metadata
license: cc-by-nc-sa-4.0
base_model: InstaDeepAI/nucleotide-transformer-500m-1000g
tags:
- generated_from_trainer
metrics:
- f1
- accuracy
model-index:
- name: mus_promoter-finetuned-lora-NT-500m-1000g
results: []
mus_promoter-finetuned-lora-NT-500m-1000g
This model is a fine-tuned version of InstaDeepAI/nucleotide-transformer-500m-1000g on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3065
- F1: 0.9351
- Mcc Score: 0.8414
- Accuracy: 0.9219
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 |
|---|---|---|---|---|---|---|
| 0.6126 | 0.43 | 100 | 0.4697 | 0.8767 | 0.7135 | 0.8594 |
| 0.3854 | 0.85 | 200 | 0.2682 | 0.9296 | 0.8460 | 0.9219 |
| 0.4832 | 1.28 | 300 | 0.2444 | 0.9296 | 0.8460 | 0.9219 |
| 0.3536 | 1.71 | 400 | 0.3433 | 0.9167 | 0.8113 | 0.9062 |
| 0.3215 | 2.14 | 500 | 0.3475 | 0.9351 | 0.8414 | 0.9219 |
| 0.2961 | 2.56 | 600 | 0.2347 | 0.9231 | 0.8108 | 0.9062 |
| 0.2742 | 2.99 | 700 | 0.3438 | 0.9333 | 0.8395 | 0.9219 |
| 0.2375 | 3.42 | 800 | 0.3448 | 0.9351 | 0.8414 | 0.9219 |
| 0.2438 | 3.85 | 900 | 0.2789 | 0.9351 | 0.8414 | 0.9219 |
| 0.2104 | 4.27 | 1000 | 0.3065 | 0.9351 | 0.8414 | 0.9219 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2