t5-small-finetuned-wikisql
This model is a fine-tuned version of t5-small on the wiki_sql dataset. It achieves the following results on the evaluation set:
- Loss: 0.1246
- Rouge2 Precision: 0.8187
- Rouge2 Recall: 0.7269
- Rouge2 Fmeasure: 0.7629
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 |
|---|---|---|---|---|---|---|
| 0.1952 | 1.0 | 4049 | 0.1567 | 0.7948 | 0.7057 | 0.7406 |
| 0.167 | 2.0 | 8098 | 0.1382 | 0.8092 | 0.7171 | 0.7534 |
| 0.1517 | 3.0 | 12147 | 0.1296 | 0.8145 | 0.7228 | 0.7589 |
| 0.1433 | 4.0 | 16196 | 0.1260 | 0.8175 | 0.7254 | 0.7617 |
| 0.1414 | 5.0 | 20245 | 0.1246 | 0.8187 | 0.7269 | 0.7629 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.10.0+cu111
- Datasets 2.0.0
- Tokenizers 0.11.6
- Downloads last month
- 9
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.