metadata

language:
  - id
license: mit
base_model: indolem/indobert-base-uncased
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - precision
  - recall
  - f1
model-index:
  - name: sentiment-unipelt-0
    results: []

sentiment-unipelt-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: 0.2811
Accuracy: 0.9023
Precision: 0.8773
Recall: 0.8933
F1: 0.8846

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
0.5459	1.0	122	0.4639	0.7469	0.6922	0.6459	0.6573
0.4335	2.0	244	0.4108	0.7845	0.7552	0.7975	0.7634
0.3375	3.0	366	0.3283	0.8596	0.8347	0.8207	0.8272
0.2801	4.0	488	0.3202	0.8596	0.8278	0.8432	0.8347
0.2572	5.0	610	0.3109	0.8747	0.8438	0.8713	0.8550
0.2339	6.0	732	0.3074	0.8672	0.8353	0.8660	0.8473
0.2249	7.0	854	0.2915	0.8672	0.8353	0.8660	0.8473
0.193	8.0	976	0.2540	0.8972	0.8781	0.8723	0.8751
0.1899	9.0	1098	0.2636	0.8822	0.8526	0.8767	0.8628
0.1801	10.0	1220	0.2371	0.9073	0.8840	0.8969	0.8900
0.157	11.0	1342	0.2567	0.8997	0.8733	0.8941	0.8825
0.1553	12.0	1464	0.2593	0.8972	0.8708	0.8898	0.8793
0.1381	13.0	1586	0.2490	0.9173	0.9010	0.8990	0.9000
0.1476	14.0	1708	0.2701	0.8997	0.8740	0.8916	0.8819
0.1447	15.0	1830	0.2611	0.9123	0.8899	0.9029	0.8960
0.1336	16.0	1952	0.3100	0.8997	0.8718	0.9016	0.8840
0.1192	17.0	2074	0.2935	0.8972	0.8696	0.8948	0.8803
0.1247	18.0	2196	0.2869	0.9023	0.8765	0.8958	0.8851
0.117	19.0	2318	0.2761	0.9023	0.8773	0.8933	0.8846
0.1092	20.0	2440	0.2811	0.9023	0.8773	0.8933	0.8846

Framework versions

Transformers 4.39.3
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.15.2