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: 1.0065
• Accuracy: {'accuracy': 0.885}

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	0.3875	{'accuracy': 0.883}
0.4366	2.0	500	0.4374	{'accuracy': 0.876}
0.4366	3.0	750	0.5551	{'accuracy': 0.873}
0.1987	4.0	1000	0.5990	{'accuracy': 0.877}
0.1987	5.0	1250	0.7351	{'accuracy': 0.889}
0.0792	6.0	1500	0.8729	{'accuracy': 0.875}
0.0792	7.0	1750	0.9701	{'accuracy': 0.882}
0.0144	8.0	2000	0.9657	{'accuracy': 0.886}
0.0144	9.0	2250	0.9803	{'accuracy': 0.885}
0.0084	10.0	2500	1.0065	{'accuracy': 0.885}

Framework versions

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