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: 1.0494
• Accuracy: {'accuracy': 0.885}

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	0.3799	{'accuracy': 0.863}
0.4468	2.0	500	0.5154	{'accuracy': 0.867}
0.4468	3.0	750	0.5412	{'accuracy': 0.879}
0.2163	4.0	1000	0.7670	{'accuracy': 0.872}
0.2163	5.0	1250	0.8273	{'accuracy': 0.878}
0.0556	6.0	1500	0.9885	{'accuracy': 0.873}
0.0556	7.0	1750	1.0767	{'accuracy': 0.873}
0.0285	8.0	2000	1.1202	{'accuracy': 0.87}
0.0285	9.0	2250	1.0409	{'accuracy': 0.886}
0.0178	10.0	2500	1.0494	{'accuracy': 0.885}

Framework versions

• PEFT 0.14.0
• Transformers 4.47.0
• Pytorch 2.5.1
• Datasets 3.1.0
• Tokenizers 0.21.0