t5-base-squad-qag-b
This model is a fine-tuned version of t5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 16.4900
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: 1e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- 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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 15.4767 | 0.5714 | 1 | 19.7375 |
| 22.2253 | 1.5714 | 2 | 19.0585 |
| 21.1788 | 2.5714 | 3 | 18.5133 |
| 21.3016 | 3.5714 | 4 | 18.0134 |
| 20.3052 | 4.5714 | 5 | 17.5808 |
| 19.7086 | 5.5714 | 6 | 17.2109 |
| 19.4675 | 6.5714 | 7 | 16.9223 |
| 19.3453 | 7.5714 | 8 | 16.7059 |
| 18.5491 | 8.5714 | 9 | 16.5610 |
| 18.5816 | 9.5714 | 10 | 16.4900 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.5.1+cu124
- Datasets 3.3.0
- Tokenizers 0.21.0