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: 0.9257
• Accuracy: {'accuracy': 0.904}

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	0.5634	{'accuracy': 0.834}
0.4354	2.0	500	0.5962	{'accuracy': 0.847}
0.4354	3.0	750	0.6723	{'accuracy': 0.85}
0.2263	4.0	1000	0.5873	{'accuracy': 0.893}
0.2263	5.0	1250	0.8506	{'accuracy': 0.886}
0.083	6.0	1500	0.7863	{'accuracy': 0.899}
0.083	7.0	1750	0.9194	{'accuracy': 0.894}
0.0196	8.0	2000	0.8792	{'accuracy': 0.904}
0.0196	9.0	2250	0.8943	{'accuracy': 0.906}
0.0045	10.0	2500	0.9257	{'accuracy': 0.904}

Framework versions

• PEFT 0.14.0
• Transformers 4.48.3
• Pytorch 2.5.1+cu124
• Datasets 3.3.0
• Tokenizers 0.21.0