|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- wikisql |
|
model-index: |
|
- name: flan-t5-base-finetune |
|
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. --> |
|
|
|
# flan-t5-base-finetune |
|
|
|
This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the wikisql dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0966 |
|
- Rouge2 Precision: 0.8525 |
|
- Rouge2 Recall: 0.5466 |
|
- Rouge2 Fmeasure: 0.6549 |
|
|
|
## 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: 32 |
|
- eval_batch_size: 128 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge2 Precision | Rouge2 Recall | Rouge2 Fmeasure | |
|
|:-------------:|:-----:|:-----:|:---------------:|:----------------:|:-------------:|:---------------:| |
|
| 0.162 | 1.0 | 2025 | 0.1235 | 0.8357 | 0.5366 | 0.6425 | |
|
| 0.1277 | 2.0 | 4050 | 0.1082 | 0.8434 | 0.5413 | 0.6482 | |
|
| 0.1142 | 3.0 | 6075 | 0.1000 | 0.8491 | 0.5443 | 0.6522 | |
|
| 0.1063 | 4.0 | 8100 | 0.0978 | 0.8516 | 0.5464 | 0.6544 | |
|
| 0.1 | 5.0 | 10125 | 0.0966 | 0.8525 | 0.5466 | 0.6549 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.28.1 |
|
- Pytorch 2.0.0+cu118 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|
