metadata

library_name: transformers
license: apache-2.0
base_model: answerdotai/ModernBERT-base
tags:
  - generated_from_trainer
model-index:
  - name: ModernBERT-base-ft-code-defect-detection-4k
    results: []

ModernBERT-base-ft-code-defect-detection-4k

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: 0.5844
Accuracy Score: 0.6537
F1 Score: 0.5784
Precision Score: 0.5171
Recall Score: 0.6562

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: 8e-05
train_batch_size: 64
eval_batch_size: 64
seed: 42
optimizer: Use adamw_torch with betas=(0.9,0.98) and epsilon=1e-06 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy Score	F1 Score	Precision Score	Recall Score
0.6795	1.0	342	0.6435	0.6120	0.3099	0.1896	0.8470
0.6168	2.0	684	0.5960	0.6395	0.4316	0.2980	0.7824
0.5605	3.0	1026	0.5844	0.6537	0.5784	0.5171	0.6562

Framework versions

Transformers 4.48.0.dev0
Pytorch 2.5.1+cu121
Datasets 3.2.0
Tokenizers 0.21.0