freyagracia/distilbert-base-uncased-finetuned-tweet_pemilu_2

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

• Train Loss: 2.3796
• Validation Loss: 2.3447
• 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': -937, '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
4.8444	4.5973	0
4.5323	4.3017	1
4.2944	4.0347	2
4.0319	3.8860	3
3.8297	3.6184	4
3.5679	3.4363	5
3.4085	3.2184	6
3.2081	3.1093	7
3.0778	2.9026	8
2.9089	2.7794	9
2.8247	2.6472	10
2.6888	2.6064	11
2.6255	2.5352	12
2.4976	2.4881	13
2.4868	2.3892	14
2.4120	2.3527	15
2.3771	2.3493	16
2.3609	2.3212	17
2.3714	2.3579	18
2.3796	2.3447	19

Framework versions

• Transformers 4.35.2
• TensorFlow 2.15.0
• Datasets 2.16.0
• Tokenizers 0.15.0