|
--- |
|
license: apache-2.0 |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
base_model: google/flan-t5-small |
|
model-index: |
|
- name: flan-t5-small-sql |
|
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-small-sql |
|
|
|
This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co./google/flan-t5-small) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3584 |
|
|
|
## 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: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- distributed_type: multi-GPU |
|
- num_devices: 8 |
|
- total_train_batch_size: 128 |
|
- total_eval_batch_size: 128 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 1000.0 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 0.3349 | 62.5 | 500 | 0.2107 | |
|
| 0.1147 | 125.0 | 1000 | 0.2410 | |
|
| 0.071 | 187.5 | 1500 | 0.2687 | |
|
| 0.0502 | 250.0 | 2000 | 0.2901 | |
|
| 0.0373 | 312.5 | 2500 | 0.3033 | |
|
| 0.0301 | 375.0 | 3000 | 0.3141 | |
|
| 0.025 | 437.5 | 3500 | 0.3235 | |
|
| 0.0212 | 500.0 | 4000 | 0.3312 | |
|
| 0.0187 | 562.5 | 4500 | 0.3404 | |
|
| 0.017 | 625.0 | 5000 | 0.3371 | |
|
| 0.0148 | 687.5 | 5500 | 0.3466 | |
|
| 0.0139 | 750.0 | 6000 | 0.3480 | |
|
| 0.0124 | 812.5 | 6500 | 0.3552 | |
|
| 0.0118 | 875.0 | 7000 | 0.3594 | |
|
| 0.0112 | 937.5 | 7500 | 0.3581 | |
|
| 0.0106 | 1000.0 | 8000 | 0.3584 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.7.1 |
|
- Transformers 4.38.0 |
|
- Pytorch 2.1.2+cu121 |
|
- Datasets 2.17.0 |
|
- Tokenizers 0.15.2 |
