TH_mt5-base-finetuned-wikisql_ENTH
This model is a fine-tuned version of google/mt5-base on the wikisql dataset. It achieves the following results on the evaluation set:
- Loss: 0.0905
- Rouge2 Precision: 0.8555
- Rouge2 Recall: 0.7782
- Rouge2 Fmeasure: 0.8093
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge2 Precision | Rouge2 Recall | Rouge2 Fmeasure |
|---|---|---|---|---|---|---|
| 0.1548 | 1.0 | 4049 | 0.1137 | 0.8322 | 0.759 | 0.7877 |
| 0.1207 | 2.0 | 8098 | 0.1006 | 0.8457 | 0.7669 | 0.7985 |
| 0.1047 | 3.0 | 12147 | 0.0945 | 0.8516 | 0.7739 | 0.805 |
| 0.096 | 4.0 | 16196 | 0.0920 | 0.8543 | 0.7774 | 0.8083 |
| 0.0938 | 5.0 | 20245 | 0.0905 | 0.8555 | 0.7782 | 0.8093 |
Framework versions
- Transformers 4.26.1
- Pytorch 2.0.1+cu117
- Datasets 2.14.7.dev0
- Tokenizers 0.13.3