distilberto / README.md
HASAN55's picture
Training in progress epoch 3
f1f1341
metadata
license: apache-2.0
tags:
  - generated_from_keras_callback
model-index:
  - name: HASAN55/distilberto
    results: []

HASAN55/distilberto

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

  • Train Loss: 0.5621
  • Train End Logits Accuracy: 0.8351
  • Train Start Logits Accuracy: 0.8011
  • Validation Loss: 0.0
  • Validation End Logits Accuracy: 0.0
  • Validation Start Logits Accuracy: 0.0
  • Epoch: 3

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': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 24664, '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, 'weight_decay_rate': 0.01}
  • training_precision: mixed_float16

Training results

Train Loss Train End Logits Accuracy Train Start Logits Accuracy Validation Loss Validation End Logits Accuracy Validation Start Logits Accuracy Epoch
1.4589 0.6168 0.5825 0.0 0.0 0.0 0
0.9226 0.7424 0.7063 0.0 0.0 0.0 1
0.7011 0.7983 0.7638 0.0 0.0 0.0 2
0.5621 0.8351 0.8011 0.0 0.0 0.0 3

Framework versions

  • Transformers 4.27.4
  • TensorFlow 2.12.0
  • Datasets 2.11.0
  • Tokenizers 0.13.3