sentiment-lora-r2a1d0.1-1

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: 0.3681
• Accuracy: 0.8396
• Precision: 0.8141
• Recall: 0.7865
• F1: 0.7980

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
0.566	1.0	122	0.5211	0.7168	0.6521	0.6396	0.6444
0.5148	2.0	244	0.5169	0.7243	0.6791	0.6974	0.6850
0.4927	3.0	366	0.4861	0.7544	0.7017	0.6887	0.6942
0.4627	4.0	488	0.4656	0.7619	0.7120	0.7065	0.7091
0.4504	5.0	610	0.4611	0.7544	0.7120	0.7337	0.7193
0.4276	6.0	732	0.4303	0.7895	0.7461	0.7410	0.7434
0.4176	7.0	854	0.4163	0.7945	0.7521	0.7546	0.7533
0.397	8.0	976	0.3960	0.8170	0.7814	0.7680	0.7741
0.3904	9.0	1098	0.3940	0.8271	0.7969	0.7726	0.7829
0.3743	10.0	1220	0.3900	0.8271	0.7994	0.7676	0.7804
0.3632	11.0	1342	0.3848	0.8346	0.8062	0.7830	0.7929
0.3599	12.0	1464	0.3795	0.8271	0.7959	0.7751	0.7841
0.3597	13.0	1586	0.3765	0.8346	0.8136	0.7705	0.7867
0.3461	14.0	1708	0.3729	0.8321	0.8061	0.7737	0.7867
0.3432	15.0	1830	0.3714	0.8371	0.8101	0.7847	0.7955
0.333	16.0	1952	0.3706	0.8421	0.8181	0.7883	0.8006
0.3323	17.0	2074	0.3700	0.8396	0.8155	0.7840	0.7969
0.3337	18.0	2196	0.3687	0.8396	0.8141	0.7865	0.7980
0.3298	19.0	2318	0.3684	0.8396	0.8141	0.7865	0.7980
0.3309	20.0	2440	0.3681	0.8396	0.8141	0.7865	0.7980

Framework versions

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