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: 0.9261
• Accuracy: {'accuracy': 0.895}

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_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	250	0.3525	{'accuracy': 0.89}
0.4331	2.0	500	0.4067	{'accuracy': 0.883}
0.4331	3.0	750	0.6208	{'accuracy': 0.885}
0.1783	4.0	1000	0.6784	{'accuracy': 0.891}
0.1783	5.0	1250	0.7692	{'accuracy': 0.89}
0.0704	6.0	1500	0.8742	{'accuracy': 0.887}
0.0704	7.0	1750	0.9085	{'accuracy': 0.896}
0.0187	8.0	2000	0.9310	{'accuracy': 0.896}
0.0187	9.0	2250	0.9163	{'accuracy': 0.897}
0.0059	10.0	2500	0.9261	{'accuracy': 0.895}

Framework versions

• PEFT 0.17.1
• Transformers 4.56.1
• Pytorch 2.8.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.0