nhankins/en_distil_lora_adapter_1.0

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: 1.3834
• Precision: 0.8310
• Recall: 0.8708
• F1 and accuracy: {'accuracy': 0.7877237851662404, 'f1': 0.8504504504504504}

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	Precision	Recall	F1 and accuracy
No log	1.0	391	0.5803	0.7346	0.9705	{'accuracy': 0.7365728900255755, 'f1': 0.836248012718601}
0.5606	2.0	782	0.5085	0.8259	0.8229	{'accuracy': 0.7570332480818415, 'f1': 0.8243992606284658}
0.4687	3.0	1173	0.6925	0.8007	0.8745	{'accuracy': 0.7621483375959079, 'f1': 0.8359788359788359}
0.3603	4.0	1564	0.8182	0.7955	0.9188	{'accuracy': 0.7800511508951407, 'f1': 0.8527397260273973}
0.3603	5.0	1955	0.8375	0.8413	0.8413	{'accuracy': 0.7800511508951407, 'f1': 0.8413284132841329}
0.2736	6.0	2346	1.0186	0.8235	0.8782	{'accuracy': 0.7851662404092071, 'f1': 0.8500000000000001}
0.1993	7.0	2737	1.1566	0.8224	0.9225	{'accuracy': 0.8081841432225064, 'f1': 0.8695652173913043}
0.1491	8.0	3128	1.2136	0.8502	0.8376	{'accuracy': 0.7851662404092071, 'f1': 0.8438661710037174}
0.1224	9.0	3519	1.3815	0.8231	0.8930	{'accuracy': 0.7928388746803069, 'f1': 0.8566371681415929}
0.1224	10.0	3910	1.3834	0.8310	0.8708	{'accuracy': 0.7877237851662404, 'f1': 0.8504504504504504}

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.17.0
• Tokenizers 0.15.1