metadata
library_name: transformers
license: apache-2.0
base_model: google-bert/bert-base-multilingual-cased
tags:
- vietnamese
- nli
- mbert
- natural-language-inference
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: mbert_vietnamese_nli
results: []
mbert_vietnamese_nli
This model is a fine-tuned version of google-bert/bert-base-multilingual-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1310
- Accuracy: 0.9686
- F1 Macro: 0.9686
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: 1e-05
- train_batch_size: 16
- eval_batch_size: 32
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 300
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro |
|---|---|---|---|---|---|
| 0.5033 | 1.0 | 1368 | 0.1542 | 0.9558 | 0.9559 |
| 0.2608 | 2.0 | 2736 | 0.1725 | 0.9584 | 0.9584 |
| 0.239 | 3.0 | 4104 | 0.1310 | 0.9686 | 0.9686 |
Framework versions
- Transformers 4.57.3
- Pytorch 2.9.0+cu126
- Datasets 4.4.2
- Tokenizers 0.22.1