<!-- 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-t5-epoch5
This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.5359
- Rouge1: 29.8849
- Rouge2: 17.4399
- Rougel: 26.3643
- Rougelsum: 28.3764
- Gen Len: 18.9869
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: 5
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
---|---|---|---|---|---|---|---|---|
1.9706 | 1.0 | 765 | 1.6150 | 28.6734 | 16.3753 | 25.3 | 27.2566 | 18.983 |
1.759 | 2.0 | 1530 | 1.5689 | 29.4543 | 16.9803 | 25.9821 | 27.9832 | 18.9895 |
1.731 | 3.0 | 2295 | 1.5487 | 29.694 | 17.2806 | 26.2035 | 28.2027 | 18.9836 |
1.7108 | 4.0 | 3060 | 1.5389 | 29.9064 | 17.4929 | 26.4006 | 28.3983 | 18.9876 |
1.7045 | 5.0 | 3825 | 1.5359 | 29.8849 | 17.4399 | 26.3643 | 28.3764 | 18.9869 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Tokenizers 0.13.2