kamel-usp
/

jbcs2025_Llama-3.1-8B-llama31_classification_lora-C2-full_context-r16

Eval Results (legacy)

Model card Files Files and versions

Model ID: Llama-3.1-8B-llama31_classification_lora-C2-full_context-r16

Results

	test_data
eval_accuracy	0.26087
eval_RMSE	68.7782
eval_QWK	0.291346
eval_Macro_F1	0.199802
eval_Weighted_F1	0.208021
eval_Micro_F1	0.26087
eval_HDIV	0.188406

Downloads last month: 1

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for kamel-usp/jbcs2025_Llama-3.1-8B-llama31_classification_lora-C2-full_context-r16

Base model

meta-llama/Llama-3.1-8B

Adapter

(745)

this model

Dataset used to train kamel-usp/jbcs2025_Llama-3.1-8B-llama31_classification_lora-C2-full_context-r16

Collection including kamel-usp/jbcs2025_Llama-3.1-8B-llama31_classification_lora-C2-full_context-r16

JBCS2025

154 items • Updated Mar 2 • 1

Evaluation results

Macro F1 on Automated Essay Score ENEM Dataset
test set self-reported

0.200
QWK on Automated Essay Score ENEM Dataset
test set self-reported

0.291
Weighted Macro F1 on Automated Essay Score ENEM Dataset
test set self-reported

0.208