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: 0.9277
• Accuracy: {'accuracy': 0.897}

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	0.3166	{'accuracy': 0.887}
0.4289	2.0	500	0.4832	{'accuracy': 0.872}
0.4289	3.0	750	0.5347	{'accuracy': 0.878}
0.1949	4.0	1000	0.6836	{'accuracy': 0.886}
0.1949	5.0	1250	0.7414	{'accuracy': 0.892}
0.0533	6.0	1500	0.8023	{'accuracy': 0.886}
0.0533	7.0	1750	0.8958	{'accuracy': 0.885}
0.0093	8.0	2000	0.9028	{'accuracy': 0.895}
0.0093	9.0	2250	0.9309	{'accuracy': 0.896}
0.0072	10.0	2500	0.9277	{'accuracy': 0.897}

Framework versions

• PEFT 0.13.2
• Transformers 4.44.2
• Pytorch 2.5.0+cu121
• Datasets 3.1.0
• Tokenizers 0.19.1