sentiment-lora-r8-2

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: 0.3056
• Accuracy: 0.8772
• Precision: 0.8609
• Recall: 0.8356
• F1: 0.8467

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
0.5584	1.0	122	0.5227	0.7118	0.6378	0.6086	0.6151
0.4972	2.0	244	0.5052	0.7293	0.6868	0.7085	0.6931
0.4566	3.0	366	0.4337	0.7845	0.7400	0.7400	0.7400
0.4192	4.0	488	0.3954	0.8170	0.7798	0.7756	0.7776
0.3833	5.0	610	0.3803	0.8446	0.8115	0.8176	0.8144
0.3457	6.0	732	0.3604	0.8521	0.8237	0.8154	0.8193
0.3328	7.0	854	0.3583	0.8471	0.8206	0.8018	0.8102
0.3144	8.0	976	0.3516	0.8521	0.8392	0.7904	0.8088
0.3078	9.0	1098	0.3393	0.8571	0.8322	0.8164	0.8236
0.3005	10.0	1220	0.3363	0.8496	0.8186	0.8186	0.8186
0.2926	11.0	1342	0.3305	0.8672	0.8463	0.8260	0.8351
0.2858	12.0	1464	0.3276	0.8596	0.8360	0.8182	0.8262
0.2798	13.0	1586	0.3244	0.8747	0.8605	0.8288	0.8422
0.2743	14.0	1708	0.3106	0.8697	0.8460	0.8353	0.8404
0.2573	15.0	1830	0.3104	0.8747	0.8568	0.8338	0.8440
0.2644	16.0	1952	0.3069	0.8697	0.8460	0.8353	0.8404
0.2597	17.0	2074	0.3080	0.8747	0.8586	0.8313	0.8431
0.2596	18.0	2196	0.3053	0.8747	0.8537	0.8388	0.8457
0.26	19.0	2318	0.3056	0.8772	0.8609	0.8356	0.8467
0.2565	20.0	2440	0.3056	0.8772	0.8609	0.8356	0.8467

Framework versions

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