sentiment-lora-r16-2

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: 0.2946
• Accuracy: 0.8747
• Precision: 0.8537
• Recall: 0.8388
• F1: 0.8457

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
0.5556	1.0	122	0.5150	0.7268	0.6608	0.6267	0.6351
0.4868	2.0	244	0.4703	0.7845	0.7425	0.7600	0.7495
0.4308	3.0	366	0.4005	0.8195	0.7818	0.7998	0.7894
0.3892	4.0	488	0.3843	0.8221	0.7847	0.8041	0.7928
0.3615	5.0	610	0.3545	0.8521	0.8193	0.8329	0.8254
0.3255	6.0	732	0.3458	0.8596	0.8293	0.8357	0.8324
0.3142	7.0	854	0.3297	0.8596	0.8325	0.8257	0.8290
0.3002	8.0	976	0.3228	0.8647	0.8439	0.8217	0.8315
0.2872	9.0	1098	0.3237	0.8697	0.8428	0.8428	0.8428
0.2794	10.0	1220	0.3075	0.8722	0.8453	0.8471	0.8462
0.2698	11.0	1342	0.3057	0.8747	0.8523	0.8413	0.8465
0.2685	12.0	1464	0.3076	0.8747	0.8537	0.8388	0.8457
0.2585	13.0	1586	0.3082	0.8722	0.8498	0.8371	0.8430
0.2548	14.0	1708	0.2983	0.8822	0.8564	0.8617	0.8590
0.2391	15.0	1830	0.2974	0.8722	0.8498	0.8371	0.8430
0.2476	16.0	1952	0.2974	0.8747	0.8479	0.8513	0.8496
0.243	17.0	2074	0.2962	0.8747	0.8552	0.8363	0.8448
0.242	18.0	2196	0.2951	0.8797	0.8560	0.8524	0.8541
0.2425	19.0	2318	0.2941	0.8747	0.8537	0.8388	0.8457
0.2403	20.0	2440	0.2946	0.8747	0.8537	0.8388	0.8457

Framework versions

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