sentiment-pt-pl5-2

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: 0.3095
• Accuracy: 0.8922
• Precision: 0.8719
• Recall: 0.8662
• F1: 0.8690

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
0.5475	1.0	122	0.5044	0.7368	0.6773	0.6563	0.6638
0.4491	2.0	244	0.4095	0.8020	0.7739	0.8199	0.7830
0.3488	3.0	366	0.3513	0.8396	0.8413	0.7565	0.7821
0.2997	4.0	488	0.3080	0.8722	0.8702	0.8121	0.8337
0.28	5.0	610	0.2876	0.8747	0.8499	0.8463	0.8481
0.2586	6.0	732	0.2767	0.8822	0.8555	0.8642	0.8596
0.2343	7.0	854	0.2850	0.8822	0.8526	0.8767	0.8628
0.2203	8.0	976	0.2838	0.8797	0.8633	0.8399	0.8502
0.2073	9.0	1098	0.2712	0.8772	0.8535	0.8481	0.8507
0.1969	10.0	1220	0.2904	0.8897	0.8827	0.8445	0.8603
0.189	11.0	1342	0.2773	0.8872	0.8687	0.8552	0.8615
0.1815	12.0	1464	0.2899	0.8947	0.8789	0.8630	0.8704
0.1731	13.0	1586	0.2974	0.8897	0.8726	0.8570	0.8642
0.1601	14.0	1708	0.2803	0.8872	0.8614	0.8702	0.8656
0.1502	15.0	1830	0.2947	0.8922	0.8719	0.8662	0.8690
0.143	16.0	1952	0.2913	0.8922	0.8694	0.8712	0.8703
0.1454	17.0	2074	0.3012	0.8922	0.8734	0.8637	0.8683
0.1475	18.0	2196	0.2980	0.8922	0.8706	0.8687	0.8697
0.1385	19.0	2318	0.3131	0.8997	0.8819	0.8741	0.8778
0.1392	20.0	2440	0.3095	0.8922	0.8719	0.8662	0.8690

Framework versions

• Transformers 4.40.2
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1