fine-tune-wangchanberta-SABINA-split-headline1
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: 1.0956
- Accuracy: 0.3861
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: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 7
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.0889 | 1.0 | 26 | 1.1080 | 0.3267 |
| 1.0772 | 2.0 | 52 | 1.0933 | 0.4010 |
| 1.0674 | 3.0 | 78 | 1.0991 | 0.3911 |
| 1.0573 | 4.0 | 104 | 1.0956 | 0.3861 |
| 1.0627 | 5.0 | 130 | 1.0963 | 0.3911 |
| 1.0557 | 6.0 | 156 | 1.1152 | 0.3960 |
| 1.0412 | 7.0 | 182 | 1.0956 | 0.3861 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 5
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.