metadata

language:
  - id
license: mit
base_model: indolem/indobert-base-uncased
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - precision
  - recall
  - f1
model-index:
  - name: sentiment-base-1
    results: []

sentiment-base-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: 0.7891
Accuracy: 0.8972
Precision: 0.8796
Recall: 0.8698
F1: 0.8745

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
0.411	1.0	122	0.2751	0.8722	0.8474	0.8421	0.8446
0.2264	2.0	244	0.3037	0.8872	0.8574	0.8977	0.8719
0.1467	3.0	366	0.3442	0.8772	0.8465	0.8756	0.8582
0.0961	4.0	488	0.3737	0.8997	0.8819	0.8741	0.8778
0.0726	5.0	610	0.4306	0.8997	0.8835	0.8716	0.8772
0.0514	6.0	732	0.6449	0.8847	0.8546	0.8884	0.8677
0.0532	7.0	854	0.5595	0.8972	0.8754	0.8773	0.8764
0.0274	8.0	976	0.6728	0.8872	0.8687	0.8552	0.8615
0.0186	9.0	1098	0.6218	0.9073	0.8977	0.8744	0.8849
0.0121	10.0	1220	0.6576	0.8922	0.8766	0.8587	0.8669
0.0244	11.0	1342	0.7507	0.8972	0.8940	0.8523	0.8695
0.0062	12.0	1464	0.6859	0.8972	0.8849	0.8623	0.8724
0.0099	13.0	1586	0.6514	0.9073	0.8904	0.8844	0.8873
0.0087	14.0	1708	0.7604	0.8997	0.8852	0.8691	0.8765
0.0056	15.0	1830	0.7282	0.9023	0.8875	0.8733	0.8799
0.0063	16.0	1952	0.6987	0.9123	0.8965	0.8904	0.8934
0.0071	17.0	2074	0.7402	0.9048	0.8897	0.8776	0.8833
0.0023	18.0	2196	0.7846	0.8922	0.8719	0.8662	0.8690
0.0043	19.0	2318	0.7948	0.8922	0.8719	0.8662	0.8690
0.0021	20.0	2440	0.7891	0.8972	0.8796	0.8698	0.8745

Framework versions

Transformers 4.39.3
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.15.2