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: 0.9488
• Accuracy: {'accuracy': 0.889}

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: 8
• eval_batch_size: 8
• 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	125	0.3898	{'accuracy': 0.888}
No log	2.0	250	0.5789	{'accuracy': 0.865}
No log	3.0	375	0.5372	{'accuracy': 0.889}
0.1772	4.0	500	0.6432	{'accuracy': 0.891}
0.1772	5.0	625	0.8819	{'accuracy': 0.889}
0.1772	6.0	750	0.9567	{'accuracy': 0.883}
0.1772	7.0	875	0.9547	{'accuracy': 0.891}
0.0207	8.0	1000	0.9466	{'accuracy': 0.895}
0.0207	9.0	1125	0.9615	{'accuracy': 0.892}
0.0207	10.0	1250	0.9488	{'accuracy': 0.889}

Framework versions

• PEFT 0.11.1
• Transformers 4.41.2
• Pytorch 2.3.1+cu121
• Datasets 2.19.2
• Tokenizers 0.19.1