|
--- |
|
license: cc-by-nc-sa-4.0 |
|
base_model: InstaDeepAI/nucleotide-transformer-v2-50m-multi-species |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- f1 |
|
- matthews_correlation |
|
- accuracy |
|
model-index: |
|
- name: gut_1024b-finetuned-lora-v2-50m-multi-species |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# gut_1024b-finetuned-lora-v2-50m-multi-species |
|
|
|
This model is a fine-tuned version of [InstaDeepAI/nucleotide-transformer-v2-50m-multi-species](https://huggingface.co/InstaDeepAI/nucleotide-transformer-v2-50m-multi-species) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4237 |
|
- F1: 0.8660 |
|
- Matthews Correlation: 0.6384 |
|
- Accuracy: 0.8252 |
|
- F1 Score: 0.8660 |
|
|
|
## 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 | Matthews Correlation | Accuracy | F1 Score | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:--------------------:|:--------:|:--------:| |
|
| 0.6937 | 0.02 | 100 | 0.6419 | 0.7758 | 0.2955 | 0.6584 | 0.7758 | |
|
| 0.652 | 0.04 | 200 | 0.5536 | 0.8102 | 0.4925 | 0.7601 | 0.8102 | |
|
| 0.5786 | 0.05 | 300 | 0.5052 | 0.8286 | 0.5183 | 0.7682 | 0.8286 | |
|
| 0.5083 | 0.07 | 400 | 0.5294 | 0.8230 | 0.4972 | 0.7475 | 0.8230 | |
|
| 0.5439 | 0.09 | 500 | 0.4759 | 0.8484 | 0.5865 | 0.8019 | 0.8484 | |
|
| 0.4945 | 0.11 | 600 | 0.5015 | 0.8363 | 0.5424 | 0.7770 | 0.8363 | |
|
| 0.4564 | 0.12 | 700 | 0.4767 | 0.8448 | 0.5911 | 0.8057 | 0.8448 | |
|
| 0.4306 | 0.14 | 800 | 0.4619 | 0.8517 | 0.6066 | 0.8129 | 0.8517 | |
|
| 0.4588 | 0.16 | 900 | 0.4485 | 0.8532 | 0.5973 | 0.8003 | 0.8532 | |
|
| 0.4784 | 0.18 | 1000 | 0.4237 | 0.8660 | 0.6384 | 0.8252 | 0.8660 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.1 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.17.1 |
|
- Tokenizers 0.15.2 |
|
|
