<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
t5-small-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: 2.4497
- Rouge1: 30.2417
- Rouge2: 14.6695
- Rougel: 25.2607
- Rougelsum: 25.5153
- Gen Len: 18.8114
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
Training results
Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
---|---|---|---|---|---|---|---|---|
No log | 1.0 | 334 | 2.6727 | 20.047 | 6.1964 | 16.1833 | 16.3393 | 18.9371 |
2.9526 | 2.0 | 668 | 2.5331 | 28.9685 | 13.0253 | 23.6028 | 23.7746 | 18.6527 |
2.6472 | 3.0 | 1002 | 2.4959 | 29.5736 | 13.7279 | 24.3909 | 24.5736 | 18.7575 |
2.6472 | 4.0 | 1336 | 2.4779 | 29.584 | 14.0206 | 24.6232 | 24.877 | 18.7754 |
2.5757 | 5.0 | 1670 | 2.4636 | 30.2583 | 14.6799 | 25.1558 | 25.3834 | 18.8263 |
2.5313 | 6.0 | 2004 | 2.4557 | 30.0589 | 14.437 | 24.972 | 25.2422 | 18.8054 |
2.5313 | 7.0 | 2338 | 2.4518 | 30.1977 | 14.5416 | 25.1319 | 25.3914 | 18.8084 |
2.513 | 8.0 | 2672 | 2.4497 | 30.2417 | 14.6695 | 25.2607 | 25.5153 | 18.8114 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3