metadata
base_model: TeeA/T5-Text2SQL-Bilingual
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: Text2SQL-Bilingual
results: []
Text2SQL-Bilingual
This model is a fine-tuned version of TeeA/T5-Text2SQL-Bilingual on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.4095
- Rouge1: 0.8431
- Rouge2: 0.7496
- Rougel: 0.8358
- Rougelsum: 0.8364
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| 1.6571 | 1.0 | 4389 | 1.5119 | 0.8292 | 0.7219 | 0.8204 | 0.8210 |
| 1.6181 | 2.0 | 8778 | 1.4851 | 0.8329 | 0.7293 | 0.8239 | 0.8245 |
| 1.6051 | 3.0 | 13167 | 1.4654 | 0.8324 | 0.7313 | 0.8243 | 0.8249 |
| 1.5903 | 4.0 | 17556 | 1.4522 | 0.8372 | 0.7396 | 0.8292 | 0.8298 |
| 1.5635 | 5.0 | 21945 | 1.4364 | 0.8399 | 0.7438 | 0.8320 | 0.8328 |
| 1.5304 | 6.0 | 26334 | 1.4274 | 0.8417 | 0.7455 | 0.8342 | 0.8346 |
| 1.5267 | 7.0 | 30723 | 1.4185 | 0.8409 | 0.7453 | 0.8336 | 0.8341 |
| 1.5241 | 8.0 | 35112 | 1.4129 | 0.8419 | 0.7480 | 0.8347 | 0.8354 |
| 1.5185 | 9.0 | 39501 | 1.4103 | 0.8431 | 0.7496 | 0.8355 | 0.8363 |
| 1.5174 | 10.0 | 43890 | 1.4095 | 0.8431 | 0.7496 | 0.8358 | 0.8364 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2