sentiment-pt-pl5-0

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: 0.3123
• Accuracy: 0.8822
• Precision: 0.8548
• Recall: 0.8667
• F1: 0.8603

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
0.5463	1.0	122	0.4832	0.7419	0.6850	0.6698	0.6759
0.4591	2.0	244	0.4429	0.7519	0.7323	0.7770	0.7338
0.3761	3.0	366	0.3485	0.8421	0.8113	0.8033	0.8071
0.3183	4.0	488	0.3375	0.8521	0.8228	0.8179	0.8203
0.2811	5.0	610	0.3170	0.8571	0.8260	0.8339	0.8298
0.2593	6.0	732	0.3106	0.8722	0.8413	0.8646	0.8511
0.2372	7.0	854	0.3502	0.8471	0.8147	0.8543	0.8277
0.2287	8.0	976	0.2938	0.8922	0.8873	0.8462	0.8631
0.2109	9.0	1098	0.2922	0.8797	0.8496	0.8749	0.8602
0.2025	10.0	1220	0.2650	0.8822	0.8574	0.8592	0.8583
0.1918	11.0	1342	0.3182	0.8772	0.8463	0.8806	0.8594
0.1807	12.0	1464	0.2841	0.8947	0.8676	0.8880	0.8766
0.1751	13.0	1586	0.2675	0.8922	0.8683	0.8737	0.8710
0.1724	14.0	1708	0.2957	0.8847	0.8573	0.8709	0.8636
0.1502	15.0	1830	0.3010	0.8822	0.8541	0.8692	0.8609
0.1469	16.0	1952	0.3227	0.8872	0.8583	0.8827	0.8687
0.1457	17.0	2074	0.3037	0.8822	0.8541	0.8692	0.8609
0.1453	18.0	2196	0.3064	0.8822	0.8555	0.8642	0.8596
0.1402	19.0	2318	0.3092	0.8797	0.8530	0.8599	0.8563
0.1301	20.0	2440	0.3123	0.8822	0.8548	0.8667	0.8603

Framework versions

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