metadata

language:
  - id
license: mit
base_model: indolem/indobert-base-uncased
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - precision
  - recall
  - f1
model-index:
  - name: sentiment-pt-pl10-0
    results: []

sentiment-pt-pl10-0

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: 0.2766
Accuracy: 0.9023
Precision: 0.8802
Recall: 0.8858
F1: 0.8830

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	0.4763	0.7393	0.6804	0.6356	0.6459
0.4528	2.0	244	0.4306	0.7845	0.7630	0.8125	0.7678
0.3653	3.0	366	0.3335	0.8622	0.8533	0.8025	0.8217
0.2987	4.0	488	0.3357	0.8546	0.8246	0.8246	0.8246
0.2746	5.0	610	0.3401	0.8546	0.8217	0.8547	0.8339
0.2477	6.0	732	0.3323	0.8496	0.8176	0.8586	0.8308
0.24	7.0	854	0.3171	0.8647	0.8325	0.8642	0.8447
0.2069	8.0	976	0.2770	0.8922	0.8734	0.8637	0.8683
0.2197	9.0	1098	0.3091	0.8672	0.8356	0.8735	0.8491
0.2005	10.0	1220	0.2552	0.9023	0.8842	0.8783	0.8812
0.1867	11.0	1342	0.2727	0.9048	0.8816	0.8926	0.8868
0.1722	12.0	1464	0.2739	0.8922	0.8657	0.8813	0.8728
0.161	13.0	1586	0.2714	0.8997	0.8852	0.8691	0.8765
0.1684	14.0	1708	0.2774	0.8972	0.8723	0.8848	0.8781
0.1548	15.0	1830	0.2742	0.8997	0.8767	0.8841	0.8803
0.1526	16.0	1952	0.2970	0.8872	0.8574	0.8902	0.8703
0.1467	17.0	2074	0.2729	0.8897	0.8618	0.8820	0.8707
0.1484	18.0	2196	0.2739	0.8972	0.8723	0.8848	0.8781
0.1434	19.0	2318	0.2729	0.8997	0.8778	0.8816	0.8797
0.1354	20.0	2440	0.2766	0.9023	0.8802	0.8858	0.8830

Framework versions

Transformers 4.39.3
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.15.2