Hugging Face's logo

AntoineD
/
camembert_classification_tools

Text Classification
Transformers
PyTorch
camembert
Generated from Trainer
Inference Endpoints
Model card Files Community
camembert_classification_tools / README.md
AntoineD's picture
AntoineD
End of training
462abcd
preview code
|
raw
history blame
No virus
3.17 kB
metadata
license: mit
base_model: camembert-base
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: camembert_classification_tools
    results: []

camembert_classification_tools

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

  • Loss: 0.5829
  • Accuracy: 0.85

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: 24
  • eval_batch_size: 192
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 30

Training results

Training Loss Epoch Step Validation Loss Accuracy
No log 1.0 5 2.0695 0.225
No log 2.0 10 1.9801 0.35
No log 3.0 15 1.8056 0.425
No log 4.0 20 1.5897 0.7
No log 5.0 25 1.4156 0.75
No log 6.0 30 1.2836 0.7
No log 7.0 35 1.1515 0.775
No log 8.0 40 1.0282 0.775
No log 9.0 45 0.9576 0.775
No log 10.0 50 0.9092 0.775
No log 11.0 55 0.8485 0.775
No log 12.0 60 0.8174 0.8
No log 13.0 65 0.7209 0.85
No log 14.0 70 0.6694 0.825
No log 15.0 75 0.6861 0.85
No log 16.0 80 0.6568 0.85
No log 17.0 85 0.6391 0.85
No log 18.0 90 0.6134 0.825
No log 19.0 95 0.6149 0.8
No log 20.0 100 0.6222 0.825
No log 21.0 105 0.6155 0.825
No log 22.0 110 0.5882 0.825
No log 23.0 115 0.5737 0.85
No log 24.0 120 0.5858 0.85
No log 25.0 125 0.5933 0.825
No log 26.0 130 0.5870 0.85
No log 27.0 135 0.5859 0.85
No log 28.0 140 0.5840 0.85
No log 29.0 145 0.5832 0.85
No log 30.0 150 0.5829 0.85

Framework versions

  • Transformers 4.34.0
  • Pytorch 2.0.1+cu117
  • Datasets 2.14.5
  • Tokenizers 0.14.1