sentiment-pt-pl50-3

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: 0.3160
• Accuracy: 0.8797
• Precision: 0.8572
• Recall: 0.8499
• F1: 0.8534

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
0.5469	1.0	122	0.4896	0.7444	0.6874	0.6516	0.6620
0.4431	2.0	244	0.4094	0.8070	0.7671	0.7685	0.7678
0.3667	3.0	366	0.3514	0.8321	0.8194	0.7562	0.7772
0.3012	4.0	488	0.3064	0.8571	0.8299	0.8214	0.8255
0.2689	5.0	610	0.2962	0.8647	0.8387	0.8317	0.8351
0.2444	6.0	732	0.2888	0.8647	0.8367	0.8367	0.8367
0.232	7.0	854	0.2827	0.8697	0.8438	0.8403	0.8420
0.2169	8.0	976	0.2947	0.8797	0.8651	0.8374	0.8494
0.1989	9.0	1098	0.2860	0.8772	0.8547	0.8456	0.8500
0.1968	10.0	1220	0.2905	0.8797	0.8633	0.8399	0.8502
0.1771	11.0	1342	0.3071	0.8797	0.8600	0.8449	0.8518
0.1766	12.0	1464	0.3037	0.8672	0.8463	0.8260	0.8351
0.1622	13.0	1586	0.3152	0.8747	0.8552	0.8363	0.8448
0.1521	14.0	1708	0.3112	0.8797	0.8539	0.8574	0.8556
0.1442	15.0	1830	0.3024	0.8872	0.8672	0.8577	0.8622
0.1481	16.0	1952	0.3089	0.8822	0.8610	0.8517	0.8561
0.1431	17.0	2074	0.3058	0.8847	0.8599	0.8634	0.8616
0.1393	18.0	2196	0.3182	0.8772	0.8535	0.8481	0.8507
0.1349	19.0	2318	0.3220	0.8797	0.8633	0.8399	0.8502
0.1359	20.0	2440	0.3160	0.8797	0.8572	0.8499	0.8534

Framework versions

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