<!-- 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. -->
flan-t5-large-da-multiwoz2.1_80
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8698
- Accuracy: 35.5192
- Num: 3689
- Gen Len: 16.1808
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: 8
- eval_batch_size: 24
- seed: 1799
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 40
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | Num | Gen Len |
---|---|---|---|---|---|---|
0.138 | 2.74 | 200 | 0.7403 | 34.8322 | 3689 | 15.4901 |
0.1062 | 5.48 | 400 | 0.7917 | 35.1824 | 3689 | 15.9629 |
0.0895 | 8.22 | 600 | 0.8698 | 35.5192 | 3689 | 16.1808 |
0.0838 | 10.96 | 800 | 0.8792 | 35.0962 | 3689 | 15.8043 |
0.0777 | 13.7 | 1000 | 0.9348 | 34.1583 | 3689 | 16.0843 |
0.0814 | 16.44 | 1200 | 0.9443 | 34.9078 | 3689 | 15.8517 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.10.0+cu111
- Datasets 2.5.1
- Tokenizers 0.12.1