metadata
base_model: airesearch/wangchanberta-base-att-spm-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: aspect-finnlp-th
results: []
aspect-finnlp-th
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: 0.9164
- Accuracy: 0.7808
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: 5e-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: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.3287 | 1.0 | 512 | 1.2494 | 0.5985 |
| 0.8335 | 2.0 | 1024 | 0.8613 | 0.7289 |
| 0.5842 | 3.0 | 1536 | 0.8177 | 0.7682 |
| 0.4046 | 4.0 | 2048 | 0.8337 | 0.7682 |
| 0.2979 | 5.0 | 2560 | 0.8745 | 0.7773 |
| 0.2083 | 6.0 | 3072 | 0.9164 | 0.7808 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.0