distilbert-base-uncased-lora-text-classification

This model is a fine-tuned version of distilbert-base-uncased on the shawhin/imdb-truncated dataset. It achieves the following results on the evaluation set:

• Loss: 1.1124
• Accuracy: {'accuracy': 0.873}

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	0.7531	{'accuracy': 0.822}
0.4366	2.0	500	0.5896	{'accuracy': 0.85}
0.4366	3.0	750	0.6032	{'accuracy': 0.891}
0.2163	4.0	1000	0.6212	{'accuracy': 0.892}
0.2163	5.0	1250	0.6968	{'accuracy': 0.882}
0.0917	6.0	1500	0.8690	{'accuracy': 0.886}
0.0917	7.0	1750	0.9716	{'accuracy': 0.875}
0.0131	8.0	2000	1.0623	{'accuracy': 0.877}
0.0131	9.0	2250	1.0750	{'accuracy': 0.874}
0.0043	10.0	2500	1.1124	{'accuracy': 0.873}

Framework versions

• PEFT 0.12.0
• Transformers 4.44.2
• Pytorch 2.4.1+cu118
• Datasets 2.21.0
• Tokenizers 0.19.1