AymanKhan/gender-bias-classifier

gender_bias_classifier_improved

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

• Loss: 0.2126
• Accuracy: 0.9034
• Precision: 0.9044
• Recall: 0.9034
• F1: 0.9030

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: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• 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
• lr_scheduler_warmup_steps: 100
• num_epochs: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
0.5976	1.0102	100	0.5380	0.6018	0.6288	0.6018	0.5979
0.398	2.0203	200	0.2619	0.8366	0.8441	0.8366	0.8337
0.2457	3.0305	300	0.2182	0.8900	0.8900	0.8900	0.8900
0.1903	4.0406	400	0.2126	0.9034	0.9044	0.9034	0.9030

Framework versions

• Transformers 4.57.1
• Pytorch 2.8.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.1