svenbl80's picture
Training in progress epoch 9
94cf0c7
metadata
license: mit
tags:
  - generated_from_keras_callback
model-index:
  - name: svenbl80/roberta-base-finetuned-new-mnli-run-5
    results: []

svenbl80/roberta-base-finetuned-new-mnli-run-5

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: 0.0252
  • Validation Loss: 0.6904
  • Train Accuracy: 0.8664
  • 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
0.4561 0.3859 0.8565 0
0.3292 0.3796 0.8647 1
0.2467 0.3988 0.8592 2
0.1801 0.4358 0.8620 3
0.1309 0.4774 0.8631 4
0.0945 0.5281 0.8590 5
0.0682 0.5577 0.8659 6
0.0486 0.6420 0.8636 7
0.0348 0.6607 0.8688 8
0.0252 0.6904 0.8664 9

Framework versions

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