roberta-finetuned-ner-en

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

• Loss: 0.0000
• Ategory B: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 325}
• Ategory I: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 325}
• Erson B: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 847}
• Erson I: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 847}
• Oc B: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 1648}
• Oc I: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 1648}
• Roduct B: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 361}
• Roduct I: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 361}
• Vent B: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 456}
• Vent I: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 645}
• Overall Precision: 1.0
• Overall Recall: 1.0
• Overall F1: 1.0
• Overall Accuracy: 1.0

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: 2e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Ategory B	Ategory I	Erson B	Erson I	Oc B	Oc I	Roduct B	Roduct I	Vent B	Vent I	Overall Precision	Overall Recall	Overall F1	Overall Accuracy
0.0343	1.0	1000	0.0036	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 325}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 325}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 847}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 847}	{'precision': 0.9969604863221885, 'recall': 0.9951456310679612, 'f1': 0.9960522320072881, 'number': 1648}	{'precision': 0.9951426836672739, 'recall': 0.9945388349514563, 'f1': 0.9948406676783005, 'number': 1648}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 361}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 361}	{'precision': 0.9978021978021978, 'recall': 0.9956140350877193, 'f1': 0.9967069154774972, 'number': 456}	{'precision': 1.0, 'recall': 0.9984496124031008, 'f1': 0.9992242048099302, 'number': 645}	0.9981	0.9973	0.9977	0.9992
0.0031	2.0	2000	0.0000	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 325}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 325}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 847}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 847}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 1648}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 1648}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 361}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 361}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 456}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 645}	1.0	1.0	1.0	1.0
0.0004	3.0	3000	0.0000	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 325}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 325}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 847}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 847}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 1648}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 1648}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 361}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 361}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 456}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 645}	1.0	1.0	1.0	1.0

Framework versions

• Transformers 4.47.0
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0