peft-adapter-jul / README.md
fgiauna's picture
update model card README.md
84801e2
metadata
license: mit
tags:
  - generated_from_trainer
model-index:
  - name: peft-adapter-jul
    results: []

peft-adapter-jul

This model is a fine-tuned version of Jean-Baptiste/camembert-ner on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0858
  • Loc: {'precision': 0.6808510638297872, 'recall': 0.7407407407407407, 'f1': 0.7095343680709535, 'number': 216}
  • Misc: {'precision': 0.5416666666666666, 'recall': 0.325, 'f1': 0.40624999999999994, 'number': 40}
  • Org: {'precision': 0.75, 'recall': 0.81, 'f1': 0.7788461538461539, 'number': 200}
  • Per: {'precision': 0.7989130434782609, 'recall': 0.75, 'f1': 0.7736842105263159, 'number': 196}
  • Overall Precision: 0.7314
  • Overall Recall: 0.7393
  • Overall F1: 0.7353
  • Overall Accuracy: 0.9799

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: 0.0001
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 10

Training results

Framework versions

  • Transformers 4.26.1
  • Pytorch 2.0.0+cu118
  • Datasets 2.12.0
  • Tokenizers 0.13.3