roberta-slop-classifier

This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.3163

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: 32
• seed: 80085
• 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: 0.06
• num_epochs: 2
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.1464	0.1693	500	0.5694
0.9725	0.3386	1000	0.4428
0.8993	0.5079	1500	0.3857
0.8407	0.6772	2000	0.3852
0.7639	0.8465	2500	0.3596
0.7553	1.0156	3000	0.3582
0.7009	1.1849	3500	0.3405
0.6725	1.3542	4000	0.3237
0.6264	1.5234	4500	0.3207
0.6226	1.6927	5000	0.3117
0.6781	1.8620	5500	0.3163

Framework versions

• Transformers 5.3.0
• Pytorch 2.9.1+rocmsdk20260116
• Datasets 4.6.1
• Tokenizers 0.22.2