test-dialogue-summarization
This model is a fine-tuned version of google/flan-t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.3848
- Rouge: {'rouge1': 45.6704, 'rouge2': 21.245, 'rougeL': 20.2411, 'rougeLsum': 20.2411}
- Bert Score: 0.8718
- Bleurt 20: -0.8946
- Gen Len: 14.99
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: 7
- eval_batch_size: 7
- 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 | Rouge | Bert Score | Bleurt 20 | Gen Len |
|---|---|---|---|---|---|---|---|
| 2.2971 | 1.0 | 186 | 2.4618 | {'rouge1': 46.8614, 'rouge2': 21.2026, 'rougeL': 20.3766, 'rougeLsum': 20.3766} | 0.8719 | -0.8804 | 15.38 |
| 2.5384 | 2.0 | 372 | 2.4062 | {'rouge1': 46.4924, 'rouge2': 21.6223, 'rougeL': 20.304, 'rougeLsum': 20.304} | 0.8724 | -0.8819 | 15.145 |
| 2.5224 | 3.0 | 558 | 2.3936 | {'rouge1': 46.0775, 'rouge2': 21.2642, 'rougeL': 20.3148, 'rougeLsum': 20.3148} | 0.871 | -0.8905 | 15.345 |
| 2.4661 | 4.0 | 744 | 2.3867 | {'rouge1': 45.6718, 'rouge2': 21.122, 'rougeL': 20.2877, 'rougeLsum': 20.2877} | 0.8719 | -0.8887 | 14.975 |
| 2.4426 | 5.0 | 930 | 2.3848 | {'rouge1': 45.6704, 'rouge2': 21.245, 'rougeL': 20.2411, 'rougeLsum': 20.2411} | 0.8718 | -0.8946 | 14.99 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0
- Downloads last month
- 6