t5-small-finetuned-acbsql
This model is a fine-tuned version of t5-small on the ACB SQL dataset. It achieves the following results on the evaluation set:
- Loss: 0.0699
- Rouge2 Precision: 0.6901
- Rouge2 Recall: 0.2546
- Rouge2 Fmeasure: 0.3639
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: 8
- eval_batch_size: 8
- 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 |
|---|---|---|---|---|---|---|
| 0.7623 | 1.0 | 155 | 0.3883 | 0.3621 | 0.1411 | 0.1985 |
| 0.3774 | 2.0 | 310 | 0.2040 | 0.5116 | 0.1845 | 0.2672 |
| 0.2693 | 3.0 | 465 | 0.1461 | 0.5462 | 0.1958 | 0.2847 |
| 0.2129 | 4.0 | 620 | 0.1147 | 0.5799 | 0.2135 | 0.3067 |
| 0.1807 | 5.0 | 775 | 0.0948 | 0.6145 | 0.2264 | 0.3242 |
| 0.1441 | 6.0 | 930 | 0.0847 | 0.6158 | 0.2298 | 0.3284 |
| 0.1361 | 7.0 | 1085 | 0.0785 | 0.6389 | 0.2358 | 0.3371 |
| 0.1268 | 8.0 | 1240 | 0.0733 | 0.6867 | 0.254 | 0.3628 |
| 0.1259 | 9.0 | 1395 | 0.0709 | 0.6875 | 0.2538 | 0.3626 |
| 0.1199 | 10.0 | 1550 | 0.0699 | 0.6901 | 0.2546 | 0.3639 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3