toxic-multilingual-bert-gn-base-cased

This model is a fine-tuned version of mmaguero/multilingual-bert-gn-base-cased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.3267
• Accuracy: 0.8779

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	0.3172	0.9023
No log	2.0	174	0.2514	0.8966
No log	3.0	261	0.2868	0.9109
No log	4.0	348	0.3744	0.9080
No log	5.0	435	0.4561	0.8879
0.1802	6.0	522	0.4963	0.8879
0.1802	7.0	609	0.5872	0.8649
0.1802	8.0	696	0.6180	0.8649
0.1802	9.0	783	0.5582	0.8793
0.1802	10.0	870	0.5764	0.8793

Framework versions

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