t5-small-finetuned-test1
This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.2837
- Rouge1: 22.7012
- Rouge2: 0.0
- Rougel: 22.7156
- Rougelsum: 22.7348
- Gen Len: 2.2686
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: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 2.5353 | 1.0 | 2601 | 2.3131 | 22.0732 | 0.0 | 22.1069 | 22.1229 | 2.2647 |
| 2.4728 | 2.0 | 5202 | 2.2838 | 22.7012 | 0.0 | 22.7156 | 22.7348 | 2.2686 |
| 2.4819 | 3.0 | 7803 | 2.2837 | 22.7012 | 0.0 | 22.7156 | 22.7348 | 2.2686 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3