Hugging Face's logo

Rodrigo1771
/
BioLinkBERT-base-drugtemist-en-fasttext-8-ner

Token Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
Edit model card

output

This model is a fine-tuned version of michiyasunaga/BioLinkBERT-base on the Rodrigo1771/drugtemist-en-fasttext-8-ner dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0080
  • Precision: 0.9272
  • Recall: 0.9376
  • F1: 0.9323
  • Accuracy: 0.9987

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: 32
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 64
  • 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
No log 0.9990 481 0.0042 0.9173 0.9413 0.9292 0.9987
0.0156 2.0 963 0.0049 0.9134 0.9245 0.9189 0.9986
0.0039 2.9990 1444 0.0053 0.8914 0.9487 0.9192 0.9986
0.0024 4.0 1926 0.0061 0.8820 0.9543 0.9167 0.9985
0.0017 4.9990 2407 0.0074 0.9199 0.9310 0.9254 0.9986
0.0011 6.0 2889 0.0079 0.9170 0.9366 0.9267 0.9986
0.0007 6.9990 3370 0.0067 0.9092 0.9422 0.9254 0.9987
0.0005 8.0 3852 0.0073 0.9249 0.9301 0.9275 0.9987
0.0004 8.9990 4333 0.0080 0.9272 0.9376 0.9323 0.9987
0.0002 9.9896 4810 0.0079 0.9247 0.9385 0.9315 0.9987

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu121
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
6
Safetensors
Model size
108M params
Tensor type
F32
·
Inference Examples
Token Classification
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for Rodrigo1771/BioLinkBERT-base-drugtemist-en-fasttext-8-ner

Base model

michiyasunaga/BioLinkBERT-base
Finetuned
(12)
this model

Dataset used to train Rodrigo1771/BioLinkBERT-base-drugtemist-en-fasttext-8-ner

Evaluation results

View on Papers With Code