modernbert_agree_classifier

This model is a fine-tuned version of answerdotai/ModernBERT-large on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.7135
• Accuracy: 0.6114

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: 6.000000000000001e-05
• train_batch_size: 6
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 10
• total_train_batch_size: 60
• 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: constant
• training_steps: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
6.6012	0.2994	20	0.6613	0.6114
5.841	0.5988	40	0.7060	0.6114
7.3284	0.8982	60	0.6671	0.6114
6.9088	1.2096	80	0.6861	0.4834
7.1679	1.5090	100	0.7135	0.6114

Framework versions

• Transformers 4.51.3
• Pytorch 2.6.0+cu124
• Datasets 2.14.4
• Tokenizers 0.21.1