|
--- |
|
license: cc-by-nc-sa-4.0 |
|
base_model: InstaDeepAI/nucleotide-transformer-v2-100m-multi-species |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- accuracy |
|
model-index: |
|
- name: nucleotide-transformer-v2-100m-multi-species_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-v2-100m-multi-species_ft_BioS45_1kbpHG19_DHSs_H3K27AC |
|
|
|
This model is a fine-tuned version of [InstaDeepAI/nucleotide-transformer-v2-100m-multi-species](https://huggingface.co/InstaDeepAI/nucleotide-transformer-v2-100m-multi-species) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.6023 |
|
- F1 Score: 0.8516 |
|
- Precision: 0.8469 |
|
- Recall: 0.8565 |
|
- Accuracy: 0.8443 |
|
- Auc: 0.9080 |
|
- Prc: 0.8870 |
|
|
|
## 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 | |
|
|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:--------:|:------:|:------:| |
|
| 0.5688 | 0.2103 | 500 | 0.4834 | 0.7745 | 0.8198 | 0.7339 | 0.7770 | 0.8595 | 0.8533 | |
|
| 0.465 | 0.4207 | 1000 | 0.4150 | 0.8388 | 0.8241 | 0.8540 | 0.8288 | 0.8941 | 0.8918 | |
|
| 0.4161 | 0.6310 | 1500 | 0.3880 | 0.8466 | 0.7966 | 0.9032 | 0.8292 | 0.9092 | 0.9071 | |
|
| 0.4113 | 0.8414 | 2000 | 0.3799 | 0.8541 | 0.8270 | 0.8831 | 0.8427 | 0.9102 | 0.9056 | |
|
| 0.3853 | 1.0517 | 2500 | 0.4211 | 0.8485 | 0.7878 | 0.9194 | 0.8288 | 0.9122 | 0.9052 | |
|
| 0.3461 | 1.2621 | 3000 | 0.4359 | 0.8510 | 0.8199 | 0.8847 | 0.8385 | 0.9117 | 0.8991 | |
|
| 0.3408 | 1.4724 | 3500 | 0.3996 | 0.8563 | 0.8179 | 0.8984 | 0.8427 | 0.9175 | 0.9079 | |
|
| 0.3354 | 1.6828 | 4000 | 0.4692 | 0.8260 | 0.8670 | 0.7887 | 0.8267 | 0.9122 | 0.9031 | |
|
| 0.3392 | 1.8931 | 4500 | 0.4410 | 0.8544 | 0.7992 | 0.9177 | 0.8368 | 0.9120 | 0.9078 | |
|
| 0.287 | 2.1035 | 5000 | 0.6023 | 0.8516 | 0.8469 | 0.8565 | 0.8443 | 0.9080 | 0.8870 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.42.3 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.19.0 |
|
|
