distilbert-base-uncased-lora-text-classification

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

• Loss: 1.1492
• Accuracy: {'accuracy': 0.872}

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	0.4627	{'accuracy': 0.866}
0.3796	2.0	500	0.5169	{'accuracy': 0.87}
0.3796	3.0	750	0.6853	{'accuracy': 0.871}
0.1693	4.0	1000	0.8606	{'accuracy': 0.869}
0.1693	5.0	1250	0.9956	{'accuracy': 0.868}
0.0357	6.0	1500	1.0542	{'accuracy': 0.868}
0.0357	7.0	1750	1.0670	{'accuracy': 0.868}
0.0202	8.0	2000	1.1235	{'accuracy': 0.87}
0.0202	9.0	2250	1.1426	{'accuracy': 0.871}
0.0022	10.0	2500	1.1492	{'accuracy': 0.872}

Framework versions

• PEFT 0.14.0
• Transformers 4.47.1
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0