<!-- 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-base-da-multiwoz2.1_400-loss-ep100
This model is a fine-tuned version of google/flan-t5-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3730
- Accuracy: 39.1491
- Num: 7365
- Gen Len: 16.1947
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: 16
- eval_batch_size: 80
- seed: 1799
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 100
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Num | Gen Len |
|---|---|---|---|---|---|---|
| 1.1193 | 2.33 | 400 | 0.5163 | 27.0396 | 7365 | 15.2292 |
| 0.5546 | 4.65 | 800 | 0.4312 | 33.6748 | 7365 | 16.0134 |
| 0.4799 | 6.98 | 1200 | 0.4032 | 34.9177 | 7365 | 15.8893 |
| 0.4377 | 9.3 | 1600 | 0.3886 | 36.8242 | 7365 | 15.6668 |
| 0.4107 | 11.63 | 2000 | 0.3822 | 36.8257 | 7365 | 16.5566 |
| 0.3868 | 13.95 | 2400 | 0.3771 | 38.1012 | 7365 | 16.2304 |
| 0.3695 | 16.28 | 2800 | 0.3738 | 38.9161 | 7365 | 15.9143 |
| 0.3524 | 18.6 | 3200 | 0.3730 | 39.1491 | 7365 | 16.1947 |
| 0.3417 | 20.93 | 3600 | 0.3767 | 40.0655 | 7365 | 15.9227 |
| 0.328 | 23.26 | 4000 | 0.3772 | 39.8485 | 7365 | 15.6276 |
| 0.3181 | 25.58 | 4400 | 0.3795 | 40.2318 | 7365 | 15.9794 |
| 0.3063 | 27.91 | 4800 | 0.3798 | 40.0663 | 7365 | 15.8098 |
| 0.2959 | 30.23 | 5200 | 0.3874 | 40.1586 | 7365 | 16.0183 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.10.0+cu111
- Datasets 2.5.1
- Tokenizers 0.12.1
