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

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

• Loss: 0.5549
• Accuracy: 41.8963
• Num: 3690
• Gen Len: 15.5154

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
0.2518	1.17	400	0.4016	42.2397	3690	15.2057
0.219	2.33	800	0.4174	42.2063	3690	15.5122
0.1916	3.5	1200	0.4534	42.0205	3690	16.2089
0.1707	4.66	1600	0.4615	41.8799	3690	15.5564
0.1534	5.83	2000	0.4778	42.1433	3690	15.2282
0.1415	7.0	2400	0.5077	42.1549	3690	15.5642
0.1279	8.16	2800	0.5406	42.0254	3690	15.968
0.1242	9.33	3200	0.5480	42.1143	3690	15.6694

Framework versions

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