---
base_model: vinai/phobert-base-v2
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: PhoBERT-train-aug_replace_synonym
  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. -->

# PhoBERT-train-aug_replace_synonym

This model is a fine-tuned version of [vinai/phobert-base-v2](https://huggingface.co./vinai/phobert-base-v2) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.1202
- Accuracy: 0.68
- F1: 0.6901

## 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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.8957        | 1.0   | 86   | 0.7282          | 0.75     | 0.7559 |
| 0.6001        | 2.0   | 172  | 0.6158          | 0.74     | 0.7414 |
| 0.3969        | 3.0   | 258  | 0.7190          | 0.76     | 0.7606 |
| 0.2842        | 4.0   | 344  | 0.9430          | 0.6      | 0.5878 |
| 0.2551        | 5.0   | 430  | 0.9202          | 0.68     | 0.6905 |
| 0.1586        | 6.0   | 516  | 1.0452          | 0.7      | 0.7089 |
| 0.1387        | 7.0   | 602  | 1.1442          | 0.67     | 0.6789 |
| 0.1218        | 8.0   | 688  | 1.1202          | 0.68     | 0.6901 |


### Framework versions

- Transformers 4.32.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3