metadata
license: cc-by-nc-sa-4.0
base_model: InstaDeepAI/nucleotide-transformer-500m-human-ref
tags:
- generated_from_trainer
metrics:
- f1
- accuracy
model-index:
- name: mus_promoter-finetuned-lora-NT-500m-human-ref
results: []
mus_promoter-finetuned-lora-NT-500m-human-ref
This model is a fine-tuned version of InstaDeepAI/nucleotide-transformer-500m-human-ref on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4766
- F1: 0.8732
- Mcc Score: 0.7192
- Accuracy: 0.8594
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: 0.0005
- train_batch_size: 8
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 1000
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Mcc Score | Accuracy |
|---|---|---|---|---|---|---|
| 0.7799 | 0.43 | 100 | 0.4819 | 0.8889 | 0.7210 | 0.8594 |
| 0.4117 | 0.85 | 200 | 0.6728 | 0.74 | 0.1475 | 0.5938 |
| 0.352 | 1.28 | 300 | 0.3396 | 0.9014 | 0.7826 | 0.8906 |
| 0.2747 | 1.71 | 400 | 0.3458 | 0.9067 | 0.7750 | 0.8906 |
| 0.2279 | 2.14 | 500 | 0.3053 | 0.9143 | 0.8181 | 0.9062 |
| 0.2304 | 2.56 | 600 | 0.4057 | 0.8919 | 0.7437 | 0.875 |
| 0.1362 | 2.99 | 700 | 0.5446 | 0.8657 | 0.7390 | 0.8594 |
| 0.0391 | 3.42 | 800 | 0.7635 | 0.8889 | 0.7210 | 0.8594 |
| 0.04 | 3.85 | 900 | 0.4871 | 0.9231 | 0.8108 | 0.9062 |
| 0.0333 | 4.27 | 1000 | 0.4766 | 0.8732 | 0.7192 | 0.8594 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2