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: 0.2809
Accuracy: 0.9023
Precision: 0.8758
Recall: 0.8983
F1: 0.8857

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	0.4692	0.7368	0.6763	0.6438	0.6531
0.4301	2.0	244	0.4378	0.7769	0.7547	0.8022	0.7593
0.3347	3.0	366	0.3451	0.8446	0.8158	0.8026	0.8086
0.2954	4.0	488	0.3337	0.8647	0.8377	0.8342	0.8359
0.2632	5.0	610	0.3356	0.8571	0.8248	0.8414	0.8321
0.2492	6.0	732	0.3261	0.8446	0.8110	0.8451	0.8231
0.227	7.0	854	0.2978	0.8797	0.8496	0.8749	0.8602
0.2189	8.0	976	0.2742	0.8947	0.8789	0.8630	0.8704
0.2068	9.0	1098	0.2875	0.8922	0.8673	0.8763	0.8716
0.1935	10.0	1220	0.2693	0.9073	0.8904	0.8844	0.8873
0.1729	11.0	1342	0.2715	0.9073	0.8840	0.8969	0.8900
0.1639	12.0	1464	0.2755	0.8997	0.8733	0.8941	0.8825
0.1564	13.0	1586	0.2662	0.9023	0.8828	0.8808	0.8818
0.1495	14.0	1708	0.2973	0.8997	0.8722	0.8991	0.8835
0.1487	15.0	1830	0.2732	0.9098	0.8865	0.9012	0.8932
0.141	16.0	1952	0.2842	0.9048	0.8784	0.9026	0.8888
0.1276	17.0	2074	0.2794	0.9048	0.8798	0.8976	0.8878
0.1383	18.0	2196	0.2787	0.9073	0.8823	0.9019	0.8910
0.1371	19.0	2318	0.2780	0.9023	0.8758	0.8983	0.8857
0.1248	20.0	2440	0.2809	0.9023	0.8758	0.8983	0.8857

Framework versions

Transformers 4.39.3
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.15.2