PaymentNonPayment-ModernBERT

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

• Loss: 0.0157
• Accuracy: 0.9985
• F1: 0.9985
• Precision: 0.9985
• Recall: 0.9985
• Roc Auc: 0.9984

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: 0.0002
• train_batch_size: 1
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 8
• optimizer: Use paged_adamw_32bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.03
• num_epochs: 1
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall	Roc Auc
16.0312	0.1996	79	0.1616	0.9823	0.9823	0.9829	0.9823	0.9803
0.0001	0.3992	158	0.1080	0.9882	0.9882	0.9884	0.9882	0.9890
0.0001	0.5989	237	0.0169	0.9985	0.9985	0.9985	0.9985	0.9984
0.0003	0.7985	316	0.0138	0.9985	0.9985	0.9985	0.9985	0.9984
0.0001	0.9981	395	0.0157	0.9985	0.9985	0.9985	0.9985	0.9984

Framework versions

• Transformers 4.48.0.dev0
• Pytorch 2.4.1+cu121
• Datasets 3.1.0
• Tokenizers 0.21.0