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-0
    results: []

sentiment-base-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: 0.8105
Accuracy: 0.9023
Precision: 0.8828
Recall: 0.8808
F1: 0.8818

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
0.4267	1.0	122	0.3586	0.8797	0.8892	0.8149	0.8409
0.2234	2.0	244	0.3668	0.8697	0.8395	0.8853	0.8539
0.126	3.0	366	0.4554	0.8922	0.8632	0.8938	0.8756
0.0886	4.0	488	0.4441	0.9073	0.8957	0.8769	0.8855
0.0611	5.0	610	0.4923	0.9048	0.8881	0.8801	0.8839
0.0366	6.0	732	0.6796	0.8997	0.8748	0.8891	0.8814
0.0358	7.0	854	0.5746	0.9048	0.8935	0.8726	0.8821
0.0272	8.0	976	0.5953	0.8947	0.8718	0.8755	0.8737
0.0231	9.0	1098	0.6506	0.8997	0.8891	0.8641	0.8752
0.0141	10.0	1220	0.6854	0.9023	0.8814	0.8833	0.8824
0.023	11.0	1342	0.7218	0.9023	0.8814	0.8833	0.8824
0.0067	12.0	1464	0.7695	0.9023	0.8814	0.8833	0.8824
0.0064	13.0	1586	0.9004	0.8797	0.8496	0.8749	0.8602
0.0103	14.0	1708	0.7978	0.9023	0.8792	0.8883	0.8835
0.0072	15.0	1830	0.8251	0.8997	0.8791	0.8791	0.8791
0.0054	16.0	1952	0.7715	0.9023	0.8814	0.8833	0.8824
0.0038	17.0	2074	0.7821	0.9073	0.8920	0.8819	0.8867
0.0021	18.0	2196	0.8211	0.8972	0.8754	0.8773	0.8764
0.0022	19.0	2318	0.8162	0.8997	0.8791	0.8791	0.8791
0.0027	20.0	2440	0.8105	0.9023	0.8828	0.8808	0.8818

Framework versions

Transformers 4.39.3
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.15.2