Ir para o conteúdo
ModelListadosExterno
Baixar

FoodEntityRecognition BioBERT Frozen Layers v4

This model is a fine-tuned version of dmis-lab/biobert-v1.1 on an unknown dataset. It achieves the following results on the evaluation set: Loss: 0.0042 Precision: 0.8063 Recall: 0.8747 F1: 0.8391 Accuracy: 0.9869

Fontehuggingface.co/fdastak/FoodEntityRecognition-BioBERT-frozen-layers-v4/tree/5285a6cfbdd8818ca79e19225bcc40b066ac3f83
TipoOtherModelo basedmis-lab/biobert-v1.1VersãoRevision 5285a6cBnota

Fonte do modelo

Tipo
Other
Tamanho do arquivo
411 MB
Modelo base
dmis-lab/biobert-v1.1
Versão
vRevision 5285a6c
Atualizado
3 de out. de 2026
Downloads
8
Fonte
Hugging Face

Descrição da fonte

FoodEntityRecognition-BioBERT-frozen-layers-v4

This model is a fine-tuned version of dmis-lab/biobert-v1.1 on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0042
  • Precision: 0.8063
  • Recall: 0.8747
  • F1: 0.8391
  • Accuracy: 0.9869

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: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 10
  • mixed_precision_training: Native AMP

Training results

Training LossEpochStepValidation LossPrecisionRecallF1Accuracy
0.04881.01170.00850.66300.76430.71010.9731
0.00862.02340.00580.70900.81740.75940.9785
0.00663.03510.00470.78470.82800.80580.9843
0.00564.04680.00460.81390.84500.82920.9853
0.00495.05850.00510.7250.86200.78760.9809
0.00436.07020.00410.82250.88540.85280.9876
0.00387.08190.00420.79610.86200.82770.9861
0.00358.09360.00420.80630.87470.83910.9869

Framework versions

  • Transformers 4.57.3
  • Pytorch 2.8.0+cpu
  • Datasets 4.0.0
  • Tokenizers 0.22.1

Fontes

1 fonte
Hugging FacePrimárioVersão 5285a6cfbdd8818ca79e19225bcc40b066ac3f83
huggingface.co/fdastak/FoodEntityRecognition-BioBERT-frozen-layers-v4/tree/5285a6cfbdd8818ca79e19225bcc40b066ac3f83

Verificado 3 de out.

Artefatos de modelo

1 artefato

model.safetensors

safetensors · 411 MB · SHA-256 a1b4c1f2b735…9ebc · Hugging Face

Baixar

Trechos de fonte

3 trechos
Readme17 de jul.huggingface.co/fdastak/FoodEntityRecognition-BioBERT-frozen-layers-v4

--- library_name: transformers base_model: dmis-lab/biobert-v1.1 tags: - generated_from_trainer metrics: - precision - recall - f1 - accuracy model-index: - name: FoodEntityRecognition-BioBERT-frozen-layers-v4 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # FoodEntityRecognition-BioBERT-frozen-layers-v4 This model is a fine-tuned version of [dmis-lab/biobert-v1.1](https://huggingface.co/dmis-lab/biobert-v1.1) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.0042 - Precision: 0.8063 - Recall: 0.8747 - F1: 0.8391 - Accuracy: 0.9869 ## 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: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 10 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| | 0.0488 | 1.0 | 117 | 0.0085 | 0.6630 | 0.7643 | 0.7101 | 0.9731 | | 0.0086 | 2.0 | 234 | 0.0058 | 0.7090 | 0.8174 | 0.7594 | 0.9785 | | 0.0066 | 3.0 | 351 | 0.0047 | 0.7847 | 0.8280 | 0.8058 | 0.9843 | | 0.0056 | 4.0 | 468 | 0.0046 | 0.8139 | 0.8450 | 0.8292 | 0.9853 | | 0.0049 | 5.0 | 585 | 0.0051 | 0.725 | 0.8620 | 0.7876 | 0.9809 | | 0.0043 | 6.0 | 702 | 0.0041 | 0.8225 | 0.8854 | 0.8528 | 0.9876 | | 0.0038 | 7.0 | 819 | 0.0042 | 0.7961 | 0.8620 | 0.8277 | 0.9861 | | 0.0035 | 8.0 | 936 | 0.0042 | 0.8063 | 0.8747 | 0.8391 | 0.9869 | ### Framework versions - Transformers 4.57.3 - Pytorch 2.8.0+cpu - Datasets 4.0.0 - Tokenizers 0.22.1

Note3 de out.huggingface.co/fdastak/FoodEntityRecognition-BioBERT-frozen-layers-v4

Source context: 8 downloads · 0 likes · Pipeline token-classification · Library transformers · Repo fdastak/FoodEntityRecognition-BioBERT-frozen-layers-v4

Note17 de jul.huggingface.co/fdastak/FoodEntityRecognition-BioBERT-frozen-layers-v4

Source context: 87 downloads · 0 likes · Pipeline token-classification · Library transformers · Repo fdastak/FoodEntityRecognition-BioBERT-frozen-layers-v4