mus_promoter-finetuned-lora-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: 0.4605
- F1: 0.9444
- Matthews Correlation: 0.8749
- Accuracy: 0.9375
- F1 Score: 0.9444
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 | Matthews Correlation | Accuracy | F1 Score |
|---|---|---|---|---|---|---|---|
| 0.7975 | 0.43 | 100 | 0.3190 | 0.9231 | 0.8108 | 0.9062 | 0.9231 |
| 0.3818 | 0.85 | 200 | 0.2951 | 0.9167 | 0.8113 | 0.9062 | 0.9167 |
| 0.3829 | 1.28 | 300 | 0.5043 | 0.9 | 0.7507 | 0.875 | 0.9 |
| 0.2565 | 1.71 | 400 | 0.2655 | 0.9351 | 0.8414 | 0.9219 | 0.9351 |
| 0.2098 | 2.14 | 500 | 0.3518 | 0.9333 | 0.8395 | 0.9219 | 0.9333 |
| 0.1841 | 2.56 | 600 | 0.2601 | 0.9211 | 0.8076 | 0.9062 | 0.9211 |
| 0.0804 | 2.99 | 700 | 0.3953 | 0.9315 | 0.8411 | 0.9219 | 0.9315 |
| 0.0463 | 3.42 | 800 | 0.4732 | 0.9444 | 0.8749 | 0.9375 | 0.9444 |
| 0.057 | 3.85 | 900 | 0.4799 | 0.9444 | 0.8749 | 0.9375 | 0.9444 |
| 0.0144 | 4.27 | 1000 | 0.4605 | 0.9444 | 0.8749 | 0.9375 | 0.9444 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.1.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2
- Downloads last month
- 11
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.