---
license: mit
base_model: facebook/esm2_t12_35M_UR50D
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: esm2_t12_35M_qlora_glycosylation_sites_2024-02-11_22-11-09
  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. -->

# esm2_t12_35M_qlora_glycosylation_sites_2024-02-11_22-11-09

This model is a fine-tuned version of [facebook/esm2_t12_35M_UR50D](https://huggingface.co/facebook/esm2_t12_35M_UR50D) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1117
- Accuracy: 0.9968
- Precision: 0.4831
- Recall: 0.9671
- F1: 0.6443
- Auc: 0.9820
- Mcc: 0.6823

## 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: 0.0003701568055793089
- train_batch_size: 36
- eval_batch_size: 36
- seed: 8893
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 3
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     | Auc    | Mcc    |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:------:|:------:|
| 0.1789        | 1.0   | 295  | 0.1102          | 0.9962   | 0.4391    | 0.9638 | 0.6034 | 0.9801 | 0.6492 |
| 0.0145        | 2.0   | 590  | 0.1105          | 0.9967   | 0.4776    | 0.9663 | 0.6393 | 0.9816 | 0.6782 |
| 0.0115        | 3.0   | 885  | 0.1117          | 0.9968   | 0.4831    | 0.9671 | 0.6443 | 0.9820 | 0.6823 |


### Framework versions

- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.1