nhankins/en_euph_distilbert_lora_final

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: 0.5041
• Precision: 0.7846
• Recall: 0.9075
• F1 and accuracy: {'accuracy': 0.7544757033248082, 'f1': 0.8415841584158416}

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	391	0.5886	0.7187	1.0	{'accuracy': 0.7186700767263428, 'f1': 0.8363095238095238}
0.6142	2.0	782	0.5735	0.7187	1.0	{'accuracy': 0.7186700767263428, 'f1': 0.8363095238095238}
0.5823	3.0	1173	0.5369	0.7321	0.9822	{'accuracy': 0.7289002557544757, 'f1': 0.838905775075988}
0.5451	4.0	1564	0.5190	0.7486	0.9537	{'accuracy': 0.7365728900255755, 'f1': 0.8388106416275432}
0.5451	5.0	1955	0.5266	0.7542	0.9609	{'accuracy': 0.7468030690537084, 'f1': 0.8450704225352114}
0.5161	6.0	2346	0.5047	0.7731	0.9217	{'accuracy': 0.7493606138107417, 'f1': 0.8409090909090909}
0.5093	7.0	2737	0.5046	0.7761	0.9253	{'accuracy': 0.7544757033248082, 'f1': 0.8441558441558441}
0.4962	8.0	3128	0.5047	0.7774	0.9075	{'accuracy': 0.7468030690537084, 'f1': 0.8374384236453202}
0.4996	9.0	3519	0.5024	0.7937	0.8897	{'accuracy': 0.7544757033248082, 'f1': 0.8389261744966443}
0.4996	10.0	3910	0.5041	0.7846	0.9075	{'accuracy': 0.7544757033248082, 'f1': 0.8415841584158416}

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.17.0
• Tokenizers 0.15.2