results

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: 0.0785
• Accuracy: 0.9859
• F1: 0.9821
• Precision: 0.9784
• Recall: 0.9859

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: 6
• eval_batch_size: 6
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 12
• 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: 1
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
No log	0.125	25	1.5465	0.4375	0.2954	0.2488	0.4375
No log	0.25	50	0.6815	0.7484	0.7144	0.7826	0.7484
No log	0.375	75	0.5321	0.8281	0.7816	0.7651	0.8281
No log	0.5	100	0.3030	0.9125	0.9002	0.9154	0.9125
No log	0.625	125	0.1586	0.9625	0.9587	0.9561	0.9625
No log	0.75	150	0.0844	0.9781	0.9743	0.9710	0.9781
No log	0.875	175	0.0785	0.9859	0.9821	0.9784	0.9859

Framework versions

• Transformers 4.48.3
• Pytorch 2.6.0+cu124
• Datasets 3.4.0
• Tokenizers 0.21.0