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: 0.9232
• Accuracy: {'accuracy': 0.899}

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	250	0.3636	{'accuracy': 0.883}
0.4385	2.0	500	0.5940	{'accuracy': 0.852}
0.4385	3.0	750	0.6047	{'accuracy': 0.891}
0.1953	4.0	1000	0.5980	{'accuracy': 0.886}
0.1953	5.0	1250	0.7089	{'accuracy': 0.89}
0.079	6.0	1500	0.8576	{'accuracy': 0.888}
0.079	7.0	1750	0.9140	{'accuracy': 0.879}
0.0241	8.0	2000	0.9769	{'accuracy': 0.875}
0.0241	9.0	2250	0.9283	{'accuracy': 0.891}
0.0101	10.0	2500	0.9232	{'accuracy': 0.899}

Framework versions

• PEFT 0.12.0
• Transformers 4.42.4
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1