metadata

language:
  - pt
  - en
tags:
  - aes
datasets:
  - kamel-usp/aes_enem_dataset
base_model: microsoft/phi-4
metrics:
  - accuracy
  - qwk
library_name: peft
model-index:
  - name: phi4-essay-prompt-balanced-C2
    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: 0.3441326647209
          - name: QWK
            type: qwk
            value: 0.5722403995178234
          - name: Weighted Macro F1
            type: f1
            value: 0.4399113248218107

Model ID: phi4-essay-prompt-balanced-C2

Results

	test_data
eval_accuracy	0.442029
eval_RMSE	50.0435
eval_QWK	0.57224
eval_Macro_F1	0.344133
eval_Weighted_F1	0.439911
eval_Micro_F1	0.442029
eval_HDIV	0.0362319