metadata
license: cc-by-nc-sa-4.0
base_model: InstaDeepAI/nucleotide-transformer-v2-100m-multi-species
tags:
- generated_from_trainer
metrics:
- f1
- accuracy
model-index:
- name: mus_promoter-finetuned-lora-NT-v2-100m-ms
results: []
mus_promoter-finetuned-lora-NT-v2-100m-ms
This model is a fine-tuned version of InstaDeepAI/nucleotide-transformer-v2-100m-multi-species on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0387
- F1: 0.9867
- Mcc Score: 0.9683
- 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 |
|---|---|---|---|---|---|---|
| 0.4137 | 0.43 | 100 | 0.1128 | 0.9722 | 0.9385 | 0.9688 |
| 0.2366 | 0.85 | 200 | 0.2834 | 0.9459 | 0.8719 | 0.9375 |
| 0.1578 | 1.28 | 300 | 0.1574 | 0.9722 | 0.9385 | 0.9688 |
| 0.0992 | 1.71 | 400 | 0.0585 | 0.9863 | 0.9686 | 0.9844 |
| 0.1293 | 2.14 | 500 | 0.0860 | 0.9863 | 0.9686 | 0.9844 |
| 0.0503 | 2.56 | 600 | 0.0916 | 0.9863 | 0.9686 | 0.9844 |
| 0.0634 | 2.99 | 700 | 0.0265 | 0.9867 | 0.9683 | 0.9844 |
| 0.007 | 3.42 | 800 | 0.0012 | 1.0 | 1.0 | 1.0 |
| 0.0135 | 3.85 | 900 | 0.0015 | 1.0 | 1.0 | 1.0 |
| 0.0113 | 4.27 | 1000 | 0.0387 | 0.9867 | 0.9683 | 0.9844 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2