svenbl80's picture
Training in progress epoch 9
724b96d
metadata
license: mit
base_model: xlnet-base-cased
tags:
  - generated_from_keras_callback
model-index:
  - name: svenbl80/xlnet-base-cased-finetuned-mnli
    results: []

svenbl80/xlnet-base-cased-finetuned-mnli

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

  • Train Loss: 0.0221
  • Validation Loss: 0.7391
  • Train Accuracy: 0.8677
  • Epoch: 9

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', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 245430, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
  • training_precision: float32

Training results

Train Loss Validation Loss Train Accuracy Epoch
0.4828 0.4066 0.8426 0
0.3364 0.3842 0.8598 1
0.2419 0.3913 0.8672 2
0.1713 0.4653 0.8624 3
0.1212 0.5090 0.8625 4
0.0857 0.5733 0.8684 5
0.0620 0.6176 0.8635 6
0.0435 0.6781 0.8670 7
0.0309 0.7102 0.8668 8
0.0221 0.7391 0.8677 9

Framework versions

  • Transformers 4.35.2
  • TensorFlow 2.9.1
  • Datasets 2.15.0
  • Tokenizers 0.15.0