bert-ner-essays-label_span

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

• Loss: 0.8463
• Claim: {'precision': 0.4140127388535032, 'recall': 0.4513888888888889, 'f1-score': 0.4318936877076412, 'support': 144.0}
• Majorclaim: {'precision': 0.6923076923076923, 'recall': 0.5, 'f1-score': 0.5806451612903226, 'support': 72.0}
• Premise: {'precision': 0.8025, 'recall': 0.816793893129771, 'f1-score': 0.8095838587641867, 'support': 393.0}
• Accuracy: 0.6929
• Macro avg: {'precision': 0.6362734770537318, 'recall': 0.5893942606728867, 'f1-score': 0.6073742359207168, 'support': 609.0}
• Weighted avg: {'precision': 0.6976132811840038, 'recall': 0.6929392446633826, 'f1-score': 0.6932111644287832, '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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Claim	Majorclaim	Premise	Accuracy	Macro avg	Weighted avg
0.7343	1.0	533	0.6230	{'precision': 0.47058823529411764, 'recall': 0.2777777777777778, 'f1-score': 0.3493449781659389, 'support': 144.0}	{'precision': 0.5647058823529412, 'recall': 0.6666666666666666, 'f1-score': 0.6114649681528662, 'support': 72.0}	{'precision': 0.7790432801822323, 'recall': 0.8702290076335878, 'f1-score': 0.8221153846153846, 'support': 393.0}	0.7061	{'precision': 0.6047791326097637, 'recall': 0.6048911506926774, 'f1-score': 0.5943084436447299, 'support': 609.0}	{'precision': 0.6807677151451265, 'recall': 0.7060755336617406, 'f1-score': 0.6854228254790602, 'support': 609.0}
0.5313	2.0	1066	0.6606	{'precision': 0.4491525423728814, 'recall': 0.3680555555555556, 'f1-score': 0.4045801526717558, 'support': 144.0}	{'precision': 0.6612903225806451, 'recall': 0.5694444444444444, 'f1-score': 0.6119402985074627, 'support': 72.0}	{'precision': 0.7878787878787878, 'recall': 0.8600508905852418, 'f1-score': 0.8223844282238443, 'support': 393.0}	0.7094	{'precision': 0.6327738842774381, 'recall': 0.5991836301950806, 'f1-score': 0.6129682931343542, 'support': 609.0}	{'precision': 0.6928197585613547, 'recall': 0.7093596059113301, 'f1-score': 0.6987131753189507, 'support': 609.0}
0.3551	3.0	1599	0.8463	{'precision': 0.4140127388535032, 'recall': 0.4513888888888889, 'f1-score': 0.4318936877076412, 'support': 144.0}	{'precision': 0.6923076923076923, 'recall': 0.5, 'f1-score': 0.5806451612903226, 'support': 72.0}	{'precision': 0.8025, 'recall': 0.816793893129771, 'f1-score': 0.8095838587641867, 'support': 393.0}	0.6929	{'precision': 0.6362734770537318, 'recall': 0.5893942606728867, 'f1-score': 0.6073742359207168, 'support': 609.0}	{'precision': 0.6976132811840038, 'recall': 0.6929392446633826, 'f1-score': 0.6932111644287832, 'support': 609.0}

Framework versions

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