deberta-v2-base-japanese-detect-ai

This model is a fine-tuned version of ku-nlp/deberta-v2-base-japanese on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1032
• Accuracy: 0.9842
• F1: 0.9842

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: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.0409	1.0	403	0.1045	0.9823	0.9823
0.0101	2.0	806	0.0567	0.9893	0.9893
0.0008	3.0	1209	0.1032	0.9842	0.9842

Framework versions

• Transformers 4.25.1
• Pytorch 1.12.0+cu113
• Datasets 2.8.0
• Tokenizers 0.13.2