metadata

license: mit
base_model: indolem/indobert-base-uncased
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - precision
  - recall
  - f1
model-index:
  - name: sentiment-pt-pl10-2
    results: []

sentiment-pt-pl10-2

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: 0.3132
Accuracy: 0.8947
Precision: 0.8743
Recall: 0.8705
F1: 0.8724

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
0.5494	1.0	122	0.5033	0.7318	0.6683	0.6278	0.6369
0.4551	2.0	244	0.4276	0.7769	0.7434	0.7797	0.7522
0.3731	3.0	366	0.3508	0.8396	0.8294	0.7665	0.7879
0.3032	4.0	488	0.3237	0.8672	0.8353	0.8635	0.8466
0.2718	5.0	610	0.3102	0.8722	0.8445	0.8496	0.8470
0.2642	6.0	732	0.3006	0.8747	0.8451	0.8613	0.8524
0.2394	7.0	854	0.3013	0.8722	0.8544	0.8296	0.8404
0.2234	8.0	976	0.2904	0.8797	0.8572	0.8499	0.8534
0.2098	9.0	1098	0.2984	0.8897	0.8625	0.8795	0.8701
0.2029	10.0	1220	0.3189	0.8822	0.8762	0.8317	0.8495
0.1917	11.0	1342	0.2848	0.8847	0.8648	0.8534	0.8588
0.1797	12.0	1464	0.3003	0.8772	0.8535	0.8481	0.8507
0.1658	13.0	1586	0.3010	0.8847	0.8634	0.8559	0.8595
0.1551	14.0	1708	0.3077	0.8847	0.8589	0.8659	0.8623
0.1517	15.0	1830	0.3014	0.8947	0.8789	0.8630	0.8704
0.1532	16.0	1952	0.3067	0.8947	0.8718	0.8755	0.8737
0.136	17.0	2074	0.3174	0.8897	0.8670	0.8670	0.8670
0.1438	18.0	2196	0.3129	0.8897	0.8682	0.8645	0.8663
0.1507	19.0	2318	0.3165	0.8922	0.8734	0.8637	0.8683
0.1326	20.0	2440	0.3132	0.8947	0.8743	0.8705	0.8724

Framework versions

Transformers 4.39.3
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.15.2