metadata
library_name: transformers
base_model: airesearch/wangchanberta-base-att-spm-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: CPALL-Stock-Trend-Prediction-Wangchanberta-APR
results: []
CPALL-Stock-Trend-Prediction-Wangchanberta-APR
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: 1.1002
- Accuracy: 0.3341
- Precision: 0.3328
- Recall: 0.3341
- F1: 0.3270
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 |
|---|---|---|---|---|---|---|---|
| 1.1226 | 1.0 | 973 | 1.1571 | 0.3377 | 0.3194 | 0.3377 | 0.1889 |
| 1.1146 | 2.0 | 1946 | 1.1015 | 0.3354 | 0.1125 | 0.3354 | 0.1685 |
| 1.1106 | 3.0 | 2919 | 1.1036 | 0.3385 | 0.2776 | 0.3385 | 0.1715 |
| 1.1083 | 4.0 | 3892 | 1.1033 | 0.3264 | 0.1065 | 0.3264 | 0.1606 |
| 1.1083 | 5.0 | 4865 | 1.1013 | 0.3380 | 0.1143 | 0.3380 | 0.1709 |
| 1.1039 | 6.0 | 5838 | 1.1065 | 0.3354 | 0.1125 | 0.3354 | 0.1685 |
| 1.1032 | 7.0 | 6811 | 1.1011 | 0.3349 | 0.2014 | 0.3349 | 0.1697 |
| 1.106 | 8.0 | 7784 | 1.1056 | 0.3356 | 0.3617 | 0.3356 | 0.1714 |
| 1.1059 | 9.0 | 8757 | 1.1025 | 0.3259 | 0.3248 | 0.3259 | 0.3085 |
| 1.1029 | 10.0 | 9730 | 1.1002 | 0.3341 | 0.3328 | 0.3341 | 0.3270 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1