distil-electra-qa
This model is a fine-tuned version of lsanochkin/distilelectra-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.6058
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.0323 | 1.0 | 1883 | 1.7828 |
| 1.6154 | 2.0 | 3766 | 1.6530 |
| 1.43 | 3.0 | 5649 | 1.6058 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.11.0+cu102
- Datasets 2.8.0
- Tokenizers 0.13.2