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: 0.2793
Accuracy: 0.8922
Precision: 0.8665
Recall: 0.8788
F1: 0.8722

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
0.5424	1.0	122	0.4762	0.7419	0.6837	0.6473	0.6575
0.4345	2.0	244	0.4157	0.7895	0.7581	0.7986	0.7674
0.3391	3.0	366	0.3388	0.8546	0.8324	0.8071	0.8180
0.2837	4.0	488	0.3279	0.8622	0.8342	0.8325	0.8333
0.2761	5.0	610	0.3132	0.8647	0.8346	0.8442	0.8391
0.2459	6.0	732	0.3033	0.8747	0.8440	0.8688	0.8544
0.2321	7.0	854	0.2871	0.8822	0.8530	0.8742	0.8622
0.2206	8.0	976	0.2634	0.8822	0.8610	0.8517	0.8561
0.2067	9.0	1098	0.2634	0.8922	0.8694	0.8712	0.8703
0.192	10.0	1220	0.2696	0.8922	0.8873	0.8462	0.8631
0.1866	11.0	1342	0.2752	0.8972	0.8691	0.8973	0.8808
0.1786	12.0	1464	0.2652	0.8972	0.8708	0.8898	0.8793
0.1695	13.0	1586	0.2536	0.9073	0.8920	0.8819	0.8867
0.1664	14.0	1708	0.2737	0.8872	0.8587	0.8802	0.8681
0.1521	15.0	1830	0.2620	0.9023	0.8802	0.8858	0.8830
0.1494	16.0	1952	0.3030	0.8922	0.8630	0.8963	0.8761
0.1487	17.0	2074	0.2702	0.8922	0.8650	0.8838	0.8734
0.1494	18.0	2196	0.2763	0.8947	0.8676	0.8880	0.8766
0.1334	19.0	2318	0.2826	0.8922	0.8650	0.8838	0.8734
0.1325	20.0	2440	0.2793	0.8922	0.8665	0.8788	0.8722

Framework versions

Transformers 4.39.3
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.15.2