nhankins/yo_xlmroberta_lora_adapter_1.0

xlm-roberta-base-finetuned-yoruba-lora-text-classification

This model is a fine-tuned version of Davlan/xlm-roberta-base-finetuned-yoruba on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.5843
• Precision: 0.6850
• Recall: 1.0
• F1 and accuracy: {'accuracy': 0.6915167095115681, 'f1': 0.8130841121495327}

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	388	0.6314	0.6710	1.0	{'accuracy': 0.6709511568123393, 'f1': 0.8030769230769231}
0.6474	2.0	776	0.6289	0.6710	1.0	{'accuracy': 0.6709511568123393, 'f1': 0.8030769230769231}
0.652	3.0	1164	0.6270	0.6710	1.0	{'accuracy': 0.6709511568123393, 'f1': 0.8030769230769231}
0.646	4.0	1552	0.6235	0.6710	1.0	{'accuracy': 0.6709511568123393, 'f1': 0.8030769230769231}
0.646	5.0	1940	0.6188	0.6710	1.0	{'accuracy': 0.6709511568123393, 'f1': 0.8030769230769231}
0.6459	6.0	2328	0.6092	0.6710	1.0	{'accuracy': 0.6709511568123393, 'f1': 0.8030769230769231}
0.6281	7.0	2716	0.5958	0.6710	1.0	{'accuracy': 0.6709511568123393, 'f1': 0.8030769230769231}
0.6268	8.0	3104	0.5912	0.6727	1.0	{'accuracy': 0.6735218508997429, 'f1': 0.8043143297380586}
0.6268	9.0	3492	0.5861	0.6850	1.0	{'accuracy': 0.6915167095115681, 'f1': 0.8130841121495327}
0.6105	10.0	3880	0.5843	0.6850	1.0	{'accuracy': 0.6915167095115681, 'f1': 0.8130841121495327}

Framework versions

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