---
base_model: vinai/bertweet-base
tags:
- generated_from_trainer
metrics:
- f1
- recall
model-index:
- name: bertweet-base
  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. -->

# bertweet-base

This model is a fine-tuned version of [vinai/bertweet-base](https://huggingface.co/vinai/bertweet-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7685
- F1 Macro: 0.8269
- F1: 0.8697
- F1 Neg: 0.7841
- Acc: 0.8375
- Prec: 0.8930
- Recall: 0.8477
- Mcc: 0.6558

## 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
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1     | F1 Neg | Acc    | Prec   | Recall | Mcc    |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:------:|:------:|:------:|:------:|
| 0.6468        | 1.0   | 592  | 0.5371          | 0.7329   | 0.8451 | 0.6207 | 0.78   | 0.7692 | 0.9375 | 0.5069 |
| 0.454         | 2.0   | 1184 | 0.5912          | 0.7849   | 0.8419 | 0.7279 | 0.8    | 0.852  | 0.8320 | 0.5702 |
| 0.4138        | 3.0   | 1776 | 0.6924          | 0.7853   | 0.8685 | 0.7020 | 0.8175 | 0.8060 | 0.9414 | 0.5951 |
| 0.3396        | 4.0   | 2368 | 0.7403          | 0.8233   | 0.8577 | 0.7888 | 0.83   | 0.9234 | 0.8008 | 0.6594 |
| 0.3215        | 5.0   | 2960 | 0.7685          | 0.8269   | 0.8697 | 0.7841 | 0.8375 | 0.8930 | 0.8477 | 0.6558 |


### Framework versions

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