t5-small-finetuned-jb-t5
This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0000
- Rouge1: 99.3236
- Rouge2: 99.2849
- Rougel: 99.323
- Rougelsum: 99.3279
- Gen Len: 16.7815
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: 2e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 235 | 0.0013 | 99.3122 | 99.2729 | 99.3126 | 99.3178 | 16.7831 |
| No log | 2.0 | 470 | 0.0001 | 99.3236 | 99.2849 | 99.323 | 99.3279 | 16.7815 |
| 0.0599 | 3.0 | 705 | 0.0000 | 99.3236 | 99.2849 | 99.323 | 99.3279 | 16.7815 |
| 0.0599 | 4.0 | 940 | 0.0000 | 99.3236 | 99.2849 | 99.323 | 99.3279 | 16.7815 |
| 0.0017 | 5.0 | 1175 | 0.0000 | 99.3236 | 99.2849 | 99.323 | 99.3279 | 16.7815 |
| 0.0017 | 6.0 | 1410 | 0.0000 | 99.3236 | 99.2849 | 99.323 | 99.3279 | 16.7815 |
| 0.0009 | 7.0 | 1645 | 0.0000 | 99.3236 | 99.2849 | 99.323 | 99.3279 | 16.7815 |
| 0.0009 | 8.0 | 1880 | 0.0000 | 99.3236 | 99.2849 | 99.323 | 99.3279 | 16.7815 |
| 0.0007 | 9.0 | 2115 | 0.0000 | 99.3236 | 99.2849 | 99.323 | 99.3279 | 16.7815 |
| 0.0007 | 10.0 | 2350 | 0.0000 | 99.3236 | 99.2849 | 99.323 | 99.3279 | 16.7815 |
| 0.0007 | 11.0 | 2585 | 0.0000 | 99.3236 | 99.2849 | 99.323 | 99.3279 | 16.7815 |
| 0.0007 | 12.0 | 2820 | 0.0000 | 99.3236 | 99.2849 | 99.323 | 99.3279 | 16.7815 |
| 0.0006 | 13.0 | 3055 | 0.0000 | 99.3236 | 99.2849 | 99.323 | 99.3279 | 16.7815 |
| 0.0006 | 14.0 | 3290 | 0.0000 | 99.3236 | 99.2849 | 99.323 | 99.3279 | 16.7815 |
| 0.0006 | 15.0 | 3525 | 0.0000 | 99.3236 | 99.2849 | 99.323 | 99.3279 | 16.7815 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.4.0
- Datasets 2.21.0
- Tokenizers 0.19.1