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: 0.8956
• Accuracy: {'accuracy': 0.886}

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	0.3099	{'accuracy': 0.898}
0.4169	2.0	500	0.5067	{'accuracy': 0.869}
0.4169	3.0	750	0.5110	{'accuracy': 0.895}
0.2113	4.0	1000	0.5795	{'accuracy': 0.891}
0.2113	5.0	1250	0.8179	{'accuracy': 0.875}
0.0677	6.0	1500	0.8340	{'accuracy': 0.878}
0.0677	7.0	1750	0.8819	{'accuracy': 0.879}
0.0289	8.0	2000	0.8894	{'accuracy': 0.877}
0.0289	9.0	2250	0.8759	{'accuracy': 0.887}
0.0047	10.0	2500	0.8956	{'accuracy': 0.886}

Framework versions

• Transformers 4.34.1
• Pytorch 2.1.0+cu118
• Datasets 2.14.5
• Tokenizers 0.14.1