CamembertQA3 / README.md
pandaIA's picture
Upload TFCamembertForQuestionAnswering
9f688ca
metadata
license: mit
tags:
  - generated_from_keras_callback
model-index:
  - name: CamembertQA3
    results: []

CamembertQA3

This model is a fine-tuned version of camembert-base on an unknown dataset. It achieves the following results on the evaluation set:

  • Train Loss: 1.3289
  • Train End Logits Accuracy: 0.7077
  • Train Start Logits Accuracy: 0.6139
  • Validation Loss: 1.6439
  • Validation End Logits Accuracy: 0.6508
  • Validation Start Logits Accuracy: 0.5665
  • Epoch: 1

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:

  • optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': 5e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
  • training_precision: float32

Training results

Train Loss Train End Logits Accuracy Train Start Logits Accuracy Validation Loss Validation End Logits Accuracy Validation Start Logits Accuracy Epoch
1.8724 0.5931 0.5097 1.6982 0.6436 0.5656 0
1.3289 0.7077 0.6139 1.6439 0.6508 0.5665 1

Framework versions

  • Transformers 4.30.2
  • TensorFlow 2.12.0
  • Datasets 2.13.1
  • Tokenizers 0.13.3