distilbert-base-uncased-lora-text-classification

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

• Loss: 0.9069
• Accuracy: {'accuracy': 0.909}

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: 0.001
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH 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	250	0.4078	{'accuracy': 0.87}
0.418	2.0	500	0.3741	{'accuracy': 0.883}
0.418	3.0	750	0.6762	{'accuracy': 0.875}
0.1992	4.0	1000	0.5752	{'accuracy': 0.904}
0.1992	5.0	1250	0.7332	{'accuracy': 0.898}
0.057	6.0	1500	0.8001	{'accuracy': 0.901}
0.057	7.0	1750	0.8734	{'accuracy': 0.905}
0.0275	8.0	2000	0.9458	{'accuracy': 0.896}
0.0275	9.0	2250	0.9224	{'accuracy': 0.905}
0.0117	10.0	2500	0.9069	{'accuracy': 0.909}

Framework versions

• PEFT 0.14.0
• Transformers 4.48.3
• Pytorch 2.5.1+cu124
• Datasets 3.3.2
• Tokenizers 0.21.0