featured-articles

This model is a fine-tuned version of answerdotai/ModernBERT-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.9620
• Weighted F1: 0.6740
• Accepted Precision: 0.7453
• Accepted Recall: 0.7790
• Accepted F1: 0.7618
• Rejected Precision: 0.5273
• Rejected Recall: 0.4807
• Rejected F1: 0.5029
• Accuracy: 0.6779

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: 3e-05
• train_batch_size: 8
• eval_batch_size: 8
• 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
• num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss	Weighted F1	Accepted Precision	Accepted Recall	Accepted F1	Rejected Precision	Rejected Recall	Rejected F1	Accuracy
0.6595	1.0	267	0.6187	0.6876	0.752	0.7989	0.7747	0.5535	0.4862	0.5176	0.6929
0.4807	2.0	534	0.7625	0.5677	0.8030	0.4504	0.5771	0.4226	0.7845	0.5493	0.5637
0.3013	3.0	801	1.7444	0.6577	0.7105	0.9178	0.8010	0.6282	0.2707	0.3784	0.6985
0.0381	4.0	1068	1.9620	0.6740	0.7453	0.7790	0.7618	0.5273	0.4807	0.5029	0.6779

Framework versions

• Transformers 4.48.0.dev0
• Pytorch 2.2.2
• Datasets 3.1.0
• Tokenizers 0.21.0