ModernBERT_large_Assign_4

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: 0.1879
• Accuracy: 0.9668
• F1: 0.9664

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: 4e-05
• train_batch_size: 32
• eval_batch_size: 8
• 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: cosine
• num_epochs: 8

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.9447	0.8386	400	0.2952	0.9387	0.9358
0.0999	1.6771	800	0.2098	0.9513	0.9506
0.0582	2.5157	1200	0.2062	0.9574	0.9570
0.0185	3.3543	1600	0.1982	0.9635	0.9629
0.011	4.1929	2000	0.2009	0.9639	0.9632
0.0044	5.0314	2400	0.1852	0.9671	0.9668
0.0022	5.8700	2800	0.1915	0.9665	0.9661
0.0009	6.7086	3200	0.1878	0.9665	0.9661
0.0002	7.5472	3600	0.1879	0.9668	0.9664

Framework versions

• Transformers 4.56.2
• Pytorch 2.8.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.1