mobilebert-uncased-squad-v2-30-10-2
This model is a fine-tuned version of csarron/mobilebert-uncased-squad-v2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 5.3852
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: 4
- eval_batch_size: 4
- 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 | 261 | 2.5342 |
| 1.1477 | 2.0 | 522 | 3.0589 |
| 1.1477 | 3.0 | 783 | 3.3153 |
| 0.8069 | 4.0 | 1044 | 3.6017 |
| 0.8069 | 5.0 | 1305 | 3.9008 |
| 0.5801 | 6.0 | 1566 | 4.2309 |
| 0.5801 | 7.0 | 1827 | 4.7884 |
| 0.425 | 8.0 | 2088 | 5.3603 |
| 0.425 | 9.0 | 2349 | 5.3233 |
| 0.3237 | 10.0 | 2610 | 5.3852 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1