flan-t5-base-insight0
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: 0.6420
- Rouge1: 44.3716
- Rouge2: 35.6515
- Rougel: 42.8415
- Rougelsum: 43.4265
- 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 |
|---|---|---|---|---|---|---|---|---|
| 1.1013 | 1.0 | 172 | 0.8463 | 43.9339 | 34.6721 | 42.7818 | 42.1925 | 19.0 |
| 0.8014 | 2.0 | 344 | 0.6918 | 43.9339 | 34.6721 | 42.7818 | 42.1925 | 19.0 |
| 0.6506 | 3.0 | 516 | 0.6697 | 43.6406 | 34.0764 | 41.9795 | 42.7117 | 19.0 |
| 0.5984 | 4.0 | 688 | 0.6433 | 45.2785 | 37.429 | 43.8208 | 44.3406 | 19.0 |
| 0.4941 | 5.0 | 860 | 0.6420 | 44.3716 | 35.6515 | 42.8415 | 43.4265 | 19.0 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.0
- Tokenizers 0.15.0