nhankins/es_xlmroberta_lora_adapter_1.0

xlm-roberta-large-lora-text-classification

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

• Loss: 0.6343
• Precision: 0.6371
• Recall: 0.9958
• F1 and accuracy: {'accuracy': 0.6353887399463807, 'f1': 0.7770491803278688}

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	372	0.6553	0.6381	1.0	{'accuracy': 0.6380697050938338, 'f1': 0.779050736497545}
0.6758	2.0	744	0.6534	0.6381	1.0	{'accuracy': 0.6380697050938338, 'f1': 0.779050736497545}
0.6765	3.0	1116	0.6518	0.6381	1.0	{'accuracy': 0.6380697050938338, 'f1': 0.779050736497545}
0.6765	4.0	1488	0.6519	0.6381	1.0	{'accuracy': 0.6380697050938338, 'f1': 0.779050736497545}
0.6722	5.0	1860	0.6470	0.6381	1.0	{'accuracy': 0.6380697050938338, 'f1': 0.779050736497545}
0.6654	6.0	2232	0.6425	0.6381	1.0	{'accuracy': 0.6380697050938338, 'f1': 0.779050736497545}
0.6626	7.0	2604	0.6419	0.6381	1.0	{'accuracy': 0.6380697050938338, 'f1': 0.779050736497545}
0.6626	8.0	2976	0.6404	0.6371	0.9958	{'accuracy': 0.6353887399463807, 'f1': 0.7770491803278688}
0.6547	9.0	3348	0.6356	0.6381	1.0	{'accuracy': 0.6380697050938338, 'f1': 0.779050736497545}
0.6544	10.0	3720	0.6343	0.6371	0.9958	{'accuracy': 0.6353887399463807, 'f1': 0.7770491803278688}

Framework versions

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