README.md

metadata

library_name: transformers
license: apache-2.0
base_model: answerdotai/ModernBERT-base
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - precision
  - recall
  - f1
model-index:
  - name: fred-guard-base
    results: []

fred-guard-base

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: 0.0508
• Accuracy: 0.9806
• Precision: 1.0
• Recall: 0.9611
• F1: 0.9802

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: 64
• eval_batch_size: 32
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
0.9662	0.1111	5	0.7300	0.5194	0.5099	1.0	0.6754
0.6438	0.2222	10	0.5574	0.6778	0.6553	0.75	0.6995
0.6016	0.3333	15	0.4892	0.7667	0.8038	0.7056	0.7515
0.4617	0.4444	20	0.4301	0.7972	0.7512	0.8889	0.8142
0.3779	0.5556	25	0.3152	0.8528	0.8588	0.8444	0.8515
0.3712	0.6667	30	0.2228	0.8944	0.9437	0.8389	0.8882
0.2169	0.7778	35	0.2674	0.8806	0.9928	0.7667	0.8652
0.2445	0.8889	40	0.1471	0.9306	0.9189	0.9444	0.9315
0.1838	1.0	45	0.2446	0.8833	0.9929	0.7722	0.8688
0.1249	1.1111	50	0.1212	0.9472	0.9215	0.9778	0.9488
0.0775	1.2222	55	0.1005	0.9556	0.9940	0.9167	0.9538
0.0776	1.3333	60	0.0783	0.9722	0.9775	0.9667	0.9721
0.0577	1.4444	65	0.0924	0.9722	0.9942	0.95	0.9716
0.0753	1.5556	70	0.0763	0.9722	0.9942	0.95	0.9716
0.0733	1.6667	75	0.0453	0.975	0.9831	0.9667	0.9748
0.0866	1.7778	80	0.0576	0.9778	1.0	0.9556	0.9773
0.041	1.8889	85	0.0583	0.9778	1.0	0.9556	0.9773
0.0579	2.0	90	0.0508	0.9806	1.0	0.9611	0.9802

Framework versions

• Transformers 4.55.4
• Pytorch 2.8.0+cu126
• Datasets 4.0.0
• Tokenizers 0.21.4