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: 0.8460
• 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: 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	0.3866	{'accuracy': 0.88}
0.4059	2.0	500	0.4802	{'accuracy': 0.882}
0.4059	3.0	750	0.5185	{'accuracy': 0.883}
0.2343	4.0	1000	0.5356	{'accuracy': 0.884}
0.2343	5.0	1250	0.6939	{'accuracy': 0.891}
0.0849	6.0	1500	0.8226	{'accuracy': 0.882}
0.0849	7.0	1750	0.7980	{'accuracy': 0.887}
0.0183	8.0	2000	0.8676	{'accuracy': 0.889}
0.0183	9.0	2250	0.8728	{'accuracy': 0.897}
0.016	10.0	2500	0.8460	{'accuracy': 0.897}

Framework versions

• PEFT 0.7.1
• Transformers 4.37.1
• Pytorch 2.1.2
• Datasets 2.16.1
• Tokenizers 0.15.1