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: 1.1443
• Accuracy: {'accuracy': 0.898}

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: Use 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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	250	0.3596	{'accuracy': 0.88}
0.4442	2.0	500	0.4824	{'accuracy': 0.867}
0.4442	3.0	750	0.5480	{'accuracy': 0.895}
0.2096	4.0	1000	0.6805	{'accuracy': 0.887}
0.2096	5.0	1250	0.9621	{'accuracy': 0.887}
0.0618	6.0	1500	0.9738	{'accuracy': 0.885}
0.0618	7.0	1750	1.0855	{'accuracy': 0.897}
0.0377	8.0	2000	1.0957	{'accuracy': 0.899}
0.0377	9.0	2250	1.1224	{'accuracy': 0.897}
0.0059	10.0	2500	1.1443	{'accuracy': 0.898}

Framework versions

• PEFT 0.14.0
• Transformers 4.48.3
• Pytorch 2.6.0+cpu
• Datasets 3.2.0
• Tokenizers 0.21.0