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-pl10-3
    results: []

sentiment-pt-pl10-3

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: 0.3389
Accuracy: 0.8822
Precision: 0.8574
Recall: 0.8592
F1: 0.8583

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
0.5509	1.0	122	0.4983	0.7393	0.6801	0.6406	0.6507
0.4511	2.0	244	0.4377	0.7769	0.7547	0.8022	0.7593
0.368	3.0	366	0.3260	0.8571	0.8381	0.8064	0.8196
0.3019	4.0	488	0.3036	0.8647	0.8410	0.8267	0.8333
0.2668	5.0	610	0.3192	0.8672	0.8372	0.8485	0.8425
0.2471	6.0	732	0.3059	0.8622	0.8305	0.8475	0.8380
0.2422	7.0	854	0.2950	0.8747	0.8451	0.8613	0.8524
0.2258	8.0	976	0.2928	0.8722	0.8463	0.8446	0.8454
0.2054	9.0	1098	0.3049	0.8797	0.8572	0.8499	0.8534
0.2009	10.0	1220	0.3013	0.8747	0.8488	0.8488	0.8488
0.1755	11.0	1342	0.3070	0.8822	0.8574	0.8592	0.8583
0.1821	12.0	1464	0.2995	0.8822	0.8596	0.8542	0.8568
0.1652	13.0	1586	0.3272	0.8847	0.8553	0.8809	0.8660
0.1566	14.0	1708	0.3336	0.8897	0.8609	0.8870	0.8719
0.1634	15.0	1830	0.3150	0.8847	0.8589	0.8659	0.8623
0.1496	16.0	1952	0.3321	0.8922	0.8706	0.8687	0.8697
0.1355	17.0	2074	0.3276	0.8847	0.8599	0.8634	0.8616
0.1477	18.0	2196	0.3365	0.8797	0.8530	0.8599	0.8563
0.1317	19.0	2318	0.3385	0.8822	0.8574	0.8592	0.8583
0.1267	20.0	2440	0.3389	0.8822	0.8574	0.8592	0.8583

Framework versions

Transformers 4.39.3
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.15.2