ModernBERT-large-anion.train.no.negation.true.irrelevant1e-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: 0.3965

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
0.6013	1.0	358	0.5308
0.512	2.0	716	0.4992
0.4833	3.0	1074	0.4760
0.4481	4.0	1432	0.4556
0.4401	5.0	1790	0.4365
0.4183	6.0	2148	0.4324
0.4104	7.0	2506	0.4216
0.3967	8.0	2864	0.4175
0.3934	9.0	3222	0.4152
0.3908	10.0	3580	0.4104
0.3876	11.0	3938	0.4056
0.378	12.0	4296	0.4108
0.3764	13.0	4654	0.4022
0.3754	14.0	5012	0.4010
0.3585	15.0	5370	0.3980
0.3565	16.0	5728	0.3993
0.3584	17.0	6086	0.3977
0.3572	18.0	6444	0.3976
0.3415	19.0	6802	0.3996
0.3416	20.0	7160	0.3955
0.3433	21.0	7518	0.3984
0.3349	22.0	7876	0.3951
0.3306	23.0	8234	0.3935
0.3363	24.0	8592	0.3976
0.3302	25.0	8950	0.3961
0.3181	26.0	9308	0.3965

Framework versions

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