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: 0.8699
• Accuracy: {'accuracy': 0.89}

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 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: 7

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	250	0.6669	{'accuracy': 0.833}
0.4291	2.0	500	0.4317	{'accuracy': 0.874}
0.4291	3.0	750	0.7625	{'accuracy': 0.871}
0.1676	4.0	1000	0.7119	{'accuracy': 0.893}
0.1676	5.0	1250	0.7995	{'accuracy': 0.897}
0.0456	6.0	1500	0.8480	{'accuracy': 0.89}
0.0456	7.0	1750	0.8699	{'accuracy': 0.89}

Framework versions

• PEFT 0.13.2
• Transformers 4.46.2
• Pytorch 2.5.1+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3