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: 1.0005
• Accuracy: {'accuracy': 0.889}

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	250	0.5429	{'accuracy': 0.833}
0.4379	2.0	500	0.4558	{'accuracy': 0.878}
0.4379	3.0	750	0.6034	{'accuracy': 0.876}
0.2125	4.0	1000	0.7067	{'accuracy': 0.892}
0.2125	5.0	1250	0.8947	{'accuracy': 0.875}
0.0695	6.0	1500	0.8737	{'accuracy': 0.886}
0.0695	7.0	1750	0.9554	{'accuracy': 0.889}
0.0271	8.0	2000	0.9786	{'accuracy': 0.894}
0.0271	9.0	2250	0.9897	{'accuracy': 0.893}
0.0052	10.0	2500	1.0005	{'accuracy': 0.889}

Framework versions

• PEFT 0.13.2
• Transformers 4.44.2
• Pytorch 2.5.0+cu121
• Tokenizers 0.19.1