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: 1.0232
• Accuracy: {'accuracy': 0.889}

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	0.4070	{'accuracy': 0.882}
0.3737	2.0	500	0.4423	{'accuracy': 0.873}
0.3737	3.0	750	0.8375	{'accuracy': 0.868}
0.1851	4.0	1000	0.7292	{'accuracy': 0.885}
0.1851	5.0	1250	0.8958	{'accuracy': 0.895}
0.0741	6.0	1500	0.8747	{'accuracy': 0.889}
0.0741	7.0	1750	0.9911	{'accuracy': 0.888}
0.0267	8.0	2000	1.0290	{'accuracy': 0.886}
0.0267	9.0	2250	1.0253	{'accuracy': 0.89}
0.0102	10.0	2500	1.0232	{'accuracy': 0.889}

Framework versions

• PEFT 0.13.2
• Transformers 4.46.3
• Pytorch 2.5.1+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3