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: 0.9338
• Accuracy: {'accuracy': 0.891}

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_FUSED 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	0.4001	{'accuracy': 0.873}
0.4331	2.0	500	0.4954	{'accuracy': 0.874}
0.4331	3.0	750	0.6302	{'accuracy': 0.866}
0.2251	4.0	1000	0.5870	{'accuracy': 0.895}
0.2251	5.0	1250	0.7450	{'accuracy': 0.891}
0.0726	6.0	1500	0.7311	{'accuracy': 0.886}
0.0726	7.0	1750	0.8337	{'accuracy': 0.893}
0.0175	8.0	2000	0.8817	{'accuracy': 0.884}
0.0175	9.0	2250	0.9239	{'accuracy': 0.885}
0.0090	10.0	2500	0.9338	{'accuracy': 0.891}

Framework versions

• Transformers 5.13.1
• Pytorch 2.13.0
• Datasets 5.0.0
• Tokenizers 0.22.2