flan-t5-large-da-multiwoz2.0_800

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

• Loss: 0.3570
• Accuracy: 41.6199
• Num: 3690
• Gen Len: 15.7011

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: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Num	Gen Len
0.4144	0.3	200	0.3585	39.267	3690	15.7322
0.3416	0.6	400	0.3570	41.6199	3690	15.7011
0.3242	0.89	600	0.3533	40.3462	3690	15.4035
0.2996	1.19	800	0.3616	40.9198	3690	16.6144
0.294	1.49	1000	0.3599	41.2309	3690	15.2799

Framework versions

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