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-pl30-2
    results: []

sentiment-pt-pl30-2

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: 0.2998
Accuracy: 0.8997
Precision: 0.8804
Recall: 0.8766
F1: 0.8785

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
0.5411	1.0	122	0.4939	0.7368	0.6762	0.6413	0.6509
0.4231	2.0	244	0.3852	0.8246	0.7888	0.8184	0.7995
0.3331	3.0	366	0.3313	0.8471	0.8233	0.7968	0.8081
0.2924	4.0	488	0.3057	0.8822	0.8610	0.8517	0.8561
0.2705	5.0	610	0.3069	0.8747	0.8605	0.8288	0.8422
0.2461	6.0	732	0.3119	0.8747	0.8436	0.8763	0.8562
0.2313	7.0	854	0.2880	0.8872	0.8606	0.8727	0.8662
0.2183	8.0	976	0.2773	0.8922	0.8749	0.8612	0.8676
0.2093	9.0	1098	0.2804	0.8847	0.8648	0.8534	0.8588
0.1986	10.0	1220	0.2890	0.8922	0.8804	0.8537	0.8655
0.1881	11.0	1342	0.2911	0.8872	0.8658	0.8602	0.8629
0.1802	12.0	1464	0.2866	0.8822	0.8596	0.8542	0.8568
0.169	13.0	1586	0.2964	0.8847	0.8697	0.8459	0.8565
0.1709	14.0	1708	0.2944	0.8872	0.8658	0.8602	0.8629
0.1492	15.0	1830	0.2866	0.8872	0.8645	0.8627	0.8636
0.1493	16.0	1952	0.2951	0.8947	0.8708	0.8780	0.8743
0.1425	17.0	2074	0.3048	0.8947	0.8773	0.8655	0.8711
0.1375	18.0	2196	0.2987	0.8997	0.8791	0.8791	0.8791
0.1326	19.0	2318	0.3073	0.8997	0.8819	0.8741	0.8778
0.1365	20.0	2440	0.2998	0.8997	0.8804	0.8766	0.8785

Framework versions

Transformers 4.39.3
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.15.2