sentiment-lora-r4a2d0.15-0

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: 0.3513
• Accuracy: 0.8471
• Precision: 0.8147
• Recall: 0.8193
• F1: 0.8169

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
0.5621	1.0	122	0.5100	0.7218	0.6593	0.6482	0.6527
0.5049	2.0	244	0.4890	0.7343	0.6945	0.7195	0.7011
0.4776	3.0	366	0.4480	0.7594	0.7150	0.7323	0.7216
0.4422	4.0	488	0.4104	0.7945	0.7524	0.7446	0.7482
0.4146	5.0	610	0.4257	0.7594	0.7202	0.7473	0.7283
0.3828	6.0	732	0.3869	0.8246	0.7880	0.7909	0.7894
0.3697	7.0	854	0.3959	0.8145	0.7766	0.7988	0.7854
0.3486	8.0	976	0.3808	0.8321	0.7961	0.8087	0.8018
0.3437	9.0	1098	0.3738	0.8271	0.7904	0.8001	0.7949
0.3317	10.0	1220	0.3643	0.8471	0.8159	0.8143	0.8151
0.3114	11.0	1342	0.3683	0.8271	0.7902	0.8051	0.7968
0.3035	12.0	1464	0.3660	0.8346	0.7988	0.8155	0.8061
0.3117	13.0	1586	0.3518	0.8471	0.8167	0.8118	0.8142
0.3048	14.0	1708	0.3533	0.8446	0.8115	0.8176	0.8144
0.2916	15.0	1830	0.3570	0.8421	0.8083	0.8158	0.8119
0.2832	16.0	1952	0.3579	0.8471	0.8138	0.8243	0.8187
0.284	17.0	2074	0.3496	0.8471	0.8153	0.8168	0.8160
0.2906	18.0	2196	0.3537	0.8446	0.8111	0.8201	0.8153
0.2805	19.0	2318	0.3505	0.8496	0.8186	0.8186	0.8186
0.2815	20.0	2440	0.3513	0.8471	0.8147	0.8193	0.8169

Framework versions

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