sentiment-lora-r16-1

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: 0.2834
• Accuracy: 0.8822
• Precision: 0.8574
• Recall: 0.8592
• F1: 0.8583

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
0.5612	1.0	122	0.5258	0.7268	0.6614	0.6317	0.6399
0.4935	2.0	244	0.4827	0.7494	0.7127	0.7427	0.7201
0.428	3.0	366	0.3863	0.8246	0.7874	0.7984	0.7924
0.363	4.0	488	0.3415	0.8446	0.8207	0.7926	0.8043
0.3321	5.0	610	0.3417	0.8521	0.8186	0.8429	0.8285
0.3086	6.0	732	0.3376	0.8496	0.8158	0.8386	0.8253
0.2899	7.0	854	0.3156	0.8722	0.8453	0.8471	0.8462
0.2828	8.0	976	0.3073	0.8722	0.8463	0.8446	0.8454
0.2638	9.0	1098	0.3156	0.8622	0.8300	0.8525	0.8395
0.2628	10.0	1220	0.3002	0.8797	0.8522	0.8624	0.8570
0.249	11.0	1342	0.2935	0.8797	0.8572	0.8499	0.8534
0.2429	12.0	1464	0.2938	0.8772	0.8514	0.8531	0.8522
0.2406	13.0	1586	0.2902	0.8797	0.8585	0.8474	0.8526
0.2377	14.0	1708	0.2889	0.8722	0.8437	0.8521	0.8477
0.2257	15.0	1830	0.2848	0.8797	0.8530	0.8599	0.8563
0.2215	16.0	1952	0.2862	0.8747	0.8451	0.8613	0.8524
0.2297	17.0	2074	0.2833	0.8822	0.8610	0.8517	0.8561
0.2263	18.0	2196	0.2854	0.8772	0.8483	0.8631	0.8550
0.2194	19.0	2318	0.2833	0.8797	0.8539	0.8574	0.8556
0.214	20.0	2440	0.2834	0.8822	0.8574	0.8592	0.8583

Framework versions

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