t5-base-da-multiwoz2.1_500

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

• Loss: 0.4253
• Accuracy: 22.6359
• Num: 3689
• Gen Len: 15.4806

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: 48
• 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
0.5137	2.78	400	0.4454	21.1276	3689	15.569
0.4673	5.56	800	0.4329	21.7406	3689	15.4573
0.4591	8.33	1200	0.4253	22.6359	3689	15.4806

Framework versions

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