metadata
license: apache-2.0
base_model: bert-base-multilingual-cased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: fine-tune-bert-stock-thai
results: []
fine-tune-bert-stock-thai
This model is a fine-tuned version of bert-base-multilingual-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.1502
- Accuracy: 0.3597
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 |
|---|---|---|---|---|
| 1.0972 | 1.0 | 450 | 1.0915 | 0.3606 |
| 1.0916 | 2.0 | 900 | 1.0926 | 0.3686 |
| 1.0813 | 3.0 | 1350 | 1.1004 | 0.3739 |
| 1.0671 | 4.0 | 1800 | 1.1064 | 0.3619 |
| 1.0376 | 5.0 | 2250 | 1.1372 | 0.3628 |
| 1.0158 | 6.0 | 2700 | 1.1502 | 0.3597 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1