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-pl10-1
    results: []

sentiment-pt-pl10-1

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: 0.3090
Accuracy: 0.8847
Precision: 0.8609
Recall: 0.8609
F1: 0.8609

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
0.5535	1.0	122	0.5041	0.7243	0.6584	0.6324	0.6401
0.4636	2.0	244	0.4692	0.7669	0.7253	0.7476	0.7331
0.4023	3.0	366	0.3605	0.8371	0.8326	0.7572	0.7809
0.3202	4.0	488	0.3256	0.8546	0.8357	0.8021	0.8159
0.2919	5.0	610	0.3067	0.8772	0.8592	0.8381	0.8475
0.2657	6.0	732	0.3400	0.8521	0.8193	0.8554	0.8320
0.2559	7.0	854	0.2993	0.8747	0.8451	0.8613	0.8524
0.2369	8.0	976	0.3018	0.8872	0.8760	0.8452	0.8584
0.2178	9.0	1098	0.2926	0.8847	0.8634	0.8559	0.8595
0.2118	10.0	1220	0.2955	0.8872	0.8672	0.8577	0.8622
0.2034	11.0	1342	0.2934	0.8847	0.8679	0.8484	0.8573
0.1856	12.0	1464	0.2978	0.8797	0.8572	0.8499	0.8534
0.1775	13.0	1586	0.3039	0.8797	0.8651	0.8374	0.8494
0.1719	14.0	1708	0.3036	0.8872	0.8672	0.8577	0.8622
0.1621	15.0	1830	0.2990	0.8822	0.8555	0.8642	0.8596
0.1535	16.0	1952	0.3040	0.8847	0.8599	0.8634	0.8616
0.1504	17.0	2074	0.3190	0.8797	0.8616	0.8424	0.8510
0.1459	18.0	2196	0.3101	0.8772	0.8514	0.8531	0.8522
0.1444	19.0	2318	0.3119	0.8822	0.8624	0.8492	0.8553
0.1384	20.0	2440	0.3090	0.8847	0.8609	0.8609	0.8609

Framework versions

Transformers 4.39.3
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.15.2