sentiment-lora-r16-3

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: 0.2726
• Accuracy: 0.8947
• Precision: 0.8757
• Recall: 0.8680
• F1: 0.8717

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
0.564	1.0	122	0.5210	0.7143	0.6432	0.6178	0.6246
0.5007	2.0	244	0.4797	0.7519	0.7062	0.7219	0.7123
0.428	3.0	366	0.3909	0.8246	0.7874	0.8009	0.7934
0.3751	4.0	488	0.3478	0.8471	0.8159	0.8143	0.8151
0.339	5.0	610	0.3369	0.8546	0.8224	0.8347	0.8280
0.3096	6.0	732	0.3206	0.8697	0.8411	0.8478	0.8443
0.2931	7.0	854	0.3140	0.8622	0.8373	0.8250	0.8307
0.2765	8.0	976	0.3045	0.8722	0.8453	0.8471	0.8462
0.2637	9.0	1098	0.3003	0.8797	0.8539	0.8574	0.8556
0.2601	10.0	1220	0.2910	0.8797	0.8549	0.8549	0.8549
0.2547	11.0	1342	0.2850	0.8897	0.8726	0.8570	0.8642
0.2426	12.0	1464	0.2798	0.8922	0.8706	0.8687	0.8697
0.2319	13.0	1586	0.2811	0.8922	0.8785	0.8562	0.8662
0.2359	14.0	1708	0.2720	0.8847	0.8609	0.8609	0.8609
0.2229	15.0	1830	0.2722	0.8947	0.8718	0.8755	0.8737
0.2218	16.0	1952	0.2731	0.8872	0.8624	0.8677	0.8650
0.2174	17.0	2074	0.2738	0.8922	0.8706	0.8687	0.8697
0.2165	18.0	2196	0.2739	0.8922	0.8694	0.8712	0.8703
0.2153	19.0	2318	0.2727	0.8972	0.8781	0.8723	0.8751
0.2159	20.0	2440	0.2726	0.8947	0.8757	0.8680	0.8717

Framework versions

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