sentiment-lora-r8a1d0.1-0

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: 0.3309
• Accuracy: 0.8672
• Precision: 0.8378
• Recall: 0.8460
• F1: 0.8417

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
0.5622	1.0	122	0.5076	0.7193	0.6565	0.6464	0.6505
0.5003	2.0	244	0.4839	0.7469	0.7107	0.7409	0.7178
0.4614	3.0	366	0.4256	0.7719	0.7281	0.7436	0.7344
0.4022	4.0	488	0.3880	0.8170	0.7798	0.7756	0.7776
0.3678	5.0	610	0.4131	0.8020	0.7657	0.7974	0.7760
0.3376	6.0	732	0.3645	0.8321	0.7965	0.8037	0.7999
0.3268	7.0	854	0.3640	0.8346	0.7988	0.8180	0.8069
0.3044	8.0	976	0.3551	0.8346	0.7996	0.8055	0.8024
0.2984	9.0	1098	0.3509	0.8496	0.8169	0.8261	0.8212
0.2922	10.0	1220	0.3413	0.8521	0.8213	0.8229	0.8221
0.2666	11.0	1342	0.3494	0.8521	0.8193	0.8329	0.8254
0.2641	12.0	1464	0.3520	0.8546	0.8220	0.8372	0.8288
0.2694	13.0	1586	0.3358	0.8496	0.8202	0.8136	0.8167
0.2678	14.0	1708	0.3355	0.8647	0.8352	0.8417	0.8383
0.255	15.0	1830	0.3406	0.8647	0.8346	0.8442	0.8391
0.2482	16.0	1952	0.3370	0.8622	0.8309	0.8450	0.8373
0.2444	17.0	2074	0.3272	0.8697	0.8411	0.8478	0.8443
0.2521	18.0	2196	0.3319	0.8622	0.8314	0.8425	0.8365
0.2456	19.0	2318	0.3293	0.8697	0.8411	0.8478	0.8443
0.2458	20.0	2440	0.3309	0.8672	0.8378	0.8460	0.8417

Framework versions

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