README.md

metadata

license: apache-2.0
base_model: michiyasunaga/BioLinkBERT-base
tags:
  - token-classification
  - generated_from_trainer
datasets:
  - Rodrigo1771/drugtemist-en-ner
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: output
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: Rodrigo1771/drugtemist-en-ner
          type: Rodrigo1771/drugtemist-en-ner
          config: DrugTEMIST English NER
          split: validation
          args: DrugTEMIST English NER
        metrics:
          - name: Precision
            type: precision
            value: 0.9139194139194139
          - name: Recall
            type: recall
            value: 0.9301025163094129
          - name: F1
            type: f1
            value: 0.9219399538106235
          - name: Accuracy
            type: accuracy
            value: 0.9985906845645076

output

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

• Loss: 0.0068
• Precision: 0.9139
• Recall: 0.9301
• F1: 0.9219
• Accuracy: 0.9986

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: 4
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• 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
0.0093	0.9997	1735	0.0096	0.9094	0.8705	0.8895	0.9982
0.0045	2.0	3471	0.0055	0.8789	0.9469	0.9116	0.9983
0.004	2.9997	5206	0.0071	0.8980	0.9189	0.9083	0.9985
0.0035	4.0	6942	0.0079	0.8373	0.9404	0.8859	0.9981
0.004	4.9997	8677	0.0071	0.9377	0.8984	0.9177	0.9985
0.0024	6.0	10413	0.0054	0.8922	0.9329	0.9121	0.9985
0.0014	6.9997	12148	0.0068	0.9139	0.9301	0.9219	0.9986
0.0012	8.0	13884	0.0073	0.9080	0.9292	0.9185	0.9986
0.0013	8.9997	15619	0.0067	0.9007	0.9301	0.9152	0.9986
0.0012	9.9971	17350	0.0069	0.9128	0.9273	0.9200	0.9986

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1