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: 0.9247
• Accuracy: {'accuracy': 0.886}

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	0.3986	{'accuracy': 0.877}
0.429	2.0	500	0.5109	{'accuracy': 0.885}
0.429	3.0	750	0.4885	{'accuracy': 0.884}
0.2188	4.0	1000	0.6639	{'accuracy': 0.882}
0.2188	5.0	1250	0.6673	{'accuracy': 0.882}
0.0841	6.0	1500	0.7289	{'accuracy': 0.895}
0.0841	7.0	1750	0.8089	{'accuracy': 0.887}
0.0278	8.0	2000	0.8884	{'accuracy': 0.88}
0.0278	9.0	2250	0.9264	{'accuracy': 0.884}
0.016	10.0	2500	0.9247	{'accuracy': 0.886}

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.1