---
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: phi-4-phi4_classification_lora-C1-full_context-r8
    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: 0.4280707196029777
          - name: QWK
            type: qwk
            value: 0.6593643937056464
          - name: Weighted Macro F1
            type: f1
            value: 0.6257619484302513
---
# Model ID: phi-4-phi4_classification_lora-C1-full_context-r8
## Results
|                  |   test_data |
|:-----------------|------------:|
| eval_accuracy    |  0.615942   |
| eval_RMSE        | 27.2402     |
| eval_QWK         |  0.659364   |
| eval_Macro_F1    |  0.428071   |
| eval_Weighted_F1 |  0.625762   |
| eval_Micro_F1    |  0.615942   |
| eval_HDIV        |  0.00724638 |