reberta-base-klue-ynat-classfication

<!-- 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. -->

reberta-base-klue-ynat-classfication

This model is a fine-tuned version of klue/roberta-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.5943
• Confidence: [[-1.1646565 -1.2498165 0.29182994 ... -1.0066916 -1.6406983 -1.7746325 ] [-1.9457322 -1.8257982 0.79716635 ... 0.10126656 -1.1954982 5.9838986 ] [-0.48572934 5.6094513 0.43222797 ... -0.75162756 -2.0966194 -1.5772848 ] ... [-1.1721573 -1.0671966 -0.65719104 ... 0.11196741 6.3824944 -0.8935116 ] [-1.0086813 -0.68413603 4.671994 ... -1.6908021 -1.5391526 -0.3495633 ] [-1.1721573 -1.0671966 -0.65719104 ... 0.11196741 6.3824944 -0.8935116 ]]

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 OptimizerNames.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: 2

Training results

Framework versions

• Transformers 4.53.2
• Pytorch 2.6.0+cu124
• Datasets 4.0.0
• Tokenizers 0.21.2