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-C5-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: 0.3552263104501911
- name: QWK
type: qwk
value: 0.5073723420766724
- name: Weighted Macro F1
type: f1
value: 0.3672380004905022
Model ID: phi-4-phi4_classification_lora-C5-full_context
Results
| test_data | |
|---|---|
| eval_accuracy | 0.362319 |
| eval_RMSE | 56.5685 |
| eval_QWK | 0.507372 |
| eval_Macro_F1 | 0.355226 |
| eval_Weighted_F1 | 0.367238 |
| eval_Micro_F1 | 0.362319 |
| eval_HDIV | 0.057971 |