|
--- |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: ALL_mt5-base_10_spider_15_wikiSQL |
|
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. --> |
|
|
|
# ALL_mt5-base_10_spider_15_wikiSQL |
|
|
|
This model was trained from scratch on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0233 |
|
- Rouge2 Precision: 0.8562 |
|
- Rouge2 Recall: 0.5679 |
|
- Rouge2 Fmeasure: 0.6471 |
|
|
|
## 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: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge2 Precision | Rouge2 Recall | Rouge2 Fmeasure | |
|
|:-------------:|:-----:|:----:|:---------------:|:----------------:|:-------------:|:---------------:| |
|
| 0.4206 | 1.0 | 875 | 0.1165 | 0.6166 | 0.4044 | 0.4599 | |
|
| 0.1438 | 2.0 | 1750 | 0.0773 | 0.7093 | 0.479 | 0.5408 | |
|
| 0.104 | 3.0 | 2625 | 0.0562 | 0.7512 | 0.5048 | 0.5713 | |
|
| 0.0839 | 4.0 | 3500 | 0.0442 | 0.7839 | 0.527 | 0.5967 | |
|
| 0.0746 | 5.0 | 4375 | 0.0367 | 0.8114 | 0.5424 | 0.616 | |
|
| 0.0641 | 6.0 | 5250 | 0.0313 | 0.8265 | 0.5497 | 0.6255 | |
|
| 0.056 | 7.0 | 6125 | 0.0277 | 0.8402 | 0.5583 | 0.6354 | |
|
| 0.0514 | 8.0 | 7000 | 0.0252 | 0.8509 | 0.5638 | 0.6425 | |
|
| 0.0484 | 9.0 | 7875 | 0.0237 | 0.8544 | 0.567 | 0.6459 | |
|
| 0.0475 | 10.0 | 8750 | 0.0233 | 0.8562 | 0.5679 | 0.6471 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.26.1 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.13.3 |
|
|