llama3.2-rank-8-weighted

hurtmongoose/llama3.2-rank-8-weighted

llama3.2-rank-8-weighted is a machine learning model from hurtmongoose. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as llama3.2.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

6% of all-time downloads

All-time downloads

Public

Repo size

261 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors24.4 MB · 59%

At a glance

Library: peft
License: llama3.2
Access: Public
Created: Dec 21, 2025
Updated: Dec 21, 2025
SHA: dec3ef52

Base models

meta-llama/Llama-3.2-3B-Instruct

Model card

From the Hugging Face model README

llama3.2-rank-8-weighted

This model is a fine-tuned version of meta-llama/Llama-3.2-3B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.7613
Accuracy: 0.9083
F1: 0.9033
Recall: 0.8567
Fpr: 0.04
Auc: 0.9671
Mcc: 0.8211

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0002
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 16
optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Recall	Fpr	Auc	Mcc
0.6145	1.0	313	0.2989	0.86	0.8700	0.9367	0.2167	0.9634	0.7286
0.5545	2.0	626	0.2630	0.895	0.8959	0.9033	0.1133	0.9664	0.7901
0.5775	3.0	939	0.7157	0.905	0.8998	0.8533	0.0433	0.9644	0.8144
0.4626	4.0	1252	0.5946	0.8867	0.8773	0.81	0.0367	0.9531	0.7826
0.1139	5.0	1565	0.7746	0.89	0.8826	0.8267	0.0467	0.9656	0.7863
0.0121	6.0	1878	1.5150	0.88	0.8681	0.79	0.03	0.9667	0.7726
0.0014	7.0	2191	1.5637	0.875	0.8619	0.78	0.03	0.9650	0.7639
0.0001	8.0	2504	1.5278	0.88	0.8686	0.7933	0.0333	0.9650	0.7717
0.0003	9.0	2817	1.5295	0.8767	0.8645	0.7867	0.0333	0.9647	0.7658
0.0001	10.0	3130	1.5303	0.8767	0.8645	0.7867	0.0333	0.9647	0.7658

Framework versions

PEFT 0.7.0
Transformers 4.57.3
Pytorch 2.9.1+cu128
Datasets 2.15.0
Tokenizers 0.22.1

Library: peft
License: llama3.2
Created: Dec 21, 2025
Updated: Dec 21, 2025