sentiment-base-1

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:

• Loss: 0.7908
• Accuracy: 0.9023
• Precision: 0.8875
• Recall: 0.8733
• F1: 0.8799

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:

• learning_rate: 5e-05
• train_batch_size: 30
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
0.3889	1.0	122	0.4200	0.8045	0.8255	0.6867	0.7110
0.2335	2.0	244	0.3136	0.8922	0.8644	0.8863	0.8739
0.1411	3.0	366	0.3569	0.8972	0.8781	0.8723	0.8751
0.1078	4.0	488	0.3537	0.9148	0.8923	0.9072	0.8992
0.0822	5.0	610	0.5069	0.8797	0.8795	0.8224	0.8439
0.0529	6.0	732	0.4262	0.9073	0.8862	0.8919	0.8890
0.0365	7.0	854	0.5586	0.8972	0.8743	0.8798	0.8770
0.033	8.0	976	0.5012	0.8947	0.8870	0.8530	0.8675
0.0248	9.0	1098	0.5833	0.8922	0.8873	0.8462	0.8631
0.0123	10.0	1220	0.6611	0.9023	0.8858	0.8758	0.8806
0.0088	11.0	1342	0.6936	0.8947	0.8847	0.8555	0.8682
0.0074	12.0	1464	0.6790	0.9023	0.8858	0.8758	0.8806
0.0141	13.0	1586	0.6981	0.8972	0.8830	0.8648	0.8731
0.0034	14.0	1708	0.7145	0.8972	0.8781	0.8723	0.8751
0.0059	15.0	1830	0.7304	0.8997	0.8871	0.8666	0.8759
0.0056	16.0	1952	0.7518	0.8997	0.8778	0.8816	0.8797
0.0039	17.0	2074	0.7390	0.9023	0.8893	0.8708	0.8793
0.004	18.0	2196	0.7641	0.9023	0.8875	0.8733	0.8799
0.007	19.0	2318	0.7848	0.9023	0.8875	0.8733	0.8799
0.0042	20.0	2440	0.7908	0.9023	0.8875	0.8733	0.8799

Framework versions

• Transformers 4.39.3
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.15.2