toneza
This model is a fine-tuned version of pythainlp/thainer-corpus-v2-base-model on the lst20 dataset. It achieves the following results on the evaluation set:
- Loss: 0.1293
- Precision: 0.7684
- Recall: 0.8120
- F1: 0.7896
- Accuracy: 0.9565
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: 3
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.1226 | 1.0 | 1978 | 0.1416 | 0.7414 | 0.7802 | 0.7603 | 0.9518 |
0.098 | 2.0 | 3956 | 0.1324 | 0.7602 | 0.7966 | 0.7780 | 0.9545 |
0.0895 | 3.0 | 5934 | 0.1293 | 0.7684 | 0.8120 | 0.7896 | 0.9565 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 62
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.
Finetuned from
Dataset used to train thanaphatt1/WangchanBERTa-LST20
Evaluation results
- Precision on lst20validation set self-reported0.768
- Recall on lst20validation set self-reported0.812
- F1 on lst20validation set self-reported0.790
- Accuracy on lst20validation set self-reported0.956