metadata

license: mit
base_model: indolem/indobert-base-uncased
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - precision
  - recall
  - f1
model-index:
  - name: sentiment-pt-pl30-1
    results: []

sentiment-pt-pl30-1

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: 0.3019
Accuracy: 0.8647
Precision: 0.8377
Recall: 0.8342
F1: 0.8359

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
0.5413	1.0	122	0.4949	0.7368	0.6763	0.6438	0.6531
0.4306	2.0	244	0.3954	0.8246	0.7902	0.8259	0.8019
0.3344	3.0	366	0.3397	0.8521	0.8370	0.7929	0.8099
0.2925	4.0	488	0.3211	0.8471	0.8264	0.7918	0.8058
0.2794	5.0	610	0.3064	0.8622	0.8314	0.8425	0.8365
0.2464	6.0	732	0.2857	0.8672	0.8356	0.8585	0.8453
0.2332	7.0	854	0.2846	0.8772	0.8496	0.8581	0.8537
0.2216	8.0	976	0.2906	0.8596	0.8360	0.8182	0.8262
0.2123	9.0	1098	0.2781	0.8697	0.8488	0.8303	0.8386
0.1911	10.0	1220	0.2896	0.8722	0.8562	0.8271	0.8395
0.1878	11.0	1342	0.2814	0.8747	0.8479	0.8513	0.8496
0.1797	12.0	1464	0.2830	0.8672	0.8402	0.8385	0.8394
0.1746	13.0	1586	0.2900	0.8672	0.8496	0.8210	0.8332
0.1677	14.0	1708	0.2798	0.8697	0.8411	0.8478	0.8443
0.1585	15.0	1830	0.2823	0.8722	0.8437	0.8521	0.8477
0.1575	16.0	1952	0.2816	0.8722	0.8413	0.8646	0.8511
0.146	17.0	2074	0.3027	0.8647	0.8377	0.8342	0.8359
0.1368	18.0	2196	0.2961	0.8672	0.8372	0.8485	0.8425
0.133	19.0	2318	0.3024	0.8622	0.8342	0.8325	0.8333
0.1377	20.0	2440	0.3019	0.8647	0.8377	0.8342	0.8359

Framework versions

Transformers 4.39.3
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.15.2