Prgrg/en-ja-v4.0

This model is a fine-tuned version of Prgrg/en-ja-v3.0 on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.7581
• Validation Loss: 1.0194
• Epoch: 9

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': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 0.0005, 'decay_steps': 162130, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.001}
• training_precision: mixed_float16

Training results

Train Loss	Validation Loss	Epoch
1.3802	1.3429	0
1.3146	1.2845	1
1.2264	1.2126	2
1.1463	1.1696	3
1.0739	1.1215	4
1.0035	1.0868	5
0.9367	1.0568	6
0.8725	1.0337	7
0.8114	1.0205	8
0.7581	1.0194	9

Framework versions

• Transformers 4.26.1
• TensorFlow 2.11.0
• Datasets 2.10.1
• Tokenizers 0.13.2