murat_chem_model_extra_data

This model is a fine-tuned version of alvaroalon2/biobert_chemical_ner on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0089
• Chemical: {'precision': 0.9656699889258029, 'recall': 0.9688888888888889, 'f1-score': 0.9672767609539656, 'support': 900}
• Micro avg: {'precision': 0.9656699889258029, 'recall': 0.9688888888888889, 'f1-score': 0.9672767609539656, 'support': 900}
• Macro avg: {'precision': 0.9656699889258029, 'recall': 0.9688888888888889, 'f1-score': 0.9672767609539656, 'support': 900}
• Weighted avg: {'precision': 0.9656699889258028, 'recall': 0.9688888888888889, 'f1-score': 0.9672767609539658, 'support': 900}

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: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Chemical	Micro avg	Macro avg	Weighted avg
0.0266	1.0	16198	0.0113	{'precision': 0.9423503325942351, 'recall': 0.9444444444444444, 'f1-score': 0.9433962264150944, 'support': 900}	{'precision': 0.9423503325942351, 'recall': 0.9444444444444444, 'f1-score': 0.9433962264150944, 'support': 900}	{'precision': 0.9423503325942351, 'recall': 0.9444444444444444, 'f1-score': 0.9433962264150944, 'support': 900}	{'precision': 0.9423503325942351, 'recall': 0.9444444444444444, 'f1-score': 0.9433962264150944, 'support': 900}
0.0092	2.0	32396	0.0077	{'precision': 0.9679203539823009, 'recall': 0.9722222222222222, 'f1-score': 0.9700665188470067, 'support': 900}	{'precision': 0.9679203539823009, 'recall': 0.9722222222222222, 'f1-score': 0.9700665188470067, 'support': 900}	{'precision': 0.9679203539823009, 'recall': 0.9722222222222222, 'f1-score': 0.9700665188470067, 'support': 900}	{'precision': 0.9679203539823009, 'recall': 0.9722222222222222, 'f1-score': 0.9700665188470067, 'support': 900}
0.0051	3.0	48594	0.0089	{'precision': 0.9656699889258029, 'recall': 0.9688888888888889, 'f1-score': 0.9672767609539656, 'support': 900}	{'precision': 0.9656699889258029, 'recall': 0.9688888888888889, 'f1-score': 0.9672767609539656, 'support': 900}	{'precision': 0.9656699889258029, 'recall': 0.9688888888888889, 'f1-score': 0.9672767609539656, 'support': 900}	{'precision': 0.9656699889258028, 'recall': 0.9688888888888889, 'f1-score': 0.9672767609539658, 'support': 900}

Framework versions

• Transformers 4.44.2
• Pytorch 2.3.0+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1