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: 1.0851
• Accuracy: {'accuracy': 0.883}

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	0.5877	{'accuracy': 0.832}
0.4308	2.0	500	0.4432	{'accuracy': 0.885}
0.4308	3.0	750	0.6005	{'accuracy': 0.872}
0.1638	4.0	1000	0.6922	{'accuracy': 0.88}
0.1638	5.0	1250	0.8969	{'accuracy': 0.884}
0.0465	6.0	1500	0.9943	{'accuracy': 0.877}
0.0465	7.0	1750	1.1570	{'accuracy': 0.878}
0.0117	8.0	2000	1.1183	{'accuracy': 0.885}
0.0117	9.0	2250	1.1008	{'accuracy': 0.883}
0.0102	10.0	2500	1.0851	{'accuracy': 0.883}

Framework versions

• PEFT 0.11.1
• Transformers 4.42.3
• Pytorch 2.3.1+rocm6.0
• Datasets 2.20.0
• Tokenizers 0.19.1