t5-small-finetuned-wikisql-with-modified-input
This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0420
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.1013 | 1.0 | 3523 | 0.0680 |
| 0.0783 | 2.0 | 7046 | 0.0569 |
| 0.0707 | 3.0 | 10569 | 0.0526 |
| 0.0604 | 4.0 | 14092 | 0.0494 |
| 0.0547 | 5.0 | 17615 | 0.0467 |
| 0.0535 | 6.0 | 21138 | 0.0464 |
| 0.05 | 7.0 | 24661 | 0.0442 |
| 0.0482 | 8.0 | 28184 | 0.0440 |
| 0.0449 | 9.0 | 31707 | 0.0431 |
| 0.0438 | 10.0 | 35230 | 0.0425 |
| 0.0441 | 11.0 | 38753 | 0.0424 |
| 0.0422 | 12.0 | 42276 | 0.0425 |
| 0.04 | 13.0 | 45799 | 0.0419 |
| 0.0401 | 14.0 | 49322 | 0.0421 |
| 0.04 | 15.0 | 52845 | 0.0420 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2