murat_chem_model

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: 0.0046
• Chemical: {'precision': 0.972939729397294, 'recall': 0.9850560398505604, 'f1-score': 0.9789603960396039, 'support': 803}
• Micro avg: {'precision': 0.972939729397294, 'recall': 0.9850560398505604, 'f1-score': 0.9789603960396039, 'support': 803}
• Macro avg: {'precision': 0.972939729397294, 'recall': 0.9850560398505604, 'f1-score': 0.9789603960396039, 'support': 803}
• Weighted avg: {'precision': 0.9729397293972939, 'recall': 0.9850560398505604, 'f1-score': 0.9789603960396039, 'support': 803}

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
0.0203	1.0	14139	0.0103	{'precision': 0.937424789410349, 'recall': 0.9701120797011208, 'f1-score': 0.9534883720930233, 'support': 803}	{'precision': 0.937424789410349, 'recall': 0.9701120797011208, 'f1-score': 0.9534883720930233, 'support': 803}	{'precision': 0.937424789410349, 'recall': 0.9701120797011208, 'f1-score': 0.9534883720930233, 'support': 803}	{'precision': 0.937424789410349, 'recall': 0.9701120797011208, 'f1-score': 0.9534883720930234, 'support': 803}
0.009	2.0	28278	0.0061	{'precision': 0.9585870889159561, 'recall': 0.9800747198007472, 'f1-score': 0.9692118226600985, 'support': 803}	{'precision': 0.9585870889159561, 'recall': 0.9800747198007472, 'f1-score': 0.9692118226600985, 'support': 803}	{'precision': 0.9585870889159561, 'recall': 0.9800747198007472, 'f1-score': 0.9692118226600985, 'support': 803}	{'precision': 0.9585870889159561, 'recall': 0.9800747198007472, 'f1-score': 0.9692118226600985, 'support': 803}
0.0024	3.0	42417	0.0046	{'precision': 0.972939729397294, 'recall': 0.9850560398505604, 'f1-score': 0.9789603960396039, 'support': 803}	{'precision': 0.972939729397294, 'recall': 0.9850560398505604, 'f1-score': 0.9789603960396039, 'support': 803}	{'precision': 0.972939729397294, 'recall': 0.9850560398505604, 'f1-score': 0.9789603960396039, 'support': 803}	{'precision': 0.9729397293972939, 'recall': 0.9850560398505604, 'f1-score': 0.9789603960396039, 'support': 803}

Framework versions

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