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: phi-4-phi4_classification_lora-C3-full_context
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: 0.2587504587012703
- name: QWK
type: qwk
value: 0.6404105501849862
- name: Weighted Macro F1
type: f1
value: 0.4145905872632278
Model ID: phi-4-phi4_classification_lora-C3-full_context
Results
| test_data | |
|---|---|
| eval_accuracy | 0.456522 |
| eval_RMSE | 38.9723 |
| eval_QWK | 0.640411 |
| eval_Macro_F1 | 0.25875 |
| eval_Weighted_F1 | 0.414591 |
| eval_Micro_F1 | 0.456522 |
| eval_HDIV | 0.00724638 |