svenbl80's picture
Training in progress epoch 9
82d27d4
metadata
license: mit
tags:
  - generated_from_keras_callback
model-index:
  - name: svenbl80/roberta-base-finetuned-new-mnli-run-4
    results: []

svenbl80/roberta-base-finetuned-new-mnli-run-4

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: 0.0254
  • Validation Loss: 0.7597
  • Train Accuracy: 0.8592
  • 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
0.4543 0.3920 0.8526 0
0.3298 0.3979 0.8546 1
0.2478 0.4089 0.8603 2
0.1821 0.4577 0.8575 3
0.1309 0.4901 0.8556 4
0.0947 0.5514 0.8551 5
0.0682 0.6368 0.8553 6
0.0489 0.6589 0.8577 7
0.0343 0.7216 0.8599 8
0.0254 0.7597 0.8592 9

Framework versions

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