t5-small-finetuned-xsum
This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0182
- Rouge1: 98.6201
- Rouge2: 98.1721
- Rougel: 98.6179
- Rougelsum: 98.6205
- Gen Len: 13.536
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: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 0.0803 | 0.9785 | 500 | 0.0575 | 97.1176 | 96.3156 | 97.1047 | 97.1116 | 13.5751 |
| 0.0355 | 1.9569 | 1000 | 0.0227 | 98.4769 | 98.0176 | 98.4844 | 98.4907 | 13.5277 |
| 0.03 | 2.9354 | 1500 | 0.0182 | 98.6201 | 98.1721 | 98.6179 | 98.6205 | 13.536 |
Framework versions
- Transformers 4.54.1
- Pytorch 2.6.0+cu124
- Datasets 4.0.0
- Tokenizers 0.21.4