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-pl30-0
    results: []

sentiment-pt-pl30-0

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: 0.2913
Accuracy: 0.9048
Precision: 0.8851
Recall: 0.8851
F1: 0.8851

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
0.5457	1.0	122	0.4753	0.7193	0.6465	0.5964	0.6014
0.4518	2.0	244	0.4070	0.7970	0.7589	0.7864	0.7685
0.3461	3.0	366	0.3412	0.8421	0.8231	0.7808	0.7970
0.2958	4.0	488	0.3253	0.8546	0.8263	0.8196	0.8229
0.2659	5.0	610	0.2941	0.8822	0.8610	0.8517	0.8561
0.2482	6.0	732	0.2965	0.8772	0.8473	0.8681	0.8563
0.2264	7.0	854	0.2869	0.8747	0.8447	0.8638	0.8531
0.2218	8.0	976	0.2795	0.8997	0.8961	0.8566	0.8730
0.2106	9.0	1098	0.2705	0.8922	0.8673	0.8763	0.8716
0.1981	10.0	1220	0.2751	0.9073	0.8920	0.8819	0.8867
0.1802	11.0	1342	0.2745	0.9048	0.8826	0.8901	0.8862
0.1828	12.0	1464	0.2799	0.9073	0.8957	0.8769	0.8855
0.1707	13.0	1586	0.2739	0.9098	0.8960	0.8837	0.8895
0.1606	14.0	1708	0.2868	0.9073	0.8862	0.8919	0.8890
0.1499	15.0	1830	0.2930	0.9023	0.8828	0.8808	0.8818
0.1555	16.0	1952	0.3041	0.8947	0.8682	0.8855	0.8760
0.1396	17.0	2074	0.2876	0.9023	0.8814	0.8833	0.8824
0.1477	18.0	2196	0.2900	0.9048	0.8865	0.8826	0.8845
0.1434	19.0	2318	0.2917	0.9048	0.8851	0.8851	0.8851
0.1386	20.0	2440	0.2913	0.9048	0.8851	0.8851	0.8851

Framework versions

Transformers 4.39.3
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.15.2