metadata
license: cc-by-nc-sa-4.0
base_model: InstaDeepAI/nucleotide-transformer-v2-500m-multi-species
tags:
- generated_from_trainer
metrics:
- f1
- accuracy
model-index:
- name: mus_promoter-finetuned-lora-NT-v2-500m-ms
results: []
mus_promoter-finetuned-lora-NT-v2-500m-ms
This model is a fine-tuned version of InstaDeepAI/nucleotide-transformer-v2-500m-multi-species on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1042
- F1: 0.9863
- Mcc Score: 0.9686
- Accuracy: 0.9844
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 |
|---|---|---|---|---|---|---|
| 0.5534 | 0.43 | 100 | 0.5989 | 0.8824 | 0.7646 | 0.875 |
| 0.3298 | 0.85 | 200 | 0.1327 | 0.9730 | 0.9359 | 0.9688 |
| 0.1827 | 1.28 | 300 | 0.0652 | 0.9867 | 0.9683 | 0.9844 |
| 0.2014 | 1.71 | 400 | 0.2227 | 0.9600 | 0.9039 | 0.9531 |
| 0.1183 | 2.14 | 500 | 0.0556 | 0.9863 | 0.9686 | 0.9844 |
| 0.1052 | 2.56 | 600 | 0.2231 | 0.9577 | 0.9094 | 0.9531 |
| 0.0781 | 2.99 | 700 | 0.1219 | 0.9730 | 0.9359 | 0.9688 |
| 0.0477 | 3.42 | 800 | 0.1048 | 0.9863 | 0.9686 | 0.9844 |
| 0.025 | 3.85 | 900 | 0.0978 | 0.9863 | 0.9686 | 0.9844 |
| 0.0221 | 4.27 | 1000 | 0.1042 | 0.9863 | 0.9686 | 0.9844 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2