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: 1.0332
• Accuracy: {'accuracy': 0.89}

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	0.4714	{'accuracy': 0.861}
0.4431	2.0	500	0.4376	{'accuracy': 0.879}
0.4431	3.0	750	0.6543	{'accuracy': 0.874}
0.2114	4.0	1000	0.6353	{'accuracy': 0.888}
0.2114	5.0	1250	0.8143	{'accuracy': 0.881}
0.0603	6.0	1500	0.8727	{'accuracy': 0.894}
0.0603	7.0	1750	0.9625	{'accuracy': 0.887}
0.0297	8.0	2000	0.9678	{'accuracy': 0.89}
0.0297	9.0	2250	1.0445	{'accuracy': 0.888}
0.0057	10.0	2500	1.0332	{'accuracy': 0.89}

Framework versions

• PEFT 0.14.0
• Transformers 4.47.0
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0