svenbl80's picture
Training in progress epoch 9
ea948d1
metadata
license: mit
tags:
  - generated_from_keras_callback
model-index:
  - name: svenbl80/roberta-base-finetuned-new-mnli-run-9
    results: []

svenbl80/roberta-base-finetuned-new-mnli-run-9

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: 0.7593
  • Train Accuracy: 0.8627
  • 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
0.4595 0.4097 0.8456 0
0.3288 0.3983 0.8531 1
0.2471 0.4441 0.8556 2
0.1807 0.4561 0.8596 3
0.1303 0.5280 0.8598 4
0.0932 0.5839 0.8555 5
0.0672 0.6134 0.8604 6
0.0484 0.6650 0.8589 7
0.0348 0.7089 0.8597 8
0.0252 0.7593 0.8627 9

Framework versions

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