kuosbert-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: 1.7454
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 | 0.4728 | 200 | 2.6289 |
| No log | 0.9456 | 400 | 2.3204 |
| No log | 1.4184 | 600 | 2.1676 |
| No log | 1.8913 | 800 | 2.0454 |
| No log | 2.3641 | 1000 | 1.9959 |
| No log | 2.8369 | 1200 | 1.8971 |
| No log | 3.3097 | 1400 | 1.8391 |
| No log | 3.7825 | 1600 | 1.8147 |
| No log | 4.2553 | 1800 | 1.7587 |
| No log | 4.7281 | 2000 | 1.7454 |
Framework versions
- Transformers 4.57.3
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2