modernbert-continue-detector-e2

This model is a fine-tuned version of answerdotai/ModernBERT-large on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0494
• Accuracy: 0.9869
• F1: 0.9868
• Precision: 0.9870
• Recall: 0.9869
• F1 Class 0: 0.9870
• Precision Class 0: 0.9784
• Recall Class 0: 0.9957
• F1 Class 1: 0.9867
• Precision Class 1: 0.9956
• Recall Class 1: 0.9779

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: 1e-05
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• distributed_type: multi-GPU
• num_devices: 6
• total_train_batch_size: 384
• total_eval_batch_size: 384
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 0.1
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall	F1 Class 0	Precision Class 0	Recall Class 0	F1 Class 1	Precision Class 1	Recall Class 1
0.3025	1.0	1363	0.0519	0.9859	0.9859	0.9862	0.9859	0.9861	0.9754	0.9971	0.9857	0.9970	0.9747
0.2852	2.0	2726	0.0494	0.9869	0.9868	0.9870	0.9869	0.9870	0.9784	0.9957	0.9867	0.9956	0.9779

Framework versions

• Transformers 4.55.0
• Pytorch 2.8.0+cu128
• Datasets 4.0.0
• Tokenizers 0.21.4