---
license: mit
base_model: microsoft/biogpt
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: MLMA-Lab8-FinetunedBioGPT-Custom
  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. -->

# MLMA-Lab8-FinetunedBioGPT-Custom

This model is a fine-tuned version of [microsoft/biogpt](https://huggingface.co/microsoft/biogpt) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0648
- Precision: 0.7018
- Recall: 0.8301
- F1: 0.7605
- Accuracy: 0.9752

## 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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3

### Training results

| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.2223        | 1.0   | 665  | 0.1261          | 0.5357    | 0.6135 | 0.5719 | 0.9529   |
| 0.1479        | 2.0   | 1330 | 0.0855          | 0.6373    | 0.7977 | 0.7085 | 0.9687   |
| 0.111         | 3.0   | 1995 | 0.0648          | 0.7018    | 0.8301 | 0.7605 | 0.9752   |


### Framework versions

- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2