|
|
--- |
|
|
license: apache-2.0 |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: t5-text2sql_v1 |
|
|
results: [] |
|
|
--- |
|
|
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
|
|
# t5-text2sql_v1 |
|
|
|
|
|
This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the None dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.0733 |
|
|
- Rouge2 Precision: 0.9124 |
|
|
- Rouge2 Recall: 0.405 |
|
|
- Rouge2 Fmeasure: 0.5291 |
|
|
|
|
|
## 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: 8 |
|
|
- eval_batch_size: 8 |
|
|
- seed: 42 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- num_epochs: 30 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge2 Precision | Rouge2 Recall | Rouge2 Fmeasure | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:----------------:|:-------------:|:---------------:| |
|
|
| No log | 1.0 | 11 | 1.9724 | 0.0931 | 0.0257 | 0.0386 | |
|
|
| No log | 2.0 | 22 | 1.2952 | 0.0923 | 0.0261 | 0.0386 | |
|
|
| No log | 3.0 | 33 | 0.8639 | 0.1081 | 0.0261 | 0.0405 | |
|
|
| No log | 4.0 | 44 | 0.5684 | 0.2273 | 0.0945 | 0.1281 | |
|
|
| No log | 5.0 | 55 | 0.3793 | 0.4304 | 0.1823 | 0.2449 | |
|
|
| No log | 6.0 | 66 | 0.2920 | 0.6664 | 0.3135 | 0.401 | |
|
|
| No log | 7.0 | 77 | 0.2351 | 0.7222 | 0.3114 | 0.4113 | |
|
|
| No log | 8.0 | 88 | 0.2055 | 0.7373 | 0.3141 | 0.4147 | |
|
|
| No log | 9.0 | 99 | 0.1787 | 0.7308 | 0.3023 | 0.4055 | |
|
|
| No log | 10.0 | 110 | 0.1540 | 0.7755 | 0.3297 | 0.4373 | |
|
|
| No log | 11.0 | 121 | 0.1406 | 0.7661 | 0.3217 | 0.4269 | |
|
|
| No log | 12.0 | 132 | 0.1299 | 0.8462 | 0.3729 | 0.488 | |
|
|
| No log | 13.0 | 143 | 0.1172 | 0.8169 | 0.353 | 0.4671 | |
|
|
| No log | 14.0 | 154 | 0.1133 | 0.8509 | 0.382 | 0.4972 | |
|
|
| No log | 15.0 | 165 | 0.1049 | 0.8509 | 0.382 | 0.4972 | |
|
|
| No log | 16.0 | 176 | 0.0988 | 0.8234 | 0.3471 | 0.462 | |
|
|
| No log | 17.0 | 187 | 0.0921 | 0.8696 | 0.3852 | 0.5048 | |
|
|
| No log | 18.0 | 198 | 0.0877 | 0.8575 | 0.3676 | 0.488 | |
|
|
| No log | 19.0 | 209 | 0.0878 | 0.8575 | 0.3648 | 0.485 | |
|
|
| No log | 20.0 | 220 | 0.0849 | 0.8575 | 0.3648 | 0.485 | |
|
|
| No log | 21.0 | 231 | 0.0806 | 0.8784 | 0.3785 | 0.499 | |
|
|
| No log | 22.0 | 242 | 0.0791 | 0.9217 | 0.4101 | 0.5348 | |
|
|
| No log | 23.0 | 253 | 0.0794 | 0.8959 | 0.3901 | 0.5133 | |
|
|
| No log | 24.0 | 264 | 0.0773 | 0.9198 | 0.412 | 0.537 | |
|
|
| No log | 25.0 | 275 | 0.0744 | 0.9217 | 0.4101 | 0.5348 | |
|
|
| No log | 26.0 | 286 | 0.0735 | 0.9217 | 0.4101 | 0.5348 | |
|
|
| No log | 27.0 | 297 | 0.0742 | 0.9257 | 0.4136 | 0.5394 | |
|
|
| No log | 28.0 | 308 | 0.0740 | 0.9124 | 0.405 | 0.5291 | |
|
|
| No log | 29.0 | 319 | 0.0734 | 0.9124 | 0.405 | 0.5291 | |
|
|
| No log | 30.0 | 330 | 0.0733 | 0.9124 | 0.405 | 0.5291 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.21.1 |
|
|
- Pytorch 1.12.1+cu113 |
|
|
- Datasets 2.4.0 |
|
|
- Tokenizers 0.12.1 |
|
|
|
