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: 1.5456
- Rouge1: 0.8237
- Rouge2: 0.7136
- Rougel: 0.8142
- Rougelsum: 0.8137
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 |
|---|---|---|---|---|---|---|---|
| 1.891 | 1.0 | 4389 | 1.7024 | 0.8289 | 0.7133 | 0.8163 | 0.8159 |
| 1.8333 | 2.0 | 8778 | 1.6619 | 0.8220 | 0.7113 | 0.8091 | 0.8089 |
| 1.7995 | 3.0 | 13167 | 1.6317 | 0.8213 | 0.7100 | 0.8102 | 0.8098 |
| 1.7632 | 4.0 | 17556 | 1.6076 | 0.8189 | 0.7074 | 0.8081 | 0.8076 |
| 1.7368 | 5.0 | 21945 | 1.5912 | 0.8219 | 0.7107 | 0.8106 | 0.8104 |
| 1.7121 | 6.0 | 26334 | 1.5715 | 0.8177 | 0.7052 | 0.8062 | 0.8060 |
| 1.7042 | 7.0 | 30723 | 1.5595 | 0.8210 | 0.7098 | 0.8104 | 0.8103 |
| 1.688 | 8.0 | 35112 | 1.5515 | 0.8220 | 0.7111 | 0.8118 | 0.8114 |
| 1.6647 | 9.0 | 39501 | 1.5482 | 0.8236 | 0.7122 | 0.8135 | 0.8131 |
| 1.6854 | 10.0 | 43890 | 1.5456 | 0.8237 | 0.7136 | 0.8142 | 0.8137 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2