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-pl10-0
    results: []

sentiment-pt-pl10-0

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: 0.2798
Accuracy: 0.8972
Precision: 0.8723
Recall: 0.8848
F1: 0.8781

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
0.5568	1.0	122	0.4822	0.7243	0.6557	0.6074	0.6144
0.4661	2.0	244	0.4453	0.7544	0.7241	0.7612	0.7304
0.3875	3.0	366	0.3447	0.8622	0.8488	0.8075	0.8239
0.318	4.0	488	0.3442	0.8496	0.8158	0.8436	0.8267
0.2855	5.0	610	0.3349	0.8496	0.8158	0.8411	0.8260
0.2638	6.0	732	0.3548	0.8371	0.8052	0.8472	0.8177
0.2397	7.0	854	0.3254	0.8647	0.8326	0.8592	0.8434
0.2428	8.0	976	0.2799	0.8922	0.8804	0.8537	0.8655
0.2229	9.0	1098	0.2903	0.8722	0.8431	0.8546	0.8484
0.2144	10.0	1220	0.2583	0.8972	0.8743	0.8798	0.8770
0.1967	11.0	1342	0.2743	0.8822	0.8530	0.8742	0.8622
0.1855	12.0	1464	0.2913	0.8772	0.8473	0.8681	0.8563
0.1761	13.0	1586	0.2660	0.9023	0.8913	0.8683	0.8786
0.1733	14.0	1708	0.2868	0.8822	0.8530	0.8742	0.8622
0.1582	15.0	1830	0.2801	0.8847	0.8561	0.8759	0.8648
0.1537	16.0	1952	0.3073	0.8747	0.8438	0.8713	0.8550
0.1537	17.0	2074	0.2702	0.8972	0.8723	0.8848	0.8781
0.1461	18.0	2196	0.2923	0.8947	0.8682	0.8855	0.8760
0.1449	19.0	2318	0.2791	0.8947	0.8690	0.8830	0.8755
0.1502	20.0	2440	0.2798	0.8972	0.8723	0.8848	0.8781

Framework versions

Transformers 4.39.3
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.15.2