t5-small-finetuned-wikisql
This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1029
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 |
|---|---|---|---|
| 0.1992 | 1.0 | 3523 | 0.1566 |
| 0.1688 | 2.0 | 7046 | 0.1350 |
| 0.1494 | 3.0 | 10569 | 0.1247 |
| 0.135 | 4.0 | 14092 | 0.1198 |
| 0.1257 | 5.0 | 17615 | 0.1140 |
| 0.1239 | 6.0 | 21138 | 0.1118 |
| 0.1179 | 7.0 | 24661 | 0.1087 |
| 0.1168 | 8.0 | 28184 | 0.1072 |
| 0.1104 | 9.0 | 31707 | 0.1066 |
| 0.1088 | 10.0 | 35230 | 0.1051 |
| 0.1087 | 11.0 | 38753 | 0.1040 |
| 0.1056 | 12.0 | 42276 | 0.1030 |
| 0.1002 | 13.0 | 45799 | 0.1031 |
| 0.1025 | 14.0 | 49322 | 0.1031 |
| 0.1011 | 15.0 | 52845 | 0.1029 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2