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-pl20-0
    results: []

sentiment-pt-pl20-0

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: 0.2882
Accuracy: 0.9073
Precision: 0.8875
Recall: 0.8894
F1: 0.8884

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
0.5417	1.0	122	0.4732	0.7544	0.7028	0.6612	0.6731
0.4395	2.0	244	0.4128	0.7920	0.7613	0.8028	0.7705
0.3319	3.0	366	0.3230	0.8647	0.8439	0.8217	0.8315
0.2873	4.0	488	0.3222	0.8521	0.8201	0.8279	0.8238
0.2571	5.0	610	0.2968	0.8722	0.8431	0.8546	0.8484
0.2443	6.0	732	0.2918	0.8672	0.8353	0.8635	0.8466
0.2256	7.0	854	0.2982	0.8647	0.8325	0.8642	0.8447
0.2172	8.0	976	0.2722	0.8922	0.8826	0.8512	0.8647
0.2049	9.0	1098	0.2648	0.8947	0.8698	0.8805	0.8749
0.1914	10.0	1220	0.2680	0.9073	0.8977	0.8744	0.8849
0.1724	11.0	1342	0.2645	0.8997	0.8757	0.8866	0.8808
0.1689	12.0	1464	0.2746	0.8997	0.8740	0.8916	0.8819
0.1473	13.0	1586	0.2837	0.9048	0.9002	0.8651	0.8801
0.1577	14.0	1708	0.2892	0.9023	0.8773	0.8933	0.8846
0.1468	15.0	1830	0.2789	0.9023	0.8802	0.8858	0.8830
0.1473	16.0	1952	0.2852	0.8972	0.8732	0.8823	0.8776
0.1274	17.0	2074	0.2858	0.9048	0.8838	0.8876	0.8857
0.1318	18.0	2196	0.2927	0.8997	0.8767	0.8841	0.8803
0.1355	19.0	2318	0.2884	0.9073	0.8875	0.8894	0.8884
0.1367	20.0	2440	0.2882	0.9073	0.8875	0.8894	0.8884

Framework versions

Transformers 4.39.3
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.15.2