README.md

metadata

language:
  - pt
  - en
tags:
  - aes
datasets:
  - kamel-usp/aes_enem_dataset
base_model: TucanoBR/Tucano-2b4-Instruct
metrics:
  - accuracy
  - qwk
library_name: peft
model-index:
  - name: Tucano-2b4-Instruct-tucano_classification_lora-C4-full_context-r16
    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: 0.3983903420523138
          - name: QWK
            type: qwk
            value: 0.5176260597947346
          - name: Weighted Macro F1
            type: f1
            value: 0.5923346844351132

Model ID: Tucano-2b4-Instruct-tucano_classification_lora-C4-full_context-r16

Results

	test_data
eval_accuracy	0.57971
eval_RMSE	33.013
eval_QWK	0.517626
eval_Macro_F1	0.39839
eval_Weighted_F1	0.592335
eval_Micro_F1	0.57971
eval_HDIV	0.0217391