Downloads · 30 days
6
8% of all-time downloads
llama3.2-rank-16-weighted
hurtmongoose/llama3.2-rank-16-weighted
llama3.2-rank-16-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
78
Public
Repo size
504 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors48.7 MB · 74%
At a glance
- Library
- peft
- License
- llama3.2
- Access
- Public
- Created
- Dec 21, 2025
- Updated
- Dec 21, 2025
- SHA
- cace4639
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-16-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: 0.3372
- Accuracy: 0.9133
- F1: 0.9107
- Recall: 0.8833
- Fpr: 0.0567
- Auc: 0.9658
- Mcc: 0.8282
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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.6247 | 1.0 | 313 | 0.5603 | 0.8967 | 0.8927 | 0.86 | 0.0667 | 0.9635 | 0.7955 |
| 0.6361 | 2.0 | 626 | 0.2650 | 0.895 | 0.8938 | 0.8833 | 0.0933 | 0.9712 | 0.7902 |
| 0.6481 | 3.0 | 939 | 0.7435 | 0.8917 | 0.8862 | 0.8433 | 0.06 | 0.9628 | 0.7870 |
| 0.3643 | 4.0 | 1252 | 0.9034 | 0.8683 | 0.8540 | 0.77 | 0.0333 | 0.9575 | 0.7513 |
| 0.2572 | 5.0 | 1565 | 0.8421 | 0.8933 | 0.8865 | 0.8333 | 0.0467 | 0.9679 | 0.7924 |
| 0.0985 | 6.0 | 1878 | 1.3124 | 0.8817 | 0.8716 | 0.8033 | 0.04 | 0.9622 | 0.7729 |
| 0.0178 | 7.0 | 2191 | 1.6465 | 0.8833 | 0.8727 | 0.8 | 0.0333 | 0.9609 | 0.7775 |
| 0.0002 | 8.0 | 2504 | 1.6032 | 0.8833 | 0.8727 | 0.8 | 0.0333 | 0.9593 | 0.7775 |
| 0.0014 | 9.0 | 2817 | 1.6719 | 0.885 | 0.8743 | 0.8 | 0.03 | 0.9591 | 0.7814 |
| 0.0008 | 10.0 | 3130 | 1.6738 | 0.885 | 0.8743 | 0.8 | 0.03 | 0.9588 | 0.7814 |
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