metadata
base_model: OwaisAhmad/flant5-text2sql-model
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: flant5-nltosql-wikisqlandspider
results: []
flant5-nltosql-wikisqlandspider
This model is a fine-tuned version of OwaisAhmad/flant5-text2sql-model on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2761
- Rouge1: 0.6182
- Rouge2: 0.5007
- Rougel: 0.6013
- Rougelsum: 0.6012
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: 0.001
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| 0.5855 | 1.0 | 2332 | 0.4335 | 0.5753 | 0.4179 | 0.5575 | 0.5575 |
| 0.3011 | 2.0 | 4664 | 0.2983 | 0.6043 | 0.4777 | 0.5891 | 0.5890 |
| 0.1745 | 3.0 | 6996 | 0.2755 | 0.6091 | 0.4867 | 0.5917 | 0.5911 |
| 0.0873 | 4.0 | 9328 | 0.2761 | 0.6182 | 0.5007 | 0.6013 | 0.6012 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.2
- Datasets 2.1.0
- Tokenizers 0.15.2