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: 1.1059
• Accuracy: {'accuracy': 0.892}

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
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	250	0.6337	{'accuracy': 0.838}
0.4489	2.0	500	0.4736	{'accuracy': 0.871}
0.4489	3.0	750	0.6530	{'accuracy': 0.879}
0.2026	4.0	1000	0.7425	{'accuracy': 0.883}
0.2026	5.0	1250	0.8993	{'accuracy': 0.877}
0.0573	6.0	1500	1.0324	{'accuracy': 0.884}
0.0573	7.0	1750	1.0653	{'accuracy': 0.891}
0.0224	8.0	2000	1.0818	{'accuracy': 0.89}
0.0224	9.0	2250	1.1406	{'accuracy': 0.884}
0.0097	10.0	2500	1.1059	{'accuracy': 0.892}

Framework versions

• PEFT 0.12.0
• Transformers 4.44.2
• Pytorch 2.5.1+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1