t5-small-finetuned-squad-qgen
This model is a fine-tuned version of t5-small on the squad dataset. It achieves the following results on the evaluation set:
- Loss: 0.3805
- Em: 0.0
- F1: 0.3643
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: 5e-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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Em | F1 |
|---|---|---|---|---|---|
| 0.4449 | 1.0 | 2738 | 0.3992 | 0.0 | 0.3859 |
| 0.4206 | 2.0 | 5476 | 0.3886 | 0.0 | 0.3781 |
| 0.4092 | 3.0 | 8214 | 0.3837 | 0.0 | 0.3827 |
| 0.4055 | 4.0 | 10952 | 0.3809 | 0.0 | 0.3747 |
| 0.3997 | 5.0 | 13690 | 0.3805 | 0.0 | 0.3643 |
Framework versions
- Transformers 4.19.2
- Pytorch 1.11.0+cu113
- Datasets 2.2.2
- Tokenizers 0.12.1