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: 1.3518
• Accuracy: {'accuracy': 0.892}

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: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	250	0.5531	{'accuracy': 0.844}
0.4257	2.0	500	0.3913	{'accuracy': 0.888}
0.4257	3.0	750	0.6203	{'accuracy': 0.865}
0.2247	4.0	1000	0.6630	{'accuracy': 0.884}
0.2247	5.0	1250	0.8218	{'accuracy': 0.885}
0.0802	6.0	1500	0.9760	{'accuracy': 0.866}
0.0802	7.0	1750	0.9308	{'accuracy': 0.882}
0.0458	8.0	2000	1.0010	{'accuracy': 0.884}
0.0458	9.0	2250	1.2157	{'accuracy': 0.884}
0.0263	10.0	2500	1.2556	{'accuracy': 0.89}
0.0263	11.0	2750	1.0911	{'accuracy': 0.892}
0.0244	12.0	3000	1.2507	{'accuracy': 0.884}
0.0244	13.0	3250	1.3437	{'accuracy': 0.889}
0.0239	14.0	3500	1.1973	{'accuracy': 0.893}
0.0239	15.0	3750	1.1784	{'accuracy': 0.894}
0.0006	16.0	4000	1.2430	{'accuracy': 0.892}
0.0006	17.0	4250	1.3177	{'accuracy': 0.888}
0.0018	18.0	4500	1.3294	{'accuracy': 0.893}
0.0018	19.0	4750	1.3637	{'accuracy': 0.891}
0.0025	20.0	5000	1.3518	{'accuracy': 0.892}

Framework versions

• PEFT 0.10.0
• Transformers 4.38.2
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2