<!-- 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-nlg-multiwoz2.0_800
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9178
- Rouge1: 36.3013
- Rouge2: 19.7789
- Rougel: 33.0604
- Rougelsum: 34.5306
- Gen Len: 17.5889
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: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
---|---|---|---|---|---|---|---|---|
1.4671 | 0.3 | 200 | 1.1001 | 32.2008 | 15.6109 | 29.2636 | 30.6894 | 17.5463 |
1.1704 | 0.6 | 400 | 1.0132 | 35.1237 | 19.2608 | 32.2073 | 33.6041 | 17.4995 |
1.1034 | 0.89 | 600 | 0.9733 | 34.8097 | 17.7552 | 31.3877 | 32.8936 | 18.0388 |
1.0207 | 1.19 | 800 | 0.9544 | 34.4615 | 17.7876 | 31.2393 | 32.6945 | 17.8274 |
0.9856 | 1.49 | 1000 | 0.9372 | 35.4821 | 19.5844 | 32.4901 | 33.8523 | 17.4778 |
0.9826 | 1.79 | 1200 | 0.9236 | 35.2746 | 18.6897 | 32.0828 | 33.6526 | 17.5149 |
0.9473 | 2.09 | 1400 | 0.9178 | 36.3013 | 19.7789 | 33.0604 | 34.5306 | 17.5889 |
0.9183 | 2.38 | 1600 | 0.9097 | 35.9042 | 19.0983 | 32.4102 | 34.0221 | 17.4669 |
0.9314 | 2.68 | 1800 | 0.9011 | 35.7411 | 19.3554 | 32.4951 | 33.9165 | 17.2751 |
0.9137 | 2.98 | 2000 | 0.8966 | 35.5147 | 18.593 | 32.1424 | 33.7225 | 17.6211 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.10.0+cu111
- Datasets 2.5.1
- Tokenizers 0.12.1