README.md

metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - indonlu
metrics:
  - accuracy
  - f1
model-index:
  - name: distilled-indobert-classification
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: indonlu
          type: indonlu
          args: smsa
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.8611111111111112
          - name: F1
            type: f1
            value: 0.8618768886720962

distilled-indobert-classification

This model is a fine-tuned version of distilbert-base-uncased on the indonlu dataset. It achieves the following results on the evaluation set:

• Loss: 0.9386
• Accuracy: 0.8611
• F1: 0.8619

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: 6e-05
• train_batch_size: 128
• eval_batch_size: 128
• seed: 33
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
2.0275	1.0	86	1.3588	0.8103	0.8104
1.2393	2.0	172	1.0187	0.8492	0.8476
0.8745	3.0	258	0.9386	0.8611	0.8619

Framework versions

• Transformers 4.18.0
• Pytorch 1.10.0+cu111
• Datasets 2.0.0
• Tokenizers 0.11.6