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: 1.0099
• Accuracy: {'accuracy': 0.888}

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	0.3473	{'accuracy': 0.874}
0.4088	2.0	500	0.5087	{'accuracy': 0.873}
0.4088	3.0	750	0.6246	{'accuracy': 0.866}
0.2221	4.0	1000	0.7013	{'accuracy': 0.887}
0.2221	5.0	1250	0.7331	{'accuracy': 0.876}
0.1013	6.0	1500	0.8383	{'accuracy': 0.88}
0.1013	7.0	1750	0.8908	{'accuracy': 0.886}
0.0269	8.0	2000	1.0219	{'accuracy': 0.884}
0.0269	9.0	2250	1.0187	{'accuracy': 0.878}
0.0102	10.0	2500	1.0099	{'accuracy': 0.888}

Framework versions

• Transformers 4.35.0
• Pytorch 2.0.0
• Datasets 2.1.0
• Tokenizers 0.14.1