ModernBERT-largemhr2004-atomic-neg-bal1e-06-64

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: 0.3867

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-06
• train_batch_size: 256
• eval_batch_size: 1024
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss
0.5253	1.0	795	0.5324
0.4545	2.0	1590	0.4699
0.4451	3.0	2385	0.4393
0.4199	4.0	3180	0.4308
0.3842	5.0	3975	0.4187
0.3744	6.0	4770	0.4084
0.3729	7.0	5565	0.4017
0.3601	8.0	6360	0.3982
0.3369	9.0	7155	0.3916
0.302	10.0	7950	0.3928
0.3333	11.0	8745	0.3869
0.3234	12.0	9540	0.3851
0.3051	13.0	10335	0.3860
0.2831	14.0	11130	0.3883
0.2838	15.0	11925	0.3867

Framework versions

• Transformers 4.51.2
• Pytorch 2.6.0+cu124
• Datasets 3.5.0
• Tokenizers 0.21.1