nhankins/zh_distilbert_lora_adapter_1.0

distilbert-base-multilingual-cased-lora-text-classification

This model is a fine-tuned version of distilbert/distilbert-base-multilingual-cased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.5474
• Precision: 0.7635
• Recall: 0.9338
• F1 and accuracy: {'accuracy': 0.7456359102244389, 'f1': 0.8401253918495297}

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: 1e-05
• 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	401	0.6017	0.7157	1.0	{'accuracy': 0.71571072319202, 'f1': 0.8343023255813953}
0.5798	2.0	802	0.5967	0.7157	1.0	{'accuracy': 0.71571072319202, 'f1': 0.8343023255813953}
0.5546	3.0	1203	0.5722	0.7157	1.0	{'accuracy': 0.71571072319202, 'f1': 0.8343023255813953}
0.5403	4.0	1604	0.5624	0.7259	0.9965	{'accuracy': 0.7281795511221946, 'f1': 0.8399412628487517}
0.5206	5.0	2005	0.5597	0.7368	0.9756	{'accuracy': 0.7331670822942643, 'f1': 0.8395802098950524}
0.5206	6.0	2406	0.5588	0.7520	0.9617	{'accuracy': 0.7456359102244389, 'f1': 0.8440366972477064}
0.5153	7.0	2807	0.5679	0.7554	0.9686	{'accuracy': 0.7531172069825436, 'f1': 0.8488549618320611}
0.4959	8.0	3208	0.5693	0.7576	0.9582	{'accuracy': 0.7506234413965087, 'f1': 0.8461538461538461}
0.4801	9.0	3609	0.5466	0.7635	0.9338	{'accuracy': 0.7456359102244389, 'f1': 0.8401253918495297}
0.4949	10.0	4010	0.5474	0.7635	0.9338	{'accuracy': 0.7456359102244389, 'f1': 0.8401253918495297}

Framework versions

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