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-pl30-1
    results: []

sentiment-pt-pl30-1

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: 0.3434
Accuracy: 0.8722
Precision: 0.8485
Recall: 0.8396
F1: 0.8438

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
0.5472	1.0	122	0.4993	0.7343	0.6726	0.6245	0.6339
0.4484	2.0	244	0.4157	0.7945	0.7655	0.8096	0.7744
0.3338	3.0	366	0.3279	0.8596	0.8510	0.7982	0.8179
0.2902	4.0	488	0.3037	0.8672	0.8449	0.8285	0.8360
0.2756	5.0	610	0.2922	0.8747	0.8499	0.8463	0.8481
0.2514	6.0	732	0.3059	0.8672	0.8359	0.8560	0.8446
0.2338	7.0	854	0.2970	0.8596	0.8278	0.8432	0.8347
0.2205	8.0	976	0.2967	0.8847	0.8784	0.8359	0.8531
0.2153	9.0	1098	0.2982	0.8672	0.8393	0.8410	0.8402
0.1969	10.0	1220	0.2943	0.8672	0.8423	0.8335	0.8377
0.185	11.0	1342	0.2973	0.8647	0.8359	0.8392	0.8376
0.1733	12.0	1464	0.3074	0.8672	0.8423	0.8335	0.8377
0.1616	13.0	1586	0.3186	0.8697	0.8460	0.8353	0.8404
0.16	14.0	1708	0.3222	0.8596	0.8278	0.8432	0.8347
0.1494	15.0	1830	0.3260	0.8747	0.8523	0.8413	0.8465
0.1501	16.0	1952	0.3233	0.8647	0.8359	0.8392	0.8376
0.1468	17.0	2074	0.3296	0.8672	0.8412	0.8360	0.8385
0.1423	18.0	2196	0.3367	0.8647	0.8398	0.8292	0.8342
0.1327	19.0	2318	0.3395	0.8697	0.8438	0.8403	0.8420
0.1413	20.0	2440	0.3434	0.8722	0.8485	0.8396	0.8438

Framework versions

Transformers 4.39.3
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.15.2