fakenews-bert-ja-local

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

fakenews-bert-ja-local

This model is a fine-tuned version of cl-tohoku/bert-base-japanese-v3 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1654
• Accuracy: 0.9594

Model description

Dataset is on kaggle tanreinama/japanese-fakenews-dataset :https://www.kaggle.com/datasets/tanreinama/japanese-fakenews-dataset

leabl0:true lebel1:partially fake lebel2:completely fake

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: 32
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Framework versions

• Transformers 5.0.0
• Pytorch 2.9.0+cu126
• Datasets 4.5.0
• Tokenizers 0.22.2