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: 1.1143
• Accuracy: {'accuracy': 0.885}

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	0.3907	{'accuracy': 0.87}
0.4307	2.0	500	0.4413	{'accuracy': 0.886}
0.4307	3.0	750	0.7302	{'accuracy': 0.879}
0.1513	4.0	1000	0.7659	{'accuracy': 0.882}
0.1513	5.0	1250	0.7540	{'accuracy': 0.877}
0.0662	6.0	1500	0.8800	{'accuracy': 0.886}
0.0662	7.0	1750	1.0128	{'accuracy': 0.885}
0.0086	8.0	2000	1.0446	{'accuracy': 0.884}
0.0086	9.0	2250	1.1049	{'accuracy': 0.884}
0.0026	10.0	2500	1.1143	{'accuracy': 0.885}

Framework versions

• PEFT 0.10.0
• Transformers 4.38.2
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2