<!-- 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_400-ep10-nonstop
This model is a fine-tuned version of google/flan-t5-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3722
- Accuracy: 38.5664
- Num: 7365
- Gen Len: 15.7136
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: 64
- seed: 1799
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | Num | Gen Len |
---|---|---|---|---|---|---|
0.8697 | 2.33 | 400 | 0.4378 | 32.8532 | 7365 | 15.4076 |
0.4586 | 4.65 | 800 | 0.3902 | 36.8539 | 7365 | 16.0242 |
0.4114 | 6.98 | 1200 | 0.3771 | 37.3063 | 7365 | 15.6236 |
0.3876 | 9.3 | 1600 | 0.3725 | 38.4075 | 7365 | 15.7772 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.10.0+cu111
- Datasets 2.5.1
- Tokenizers 0.12.1