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: 0.9300
• 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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	125	0.3399	{'accuracy': 0.871}
No log	2.0	250	0.4717	{'accuracy': 0.853}
No log	3.0	375	0.3759	{'accuracy': 0.893}
0.2676	4.0	500	0.3800	{'accuracy': 0.897}
0.2676	5.0	625	0.6089	{'accuracy': 0.892}
0.2676	6.0	750	0.6365	{'accuracy': 0.893}
0.2676	7.0	875	0.7513	{'accuracy': 0.884}
0.0476	8.0	1000	0.7167	{'accuracy': 0.893}
0.0476	9.0	1125	0.7829	{'accuracy': 0.895}
0.0476	10.0	1250	0.8211	{'accuracy': 0.895}
0.0476	11.0	1375	0.8894	{'accuracy': 0.89}
0.0059	12.0	1500	0.9043	{'accuracy': 0.89}
0.0059	13.0	1625	0.9287	{'accuracy': 0.894}
0.0059	14.0	1750	0.9314	{'accuracy': 0.892}
0.0059	15.0	1875	0.9300	{'accuracy': 0.892}

Framework versions

• PEFT 0.14.0
• Transformers 4.47.1
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0