murat_chem_model_extra_data_3epochlr5e8

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: 0.0524
• Chemical: {'precision': 0.7696030977734754, 'recall': 0.8229813664596274, 'f1-score': 0.7953976988494248, 'support': 966}
• Micro avg: {'precision': 0.7696030977734754, 'recall': 0.8229813664596274, 'f1-score': 0.7953976988494248, 'support': 966}
• Macro avg: {'precision': 0.7696030977734754, 'recall': 0.8229813664596274, 'f1-score': 0.7953976988494248, 'support': 966}
• Weighted avg: {'precision': 0.7696030977734754, 'recall': 0.8229813664596274, 'f1-score': 0.7953976988494248, 'support': 966}

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-08
• 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
0.1661	1.0	16198	0.0916	{'precision': 0.757026291931097, 'recall': 0.8643892339544513, 'f1-score': 0.8071532141130981, 'support': 966}	{'precision': 0.757026291931097, 'recall': 0.8643892339544513, 'f1-score': 0.8071532141130981, 'support': 966}	{'precision': 0.757026291931097, 'recall': 0.8643892339544513, 'f1-score': 0.8071532141130981, 'support': 966}	{'precision': 0.757026291931097, 'recall': 0.8643892339544513, 'f1-score': 0.8071532141130981, 'support': 966}
0.0663	2.0	32396	0.0570	{'precision': 0.7653846153846153, 'recall': 0.8240165631469979, 'f1-score': 0.7936191425722832, 'support': 966}	{'precision': 0.7653846153846153, 'recall': 0.8240165631469979, 'f1-score': 0.7936191425722832, 'support': 966}	{'precision': 0.7653846153846153, 'recall': 0.8240165631469979, 'f1-score': 0.7936191425722832, 'support': 966}	{'precision': 0.7653846153846153, 'recall': 0.8240165631469979, 'f1-score': 0.7936191425722832, 'support': 966}
0.0564	3.0	48594	0.0524	{'precision': 0.7696030977734754, 'recall': 0.8229813664596274, 'f1-score': 0.7953976988494248, 'support': 966}	{'precision': 0.7696030977734754, 'recall': 0.8229813664596274, 'f1-score': 0.7953976988494248, 'support': 966}	{'precision': 0.7696030977734754, 'recall': 0.8229813664596274, 'f1-score': 0.7953976988494248, 'support': 966}	{'precision': 0.7696030977734754, 'recall': 0.8229813664596274, 'f1-score': 0.7953976988494248, 'support': 966}

Framework versions

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