sentiment-lora-r2a2d0.05-0

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: 0.3642
• Accuracy: 0.8346
• Precision: 0.7993
• Recall: 0.8080
• F1: 0.8034

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
0.5633	1.0	122	0.5100	0.7168	0.6536	0.6446	0.6484
0.5083	2.0	244	0.4999	0.7243	0.6825	0.7049	0.6887
0.4904	3.0	366	0.4595	0.7619	0.7120	0.7065	0.7091
0.4644	4.0	488	0.4287	0.7920	0.7520	0.7253	0.7358
0.4439	5.0	610	0.4399	0.7519	0.7127	0.7395	0.7203
0.4241	6.0	732	0.4027	0.8221	0.7860	0.7816	0.7837
0.4092	7.0	854	0.4019	0.8070	0.7674	0.7835	0.7743
0.3891	8.0	976	0.3805	0.8271	0.7912	0.7926	0.7919
0.3777	9.0	1098	0.3789	0.8271	0.7912	0.7926	0.7919
0.369	10.0	1220	0.3758	0.8396	0.8071	0.8040	0.8055
0.3531	11.0	1342	0.3805	0.8296	0.7933	0.8044	0.7984
0.3486	12.0	1464	0.3801	0.8321	0.7960	0.8112	0.8027
0.3472	13.0	1586	0.3675	0.8421	0.8098	0.8083	0.8091
0.3379	14.0	1708	0.3654	0.8371	0.8032	0.8047	0.8040
0.3353	15.0	1830	0.3703	0.8421	0.8080	0.8183	0.8127
0.3213	16.0	1952	0.3709	0.8371	0.8019	0.8147	0.8077
0.3214	17.0	2074	0.3641	0.8371	0.8024	0.8097	0.8059
0.3225	18.0	2196	0.3640	0.8371	0.8024	0.8097	0.8059
0.3159	19.0	2318	0.3649	0.8346	0.7993	0.8080	0.8034
0.3195	20.0	2440	0.3642	0.8346	0.7993	0.8080	0.8034

Framework versions

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