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: 0.9987
• Accuracy: {'accuracy': 0.885}

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	0.3276	{'accuracy': 0.882}
0.4241	2.0	500	0.3495	{'accuracy': 0.895}
0.4241	3.0	750	0.3984	{'accuracy': 0.891}
0.2107	4.0	1000	0.5830	{'accuracy': 0.886}
0.2107	5.0	1250	0.7312	{'accuracy': 0.878}
0.0707	6.0	1500	0.8286	{'accuracy': 0.89}
0.0707	7.0	1750	0.9673	{'accuracy': 0.881}
0.0208	8.0	2000	0.9845	{'accuracy': 0.885}
0.0208	9.0	2250	0.9831	{'accuracy': 0.884}
0.0119	10.0	2500	0.9987	{'accuracy': 0.885}

Framework versions

• PEFT 0.8.2
• Transformers 4.37.2
• Pytorch 2.2.0+cpu
• Datasets 2.17.0
• Tokenizers 0.15.1