distilbert-base-ja-cased-JaQuAD

This model is a fine-tuned version of line-corporation/line-distilbert-base-japanese on the ja_qu_ad dataset. It achieves the following results on the evaluation set:

• Loss: 1.7949

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
2.554	1.0	1588	2.1749
1.9802	2.0	3176	1.8883
1.7083	3.0	4764	1.7949

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0