damand2061/innermore-x-indobertweet-base-uncased

This model is a fine-tuned version of indolem/indobertweet-base-uncased on Innermore-X dataset, an Indonesian NER Movie Reviews on X (Twitter). It achieves the following results on the evaluation set:

• Train Loss: 0.0062
• Validation Loss: 0.1791
• Validation Precision: 0.8073
• Validation Recall: 0.7652
• Validation F1: 0.7857
• Validation Accuracy: 0.9622
• Epoch: 14

Model description

This model is a fine-tuned version of indolem/indobertweet-base-uncased on Innermore-X dataset, an Indonesian NER Movie Reviews on X (Twitter).

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': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 0.0002, 'decay_steps': 420, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_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	Validation Precision	Validation Recall	Validation F1	Validation Accuracy	Epoch
0.8107	0.5161	0.1270	0.1348	0.1308	0.8446	0
0.4721	0.3254	0.3232	0.2304	0.2690	0.9003	1
0.3198	0.2431	0.4776	0.5087	0.4926	0.9211	2
0.1784	0.1581	0.6741	0.6565	0.6652	0.9497	3
0.1177	0.1304	0.7890	0.7478	0.7679	0.9627	4
0.0666	0.1428	0.7545	0.7348	0.7445	0.9598	5
0.0499	0.1526	0.7456	0.7391	0.7424	0.9584	6
0.0339	0.1677	0.7945	0.7565	0.7751	0.9627	7
0.0261	0.1598	0.6996	0.7087	0.7041	0.9540	8
0.0178	0.1792	0.7668	0.7435	0.7550	0.9598	9
0.0127	0.1943	0.8186	0.7261	0.7696	0.9593	10
0.0102	0.1825	0.7890	0.7478	0.7679	0.9598	11
0.0083	0.1765	0.8102	0.7609	0.7848	0.9622	12
0.0062	0.1778	0.8018	0.7565	0.7785	0.9618	13
0.0062	0.1791	0.8073	0.7652	0.7857	0.9622	14

Framework versions

• Transformers 4.38.2
• TensorFlow 2.15.0
• Tokenizers 0.15.2