kubert-from_multilingual
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: 1.7621
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- 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
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.4785 | 200 | 2.5883 |
| No log | 0.9569 | 400 | 2.3145 |
| No log | 1.4354 | 600 | 2.1484 |
| No log | 1.9139 | 800 | 2.0133 |
| No log | 2.3923 | 1000 | 1.9202 |
| No log | 2.8708 | 1200 | 1.8627 |
| No log | 3.3493 | 1400 | 1.8354 |
| No log | 3.8278 | 1600 | 1.7811 |
| No log | 4.3062 | 1800 | 1.7584 |
| No log | 4.7847 | 2000 | 1.7621 |
Framework versions
- Transformers 4.57.3
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2