<!-- 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-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: 0.3645
- Accuracy: 41.095
- Num: 7358
- Gen Len: 15.742
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 |
---|---|---|---|---|---|---|
1.1167 | 1.74 | 200 | 0.4747 | 31.234 | 7358 | 15.2488 |
0.5091 | 3.48 | 400 | 0.4131 | 34.1646 | 7358 | 15.8133 |
0.4437 | 5.22 | 600 | 0.3853 | 36.2445 | 7358 | 16.1331 |
0.404 | 6.96 | 800 | 0.3737 | 37.5071 | 7358 | 14.6509 |
0.3757 | 8.7 | 1000 | 0.3716 | 38.9774 | 7358 | 15.2675 |
0.3572 | 10.43 | 1200 | 0.3656 | 40.1172 | 7358 | 15.8316 |
0.3442 | 12.17 | 1400 | 0.3672 | 39.8165 | 7358 | 15.8572 |
0.3278 | 13.91 | 1600 | 0.3667 | 40.5284 | 7358 | 15.4951 |
0.3111 | 15.65 | 1800 | 0.3645 | 41.095 | 7358 | 15.742 |
0.3026 | 17.39 | 2000 | 0.3719 | 40.8885 | 7358 | 15.6101 |
0.2876 | 19.13 | 2200 | 0.3813 | 40.3016 | 7358 | 15.3199 |
0.2809 | 20.87 | 2400 | 0.3765 | 41.9514 | 7358 | 15.7381 |
0.2685 | 22.61 | 2600 | 0.3841 | 41.8625 | 7358 | 15.5582 |
0.2609 | 24.35 | 2800 | 0.3922 | 42.1265 | 7358 | 15.8797 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.10.0+cu111
- Datasets 2.5.1
- Tokenizers 0.12.1