metadata
library_name: transformers
base_model: airesearch/wangchanberta-base-att-spm-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: wangchan-sentiment-thai-text-model
results: []
datasets:
- pythainlp/wisesight_sentiment
- Wongnai/wongnai_reviews
language:
- th
pipeline_tag: text-classification
wangchan-sentiment-thai-text-model
This model is a fine-tuned version of airesearch/wangchanberta-base-att-spm-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.1248
- Accuracy: 0.7413
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6058 | 1.0 | 1911 | 0.5904 | 0.7442 |
| 0.5355 | 2.0 | 3822 | 0.5625 | 0.7559 |
| 0.4737 | 3.0 | 5733 | 0.5731 | 0.7493 |
| 0.4039 | 4.0 | 7644 | 0.6235 | 0.7547 |
| 0.3286 | 5.0 | 9555 | 0.7004 | 0.7524 |
| 0.2704 | 6.0 | 11466 | 0.7713 | 0.7416 |
| 0.21 | 7.0 | 13377 | 0.9502 | 0.7432 |
| 0.1808 | 8.0 | 15288 | 0.9720 | 0.7407 |
| 0.1494 | 9.0 | 17199 | 1.0570 | 0.7361 |
| 0.1304 | 10.0 | 19110 | 1.1248 | 0.7413 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1