metadata
library_name: transformers
base_model: airesearch/wangchanberta-base-att-spm-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: KBANK-finetune-wangchan2
results: []
KBANK-finetune-wangchan2
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: 1.0220
- Accuracy: 0.4078
- Precision: 0.3996
- Recall: 0.4078
- F1: 0.3891
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 15 | 0.9362 | 0.5534 | 0.4303 | 0.5534 | 0.4286 |
| No log | 2.0 | 30 | 0.9895 | 0.4757 | 0.4461 | 0.4757 | 0.4563 |
| No log | 3.0 | 45 | 0.9732 | 0.4757 | 0.4209 | 0.4757 | 0.4458 |
| No log | 4.0 | 60 | 0.9737 | 0.4175 | 0.3414 | 0.4175 | 0.3717 |
| No log | 5.0 | 75 | 1.0453 | 0.4078 | 0.4099 | 0.4078 | 0.3739 |
| No log | 6.0 | 90 | 1.0218 | 0.4175 | 0.4126 | 0.4175 | 0.3950 |
| No log | 7.0 | 105 | 1.0220 | 0.4078 | 0.3996 | 0.4078 | 0.3891 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1