metadata

license: mit
base_model: indolem/indobert-base-uncased
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - precision
  - recall
  - f1
model-index:
  - name: sentiment-ia3
    results: []

sentiment-ia3

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: 0.4042
Accuracy: 0.8145
Precision: 0.7763
Recall: 0.7763
F1: 0.7763

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
0.5636	1.0	122	0.5070	0.7243	0.6575	0.6274	0.6354
0.5128	2.0	244	0.5015	0.7343	0.6911	0.7120	0.6976
0.4941	3.0	366	0.4709	0.7469	0.6955	0.6984	0.6969
0.4702	4.0	488	0.4496	0.7744	0.7275	0.7154	0.7207
0.4704	5.0	610	0.4521	0.7719	0.7270	0.7386	0.7320
0.4616	6.0	732	0.4490	0.7644	0.7175	0.7258	0.7213
0.4543	7.0	854	0.4381	0.7820	0.7389	0.7532	0.7449
0.4532	8.0	976	0.4197	0.8070	0.7744	0.7385	0.7519
0.4517	9.0	1098	0.4195	0.7970	0.7551	0.7539	0.7545
0.4438	10.0	1220	0.4102	0.8170	0.8013	0.7330	0.7540
0.4389	11.0	1342	0.4112	0.8271	0.7933	0.7826	0.7876
0.4428	12.0	1464	0.4179	0.7970	0.7555	0.7664	0.7604
0.4421	13.0	1586	0.4030	0.8321	0.8110	0.7662	0.7828
0.4403	14.0	1708	0.4037	0.8321	0.8014	0.7837	0.7915
0.4392	15.0	1830	0.4077	0.8221	0.7852	0.7866	0.7859
0.4329	16.0	1952	0.4062	0.8195	0.7820	0.7848	0.7834
0.4338	17.0	2074	0.4058	0.8145	0.7761	0.7788	0.7774
0.4407	18.0	2196	0.4042	0.8145	0.7763	0.7763	0.7763
0.4329	19.0	2318	0.4033	0.8195	0.7827	0.7798	0.7812
0.4292	20.0	2440	0.4042	0.8145	0.7763	0.7763	0.7763

Framework versions

Transformers 4.39.3
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.15.2