bert-finetuned-multilingual-xquad2
This model is a fine-tuned version of AnshulRustogi/bert-base-multilingual-cased1 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.3256
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-06
- 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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 209 | 1.4790 |
| No log | 2.0 | 418 | 1.3976 |
| 1.5107 | 3.0 | 627 | 1.3624 |
| 1.5107 | 4.0 | 836 | 1.3265 |
| 1.1003 | 5.0 | 1045 | 1.3174 |
| 1.1003 | 6.0 | 1254 | 1.3216 |
| 1.1003 | 7.0 | 1463 | 1.3219 |
| 0.9379 | 8.0 | 1672 | 1.3234 |
| 0.9379 | 9.0 | 1881 | 1.3234 |
| 0.8494 | 10.0 | 2090 | 1.3256 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3