racheilla/indobertweet-base-uncased-finetuned-pemilu

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

• Train Loss: 4.0475
• Validation Loss: 3.8312
• Epoch: 19

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': {'module': 'transformers.optimization_tf', 'class_name': 'WarmUp', 'config': {'initial_learning_rate': 2e-05, 'decay_schedule_fn': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': -957, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'warmup_steps': 1000, 'power': 1.0, 'name': None}, 'registered_name': 'WarmUp'}, '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	Validation Loss	Epoch
6.5041	6.0066	0
6.1286	5.6638	1
5.8608	5.3912	2
5.7038	5.1285	3
5.4613	4.9963	4
5.3015	4.8188	5
5.1496	4.6837	6
4.9652	4.6265	7
4.8800	4.4863	8
4.7938	4.3898	9
4.7163	4.3376	10
4.5680	4.1990	11
4.5108	4.1732	12
4.4189	4.0172	13
4.3261	4.0899	14
4.2851	4.0001	15
4.2012	3.9487	16
4.1282	3.9110	17
4.1267	3.9193	18
4.0475	3.8312	19

Framework versions

• Transformers 4.35.2
• TensorFlow 2.15.0
• Datasets 2.15.0
• Tokenizers 0.15.0