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-0
    results: []

sentiment-pt-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: 0.2808
Accuracy: 0.8797
Precision: 0.8504
Recall: 0.8699
F1: 0.8590

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: 1
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
0.5437	1.0	122	0.4910	0.7368	0.7052	0.5813	0.5755
0.4527	2.0	244	0.3825	0.8321	0.7972	0.7987	0.7979
0.3443	3.0	366	0.3294	0.8622	0.8373	0.8250	0.8307
0.3026	4.0	488	0.3161	0.8722	0.8474	0.8421	0.8446
0.2848	5.0	610	0.3151	0.8647	0.8336	0.8492	0.8406
0.2605	6.0	732	0.2879	0.8772	0.8524	0.8506	0.8515
0.2292	7.0	854	0.2645	0.8797	0.8560	0.8524	0.8541
0.2196	8.0	976	0.2868	0.8772	0.8470	0.8706	0.8570
0.2076	9.0	1098	0.2795	0.8797	0.8496	0.8749	0.8602
0.201	10.0	1220	0.3010	0.8772	0.8465	0.8756	0.8582
0.1919	11.0	1342	0.2928	0.8747	0.8436	0.8738	0.8556
0.1866	12.0	1464	0.2660	0.8922	0.8644	0.8863	0.8739
0.1721	13.0	1586	0.2594	0.8922	0.8657	0.8813	0.8728
0.1734	14.0	1708	0.2487	0.8847	0.8581	0.8684	0.8629
0.1601	15.0	1830	0.2958	0.8847	0.8550	0.8834	0.8666
0.1586	16.0	1952	0.2719	0.8822	0.8548	0.8667	0.8603
0.1486	17.0	2074	0.2737	0.8772	0.8489	0.8606	0.8544
0.1474	18.0	2196	0.2678	0.8872	0.8634	0.8652	0.8643
0.1511	19.0	2318	0.2719	0.8797	0.8509	0.8674	0.8583
0.1296	20.0	2440	0.2808	0.8797	0.8504	0.8699	0.8590

Framework versions

Transformers 4.39.3
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.15.2