sentiment-lora-r4a2d0.1-1

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: 0.3239
• Accuracy: 0.8622
• Precision: 0.8373
• Recall: 0.8250
• F1: 0.8307

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
0.5658	1.0	122	0.5195	0.7268	0.6646	0.6492	0.6550
0.5125	2.0	244	0.5060	0.7293	0.6805	0.6935	0.6855
0.4809	3.0	366	0.4686	0.7669	0.7184	0.7151	0.7167
0.4353	4.0	488	0.4295	0.7920	0.7500	0.7353	0.7417
0.4116	5.0	610	0.4171	0.8020	0.7628	0.7849	0.7714
0.3809	6.0	732	0.3865	0.8446	0.8148	0.8051	0.8096
0.3681	7.0	854	0.3697	0.8496	0.8193	0.8161	0.8177
0.3469	8.0	976	0.3554	0.8471	0.8206	0.8018	0.8102
0.3455	9.0	1098	0.3494	0.8496	0.8211	0.8111	0.8158
0.3284	10.0	1220	0.3437	0.8496	0.8289	0.7961	0.8096
0.3132	11.0	1342	0.3371	0.8596	0.8389	0.8132	0.8243
0.3042	12.0	1464	0.3371	0.8546	0.8254	0.8221	0.8238
0.3063	13.0	1586	0.3317	0.8596	0.8406	0.8107	0.8233
0.3013	14.0	1708	0.3304	0.8622	0.8373	0.8250	0.8307
0.2928	15.0	1830	0.3295	0.8596	0.8325	0.8257	0.8290
0.2864	16.0	1952	0.3284	0.8622	0.8351	0.8300	0.8325
0.2819	17.0	2074	0.3254	0.8596	0.8347	0.8207	0.8272
0.2877	18.0	2196	0.3249	0.8596	0.8336	0.8232	0.8281
0.2819	19.0	2318	0.3241	0.8647	0.8410	0.8267	0.8333
0.2803	20.0	2440	0.3239	0.8622	0.8373	0.8250	0.8307

Framework versions

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