flan-t5-large-da-multiwoz2.1_400-new

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.4001
• Accuracy: 41.6587
• Num: 3689
• Gen Len: 15.8552

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: 32
• seed: 1799
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Num	Gen Len
0.2898	1.16	200	0.3753	41.3216	3689	15.5324
0.2614	2.33	400	0.3880	41.2815	3689	15.9111
0.2401	3.49	600	0.3934	41.9986	3689	15.7373
0.2279	4.65	800	0.4010	41.6882	3689	15.8452

Framework versions

• Transformers 4.18.0
• Pytorch 1.10.0+cu111
• Datasets 2.5.1
• Tokenizers 0.12.1