basic_roberta / README.md
ayshi's picture
Training in progress epoch 5
7fed238
|
raw
history blame
2.07 kB
metadata
license: mit
base_model: ayshi/basic_roberta
tags:
  - generated_from_keras_callback
model-index:
  - name: ayshi/basic_roberta
    results: []

ayshi/basic_roberta

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

  • Train Loss: 0.1342
  • Validation Loss: 0.8232
  • Train Accuracy: 0.7733
  • Epoch: 5

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', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 960, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, '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
0.5675 0.8138 0.7556 0
0.4192 0.8947 0.76 1
0.3365 0.9022 0.7644 2
0.2620 0.9279 0.76 3
0.1945 0.9473 0.7644 4
0.1342 0.8232 0.7733 5

Framework versions

  • Transformers 4.34.0
  • TensorFlow 2.13.0
  • Datasets 2.14.5
  • Tokenizers 0.14.1