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: 0.9401
• Accuracy: {'accuracy': 0.894}

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	0.4820	{'accuracy': 0.871}
0.4484	2.0	500	0.5434	{'accuracy': 0.858}
0.4484	3.0	750	0.7357	{'accuracy': 0.853}
0.2071	4.0	1000	0.5956	{'accuracy': 0.899}
0.2071	5.0	1250	0.8141	{'accuracy': 0.88}
0.0731	6.0	1500	0.8197	{'accuracy': 0.882}
0.0731	7.0	1750	0.9412	{'accuracy': 0.888}
0.0201	8.0	2000	0.9169	{'accuracy': 0.894}
0.0201	9.0	2250	0.9390	{'accuracy': 0.892}
0.0111	10.0	2500	0.9401	{'accuracy': 0.894}

Framework versions

• PEFT 0.9.0
• Transformers 4.38.2
• Pytorch 2.2.1
• Datasets 2.18.0
• Tokenizers 0.15.2