<!-- 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. -->
first_s2s_model
This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.1438
- Rouge1: 0.2338
- Rouge2: 0.0532
- Rougel: 0.1863
- Rougelsum: 0.1866
- Gen Len: 18.8841
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: 5
- eval_batch_size: 5
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
Training results
Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
---|---|---|---|---|---|---|---|---|
No log | 1.0 | 110 | 3.3690 | 0.1927 | 0.0435 | 0.1555 | 0.1554 | 19.0 |
No log | 2.0 | 220 | 3.2565 | 0.1986 | 0.0441 | 0.1571 | 0.1568 | 19.0 |
No log | 3.0 | 330 | 3.2053 | 0.2262 | 0.0522 | 0.1789 | 0.1786 | 18.8913 |
No log | 4.0 | 440 | 3.1787 | 0.2346 | 0.0566 | 0.1862 | 0.1869 | 18.8841 |
3.5678 | 5.0 | 550 | 3.1615 | 0.2349 | 0.0553 | 0.1879 | 0.1885 | 18.9493 |
3.5678 | 6.0 | 660 | 3.1521 | 0.2348 | 0.0538 | 0.1886 | 0.1892 | 18.9058 |
3.5678 | 7.0 | 770 | 3.1458 | 0.2346 | 0.0527 | 0.1866 | 0.1873 | 18.9058 |
3.5678 | 8.0 | 880 | 3.1438 | 0.2338 | 0.0532 | 0.1863 | 0.1866 | 18.8841 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.9.0+cu102
- Datasets 2.9.0
- Tokenizers 0.13.2