<!-- 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_800-new
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4114
- Accuracy: 43.9201
- Num: 3690
- Gen Len: 15.5379
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Num | Gen Len |
|---|---|---|---|---|---|---|
| 0.2469 | 0.6 | 400 | 0.3603 | 44.476 | 3690 | 15.4371 |
| 0.2329 | 1.19 | 800 | 0.3762 | 44.0606 | 3690 | 16.136 |
| 0.2181 | 1.79 | 1200 | 0.3740 | 43.4354 | 3690 | 15.3539 |
| 0.203 | 2.38 | 1600 | 0.3791 | 43.2672 | 3690 | 15.0631 |
| 0.198 | 2.98 | 2000 | 0.3820 | 44.501 | 3690 | 15.4458 |
| 0.1824 | 3.58 | 2400 | 0.3979 | 43.5607 | 3690 | 15.6407 |
| 0.1759 | 4.17 | 2800 | 0.4041 | 43.9889 | 3690 | 15.6244 |
| 0.171 | 4.77 | 3200 | 0.4113 | 43.979 | 3690 | 15.5192 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.10.0+cu111
- Datasets 2.5.1
- Tokenizers 0.12.1
