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: 0.8872
• Accuracy: {'accuracy': 0.8908}

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: 20

Training results

Training Loss	Epoch	Step	Accuracy	Validation Loss
0.4558	1.0	1250	{'accuracy': 0.8712}	0.3897
0.4381	2.0	2500	{'accuracy': 0.8618}	0.4826
0.4148	3.0	3750	{'accuracy': 0.8706}	0.4758
0.3985	4.0	5000	{'accuracy': 0.8694}	0.4546
0.3799	5.0	6250	{'accuracy': 0.8636}	0.4727
0.4093	6.0	7500	{'accuracy': 0.8722}	0.5367
0.3878	7.0	8750	{'accuracy': 0.8726}	0.5077
0.3695	8.0	10000	{'accuracy': 0.8658}	0.5626
0.3351	9.0	11250	{'accuracy': 0.8658}	0.5772
0.3235	10.0	12500	{'accuracy': 0.8726}	0.6166
0.3306	11.0	13750	0.6393	{'accuracy': 0.8766}
0.2685	12.0	15000	0.7127	{'accuracy': 0.8806}
0.3045	13.0	16250	0.6702	{'accuracy': 0.8834}
0.2369	14.0	17500	0.7114	{'accuracy': 0.8808}
0.2066	15.0	18750	0.7414	{'accuracy': 0.8856}
0.1799	16.0	20000	0.7425	{'accuracy': 0.8896}
0.1256	17.0	21250	0.7796	{'accuracy': 0.888}
0.0998	18.0	22500	0.8461	{'accuracy': 0.8856}
0.0809	19.0	23750	0.8729	{'accuracy': 0.8898}
0.124	20.0	25000	0.8872	{'accuracy': 0.8908}

Framework versions

• PEFT 0.14.0
• Transformers 4.49.0
• Pytorch 2.6.0+cu124
• Datasets 3.3.2
• Tokenizers 0.21.0