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-pl20-1
    results: []

sentiment-pt-pl20-1

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: 0.3296
Accuracy: 0.8872
Precision: 0.8624
Recall: 0.8677
F1: 0.8650

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
0.5524	1.0	122	0.5143	0.7168	0.6417	0.5921	0.5963
0.468	2.0	244	0.4272	0.7920	0.7507	0.7678	0.7577
0.3759	3.0	366	0.3480	0.8346	0.8175	0.7655	0.7841
0.3116	4.0	488	0.3080	0.8647	0.8439	0.8217	0.8315
0.2812	5.0	610	0.3000	0.8697	0.8520	0.8253	0.8368
0.2692	6.0	732	0.2970	0.8772	0.8473	0.8681	0.8563
0.2603	7.0	854	0.2929	0.8772	0.8489	0.8606	0.8544
0.231	8.0	976	0.3083	0.8596	0.8486	0.8007	0.8190
0.2278	9.0	1098	0.2939	0.8697	0.8428	0.8428	0.8428
0.2117	10.0	1220	0.3240	0.8747	0.8647	0.8238	0.8404
0.2014	11.0	1342	0.2902	0.8797	0.8572	0.8499	0.8534
0.1869	12.0	1464	0.2760	0.8947	0.8698	0.8805	0.8749
0.1685	13.0	1586	0.3016	0.8822	0.8610	0.8517	0.8561
0.1703	14.0	1708	0.3027	0.8897	0.8632	0.8770	0.8695
0.1617	15.0	1830	0.3020	0.8897	0.8632	0.8770	0.8695
0.1524	16.0	1952	0.3177	0.8822	0.8530	0.8742	0.8622
0.1356	17.0	2074	0.3291	0.8897	0.8649	0.8720	0.8683
0.1474	18.0	2196	0.3268	0.8897	0.8649	0.8720	0.8683
0.145	19.0	2318	0.3315	0.8872	0.8614	0.8702	0.8656
0.1466	20.0	2440	0.3296	0.8872	0.8624	0.8677	0.8650

Framework versions

Transformers 4.39.3
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.15.2