Downloads · 30 days
7
10% of all-time downloads
llama3.2-rank-4-weighted
hurtmongoose/llama3.2-rank-4-weighted
llama3.2-rank-4-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. --
All-time downloads
72
Public
Repo size
139 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.json17.3 MB · 59%
At a glance
- Library
- peft
- License
- llama3.2
- Access
- Public
- Created
- Dec 21, 2025
- Updated
- Dec 21, 2025
- SHA
- 434cfab2
Base models
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
llama3.2-rank-4-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: 0.3552
- Accuracy: 0.8967
- F1: 0.8980
- Recall: 0.91
- Fpr: 0.1167
- Auc: 0.9574
- Mcc: 0.7936
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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.6516 | 1.0 | 313 | 0.3858 | 0.8633 | 0.8715 | 0.9267 | 0.2 | 0.9511 | 0.7326 |
| 0.603 | 2.0 | 626 | 0.2577 | 0.8967 | 0.8997 | 0.9267 | 0.1333 | 0.9669 | 0.7948 |
| 0.6374 | 3.0 | 939 | 0.6223 | 0.89 | 0.8817 | 0.82 | 0.04 | 0.9654 | 0.7878 |
| 0.4289 | 4.0 | 1252 | 0.7321 | 0.8817 | 0.8716 | 0.8033 | 0.04 | 0.9529 | 0.7729 |
| 0.1083 | 5.0 | 1565 | 0.8781 | 0.8867 | 0.8777 | 0.8133 | 0.04 | 0.9603 | 0.7818 |
| 0.0747 | 6.0 | 1878 | 1.2371 | 0.88 | 0.8686 | 0.7933 | 0.0333 | 0.9627 | 0.7717 |
| 0.0112 | 7.0 | 2191 | 1.2676 | 0.8833 | 0.8727 | 0.8 | 0.0333 | 0.9631 | 0.7775 |
| 0.0041 | 8.0 | 2504 | 1.2726 | 0.8833 | 0.8727 | 0.8 | 0.0333 | 0.9630 | 0.7775 |
| 0.0011 | 9.0 | 2817 | 1.2964 | 0.8817 | 0.8707 | 0.7967 | 0.0333 | 0.9628 | 0.7746 |
| 0.0001 | 10.0 | 3130 | 1.2992 | 0.8817 | 0.8707 | 0.7967 | 0.0333 | 0.9629 | 0.7746 |
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