Modelpublic

damand2061/innermore-x-indobertweet-base-uncased

sourceHugging Faceapache-2.0updated 3y agoView on Hugging Face

0likes10downloads

Model Card

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:

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

More information needed

More information needed

The following hyperparameters were used during training:

—optimizer: {'name': 'AdamWeightDecay', 'learningrate': {'module': 'keras.optimizers.schedules', 'classname': 'PolynomialDecay', 'config': {'initiallearningrate': 0.0002, 'decaysteps': 420, 'endlearningrate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registeredname': None}, 'decay': 0.0, 'beta1': 0.9, 'beta2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weightdecayrate': 0.01}
—training_precision: float32

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