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: 1.1755
• Accuracy: {'accuracy': 0.87}

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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	250	0.6031	{'accuracy': 0.831}
0.3891	2.0	500	0.5601	{'accuracy': 0.838}
0.3891	3.0	750	0.7037	{'accuracy': 0.863}
0.1769	4.0	1000	0.7392	{'accuracy': 0.867}
0.1769	5.0	1250	1.0238	{'accuracy': 0.858}
0.0589	6.0	1500	1.0032	{'accuracy': 0.859}
0.0589	7.0	1750	1.1299	{'accuracy': 0.865}
0.0165	8.0	2000	1.2141	{'accuracy': 0.862}
0.0165	9.0	2250	1.1966	{'accuracy': 0.865}
0.0087	10.0	2500	1.1755	{'accuracy': 0.87}

Framework versions

• PEFT 0.14.0
• Transformers 4.48.3
• Pytorch 2.5.1+cu124
• Datasets 3.3.1
• Tokenizers 0.21.0