metadata
license: cc-by-nc-sa-4.0
base_model: InstaDeepAI/nucleotide-transformer-500m-human-ref
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: gut_1024-finetuned-lora-NT-500m-human-ref
results: []
gut_1024-finetuned-lora-NT-500m-human-ref
This model is a fine-tuned version of InstaDeepAI/nucleotide-transformer-500m-human-ref on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5875
- F1: 0.7769
- Mcc Score: 0.3628
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 |
|---|---|---|---|---|---|
| 0.8285 | 0.02 | 100 | 0.6805 | 0.7478 | 0.0 |
| 0.7353 | 0.04 | 200 | 0.6825 | 0.7478 | 0.0 |
| 0.7131 | 0.05 | 300 | 0.6285 | 0.7644 | 0.2641 |
| 0.7292 | 0.07 | 400 | 0.6473 | 0.7680 | 0.3281 |
| 0.6666 | 0.09 | 500 | 0.6445 | 0.7199 | 0.3140 |
| 0.6413 | 0.11 | 600 | 0.6176 | 0.7702 | 0.3201 |
| 0.6056 | 0.12 | 700 | 0.6388 | 0.7170 | 0.3337 |
| 0.6215 | 0.14 | 800 | 0.6161 | 0.7506 | 0.3337 |
| 0.596 | 0.16 | 900 | 0.6000 | 0.7814 | 0.3515 |
| 0.6444 | 0.18 | 1000 | 0.5875 | 0.7769 | 0.3628 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.1.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2