<!-- 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_400
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3937
- Accuracy: 42.1678
- Num: 3690
- Gen Len: 15.068
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 |
---|---|---|---|---|---|---|
0.3906 | 0.58 | 200 | 0.3696 | 39.2853 | 3690 | 15.6537 |
0.3121 | 1.17 | 400 | 0.3800 | 40.0713 | 3690 | 14.6409 |
0.2917 | 1.75 | 600 | 0.3767 | 40.8777 | 3690 | 16.0501 |
0.2787 | 2.33 | 800 | 0.3813 | 40.4469 | 3690 | 15.5022 |
0.2684 | 2.92 | 1000 | 0.3826 | 40.6007 | 3690 | 15.9691 |
0.2513 | 3.5 | 1200 | 0.3930 | 41.4134 | 3690 | 16.142 |
0.2575 | 4.08 | 1400 | 0.3993 | 41.1223 | 3690 | 15.6314 |
0.2491 | 4.66 | 1600 | 0.3930 | 41.6826 | 3690 | 15.265 |
0.2481 | 5.25 | 1800 | 0.3930 | 40.933 | 3690 | 15.9691 |
0.2474 | 5.83 | 2000 | 0.3937 | 42.1678 | 3690 | 15.068 |
0.2538 | 6.41 | 2200 | 0.3994 | 41.0725 | 3690 | 14.8117 |
0.2505 | 7.0 | 2400 | 0.3951 | 41.0125 | 3690 | 15.448 |
0.2436 | 7.58 | 2600 | 0.3961 | 41.6418 | 3690 | 15.2146 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.10.0+cu111
- Datasets 2.5.1
- Tokenizers 0.12.1