metadata
license: cc-by-nc-sa-4.0
base_model: InstaDeepAI/nucleotide-transformer-2.5b-1000g
tags:
- generated_from_trainer
metrics:
- f1
- accuracy
model-index:
- name: nucleotide-transformer-finetuned-lora-NucleotideTransformer
results: []
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: 0.6900
- F1: 0.8402
- Mcc Score: 0.5492
- Accuracy: 0.7891
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: 3
- 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 |
|---|---|---|---|---|---|---|
| 1.3108 | 0.05 | 100 | 0.8230 | 0.6491 | 0.3170 | 0.6367 |
| 0.9207 | 0.11 | 200 | 0.6670 | 0.6016 | 0.2636 | 0.6016 |
| 0.6734 | 0.16 | 300 | 0.5539 | 0.8190 | 0.4873 | 0.7617 |
| 0.7133 | 0.21 | 400 | 0.5834 | 0.8148 | 0.4994 | 0.7656 |
| 0.6225 | 0.26 | 500 | 0.8411 | 0.8343 | 0.5144 | 0.7656 |
| 0.8485 | 0.32 | 600 | 0.6813 | 0.7336 | 0.3999 | 0.6992 |
| 0.7567 | 0.37 | 700 | 0.6454 | 0.8504 | 0.5770 | 0.8008 |
| 0.5729 | 0.42 | 800 | 0.8756 | 0.7910 | 0.4676 | 0.7461 |
| 0.7708 | 0.47 | 900 | 0.6872 | 0.8303 | 0.5314 | 0.7812 |
| 0.6194 | 0.53 | 1000 | 0.6900 | 0.8402 | 0.5492 | 0.7891 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2