<!-- 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-multiwoz2.0_80
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5551
- Accuracy: 35.4652
- Num: 3690
- Gen Len: 15.7705
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: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Num | Gen Len |
|---|---|---|---|---|---|---|
| 0.12 | 2.74 | 200 | 0.7870 | 33.7402 | 3690 | 15.8558 |
| 0.0847 | 5.48 | 400 | 0.9485 | 33.645 | 3690 | 15.6314 |
| 0.1028 | 8.22 | 600 | 0.7984 | 33.9271 | 3690 | 15.8528 |
| 0.1534 | 10.96 | 800 | 0.7475 | 33.5491 | 3690 | 16.007 |
| 0.166 | 13.7 | 1000 | 0.6798 | 34.529 | 3690 | 15.7453 |
| 0.277 | 16.44 | 1200 | 0.5577 | 35.1295 | 3690 | 15.5201 |
| 0.2561 | 19.18 | 1400 | 0.5551 | 35.4652 | 3690 | 15.7705 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.10.0+cu111
- Datasets 2.5.1
- Tokenizers 0.12.1
