complexity-router-weighted

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: 4.0259
• Accuracy: 0.8135
• F1: 0.8036
• High To Low Error: 64.5497

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: 0.0002
• train_batch_size: 128
• eval_batch_size: 128
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.01
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	High To Low Error
0.5968	1.0	346	0.5067	0.8050	0.8055	54.7344
0.4356	2.0	692	0.5328	0.7973	0.8042	47.6905
0.2555	3.0	1038	0.6893	0.7971	0.8032	48.9607
0.1651	4.0	1384	0.8980	0.8127	0.8071	60.1617
0.132	5.0	1730	0.9915	0.8085	0.8051	58.6605
0.0706	6.0	2076	1.4578	0.8146	0.8078	60.9700
0.0535	7.0	2422	2.1353	0.8139	0.8083	59.8152
0.0371	8.0	2768	2.3199	0.8239	0.8048	70.5543
0.042	9.0	3114	2.6879	0.8111	0.8048	61.3164
0.0105	10.0	3460	4.0259	0.8135	0.8036	64.5497

Framework versions

• Transformers 4.48.1
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0