t5-small-finetuned-xsum-ss
This model is a fine-tuned version of t5-small on the xsum dataset. It achieves the following results on the evaluation set:
- Loss: 2.5823
- Rouge1: 26.3663
- Rouge2: 6.4727
- Rougel: 20.538
- Rougelsum: 20.5411
- Gen Len: 18.8006
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 0.25
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 2.8125 | 0.25 | 3189 | 2.5823 | 26.3663 | 6.4727 | 20.538 | 20.5411 | 18.8006 |
Framework versions
- Transformers 4.22.1
- Pytorch 1.12.1+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1