NLP_projet / README.md
clairedhx's picture
End of training
7f2f31c verified
metadata
license: mit
base_model: almanach/camembert-base
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: NLP_projet
    results: []

NLP_projet

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

  • Loss: 0.5036
  • Precision: 0.9590
  • Recall: 0.9634
  • F1: 0.9612
  • Accuracy: 0.9636

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-05
  • 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: 2

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy
1.7382 1.0 955 0.7058 0.9442 0.9551 0.9496 0.9554
0.6625 2.0 1910 0.5036 0.9590 0.9634 0.9612 0.9636

Framework versions

  • Transformers 4.39.3
  • Pytorch 2.2.2+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2