svenbl80's picture
Training in progress epoch 9
4f82ef8
metadata
license: mit
tags:
  - generated_from_keras_callback
model-index:
  - name: svenbl80/roberta-base-finetuned-new-mnli-run-8
    results: []

svenbl80/roberta-base-finetuned-new-mnli-run-8

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

  • Train Loss: 0.0268
  • Validation Loss: 0.7096
  • Train Accuracy: 0.8620
  • 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
0.4621 0.3920 0.8564 0
0.3309 0.3669 0.8612 1
0.2495 0.3910 0.8651 2
0.1824 0.4444 0.8621 3
0.1339 0.4744 0.8636 4
0.0960 0.5237 0.8595 5
0.0692 0.5846 0.8586 6
0.0507 0.6444 0.8605 7
0.0360 0.6733 0.8612 8
0.0268 0.7096 0.8620 9

Framework versions

  • Transformers 4.28.0
  • TensorFlow 2.9.1
  • Datasets 2.15.0
  • Tokenizers 0.13.3