oop-de-qag-flan-t5-base-v2
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: 0.7799
- Rouge1: 65.8963
- Rouge2: 52.5334
- Rougel: 63.8234
- Rougelsum: 63.862
- Gen Len: 15.1027
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
---|---|---|---|---|---|---|---|---|
No log | 1.0 | 291 | 0.9267 | 58.354 | 44.5703 | 56.3088 | 56.4247 | 14.9335 |
1.0671 | 2.0 | 582 | 0.8478 | 58.9803 | 46.058 | 57.5088 | 57.7033 | 14.2145 |
1.0671 | 3.0 | 873 | 0.8198 | 63.8733 | 51.2538 | 62.2852 | 62.3529 | 14.6979 |
0.7879 | 4.0 | 1164 | 0.7871 | 65.4153 | 51.7642 | 63.1634 | 63.2417 | 15.1450 |
0.7879 | 5.0 | 1455 | 0.7899 | 65.9948 | 52.9992 | 63.9656 | 64.0437 | 15.3988 |
0.6773 | 6.0 | 1746 | 0.7799 | 65.8963 | 52.5334 | 63.8234 | 63.862 | 15.1027 |
0.6008 | 7.0 | 2037 | 0.7881 | 65.8796 | 52.85 | 64.0634 | 64.1241 | 15.5347 |
0.6008 | 8.0 | 2328 | 0.7805 | 66.5459 | 53.6971 | 64.4793 | 64.5541 | 15.4199 |
0.5493 | 9.0 | 2619 | 0.7823 | 66.217 | 53.3816 | 64.4162 | 64.4861 | 15.5347 |
0.5493 | 10.0 | 2910 | 0.7848 | 65.8257 | 52.9735 | 63.8224 | 63.8886 | 15.4622 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1
- Downloads last month
- 2