Edit model card

electra-base-ner-food-recipe

This model is a fine-tuned version of google/electra-base-discriminator on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1889
  • Precision: 0.7866
  • Recall: 0.8144
  • F1: 0.8003
  • Accuracy: 0.9558

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: 2e-06
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 15

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy
0.0216 2.66 2121 0.1672 0.7858 0.8183 0.8017 0.9575
0.0237 5.33 4242 0.1744 0.7842 0.8122 0.7980 0.9564
0.0281 7.99 6363 0.1793 0.7812 0.8148 0.7976 0.9558
0.0236 10.66 8484 0.1863 0.7923 0.8148 0.8034 0.9567
0.0246 13.32 10605 0.1881 0.7871 0.8170 0.8018 0.9561

Framework versions

  • Transformers 4.27.4
  • Pytorch 2.0.0+cu118
  • Datasets 2.11.0
  • Tokenizers 0.13.3
Downloads last month
9