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: 0.9858
• Accuracy: {'accuracy': 0.887}

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	0.4170	{'accuracy': 0.863}
0.4398	2.0	500	0.4620	{'accuracy': 0.874}
0.4398	3.0	750	0.5895	{'accuracy': 0.888}
0.1779	4.0	1000	0.6279	{'accuracy': 0.893}
0.1779	5.0	1250	0.8134	{'accuracy': 0.895}
0.0456	6.0	1500	0.8367	{'accuracy': 0.897}
0.0456	7.0	1750	0.8926	{'accuracy': 0.887}
0.0234	8.0	2000	0.9301	{'accuracy': 0.888}
0.0234	9.0	2250	0.9804	{'accuracy': 0.884}
0.0063	10.0	2500	0.9858	{'accuracy': 0.887}

Framework versions

• Transformers 4.48.0
• Pytorch 2.3.0
• Datasets 4.1.1
• Tokenizers 0.21.4