<!-- 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. -->
REPEAT_4wangchanberta-base-att-spm-uncased
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: 0.5948
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: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5182 | 1.0 | 8561 | 0.3278 |
| 0.2837 | 2.0 | 17122 | 0.3973 |
| 0.2215 | 3.0 | 25683 | 0.5649 |
| 0.1851 | 4.0 | 34244 | 0.6375 |
| 0.1667 | 5.0 | 42805 | 0.5948 |
Framework versions
- Transformers 4.15.0
- Pytorch 1.13.0+cu116
- Datasets 1.17.0
- Tokenizers 0.10.3
