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-pl5-1
    results: []

sentiment-pt-pl5-1

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: 0.2868
Accuracy: 0.8847
Precision: 0.8599
Recall: 0.8634
F1: 0.8616

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
0.5526	1.0	122	0.5135	0.7118	0.6438	0.6286	0.6339
0.4696	2.0	244	0.4522	0.7569	0.7328	0.7755	0.7369
0.3867	3.0	366	0.3466	0.8371	0.8297	0.7597	0.7824
0.3349	4.0	488	0.3128	0.8546	0.8395	0.7971	0.8137
0.2998	5.0	610	0.2932	0.8596	0.8293	0.8357	0.8324
0.2787	6.0	732	0.2855	0.8697	0.8419	0.8453	0.8436
0.2551	7.0	854	0.2898	0.8747	0.8438	0.8713	0.8550
0.2496	8.0	976	0.2936	0.8697	0.8653	0.8103	0.8309
0.2347	9.0	1098	0.2755	0.8847	0.8599	0.8634	0.8616
0.2199	10.0	1220	0.3038	0.8722	0.8675	0.8146	0.8347
0.2089	11.0	1342	0.2695	0.8822	0.8574	0.8592	0.8583
0.1992	12.0	1464	0.2710	0.8747	0.8488	0.8488	0.8488
0.1841	13.0	1586	0.2807	0.8722	0.8512	0.8346	0.8422
0.1808	14.0	1708	0.2822	0.8822	0.8548	0.8667	0.8603
0.1677	15.0	1830	0.2841	0.8747	0.8479	0.8513	0.8496
0.1683	16.0	1952	0.2821	0.8772	0.8496	0.8581	0.8537
0.1748	17.0	2074	0.2824	0.8797	0.8572	0.8499	0.8534
0.1566	18.0	2196	0.2847	0.8872	0.8606	0.8727	0.8662
0.1522	19.0	2318	0.2880	0.8822	0.8574	0.8592	0.8583
0.1566	20.0	2440	0.2868	0.8847	0.8599	0.8634	0.8616

Framework versions

Transformers 4.40.2
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.19.1