sentiment-pt-pl20-4

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: 0.3189
• Accuracy: 0.8772
• Precision: 0.8514
• Recall: 0.8531
• F1: 0.8522

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
0.55	1.0	122	0.5115	0.7143	0.6535	0.6503	0.6518
0.4708	2.0	244	0.4093	0.8070	0.7770	0.7335	0.7489
0.3841	3.0	366	0.3797	0.8321	0.8611	0.7287	0.7587
0.3154	4.0	488	0.3147	0.8772	0.8670	0.8281	0.8440
0.2764	5.0	610	0.3043	0.8697	0.8488	0.8303	0.8386
0.2589	6.0	732	0.2923	0.8747	0.8537	0.8388	0.8457
0.24	7.0	854	0.3074	0.8647	0.8491	0.8142	0.8286
0.2257	8.0	976	0.3176	0.8596	0.8389	0.8132	0.8243
0.2077	9.0	1098	0.3044	0.8722	0.8562	0.8271	0.8395
0.1982	10.0	1220	0.3065	0.8672	0.8423	0.8335	0.8377
0.1806	11.0	1342	0.2871	0.8822	0.8574	0.8592	0.8583
0.1843	12.0	1464	0.3042	0.8822	0.8596	0.8542	0.8568
0.1792	13.0	1586	0.2948	0.8722	0.8463	0.8446	0.8454
0.1644	14.0	1708	0.2986	0.8797	0.8509	0.8674	0.8583
0.1593	15.0	1830	0.3163	0.8822	0.8535	0.8717	0.8616
0.1517	16.0	1952	0.3026	0.8822	0.8596	0.8542	0.8568
0.1478	17.0	2074	0.3101	0.8822	0.8564	0.8617	0.8590
0.1329	18.0	2196	0.3152	0.8772	0.8504	0.8556	0.8530
0.1363	19.0	2318	0.3179	0.8747	0.8471	0.8538	0.8503
0.1292	20.0	2440	0.3189	0.8772	0.8514	0.8531	0.8522

Framework versions

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