nucleotide-transformer-finetuned-lora-NucleotideTransformer
This model is a fine-tuned version of InstaDeepAI/nucleotide-transformer-2.5b-1000g on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1687
- F1: 0.9863
- Mcc Score: 0.9686
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 |
---|---|---|---|---|---|
0.2508 | 0.43 | 100 | 0.1791 | 0.9863 | 0.9686 |
0.0793 | 0.85 | 200 | 0.4908 | 0.9429 | 0.8814 |
0.0408 | 1.28 | 300 | 0.3990 | 0.9600 | 0.9039 |
0.0184 | 1.71 | 400 | 0.2259 | 0.9730 | 0.9359 |
0.014 | 2.14 | 500 | 0.1308 | 0.9863 | 0.9686 |
0.0313 | 2.56 | 600 | 0.1841 | 0.9863 | 0.9686 |
0.0162 | 2.99 | 700 | 0.4267 | 0.9730 | 0.9359 |
0.0114 | 3.42 | 800 | 0.2700 | 0.9730 | 0.9359 |
0.0 | 3.85 | 900 | 0.1612 | 0.9863 | 0.9686 |
0.0 | 4.27 | 1000 | 0.1687 | 0.9863 | 0.9686 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.1.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2
- Downloads last month
- 20
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.