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-pl5-3
    results: []

sentiment-pt-pl5-3

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: 0.2683
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
0.5455	1.0	122	0.4877	0.7544	0.7053	0.6512	0.6639
0.4356	2.0	244	0.3537	0.8446	0.8103	0.8376	0.8210
0.3468	3.0	366	0.3416	0.8496	0.8326	0.7911	0.8073
0.3049	4.0	488	0.3126	0.8546	0.8324	0.8071	0.8180
0.2673	5.0	610	0.2919	0.8596	0.8299	0.8332	0.8315
0.2516	6.0	732	0.2823	0.8647	0.8387	0.8317	0.8351
0.2243	7.0	854	0.2688	0.8822	0.8530	0.8742	0.8622
0.2157	8.0	976	0.2641	0.8947	0.8807	0.8605	0.8697
0.2052	9.0	1098	0.2627	0.8847	0.8679	0.8484	0.8573
0.1864	10.0	1220	0.2881	0.8847	0.8737	0.8409	0.8548
0.1928	11.0	1342	0.2785	0.8872	0.8593	0.8777	0.8675
0.1804	12.0	1464	0.2506	0.8997	0.8871	0.8666	0.8759
0.1654	13.0	1586	0.2664	0.8997	0.8791	0.8791	0.8791
0.1567	14.0	1708	0.2661	0.9048	0.8798	0.8976	0.8878
0.1438	15.0	1830	0.2615	0.9098	0.8898	0.8937	0.8917
0.1472	16.0	1952	0.2555	0.9048	0.8838	0.8876	0.8857
0.1394	17.0	2074	0.2648	0.8997	0.8791	0.8791	0.8791
0.1387	18.0	2196	0.2630	0.9048	0.8826	0.8901	0.8862
0.1378	19.0	2318	0.2689	0.9048	0.8865	0.8826	0.8845
0.1365	20.0	2440	0.2683	0.9023	0.8828	0.8808	0.8818

Framework versions

Transformers 4.40.2
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.19.1