flan-t5-base-insight1
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: 1.0973
- Rouge1: 19.9416
- Rouge2: 11.0595
- Rougel: 18.2669
- Rougelsum: 18.9114
- 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 |
|---|---|---|---|---|---|---|---|---|
| 1.8224 | 1.0 | 172 | 1.4368 | 18.9061 | 9.9663 | 17.2809 | 17.9391 | 19.0 |
| 1.552 | 2.0 | 344 | 1.2372 | 17.5873 | 9.5234 | 16.5266 | 16.807 | 19.0 |
| 1.3182 | 3.0 | 516 | 1.1590 | 19.8845 | 10.9343 | 18.0006 | 18.9139 | 19.0 |
| 1.2528 | 4.0 | 688 | 1.1116 | 19.6058 | 10.6169 | 17.8829 | 18.5154 | 19.0 |
| 1.2706 | 5.0 | 860 | 1.0973 | 19.9416 | 11.0595 | 18.2669 | 18.9114 | 19.0 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.0
- Tokenizers 0.15.0