bert_results
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: 0.1916
- Precision: 0.8920
- Recall: 0.8986
- F1: 0.8953
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: 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: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 |
|---|---|---|---|---|---|---|
| 0.1686 | 1.0 | 12500 | 0.1961 | 0.8800 | 0.8837 | 0.8818 |
| 0.1048 | 2.0 | 25000 | 0.1901 | 0.8931 | 0.8987 | 0.8959 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.14.1+cu130
- Datasets 3.1.0
- Tokenizers 0.20.3