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: 0.5985
• Accuracy: {'accuracy': 0.897}

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	0.5985	{'accuracy': 0.897}
0.2977	2.0	500	0.7703	{'accuracy': 0.873}
0.2977	3.0	750	0.8496	{'accuracy': 0.877}
0.2002	4.0	1000	0.8023	{'accuracy': 0.884}
0.2002	5.0	1250	1.0785	{'accuracy': 0.888}
0.0307	6.0	1500	1.1893	{'accuracy': 0.881}
0.0307	7.0	1750	1.2543	{'accuracy': 0.882}
0.0244	8.0	2000	1.3205	{'accuracy': 0.876}
0.0244	9.0	2250	1.2482	{'accuracy': 0.882}
0.0121	10.0	2500	1.2665	{'accuracy': 0.886}

Framework versions

• PEFT 0.17.1
• Transformers 4.55.4
• Pytorch 2.8.0+cu126
• Datasets 4.0.0
• Tokenizers 0.21.4