---
language:
- pt
- en
tags:
- aes
datasets:
- kamel-usp/aes_enem_dataset
base_model: microsoft/Phi-3.5-mini-instruct
metrics:
- accuracy
- qwk
library_name: peft
model-index:
  - name: phi35-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: 0.27377240938451114
          - name: QWK
            type: qwk
            value: 0.41621854162185423
          - name: Weighted Macro F1
            type: f1
            value: 0.3898085539478307
---
# Model ID: phi35-essay-prompt-balanced-C2
## Results
|                  |   test_data |
|:-----------------|------------:|
| eval_accuracy    |    0.391304 |
| eval_RMSE        |   52.309    |
| eval_QWK         |    0.416219 |
| eval_Macro_F1    |    0.273772 |
| eval_Weighted_F1 |    0.389809 |
| eval_Micro_F1    |    0.391304 |
| eval_HDIV        |    0.057971 |