flan-t5-base-insight2
This model is a fine-tuned version of google/flan-t5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9687
- Rouge1: 24.6641
- Rouge2: 19.0841
- Rougel: 23.6027
- Rougelsum: 24.2082
- 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: 5e-05
- train_batch_size: 1
- eval_batch_size: 1
- 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 |
|---|---|---|---|---|---|---|---|---|
| 1.5604 | 1.0 | 172 | 1.1982 | 23.0727 | 15.1292 | 21.7613 | 22.3596 | 19.0 |
| 1.2717 | 2.0 | 344 | 1.0511 | 24.16 | 18.1468 | 22.8935 | 23.6175 | 19.0 |
| 1.1373 | 3.0 | 516 | 1.0002 | 24.5212 | 18.789 | 23.4331 | 24.0315 | 19.0 |
| 1.0895 | 4.0 | 688 | 0.9699 | 24.7531 | 19.3582 | 23.694 | 24.3304 | 19.0 |
| 1.0176 | 5.0 | 860 | 0.9687 | 24.6641 | 19.0841 | 23.6027 | 24.2082 | 19.0 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.0
- Tokenizers 0.15.0