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: 0.9456
• 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: 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	0.6952	{'accuracy': 0.808}
0.4327	2.0	500	0.5493	{'accuracy': 0.857}
0.4327	3.0	750	0.5937	{'accuracy': 0.874}
0.212	4.0	1000	0.6253	{'accuracy': 0.891}
0.212	5.0	1250	0.7137	{'accuracy': 0.884}
0.0841	6.0	1500	0.7189	{'accuracy': 0.89}
0.0841	7.0	1750	0.8318	{'accuracy': 0.892}
0.0273	8.0	2000	0.9064	{'accuracy': 0.892}
0.0273	9.0	2250	0.9400	{'accuracy': 0.89}
0.0068	10.0	2500	0.9456	{'accuracy': 0.889}

Framework versions

• PEFT 0.11.1
• Transformers 4.41.2
• Pytorch 2.3.0
• Datasets 2.19.2
• Tokenizers 0.19.1