t5_small_A-finetuned-xsum
This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.3096
- Rouge1: 0.1758
- Rouge2: 0.0431
- Rougel: 0.1616
- Rougelsum: 0.1616
- Gen Len: 8.2832
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: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 12
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 2.8609 | 1.0 | 527 | 1.6450 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 1.6144 | 2.0 | 1054 | 1.4493 | 0.0233 | 0.0006 | 0.0213 | 0.0214 | 1.7788 |
| 1.5156 | 3.0 | 1581 | 1.3990 | 0.1232 | 0.025 | 0.1137 | 0.1133 | 8.2124 |
| 1.3827 | 4.0 | 2108 | 1.3733 | 0.1276 | 0.0225 | 0.1211 | 0.121 | 8.8938 |
| 1.3815 | 5.0 | 2635 | 1.3547 | 0.1383 | 0.0366 | 0.1289 | 0.1298 | 8.3982 |
| 1.3366 | 6.0 | 3162 | 1.3406 | 0.1498 | 0.0347 | 0.1399 | 0.1407 | 8.6903 |
| 1.2798 | 7.0 | 3689 | 1.3313 | 0.1678 | 0.0373 | 0.1581 | 0.1564 | 8.6195 |
| 1.2619 | 8.0 | 4216 | 1.3205 | 0.1678 | 0.0398 | 0.1592 | 0.1581 | 9.2212 |
| 1.3182 | 9.0 | 4743 | 1.3170 | 0.1689 | 0.0369 | 0.1573 | 0.157 | 8.1593 |
| 1.2617 | 10.0 | 5270 | 1.3128 | 0.169 | 0.038 | 0.1555 | 0.1554 | 8.2832 |
| 1.2902 | 11.0 | 5797 | 1.3105 | 0.1647 | 0.0333 | 0.1518 | 0.1515 | 8.3363 |
| 1.1897 | 12.0 | 6324 | 1.3096 | 0.1758 | 0.0431 | 0.1616 | 0.1616 | 8.2832 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2