metadata

license: mit
base_model: indolem/indobert-base-uncased
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - precision
  - recall
  - f1
model-index:
  - name: sentiment-pt-pl30-4
    results: []

sentiment-pt-pl30-4

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: 0.3072
Accuracy: 0.8822
Precision: 0.8574
Recall: 0.8592
F1: 0.8583

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
0.5438	1.0	122	0.4988	0.7218	0.6601	0.6507	0.6546
0.4428	2.0	244	0.3788	0.8446	0.8107	0.8226	0.8161
0.3441	3.0	366	0.3289	0.8596	0.8510	0.7982	0.8179
0.2986	4.0	488	0.2884	0.8797	0.8572	0.8499	0.8534
0.2667	5.0	610	0.2698	0.8772	0.8535	0.8481	0.8507
0.2524	6.0	732	0.2723	0.8847	0.8609	0.8609	0.8609
0.2343	7.0	854	0.3180	0.8647	0.8533	0.8092	0.8266
0.2212	8.0	976	0.2949	0.8822	0.8674	0.8417	0.8529
0.2142	9.0	1098	0.2828	0.8847	0.8697	0.8459	0.8565
0.1958	10.0	1220	0.2887	0.8697	0.8399	0.8528	0.8458
0.1855	11.0	1342	0.2868	0.8822	0.8548	0.8667	0.8603
0.1742	12.0	1464	0.2981	0.8747	0.8552	0.8363	0.8448
0.1601	13.0	1586	0.2930	0.8797	0.8539	0.8574	0.8556
0.1602	14.0	1708	0.2979	0.8797	0.8504	0.8699	0.8590
0.1497	15.0	1830	0.2969	0.8872	0.8606	0.8727	0.8662
0.1447	16.0	1952	0.2963	0.8847	0.8599	0.8634	0.8616
0.1394	17.0	2074	0.3018	0.8822	0.8564	0.8617	0.8590
0.1333	18.0	2196	0.3065	0.8822	0.8574	0.8592	0.8583
0.1406	19.0	2318	0.3062	0.8822	0.8574	0.8592	0.8583
0.1243	20.0	2440	0.3072	0.8822	0.8574	0.8592	0.8583

Framework versions

Transformers 4.39.3
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.15.2