final_model / README.md
cruiser's picture
Training in progress epoch 10
37fd1cc
metadata
license: apache-2.0
tags:
  - generated_from_keras_callback
model-index:
  - name: cruiser/final_model
    results: []

cruiser/final_model

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

  • Train Loss: 0.0316
  • Validation Loss: 1.1405
  • Train Accuracy: 0.7835
  • Epoch: 10

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': {'class_name': 'WarmUp', 'config': {'initial_learning_rate': 1e-05, 'decay_schedule_fn': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 1e-05, 'decay_steps': 34090, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'passive_serialization': True}, 'warmup_steps': 250, 'power': 1.0, '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
0.6358 0.5405 0.7821 0
0.4380 0.5118 0.7844 1
0.3382 0.5437 0.7960 2
0.2327 0.6227 0.7878 3
0.1581 0.7234 0.7795 4
0.1104 0.8340 0.7832 5
0.0826 0.8824 0.7778 6
0.0608 1.0342 0.7827 7
0.0456 1.0815 0.7818 8
0.0396 1.0829 0.7852 9
0.0316 1.1405 0.7835 10

Framework versions

  • Transformers 4.27.4
  • TensorFlow 2.11.0
  • Datasets 2.1.0
  • Tokenizers 0.13.2