t5-small-finetuned-wikisql
This model is a fine-tuned version of t5-small on the wikisql dataset. It achieves the following results on the evaluation set:
- Loss: 0.1242
- Rouge2 Precision: 0.8193
- Rouge2 Recall: 0.7267
- Rouge2 Fmeasure: 0.7631
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: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Rouge2 Precision | Rouge2 Recall | Rouge2 Fmeasure |
---|---|---|---|---|---|---|
0.2718 | 1.0 | 2025 | 0.2103 | 0.7551 | 0.6695 | 0.7026 |
0.2172 | 2.0 | 4050 | 0.1762 | 0.7779 | 0.6893 | 0.7237 |
0.1982 | 3.0 | 6075 | 0.1608 | 0.7918 | 0.7014 | 0.7369 |
0.183 | 4.0 | 8100 | 0.1504 | 0.8006 | 0.71 | 0.7456 |
0.1702 | 5.0 | 10125 | 0.1433 | 0.8052 | 0.7137 | 0.7497 |
0.1631 | 6.0 | 12150 | 0.1378 | 0.8086 | 0.7166 | 0.7529 |
0.1575 | 7.0 | 14175 | 0.1336 | 0.8123 | 0.7203 | 0.7566 |
0.152 | 8.0 | 16200 | 0.1300 | 0.8154 | 0.7234 | 0.7597 |
0.1458 | 9.0 | 18225 | 0.1266 | 0.8171 | 0.7251 | 0.7613 |
0.1422 | 10.0 | 20250 | 0.1242 | 0.8193 | 0.7267 | 0.7631 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu116
- Datasets 2.8.0
- Tokenizers 0.13.2
- Downloads last month
- 3