metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- wikisql
model-index:
- name: t5-small-finetuned-wikisql
results: []
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: 0.1266
- Rouge2 Precision: 0.817
- Rouge2 Recall: 0.7258
- Rouge2 Fmeasure: 0.7616
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 |
|---|---|---|---|---|---|---|
| 0.2018 | 1.0 | 4049 | 0.1603 | 0.7905 | 0.7009 | 0.736 |
| 0.1677 | 2.0 | 8098 | 0.1414 | 0.8061 | 0.7147 | 0.7506 |
| 0.156 | 3.0 | 12147 | 0.1314 | 0.8127 | 0.722 | 0.7576 |
| 0.1469 | 4.0 | 16196 | 0.1280 | 0.8152 | 0.7238 | 0.7597 |
| 0.1433 | 5.0 | 20245 | 0.1266 | 0.817 | 0.7258 | 0.7616 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2