metadata

license: mit
base_model: indolem/indobert-base-uncased
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - precision
  - recall
  - f1
model-index:
  - name: sentiment-pt-pl20-3
    results: []

sentiment-pt-pl20-3

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: 0.3253
Accuracy: 0.8822
Precision: 0.8564
Recall: 0.8617
F1: 0.8590

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
0.5445	1.0	122	0.4894	0.7519	0.6988	0.6594	0.6708
0.432	2.0	244	0.3691	0.8195	0.7843	0.8173	0.7954
0.3342	3.0	366	0.3301	0.8496	0.8574	0.7686	0.7957
0.2846	4.0	488	0.2886	0.8797	0.8633	0.8399	0.8502
0.2621	5.0	610	0.2728	0.8747	0.8488	0.8488	0.8488
0.2419	6.0	732	0.2753	0.8747	0.8471	0.8538	0.8503
0.2132	7.0	854	0.2753	0.8847	0.8589	0.8659	0.8623
0.2055	8.0	976	0.2791	0.8797	0.8560	0.8524	0.8541
0.1903	9.0	1098	0.3009	0.8622	0.8373	0.8250	0.8307
0.1852	10.0	1220	0.3085	0.8672	0.8479	0.8235	0.8342
0.1758	11.0	1342	0.2852	0.8797	0.8539	0.8574	0.8556
0.1617	12.0	1464	0.3011	0.8872	0.8634	0.8652	0.8643
0.1581	13.0	1586	0.3050	0.8922	0.8694	0.8712	0.8703
0.149	14.0	1708	0.3143	0.8922	0.8639	0.8888	0.8745
0.1386	15.0	1830	0.3028	0.8997	0.8791	0.8791	0.8791
0.1465	16.0	1952	0.3112	0.8922	0.8706	0.8687	0.8697
0.1307	17.0	2074	0.3198	0.8847	0.8581	0.8684	0.8629
0.1231	18.0	2196	0.3253	0.8847	0.8609	0.8609	0.8609
0.1344	19.0	2318	0.3290	0.8797	0.8560	0.8524	0.8541
0.1229	20.0	2440	0.3253	0.8822	0.8564	0.8617	0.8590

Framework versions

Transformers 4.39.3
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.15.2