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: 1.0084
• 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	0.3984	{'accuracy': 0.876}
0.427	2.0	500	0.4450	{'accuracy': 0.872}
0.427	3.0	750	0.5137	{'accuracy': 0.894}
0.2043	4.0	1000	0.7553	{'accuracy': 0.876}
0.2043	5.0	1250	0.8029	{'accuracy': 0.892}
0.0737	6.0	1500	0.8049	{'accuracy': 0.884}
0.0737	7.0	1750	0.9252	{'accuracy': 0.888}
0.0225	8.0	2000	0.9358	{'accuracy': 0.892}
0.0225	9.0	2250	0.9769	{'accuracy': 0.889}
0.0027	10.0	2500	1.0084	{'accuracy': 0.885}

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.15.0
• Tokenizers 0.15.0