apwic's picture
Training in progress epoch 24
34e803b
|
raw
history blame
3.04 kB
metadata
license: mit
base_model: indolem/indobert-base-uncased
tags:
  - generated_from_keras_callback
model-index:
  - name: apwic/indobert-base-uncased-finetuned-nergrit
    results: []

apwic/indobert-base-uncased-finetuned-nergrit

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

  • Train Loss: 0.1167
  • Validation Loss: 0.1784
  • Train Accuracy: 0.9483
  • Epoch: 24

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': 2352, '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: float32

Training results

Train Loss Validation Loss Train Accuracy Epoch
0.4507 0.1933 0.9437 0
0.1708 0.1795 0.9471 1
0.1295 0.1784 0.9483 2
0.1169 0.1784 0.9483 3
0.1172 0.1784 0.9483 4
0.1180 0.1784 0.9483 5
0.1176 0.1784 0.9483 6
0.1172 0.1784 0.9483 7
0.1168 0.1784 0.9483 8
0.1174 0.1784 0.9483 9
0.1174 0.1784 0.9483 10
0.1178 0.1784 0.9483 11
0.1175 0.1784 0.9483 12
0.1175 0.1784 0.9483 13
0.1179 0.1784 0.9483 14
0.1176 0.1784 0.9483 15
0.1165 0.1784 0.9483 16
0.1179 0.1784 0.9483 17
0.1169 0.1784 0.9483 18
0.1170 0.1784 0.9483 19
0.1175 0.1784 0.9483 20
0.1177 0.1784 0.9483 21
0.1161 0.1784 0.9483 22
0.1174 0.1784 0.9483 23
0.1167 0.1784 0.9483 24

Framework versions

  • Transformers 4.33.0
  • TensorFlow 2.12.0
  • Datasets 2.14.6
  • Tokenizers 0.13.3