bert-base-uncased-finetuned-squad
This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0943
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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.0511 | 1.0 | 5533 | 1.0411 |
| 0.788 | 2.0 | 11066 | 1.0211 |
| 0.5838 | 3.0 | 16599 | 1.0943 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.5.1+cu124
- Datasets 3.3.2
- Tokenizers 0.21.0
- Downloads last month
- 13
Model tree for Maxymin/bert-base-uncased-finetuned-squad
Base model
google-bert/bert-base-uncased