answerdotai-ModernBERT-basemhr2004-atomic.anion.train.no1e-06-64

This model is a fine-tuned version of answerdotai/ModernBERT-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.4237

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: 128
• eval_batch_size: 512
• 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
0.5508	1.0	2304	0.5309
0.4909	2.0	4608	0.4951
0.4684	3.0	6912	0.4759
0.4607	4.0	9216	0.4630
0.4396	5.0	11520	0.4563
0.4361	6.0	13824	0.4505
0.4235	7.0	16128	0.4534
0.4199	8.0	18432	0.4429
0.4154	9.0	20736	0.4396
0.4155	10.0	23040	0.4369
0.4021	11.0	25344	0.4324
0.3966	12.0	27648	0.4323
0.3929	13.0	29952	0.4292
0.3908	14.0	32256	0.4273
0.3872	15.0	34560	0.4289
0.3834	16.0	36864	0.4261
0.3767	17.0	39168	0.4276
0.3775	18.0	41472	0.4270
0.367	19.0	43776	0.4260
0.3673	20.0	46080	0.4275
0.3726	21.0	48384	0.4233
0.3575	22.0	50688	0.4248
0.3633	23.0	52992	0.4251
0.36	24.0	55296	0.4237

Framework versions

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