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: 1.0266
• Accuracy: {'accuracy': 0.879}

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 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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	250	0.5728	{'accuracy': 0.836}
0.4465	2.0	500	0.5879	{'accuracy': 0.84}
0.4465	3.0	750	0.5660	{'accuracy': 0.87}
0.2143	4.0	1000	0.7156	{'accuracy': 0.884}
0.2143	5.0	1250	0.8289	{'accuracy': 0.878}
0.0678	6.0	1500	0.8860	{'accuracy': 0.881}
0.0678	7.0	1750	0.8860	{'accuracy': 0.89}
0.0197	8.0	2000	0.9478	{'accuracy': 0.878}
0.0197	9.0	2250	1.0301	{'accuracy': 0.878}
0.0096	10.0	2500	1.0266	{'accuracy': 0.879}

Framework versions

• PEFT 0.13.2
• Transformers 4.46.3
• Pytorch 2.5.1+cu124
• Datasets 3.1.0
• Tokenizers 0.20.3