modernBERT-finetuned

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: 0.4387
• Accuracy: 0.9089
• F1: 0.9059

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: 5e-05
• train_batch_size: 32
• eval_batch_size: 32
• 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
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
2.0379	0.2096	100	0.8487	0.7982	0.7929
0.3466	0.4193	200	0.7759	0.8251	0.8137
0.2423	0.6289	300	0.4812	0.8929	0.8904
0.1841	0.8386	400	0.5286	0.8815	0.8785
0.1263	1.0482	500	0.4933	0.8944	0.8921
0.0525	1.2579	600	0.4623	0.8998	0.8972
0.0384	1.4675	700	0.4990	0.8944	0.8896
0.0302	1.6771	800	0.4860	0.9015	0.8972
0.0273	1.8868	900	0.4387	0.9089	0.9059

Framework versions

• Transformers 4.57.0
• Pytorch 2.8.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.1