madatnlp/sk-kogptv2-kormath-causal

This model is a fine-tuned version of skt/kogpt2-base-v2 on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.3184
• Validation Loss: 1.4046
• Epoch: 15

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': 2.2999999e-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
2.7142	1.8683	0
1.6077	1.4417	1
1.2458	1.3161	2
1.0396	1.2704	3
0.8848	1.2818	4
0.7634	1.2579	5
0.6699	1.2724	6
0.5948	1.2718	7
0.5306	1.3300	8
0.4832	1.3377	9
0.4401	1.3038	10
0.4053	1.3622	11
0.3782	1.3577	12
0.3550	1.3696	13
0.3347	1.3682	14
0.3184	1.4046	15

Framework versions

• Transformers 4.19.1
• TensorFlow 2.8.0
• Datasets 2.2.1
• Tokenizers 0.12.1