distilbert-base-uncased-lora-text-classification

This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2719
• Accuracy: {'accuracy': 0.9169444444444445}

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: 2e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.676	1.0	1050	0.5094	{'accuracy': 0.8197222222222222}
0.4394	2.0	2100	0.3866	{'accuracy': 0.8675}
0.3705	3.0	3150	0.3472	{'accuracy': 0.8822222222222222}
0.3458	4.0	4200	0.3141	{'accuracy': 0.8908333333333334}
0.3287	5.0	5250	0.3063	{'accuracy': 0.8977777777777778}
0.2942	6.0	6300	0.2930	{'accuracy': 0.9033333333333333}
0.2735	7.0	7350	0.2864	{'accuracy': 0.9091666666666667}
0.2856	8.0	8400	0.2797	{'accuracy': 0.9122222222222223}
0.2826	9.0	9450	0.2800	{'accuracy': 0.9113888888888889}
0.2728	10.0	10500	0.2731	{'accuracy': 0.9147222222222222}
0.2674	11.0	11550	0.2763	{'accuracy': 0.9136111111111112}
0.2454	12.0	12600	0.2742	{'accuracy': 0.915}
0.2661	13.0	13650	0.2716	{'accuracy': 0.9177777777777778}
0.2704	14.0	14700	0.2721	{'accuracy': 0.9172222222222223}
0.2735	15.0	15750	0.2719	{'accuracy': 0.9169444444444445}

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0