gpt2-pos-neg-vibe

This model is a fine-tuned version of indonesian-nlp/gpt2-medium-indonesian on an unknown dataset. It achieves the following results on the evaluation set:

  • Train Loss: 2.5004
  • Epoch: 14

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: {'inner_optimizer': {'module': 'keras.optimizers', 'class_name': 'Adam', 'config': {'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': 5e-05, 'decay_steps': 375, '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-07, 'amsgrad': False}, 'registered_name': None}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
  • training_precision: mixed_float16

Training results

Train Loss Epoch
5.9419 0
3.7470 1
2.8806 2
2.4959 3
2.5001 4
2.5031 5
2.4947 6
2.4993 7
2.5025 8
2.4977 9
2.5018 10
2.4995 11
2.4963 12
2.5009 13
2.5004 14

Framework versions

  • Transformers 4.33.3
  • TensorFlow 2.13.0
  • Tokenizers 0.13.3
Downloads last month
9
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for pembelajarff/gpt2-pos-neg-vibe

Finetuned
(1)
this model