metadata
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: ALL_mt5-base_10_wikiSQL
results: []
ALL_mt5-base_10_wikiSQL
This model is a fine-tuned version of google/mt5-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2056
- Rouge2 Precision: 0.7601
- Rouge2 Recall: 0.6878
- Rouge2 Fmeasure: 0.7165
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: 35
- 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 |
|---|---|---|---|---|---|---|
| 0.3197 | 1.0 | 3702 | 0.2658 | 0.7084 | 0.6348 | 0.6636 |
| 0.2666 | 2.0 | 7404 | 0.2348 | 0.7294 | 0.6574 | 0.686 |
| 0.2356 | 3.0 | 11106 | 0.2229 | 0.7409 | 0.6678 | 0.6968 |
| 0.2169 | 4.0 | 14808 | 0.2162 | 0.7471 | 0.6747 | 0.7035 |
| 0.2021 | 5.0 | 18510 | 0.2121 | 0.7513 | 0.6796 | 0.708 |
| 0.1959 | 6.0 | 22212 | 0.2089 | 0.7545 | 0.6824 | 0.711 |
| 0.1878 | 7.0 | 25914 | 0.2069 | 0.757 | 0.6848 | 0.7134 |
| 0.1801 | 8.0 | 29616 | 0.2060 | 0.7586 | 0.6862 | 0.715 |
| 0.1763 | 9.0 | 33318 | 0.2055 | 0.7594 | 0.6877 | 0.7161 |
| 0.1752 | 10.0 | 37020 | 0.2056 | 0.7601 | 0.6878 | 0.7165 |
Framework versions
- Transformers 4.26.1
- Pytorch 2.1.2
- Datasets 2.16.1
- Tokenizers 0.13.3