sentiment-lora-r16-4

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: 0.2751
• Accuracy: 0.8872
• Precision: 0.8658
• Recall: 0.8602
• F1: 0.8629

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
0.5585	1.0	122	0.5224	0.7218	0.6715	0.6832	0.6760
0.4948	2.0	244	0.4534	0.7970	0.7873	0.6914	0.7128
0.4389	3.0	366	0.3953	0.8145	0.7809	0.7563	0.7665
0.3871	4.0	488	0.3608	0.8195	0.7818	0.7998	0.7894
0.3569	5.0	610	0.3384	0.8421	0.8092	0.8108	0.8100
0.3206	6.0	732	0.3370	0.8446	0.8103	0.8276	0.8178
0.309	7.0	854	0.3202	0.8672	0.8449	0.8285	0.8360
0.2971	8.0	976	0.3165	0.8747	0.8625	0.8263	0.8413
0.2834	9.0	1098	0.3064	0.8672	0.8496	0.8210	0.8332
0.266	10.0	1220	0.3070	0.8722	0.8431	0.8546	0.8484
0.2627	11.0	1342	0.2936	0.8797	0.8549	0.8549	0.8549
0.2523	12.0	1464	0.2869	0.8797	0.8616	0.8424	0.8510
0.2503	13.0	1586	0.2826	0.8722	0.8445	0.8496	0.8470
0.2505	14.0	1708	0.2885	0.8772	0.8483	0.8631	0.8550
0.2373	15.0	1830	0.2788	0.8772	0.8489	0.8606	0.8544
0.2308	16.0	1952	0.2759	0.8897	0.8649	0.8720	0.8683
0.2354	17.0	2074	0.2755	0.8847	0.8609	0.8609	0.8609
0.2304	18.0	2196	0.2755	0.8847	0.8621	0.8584	0.8602
0.2262	19.0	2318	0.2754	0.8872	0.8634	0.8652	0.8643
0.2293	20.0	2440	0.2751	0.8872	0.8658	0.8602	0.8629

Framework versions

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