bert-ner-essays-classify_span

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

• Loss: 0.6785
• Claim: {'precision': 0.47368421052631576, 'recall': 0.375, 'f1-score': 0.4186046511627907, 'support': 144.0}
• Majorclaim: {'precision': 0.6923076923076923, 'recall': 0.5, 'f1-score': 0.5806451612903226, 'support': 72.0}
• Premise: {'precision': 0.7900677200902935, 'recall': 0.8905852417302799, 'f1-score': 0.8373205741626795, 'support': 393.0}
• Accuracy: 0.7225
• Macro avg: {'precision': 0.6520198743081005, 'recall': 0.5885284139100934, 'f1-score': 0.6121901288719309, 'support': 609.0}
• Weighted avg: {'precision': 0.7036999904062868, 'recall': 0.722495894909688, 'f1-score': 0.707967991832969, 'support': 609.0}

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Claim	Majorclaim	Premise	Accuracy	Macro avg	Weighted avg
No log	1.0	267	0.7119	{'precision': 0.5072463768115942, 'recall': 0.24305555555555555, 'f1-score': 0.32863849765258213, 'support': 144.0}	{'precision': 0.5753424657534246, 'recall': 0.5833333333333334, 'f1-score': 0.5793103448275863, 'support': 72.0}	{'precision': 0.7687366167023555, 'recall': 0.9134860050890585, 'f1-score': 0.8348837209302326, 'support': 393.0}	0.7159	{'precision': 0.6171084864224582, 'recall': 0.5799582979926492, 'f1-score': 0.580944187803467, 'support': 609.0}	{'precision': 0.6840420790790506, 'recall': 0.715927750410509, 'f1-score': 0.6849648453450565, 'support': 609.0}
0.7298	2.0	534	0.6785	{'precision': 0.47368421052631576, 'recall': 0.375, 'f1-score': 0.4186046511627907, 'support': 144.0}	{'precision': 0.6923076923076923, 'recall': 0.5, 'f1-score': 0.5806451612903226, 'support': 72.0}	{'precision': 0.7900677200902935, 'recall': 0.8905852417302799, 'f1-score': 0.8373205741626795, 'support': 393.0}	0.7225	{'precision': 0.6520198743081005, 'recall': 0.5885284139100934, 'f1-score': 0.6121901288719309, 'support': 609.0}	{'precision': 0.7036999904062868, 'recall': 0.722495894909688, 'f1-score': 0.707967991832969, 'support': 609.0}

Framework versions

• Transformers 4.37.1
• Pytorch 2.1.2+cu121
• Datasets 2.16.1
• Tokenizers 0.15.1