madatnlp/ket5-config-scratch

This model is a fine-tuned version of madatnlp/ket5-config-scratch on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 1.3667
• Validation Loss: 1.4931
• Epoch: 18

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:

• optimizer: {'name': 'Adam', 'learning_rate': 1e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
• training_precision: float32

Training results

Train Loss	Validation Loss	Epoch
1.4117	1.5494	0
1.4012	1.5838	1
1.4056	1.5710	2
1.4133	1.5190	3
1.3887	1.4858	4
1.3951	1.4920	5
1.3889	1.5038	6
1.3804	1.5079	7
1.3991	1.4368	8
1.3852	1.4974	9
1.3971	1.5164	10
1.3853	1.5632	11
1.3719	1.5163	12
1.3805	1.4271	13
1.3818	1.5078	14
1.3741	1.4687	15
1.3796	1.4623	16
1.3701	1.5326	17
1.3667	1.4931	18

Framework versions

• Transformers 4.18.0
• TensorFlow 2.8.0
• Datasets 2.1.0
• Tokenizers 0.12.1