bert-3lang
This model is a fine-tuned version of bert-base-multilingual-cased on the tydiqa dataset. It achieves the following results on the evaluation set:
- Loss: 0.6422
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: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.8161 | 1.0 | 905 | 0.6422 |
Framework versions
- Transformers 4.15.0
- Pytorch 1.9.1
- Datasets 2.0.0
- Tokenizers 0.10.3