|
--- |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: ALL_mt5-base_10_spider_10_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_10_wikiSQL |
|
|
|
This model was trained from scratch on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0241 |
|
- Rouge2 Precision: 0.8525 |
|
- Rouge2 Recall: 0.5646 |
|
- Rouge2 Fmeasure: 0.6434 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:----------------:|:-------------:|:---------------:| |
|
| 0.4259 | 1.0 | 875 | 0.1208 | 0.6006 | 0.3892 | 0.4443 | |
|
| 0.1482 | 2.0 | 1750 | 0.0808 | 0.7001 | 0.4721 | 0.5333 | |
|
| 0.1073 | 3.0 | 2625 | 0.0588 | 0.7416 | 0.5007 | 0.5657 | |
|
| 0.0867 | 4.0 | 3500 | 0.0461 | 0.7741 | 0.5208 | 0.5894 | |
|
| 0.0769 | 5.0 | 4375 | 0.0382 | 0.7999 | 0.5351 | 0.6073 | |
|
| 0.0658 | 6.0 | 5250 | 0.0327 | 0.8225 | 0.5465 | 0.6217 | |
|
| 0.0574 | 7.0 | 6125 | 0.0283 | 0.8364 | 0.5546 | 0.6314 | |
|
| 0.0525 | 8.0 | 7000 | 0.0261 | 0.8444 | 0.5593 | 0.6371 | |
|
| 0.0498 | 9.0 | 7875 | 0.0245 | 0.8515 | 0.5643 | 0.6429 | |
|
| 0.0491 | 10.0 | 8750 | 0.0241 | 0.8525 | 0.5646 | 0.6434 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.26.1 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.13.3 |
|
|