metadata

language:
  - id
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: 0.2786
Accuracy: 0.8847
Precision: 0.8648
Recall: 0.8534
F1: 0.8588

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
0.5623	1.0	122	0.5217	0.7268	0.6604	0.6217	0.6301
0.5061	2.0	244	0.4898	0.7569	0.7074	0.7105	0.7089
0.4443	3.0	366	0.4085	0.8120	0.7751	0.7620	0.7679
0.3805	4.0	488	0.3672	0.8246	0.7980	0.7609	0.7752
0.3488	5.0	610	0.3535	0.8521	0.8207	0.8254	0.8229
0.3156	6.0	732	0.3337	0.8571	0.8299	0.8214	0.8255
0.3055	7.0	854	0.3217	0.8622	0.8385	0.8225	0.8298
0.2995	8.0	976	0.3145	0.8596	0.8347	0.8207	0.8272
0.2825	9.0	1098	0.3090	0.8672	0.8402	0.8385	0.8394
0.272	10.0	1220	0.2992	0.8722	0.8453	0.8471	0.8462
0.2626	11.0	1342	0.3008	0.8747	0.8568	0.8338	0.8440
0.2641	12.0	1464	0.2949	0.8747	0.8488	0.8488	0.8488
0.257	13.0	1586	0.2885	0.8772	0.8592	0.8381	0.8475
0.2473	14.0	1708	0.2826	0.8822	0.8596	0.8542	0.8568
0.2456	15.0	1830	0.2826	0.8847	0.8609	0.8609	0.8609
0.2477	16.0	1952	0.2795	0.8847	0.8621	0.8584	0.8602
0.2426	17.0	2074	0.2794	0.8797	0.8585	0.8474	0.8526
0.2359	18.0	2196	0.2796	0.8872	0.8658	0.8602	0.8629
0.2417	19.0	2318	0.2787	0.8847	0.8648	0.8534	0.8588
0.2319	20.0	2440	0.2786	0.8847	0.8648	0.8534	0.8588

Framework versions

Transformers 4.39.3
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.15.2