ModernBERT-largemhr2004-anion-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: 0.2880

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: 192
• eval_batch_size: 768
• 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
0.4231	1.0	478	0.4124
0.345	2.0	956	0.3397
0.2893	3.0	1434	0.3129
0.2458	4.0	1912	0.2947
0.2165	5.0	2390	0.2771
0.2169	6.0	2868	0.2650
0.1898	7.0	3346	0.2692
0.1781	8.0	3824	0.2556
0.145	9.0	4302	0.2669
0.1317	10.0	4780	0.2646
0.1327	11.0	5258	0.2880

Framework versions

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