metadata

base_model: naufalihsan/indonesian-sbert-large
tags:
  - generated_from_trainer
datasets:
  - indonlu
metrics:
  - accuracy
  - precision
  - recall
  - f1
model-index:
  - name: sentiment
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: indonlu
          type: indonlu
          config: smsa
          split: validation
          args: smsa
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.95
          - name: Precision
            type: precision
            value: 0.9499758037063356
          - name: Recall
            type: recall
            value: 0.95
          - name: F1
            type: f1
            value: 0.9496487652420723

sentiment

This model is a fine-tuned version of naufalihsan/indonesian-sbert-large on the indonlu dataset. It achieves the following results on the evaluation set:

Loss: 0.4450
Accuracy: 0.95
Precision: 0.9500
Recall: 0.95
F1: 0.9496

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: 40
eval_batch_size: 40
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.01
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
No log	1.0	275	0.2837	0.9405	0.9427	0.9405	0.9396
0.0501	2.0	550	0.1966	0.9460	0.9468	0.9460	0.9458
0.0501	3.0	825	0.2927	0.9437	0.9435	0.9437	0.9427
0.0369	4.0	1100	0.3666	0.9460	0.9459	0.9460	0.9456
0.0369	5.0	1375	0.3579	0.9468	0.9465	0.9468	0.9465
0.0098	6.0	1650	0.4497	0.9476	0.9479	0.9476	0.9471
0.0098	7.0	1925	0.4308	0.95	0.9501	0.95	0.9496
0.0012	8.0	2200	0.4402	0.95	0.9499	0.95	0.9496
0.0012	9.0	2475	0.4429	0.95	0.9500	0.95	0.9496
0.0007	10.0	2750	0.4450	0.95	0.9500	0.95	0.9496

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu121
Datasets 2.17.1
Tokenizers 0.15.2