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-pl10-1
    results: []

sentiment-pt-pl10-1

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: 0.3011
Accuracy: 0.8972
Precision: 0.8754
Recall: 0.8773
F1: 0.8764

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
0.5535	1.0	122	0.5078	0.7268	0.6606	0.6242	0.6327
0.4682	2.0	244	0.4185	0.8170	0.7798	0.7756	0.7776
0.3849	3.0	366	0.3809	0.8170	0.7968	0.7380	0.7573
0.3127	4.0	488	0.3280	0.8571	0.8266	0.8314	0.8289
0.2869	5.0	610	0.3169	0.8622	0.8333	0.8350	0.8341
0.274	6.0	732	0.3218	0.8772	0.8467	0.8731	0.8576
0.2539	7.0	854	0.3038	0.8672	0.8378	0.8460	0.8417
0.2286	8.0	976	0.3202	0.8672	0.8479	0.8235	0.8342
0.2249	9.0	1098	0.2973	0.8872	0.8606	0.8727	0.8662
0.2083	10.0	1220	0.3128	0.8722	0.8602	0.8221	0.8377
0.1935	11.0	1342	0.2957	0.8922	0.8665	0.8788	0.8722
0.1859	12.0	1464	0.2869	0.8822	0.8548	0.8667	0.8603
0.1735	13.0	1586	0.3061	0.8797	0.8633	0.8399	0.8502
0.1804	14.0	1708	0.2955	0.8897	0.8632	0.8770	0.8695
0.1628	15.0	1830	0.2973	0.8972	0.8767	0.8748	0.8757
0.1619	16.0	1952	0.3023	0.8897	0.8618	0.8820	0.8707
0.1514	17.0	2074	0.2997	0.8972	0.8732	0.8823	0.8776
0.1503	18.0	2196	0.3002	0.8947	0.8718	0.8755	0.8737
0.154	19.0	2318	0.3031	0.8947	0.8730	0.8730	0.8730
0.1408	20.0	2440	0.3011	0.8972	0.8754	0.8773	0.8764

Framework versions

Transformers 4.39.3
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.15.2