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: 0.9635
• Accuracy: {'accuracy': 0.888}

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	0.4712	{'accuracy': 0.855}
0.4347	2.0	500	0.4550	{'accuracy': 0.876}
0.4347	3.0	750	0.4948	{'accuracy': 0.885}
0.1809	4.0	1000	0.6488	{'accuracy': 0.885}
0.1809	5.0	1250	0.8407	{'accuracy': 0.888}
0.0747	6.0	1500	0.7641	{'accuracy': 0.892}
0.0747	7.0	1750	0.9308	{'accuracy': 0.888}
0.0174	8.0	2000	1.0031	{'accuracy': 0.885}
0.0174	9.0	2250	0.9573	{'accuracy': 0.885}
0.0067	10.0	2500	0.9635	{'accuracy': 0.888}

Framework versions

• PEFT 0.11.1
• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1