output

This model is a fine-tuned version of michiyasunaga/BioLinkBERT-large on the Rodrigo1771/drugtemist-en-ner dataset. It achieves the following results on the evaluation set:

• Loss: 0.0549
• Precision: 0.0
• Recall: 0.0
• F1: 0.0
• Accuracy: 0.9911

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
• num_epochs: 10.0

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.0621	0.9994	867	0.0549	0.0	0.0	0.0	0.9911
0.0564	2.0	1735	0.0548	0.0	0.0	0.0	0.9911
0.054	2.9994	2602	0.0551	0.0	0.0	0.0	0.9911
0.0578	4.0	3470	0.0549	0.0	0.0	0.0	0.9911
0.0529	4.9994	4337	0.0549	0.0	0.0	0.0	0.9911
0.0551	6.0	5205	0.0549	0.0	0.0	0.0	0.9911
0.0553	6.9994	6072	0.0553	0.0	0.0	0.0	0.9911
0.056	8.0	6940	0.0548	0.0	0.0	0.0	0.9911
0.0549	8.9994	7807	0.0548	0.0	0.0	0.0	0.9911
0.0542	9.9942	8670	0.0549	0.0	0.0	0.0	0.9911

Framework versions

• Transformers 4.40.2
• Pytorch 2.2.1+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1