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-pl50-2
    results: []

sentiment-pt-pl50-2

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: 0.3235
Accuracy: 0.8747
Precision: 0.8537
Recall: 0.8388
F1: 0.8457

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
0.5384	1.0	122	0.4919	0.7368	0.6770	0.6538	0.6617
0.4212	2.0	244	0.4175	0.8246	0.7930	0.8359	0.8048
0.3413	3.0	366	0.3403	0.8446	0.8257	0.7851	0.8009
0.2888	4.0	488	0.3278	0.8471	0.8159	0.8143	0.8151
0.2577	5.0	610	0.3103	0.8596	0.8325	0.8257	0.8290
0.2495	6.0	732	0.3074	0.8672	0.8436	0.8310	0.8369
0.2391	7.0	854	0.3005	0.8672	0.8402	0.8385	0.8394
0.2177	8.0	976	0.2979	0.8697	0.8449	0.8378	0.8412
0.2102	9.0	1098	0.2961	0.8797	0.8549	0.8549	0.8549
0.2029	10.0	1220	0.3043	0.8697	0.8579	0.8178	0.8340
0.1829	11.0	1342	0.3059	0.8797	0.8572	0.8499	0.8534
0.184	12.0	1464	0.3002	0.8772	0.8609	0.8356	0.8467
0.1802	13.0	1586	0.2954	0.8897	0.8710	0.8595	0.8649
0.1684	14.0	1708	0.3008	0.8872	0.8634	0.8652	0.8643
0.1627	15.0	1830	0.3067	0.8872	0.8672	0.8577	0.8622
0.1581	16.0	1952	0.3107	0.8772	0.8514	0.8531	0.8522
0.1468	17.0	2074	0.3229	0.8772	0.8576	0.8406	0.8484
0.1433	18.0	2196	0.3247	0.8747	0.8537	0.8388	0.8457
0.1538	19.0	2318	0.3246	0.8747	0.8537	0.8388	0.8457
0.1412	20.0	2440	0.3235	0.8747	0.8537	0.8388	0.8457

Framework versions

Transformers 4.40.2
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.19.1