toxic-gn-bert-tiny-cased

This model is a fine-tuned version of mmaguero/gn-bert-tiny-cased on mmaguero/gn-offensive-language-identification dataset. It achieves the following results on the evaluation set:

• Loss: 0.3441
• Accuracy: 0.8733

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
• 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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	87	0.3798	0.8649
No log	2.0	174	0.3606	0.8649
No log	3.0	261	0.3317	0.8879
No log	4.0	348	0.3102	0.8966
No log	5.0	435	0.2947	0.8994
0.3717	6.0	522	0.2853	0.9023
0.3717	7.0	609	0.2800	0.8879
0.3717	8.0	696	0.2788	0.8851
0.3717	9.0	783	0.2777	0.8822
0.3717	10.0	870	0.2777	0.8822

Framework versions

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