bert-base-multilingual-cased1
This model is a fine-tuned version of bert-base-multilingual-cased on the squad_v2 dataset. It achieves the following results on the evaluation set:
- Loss: 1.3467
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.1335 | 1.0 | 1547 | 1.0084 |
| 0.7574 | 2.0 | 3094 | 0.9890 |
| 0.5211 | 3.0 | 4641 | 1.0139 |
| 0.335 | 4.0 | 6188 | 1.1702 |
| 0.2465 | 5.0 | 7735 | 1.3467 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3