258 | 2000 | 0.6570 | 0.7039 | 0.5813 | 0.8920 | 0.6072 | 0.6888 | 0.6876 | |
|
| 0.6467 | 0.6572 | 2500 | 0.6336 | 0.7081 | 0.6139 | 0.8363 | 0.6390 | 0.7102 | 0.7119 | |
|
| 0.6407 | 0.7886 | 3000 | 0.6094 | 0.6627 | 0.7235 | 0.6113 | 0.6742 | 0.7346 | 0.7343 | |
|
| 0.6328 | 0.9201 | 3500 | 0.6017 | 0.7155 | 0.6649 | 0.7745 | 0.6776 | 0.7392 | 0.7450 | |
|
| 0.619 | 1.0515 | 4000 | 0.6767 | 0.5531 | 0.7975 | 0.4234 | 0.6419 | 0.7419 | 0.7422 | |
|
| 0.6088 | 1.1830 | 4500 | 0.5867 | 0.7182 | 0.6960 | 0.7418 | 0.6952 | 0.7564 | 0.7570 | |
|
| 0.6099 | 1.3144 | 5000 | 0.5861 | 0.7162 | 0.6959 | 0.7378 | 0.6939 | 0.7557 | 0.7546 | |
|
| 0.6022 | 1.4458 | 5500 | 0.5849 | 0.6920 | 0.7243 | 0.6625 | 0.6913 | 0.7602 | 0.7581 | |
|
| 0.582 | 1.5773 | 6000 | 0.5809 | 0.7069 | 0.7107 | 0.7032 | 0.6947 | 0.7638 | 0.7611 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.42.3 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.19.0 |
|
|
