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-pl30-3
    results: []

sentiment-pt-pl30-3

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: 0.2943
Accuracy: 0.8922
Precision: 0.8706
Recall: 0.8687
F1: 0.8697

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
0.5452	1.0	122	0.4919	0.7469	0.6922	0.6459	0.6573
0.4299	2.0	244	0.4071	0.8070	0.7802	0.8285	0.7892
0.3291	3.0	366	0.3091	0.8672	0.8412	0.8360	0.8385
0.2887	4.0	488	0.3033	0.8521	0.8237	0.8154	0.8193
0.2579	5.0	610	0.2880	0.8647	0.8340	0.8467	0.8399
0.232	6.0	732	0.2919	0.8747	0.8443	0.8663	0.8537
0.2181	7.0	854	0.2797	0.8822	0.8574	0.8592	0.8583
0.2114	8.0	976	0.2828	0.8747	0.8488	0.8488	0.8488
0.199	9.0	1098	0.2835	0.8797	0.8522	0.8624	0.8570
0.189	10.0	1220	0.2816	0.8772	0.8547	0.8456	0.8500
0.1738	11.0	1342	0.2905	0.8822	0.8574	0.8592	0.8583
0.1688	12.0	1464	0.3152	0.8822	0.8674	0.8417	0.8529
0.1655	13.0	1586	0.2901	0.8697	0.8449	0.8378	0.8412
0.1467	14.0	1708	0.2955	0.8797	0.8515	0.8649	0.8577
0.1442	15.0	1830	0.2866	0.8822	0.8564	0.8617	0.8590
0.1419	16.0	1952	0.2902	0.8847	0.8599	0.8634	0.8616
0.1416	17.0	2074	0.2898	0.8897	0.8659	0.8695	0.8676
0.1389	18.0	2196	0.2956	0.8872	0.8658	0.8602	0.8629
0.1401	19.0	2318	0.2937	0.8922	0.8706	0.8687	0.8697
0.1348	20.0	2440	0.2943	0.8922	0.8706	0.8687	0.8697

Framework versions

Transformers 4.39.3
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.15.2