<!-- 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_readme_summarizer
This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.0817
- Rouge1: 0.458
- Rouge2: 0.3275
- Rougel: 0.4305
- Rougelsum: 0.4302
- Gen Len: 15.1049
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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
---|---|---|---|---|---|---|---|---|
2.7923 | 1.0 | 785 | 2.2466 | 0.4258 | 0.2925 | 0.3972 | 0.3973 | 15.4728 |
2.4405 | 2.0 | 1570 | 2.1587 | 0.4378 | 0.306 | 0.4102 | 0.4106 | 15.1037 |
2.3561 | 3.0 | 2355 | 2.1122 | 0.4508 | 0.3205 | 0.4227 | 0.4227 | 15.0177 |
2.3496 | 4.0 | 3140 | 2.0867 | 0.4546 | 0.3233 | 0.4272 | 0.4268 | 15.1631 |
2.2977 | 5.0 | 3925 | 2.0817 | 0.458 | 0.3275 | 0.4305 | 0.4302 | 15.1049 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1