metadata
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: ALL_mt5-base_10_wikiSQL_sch
results: []
ALL_mt5-base_10_wikiSQL_sch
This model is a fine-tuned version of google/mt5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0566
- Rouge2 Precision: 0.8825
- Rouge2 Recall: 0.802
- Rouge2 Fmeasure: 0.8343
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: 15
- 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 |
|---|---|---|---|---|---|---|
| 0.0789 | 1.0 | 8637 | 0.0678 | 0.859 | 0.7788 | 0.8103 |
| 0.0683 | 2.0 | 17274 | 0.0613 | 0.8688 | 0.7867 | 0.8196 |
| 0.0587 | 3.0 | 25911 | 0.0595 | 0.8726 | 0.7917 | 0.8241 |
| 0.0546 | 4.0 | 34548 | 0.0578 | 0.8771 | 0.7957 | 0.8284 |
| 0.0499 | 5.0 | 43185 | 0.0572 | 0.8793 | 0.7981 | 0.8308 |
| 0.0484 | 6.0 | 51822 | 0.0568 | 0.8797 | 0.7992 | 0.8315 |
| 0.0447 | 7.0 | 60459 | 0.0565 | 0.8809 | 0.8003 | 0.8326 |
| 0.0415 | 8.0 | 69096 | 0.0565 | 0.882 | 0.8013 | 0.8337 |
| 0.042 | 9.0 | 77733 | 0.0564 | 0.8822 | 0.8019 | 0.8341 |
| 0.0407 | 10.0 | 86370 | 0.0566 | 0.8825 | 0.802 | 0.8343 |
Framework versions
- Transformers 4.26.1
- Pytorch 2.1.2
- Datasets 2.16.1
- Tokenizers 0.13.3