<!-- 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_summarization_pretrained
This model is a fine-tuned version of t5-small on the billsum dataset. It achieves the following results on the evaluation set:
- Loss: 2.1515
- Rouge1: 0.1939
- Rouge2: 0.101
- Rougel: 0.1678
- Rougelsum: 0.1678
- 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: 10
- eval_batch_size: 10
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
---|---|---|---|---|---|---|---|---|
No log | 1.0 | 99 | 2.1685 | 0.1945 | 0.1012 | 0.1677 | 0.1678 | 19.0 |
No log | 2.0 | 198 | 2.1605 | 0.1954 | 0.102 | 0.1688 | 0.1688 | 19.0 |
No log | 3.0 | 297 | 2.1537 | 0.1945 | 0.102 | 0.168 | 0.168 | 19.0 |
No log | 4.0 | 396 | 2.1515 | 0.1939 | 0.101 | 0.1678 | 0.1678 | 19.0 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3