flan-t5-large-da-multiwoz2.0_400-ep10

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: 0.3728
• Accuracy: 38.5105
• Num: 7358
• Gen Len: 15.3954

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: 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
1.1897	1.16	200	0.5257	28.1911	7358	14.6738
0.5545	2.33	400	0.4348	32.8522	7358	15.5008
0.4745	3.49	600	0.4070	34.818	7358	16.0076
0.4439	4.65	800	0.3872	36.4827	7358	16.0594
0.4214	5.81	1000	0.3818	36.5826	7358	14.9643
0.4024	6.98	1200	0.3756	37.6167	7358	15.3856
0.3911	8.14	1400	0.3728	38.5105	7358	15.3954
0.3812	9.3	1600	0.3715	38.2191	7358	15.5928

Framework versions

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