YSKartal's picture
Training in progress epoch 3
3c2f8ad
|
raw
history blame
1.9 kB
metadata
tags:
  - generated_from_keras_callback
model-index:
  - name: YSKartal/bertweet-base-finetuned-2-ref_disam
    results: []

YSKartal/bertweet-base-finetuned-2-ref_disam

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

  • Train Loss: 5.0043
  • Validation Loss: 6.1571
  • Train Accuracy: 0.0468
  • 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': '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': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 16308, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, '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
6.2549 6.7603 0.0191 0
5.7374 6.4441 0.0316 1
5.3233 6.2700 0.0428 2
5.0043 6.1571 0.0468 3

Framework versions

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