test_trainer

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

• Loss: 0.2071
• Accuracy: 0.7405

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: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 1.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.0935	200	0.2734	0.5675
No log	0.1871	400	0.2632	0.5931
0.3013	0.2806	600	0.2381	0.6531
0.3013	0.3742	800	0.2324	0.6814
0.2601	0.4677	1000	0.2241	0.7087
0.2601	0.5613	1200	0.2163	0.7229
0.2601	0.6548	1400	0.2173	0.7299
0.2511	0.7484	1600	0.2115	0.7343
0.2511	0.8419	1800	0.2073	0.7387
0.2369	0.9355	2000	0.2071	0.7405

Framework versions

• Transformers 4.47.1
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0