ayameRushia's picture
update model card README.md
5e6ce61
|
raw
history blame
2.26 kB
metadata
tags:
  - generated_from_trainer
datasets:
  - indonlu
metrics:
  - accuracy
model-index:
  - name: roberta-base-indonesian-1.5G-sentiment-analysis-smsa
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: indonlu
          type: indonlu
          args: smsa
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9261904761904762

roberta-base-indonesian-1.5G-sentiment-analysis-smsa

This model is a fine-tuned version of cahya/roberta-base-indonesian-1.5G on the indonlu dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4294
  • Accuracy: 0.9262

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: 1e-05
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 1500
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.6461 1.0 688 0.2620 0.9087
0.2627 2.0 1376 0.2291 0.9151
0.1784 3.0 2064 0.2891 0.9167
0.1099 4.0 2752 0.3317 0.9230
0.0857 5.0 3440 0.4294 0.9262
0.0346 6.0 4128 0.4759 0.9246
0.0221 7.0 4816 0.4946 0.9206
0.006 8.0 5504 0.5823 0.9175
0.0047 9.0 6192 0.5777 0.9159
0.004 10.0 6880 0.5800 0.9175

Framework versions

  • Transformers 4.14.1
  • Pytorch 1.10.0+cu111
  • Datasets 1.16.1
  • Tokenizers 0.10.3