MobileBERT-uncased-squad-v1-BiLSTM-finetuned-squad-resize-fc1-beforedropout02
This model is a fine-tuned version of csarron/mobilebert-uncased-squad-v1 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0264
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: 3e-05
- train_batch_size: 6
- eval_batch_size: 60
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5555 | 1.0 | 14619 | 1.0491 |
| 0.6854 | 2.0 | 29238 | 1.0264 |
Framework versions
- Transformers 4.40.0
- Pytorch 2.5.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1