Text Classification
Transformers
Safetensors
Portuguese
English
bert
aes
Eval Results (legacy)
text-embeddings-inference
Instructions to use kamel-usp/jbcs2025_bert-large-portuguese-cased-encoder_classification-C4-essay_only with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use kamel-usp/jbcs2025_bert-large-portuguese-cased-encoder_classification-C4-essay_only with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="kamel-usp/jbcs2025_bert-large-portuguese-cased-encoder_classification-C4-essay_only")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("kamel-usp/jbcs2025_bert-large-portuguese-cased-encoder_classification-C4-essay_only") model = AutoModelForSequenceClassification.from_pretrained("kamel-usp/jbcs2025_bert-large-portuguese-cased-encoder_classification-C4-essay_only", device_map="auto") - Notebooks
- Google Colab
- Kaggle
metadata
language:
- pt
- en
tags:
- aes
datasets:
- kamel-usp/aes_enem_dataset
base_model: neuralmind/bert-large-portuguese-cased
metrics:
- accuracy
- qwk
library_name: transformers
model-index:
- name: bert-large-portuguese-cased-encoder_classification-C4-essay_only
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: 0.4550282038102597
- name: QWK
type: qwk
value: 0.5985849056603774
- name: Weighted Macro F1
type: f1
value: 0.6030619269196934
Model ID: bert-large-portuguese-cased-encoder_classification-C4-essay_only
Results
| test_data | |
|---|---|
| eval_accuracy | 0.586957 |
| eval_RMSE | 29.2911 |
| eval_QWK | 0.598585 |
| eval_Macro_F1 | 0.455028 |
| eval_Weighted_F1 | 0.603062 |
| eval_Micro_F1 | 0.586957 |
| eval_HDIV | 0.00724638 |