modernbert-3pair-adv-3label

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: 0.2386
• Accuracy: 0.9065
• F1: 0.9063
• Precision: 0.9063
• Recall: 0.9065
• F1 Class 0: 0.9070
• Precision Class 0: 0.9057
• Recall Class 0: 0.9084
• F1 Class 1: 0.9297
• Precision Class 1: 0.9176
• Recall Class 1: 0.9421
• F1 Class 2: 0.8824
• Precision Class 2: 0.8958
• Recall Class 2: 0.8694

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: 200
• eval_batch_size: 200
• seed: 42
• distributed_type: multi-GPU
• num_devices: 6
• total_train_batch_size: 1200
• total_eval_batch_size: 1200
• 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: 1

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	F1 Class 2	Precision Class 2	Recall Class 2
1.4646	1.0	2177	0.2386	0.9065	0.9063	0.9063	0.9065	0.9070	0.9057	0.9084	0.9297	0.9176	0.9421	0.8824	0.8958	0.8694

Framework versions

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