|
--- |
|
license: cc-by-nc-sa-4.0 |
|
base_model: InstaDeepAI/nucleotide-transformer-500m-1000g |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- f1 |
|
model-index: |
|
- name: gut_1024-finetuned-lora-NT-500m-1000g |
|
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_1024-finetuned-lora-NT-500m-1000g |
|
|
|
This model is a fine-tuned version of [InstaDeepAI/nucleotide-transformer-500m-1000g](https://huggingface.co/InstaDeepAI/nucleotide-transformer-500m-1000g) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4974 |
|
- F1: 0.8222 |
|
- Mcc Score: 0.5121 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:---------:| |
|
| 0.81 | 0.02 | 100 | 0.6937 | 0.7478 | 0.0 | |
|
| 0.7437 | 0.04 | 200 | 0.9181 | 0.0 | 0.0 | |
|
| 0.7256 | 0.05 | 300 | 0.6935 | 0.7478 | 0.0 | |
|
| 0.6717 | 0.07 | 400 | 0.6097 | 0.7208 | 0.3287 | |
|
| 0.6583 | 0.09 | 500 | 0.6723 | 0.6032 | 0.3371 | |
|
| 0.6158 | 0.11 | 600 | 0.5444 | 0.7973 | 0.4579 | |
|
| 0.5618 | 0.12 | 700 | 0.5551 | 0.7728 | 0.4420 | |
|
| 0.5324 | 0.14 | 800 | 0.5200 | 0.7764 | 0.4601 | |
|
| 0.5326 | 0.16 | 900 | 0.5166 | 0.8190 | 0.4874 | |
|
| 0.5769 | 0.18 | 1000 | 0.4974 | 0.8222 | 0.5121 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.1 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.17.1 |
|
- Tokenizers 0.15.2 |
|
|
