sentiment-pt-pl20-3

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: 0.2974
• Accuracy: 0.8847
• Precision: 0.8609
• Recall: 0.8609
• F1: 0.8609

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
0.551	1.0	122	0.5009	0.7243	0.6557	0.6074	0.6144
0.4528	2.0	244	0.4118	0.7820	0.7487	0.7857	0.7578
0.3588	3.0	366	0.3428	0.8521	0.8440	0.7854	0.8064
0.3192	4.0	488	0.3117	0.8546	0.8246	0.8246	0.8246
0.2714	5.0	610	0.3037	0.8672	0.8359	0.8560	0.8446
0.257	6.0	732	0.2833	0.8772	0.8592	0.8381	0.8475
0.2405	7.0	854	0.2861	0.8847	0.8599	0.8634	0.8616
0.2163	8.0	976	0.2954	0.8797	0.8539	0.8574	0.8556
0.2135	9.0	1098	0.2942	0.8747	0.8510	0.8438	0.8473
0.2001	10.0	1220	0.3002	0.8822	0.8656	0.8442	0.8537
0.1825	11.0	1342	0.3011	0.8922	0.8749	0.8612	0.8676
0.1765	12.0	1464	0.2858	0.8897	0.8695	0.8620	0.8656
0.1674	13.0	1586	0.2932	0.8947	0.8698	0.8805	0.8749
0.1597	14.0	1708	0.2937	0.8872	0.8599	0.8752	0.8669
0.1564	15.0	1830	0.2963	0.8947	0.8757	0.8680	0.8717
0.142	16.0	1952	0.3025	0.8922	0.8734	0.8637	0.8683
0.143	17.0	2074	0.2951	0.8897	0.8649	0.8720	0.8683
0.1315	18.0	2196	0.3013	0.8822	0.8574	0.8592	0.8583
0.1378	19.0	2318	0.3038	0.8872	0.8658	0.8602	0.8629
0.1333	20.0	2440	0.2974	0.8847	0.8609	0.8609	0.8609

Framework versions

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