flan-t5-large-da-multiwoz2.1_fs0.05

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: 0.3605
• Accuracy: 40.7025
• Num: 3689
• Gen Len: 15.8311

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	Accuracy	Num	Gen Len
0.9665	1.1	400	0.4662	32.999	3689	15.8777
0.5021	2.2	800	0.4089	35.1765	3689	15.0667
0.4467	3.3	1200	0.3839	35.8487	3689	15.7387
0.4066	4.4	1600	0.3751	37.5848	3689	14.9287
0.3907	5.49	2000	0.3654	38.7608	3689	15.4836
0.3644	6.59	2400	0.3620	40.1207	3689	15.154
0.3623	7.69	2800	0.3605	40.7025	3689	15.8311
0.3501	8.79	3200	0.3592	40.4075	3689	15.6419
0.3436	9.89	3600	0.3601	40.614	3689	15.7143

Framework versions

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