metadata

license: mit
base_model: indolem/indobert-base-uncased
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - precision
  - recall
  - f1
model-index:
  - name: sentiment-lora-r8
    results: []

sentiment-lora-r8

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: 0.3143
Accuracy: 0.8622
Precision: 0.8333
Recall: 0.8350
F1: 0.8341

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
0.5637	1.0	122	0.5043	0.7193	0.6506	0.6239	0.6312
0.5058	2.0	244	0.4905	0.7343	0.6956	0.7220	0.7022
0.4607	3.0	366	0.4207	0.7845	0.7425	0.7600	0.7495
0.3992	4.0	488	0.3723	0.8496	0.8221	0.8086	0.8148
0.3565	5.0	610	0.3855	0.8145	0.7773	0.8038	0.7872
0.332	6.0	732	0.3689	0.8271	0.7903	0.8076	0.7977
0.3089	7.0	854	0.3519	0.8446	0.8132	0.8101	0.8116
0.2979	8.0	976	0.3406	0.8571	0.8289	0.8239	0.8264
0.2887	9.0	1098	0.3582	0.8471	0.8132	0.8293	0.8204
0.268	10.0	1220	0.3394	0.8622	0.8361	0.8275	0.8316
0.267	11.0	1342	0.3339	0.8571	0.8281	0.8264	0.8272
0.2609	12.0	1464	0.3397	0.8622	0.8314	0.8425	0.8365
0.2564	13.0	1586	0.3227	0.8672	0.8436	0.8310	0.8369
0.2566	14.0	1708	0.3246	0.8672	0.8393	0.8410	0.8402
0.2503	15.0	1830	0.3297	0.8722	0.8431	0.8546	0.8484
0.2539	16.0	1952	0.3228	0.8697	0.8404	0.8503	0.8451
0.2478	17.0	2074	0.3142	0.8571	0.8289	0.8239	0.8264
0.2449	18.0	2196	0.3190	0.8722	0.8437	0.8521	0.8477
0.2401	19.0	2318	0.3139	0.8622	0.8333	0.8350	0.8341
0.2392	20.0	2440	0.3143	0.8622	0.8333	0.8350	0.8341

Framework versions

Transformers 4.39.3
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.15.2