README.md

metadata

language:
  - pt
  - en
tags:
  - aes
datasets:
  - kamel-usp/aes_enem_dataset
base_model: google-bert/bert-base-multilingual-cased
metrics:
  - f1
  - qwk
model-index:
  - name: mbert_base-C1
    results:
      - task:
          type: text-classification
          name: Automated Essay Score
        dataset:
          name: Automated Essay Score ENEM Dataset
          type: kamel-usp/aes_enem_dataset
          config: JBCS2025
          split: test
        metrics:
          - name: Macro F1
            type: f1
            value: 0.3244639912039582
          - name: QWK
            type: qwk
            value: 0.4505920783993467
          - name: Weighted Macro F1
            type: f1
            value: 0.518137852459147

Model ID: mbert_base-C1

Results

	test_data
eval_accuracy	0.536232
eval_RMSE	30.0724
eval_QWK	0.450592
eval_Macro_F1	0.324464
eval_Weighted_F1	0.518138
eval_Micro_F1	0.536232
eval_HDIV	0.00724638