metadata
base_model: clicknext/phayathaibert
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: phayathaibert-thainer
results: []
phayathaibert-thainer
This model is a fine-tuned version of clicknext/phayathaibert on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1320
- Precision: 0.8493
- Recall: 0.8937
- F1: 0.8710
- Accuracy: 0.9735
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: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 493 | 0.1341 | 0.7524 | 0.8047 | 0.7777 | 0.9630 |
| 0.2346 | 2.0 | 986 | 0.1117 | 0.8015 | 0.8499 | 0.8250 | 0.9702 |
| 0.0922 | 3.0 | 1479 | 0.1173 | 0.8192 | 0.8716 | 0.8446 | 0.9719 |
| 0.059 | 4.0 | 1972 | 0.1157 | 0.8275 | 0.8744 | 0.8503 | 0.9725 |
| 0.0419 | 5.0 | 2465 | 0.1203 | 0.8149 | 0.8766 | 0.8446 | 0.9732 |
| 0.0297 | 6.0 | 2958 | 0.1335 | 0.8361 | 0.8802 | 0.8576 | 0.9736 |
| 0.0237 | 7.0 | 3451 | 0.1335 | 0.8394 | 0.8798 | 0.8591 | 0.9745 |
| 0.0161 | 8.0 | 3944 | 0.1383 | 0.8409 | 0.8843 | 0.8621 | 0.9744 |
| 0.0133 | 9.0 | 4437 | 0.1457 | 0.8446 | 0.8828 | 0.8633 | 0.9743 |
| 0.01 | 10.0 | 4930 | 0.1437 | 0.8433 | 0.8811 | 0.8618 | 0.9747 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0