<!-- 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-loss-ep50
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: 0.3664
- Accuracy: 41.1172
- Num: 7365
- Gen Len: 15.7299
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: 24
- eval_batch_size: 192
- seed: 1799
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | Num | Gen Len |
---|---|---|---|---|---|---|
1.1147 | 1.74 | 200 | 0.4745 | 31.5892 | 7365 | 15.6221 |
0.5089 | 3.48 | 400 | 0.4116 | 33.9236 | 7365 | 15.4714 |
0.4429 | 5.22 | 600 | 0.3875 | 36.3199 | 7365 | 16.0663 |
0.4049 | 6.96 | 800 | 0.3784 | 37.5867 | 7365 | 15.0832 |
0.3777 | 8.7 | 1000 | 0.3717 | 37.7875 | 7365 | 15.0001 |
0.3562 | 10.43 | 1200 | 0.3692 | 39.6733 | 7365 | 15.9566 |
0.343 | 12.17 | 1400 | 0.3665 | 39.9906 | 7365 | 15.65 |
0.3263 | 13.91 | 1600 | 0.3731 | 39.9249 | 7365 | 15.7365 |
0.3103 | 15.65 | 1800 | 0.3664 | 41.1172 | 7365 | 15.7299 |
0.3036 | 17.39 | 2000 | 0.3715 | 40.9342 | 7365 | 15.4845 |
0.2876 | 19.13 | 2200 | 0.3763 | 40.8108 | 7365 | 15.6081 |
0.2816 | 20.87 | 2400 | 0.3802 | 41.5156 | 7365 | 15.9868 |
0.2685 | 22.61 | 2600 | 0.3936 | 41.4108 | 7365 | 15.8193 |
0.2603 | 24.35 | 2800 | 0.3925 | 41.5357 | 7365 | 15.7604 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.10.0+cu111
- Datasets 2.5.1
- Tokenizers 0.12.1