EN_t5-base_15_spider_baseline
This model is a fine-tuned version of t5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2982
- Rouge2 Precision: 0.6176
- Rouge2 Recall: 0.3986
- Rouge2 Fmeasure: 0.4563
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: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge2 Precision | Rouge2 Recall | Rouge2 Fmeasure |
|---|---|---|---|---|---|---|
| 0.5776 | 1.0 | 578 | 0.2555 | 0.4867 | 0.3288 | 0.3659 |
| 0.1904 | 2.0 | 1156 | 0.2377 | 0.5496 | 0.3556 | 0.4059 |
| 0.1416 | 3.0 | 1734 | 0.2409 | 0.5633 | 0.3697 | 0.4187 |
| 0.114 | 4.0 | 2312 | 0.2486 | 0.585 | 0.381 | 0.4333 |
| 0.0958 | 5.0 | 2890 | 0.2525 | 0.5861 | 0.3781 | 0.4312 |
| 0.0849 | 6.0 | 3468 | 0.2625 | 0.6083 | 0.3973 | 0.4526 |
| 0.0676 | 7.0 | 4046 | 0.2606 | 0.5991 | 0.3878 | 0.4426 |
| 0.061 | 8.0 | 4624 | 0.2711 | 0.6127 | 0.3948 | 0.4518 |
| 0.0559 | 9.0 | 5202 | 0.2771 | 0.6082 | 0.3903 | 0.4468 |
| 0.0527 | 10.0 | 5780 | 0.2845 | 0.6181 | 0.399 | 0.4559 |
| 0.0489 | 11.0 | 6358 | 0.2909 | 0.6235 | 0.4037 | 0.4615 |
| 0.0459 | 12.0 | 6936 | 0.2941 | 0.6163 | 0.3991 | 0.4564 |
| 0.0423 | 13.0 | 7514 | 0.2944 | 0.6086 | 0.3947 | 0.4507 |
| 0.0414 | 14.0 | 8092 | 0.2966 | 0.6158 | 0.3978 | 0.4551 |
| 0.0393 | 15.0 | 8670 | 0.2982 | 0.6176 | 0.3986 | 0.4563 |
Framework versions
- Transformers 4.26.1
- Pytorch 2.0.1+cu117
- Datasets 2.14.7.dev0
- Tokenizers 0.13.3