<!-- 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. -->
TextSummarization
This model is a fine-tuned version of t5-small on the billsum dataset. It achieves the following results on the evaluation set:
- Loss: 2.3754
- Rouge1: 0.203
- Rouge2: 0.1015
- Rougel: 0.1714
- Rougelsum: 0.1715
- Gen Len: 19.0
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: 4
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
---|---|---|---|---|---|---|---|---|
No log | 1.0 | 248 | 2.5358 | 0.1376 | 0.0472 | 0.1131 | 0.113 | 19.0 |
No log | 2.0 | 496 | 2.4252 | 0.1994 | 0.0979 | 0.1688 | 0.1689 | 19.0 |
2.8754 | 3.0 | 744 | 2.3856 | 0.2027 | 0.1004 | 0.1709 | 0.171 | 19.0 |
2.8754 | 4.0 | 992 | 2.3754 | 0.203 | 0.1015 | 0.1714 | 0.1715 | 19.0 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3