| --- |
| license: apache-2.0 |
| base_model: cssupport/t5-small-awesome-text-to-sql |
| tags: |
| - generated_from_trainer |
| model-index: |
| - name: text2sql-finetuned-60M |
| 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. --> |
|
|
| # text2sql-finetuned-60M |
|
|
| This model is a fine-tuned version of [cssupport/t5-small-awesome-text-to-sql](https://huggingface.co/cssupport/t5-small-awesome-text-to-sql) on an unknown dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.0054 |
|
|
| ## 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: 0.0001 |
| - train_batch_size: 8 |
| - eval_batch_size: 8 |
| - seed: 42 |
| - gradient_accumulation_steps: 4 |
| - total_train_batch_size: 32 |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| - lr_scheduler_type: linear |
| - lr_scheduler_warmup_steps: 50 |
| - training_steps: 2100 |
| - mixed_precision_training: Native AMP |
|
|
| ### Training results |
|
|
| | Training Loss | Epoch | Step | Validation Loss | |
| |:-------------:|:-----:|:----:|:---------------:| |
| | 0.3586 | 0.29 | 150 | 0.1971 | |
| | 0.1748 | 0.57 | 300 | 0.0731 | |
| | 0.1453 | 0.86 | 450 | 0.0360 | |
| | 0.0947 | 1.15 | 600 | 0.0215 | |
| | 0.0816 | 1.44 | 750 | 0.0145 | |
| | 0.0635 | 1.72 | 900 | 0.0106 | |
| | 0.0464 | 2.01 | 1050 | 0.0085 | |
| | 0.0472 | 2.3 | 1200 | 0.0073 | |
| | 0.0414 | 2.59 | 1350 | 0.0065 | |
| | 0.0376 | 2.87 | 1500 | 0.0061 | |
| | 0.0342 | 3.16 | 1650 | 0.0057 | |
| | 0.0363 | 3.45 | 1800 | 0.0055 | |
| | 0.0389 | 3.74 | 1950 | 0.0055 | |
| | 0.0308 | 4.02 | 2100 | 0.0054 | |
|
|
|
|
| ### Framework versions |
|
|
| - Transformers 4.35.2 |
| - Pytorch 2.1.0+cu121 |
| - Datasets 2.16.1 |
| - Tokenizers 0.15.1 |
|
|
