modernbert-CGEdit-AAE_risk

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

• Loss: 0.5195

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: 5e-05
• train_batch_size: 32
• eval_batch_size: 8
• 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: cosine
• lr_scheduler_warmup_steps: 0.1
• num_epochs: 20
• label_smoothing_factor: 0.1

Training results

Training Loss	Epoch	Step	Validation Loss
0.7306	1.0	26	0.6872
0.6044	2.0	52	0.5836
0.5659	3.0	78	0.5501
0.5389	4.0	104	0.5354
0.5233	5.0	130	0.5280
0.5191	6.0	156	0.5229
0.5144	7.0	182	0.5226
0.5189	8.0	208	0.5213
0.5157	9.0	234	0.5203
0.5153	10.0	260	0.5201
0.5153	11.0	286	0.5201
0.5190	12.0	312	0.5198
0.5237	13.0	338	0.5196
0.5170	14.0	364	0.5196
0.5234	15.0	390	0.5195
0.5127	16.0	416	0.5195
0.5157	17.0	442	0.5195
0.5134	18.0	468	0.5195
0.5123	19.0	494	0.5195
0.5093	20.0	520	0.5195

Framework versions

• Transformers 5.0.0
• Pytorch 2.5.1+cu121
• Tokenizers 0.22.1