abacus-cheat-tell-v2

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

• Loss: 0.7369
• Accuracy: 0.5429
• F1: 0.6522

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: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• 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: linear
• lr_scheduler_warmup_steps: 0.1
• num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
No log	1.0	9	0.7369	0.5429	0.6522
0.7391	2.0	18	0.7043	0.4857	0.4375
0.6190	3.0	27	0.7502	0.5143	0.5854
0.5088	4.0	36	0.7590	0.4857	0.5

Framework versions

• Transformers 5.0.0
• Pytorch 2.10.0+cu128
• Datasets 4.0.0
• Tokenizers 0.22.2