Downloads · 30 days
6
13% of all-time downloads
Llama-3.2-3B-banking77-lora
AzadDjan/Llama-3.2-3B-banking77-lora
Llama-3.2-3B-banking77-lora is a machine learning model from AzadDjan. 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
45
Public
Repo size
230 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors97.8 MB · 85%
At a glance
- Library
- peft
- License
- llama3.2
- Access
- Public
- Created
- Sep 17, 2026
- Updated
- Sep 17, 2026
- SHA
- 066287af
Base models
Datasets
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. -->
Llama-3.2-3B-banking77-lora
This model is a fine-tuned version of meta-llama/Llama-3.2-3B on the banking77 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3595
- Accuracy: 0.9301
- Precision: 0.9373
- Recall: 0.9338
- F1: 0.9328
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: 0.0001
- train_batch_size: 16
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.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: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.7430 | 1.0 | 282 | 0.4343 | 0.8931 | 0.9162 | 0.8975 | 0.8955 |
| 0.3837 | 2.0 | 564 | 0.3505 | 0.9141 | 0.9251 | 0.9189 | 0.9175 |
| 0.1656 | 3.0 | 846 | 0.3458 | 0.9321 | 0.9389 | 0.9367 | 0.9346 |
| 0.0814 | 4.0 | 1128 | 0.3654 | 0.9301 | 0.9404 | 0.9349 | 0.9343 |
| 0.0426 | 5.0 | 1410 | 0.3762 | 0.9271 | 0.9353 | 0.9323 | 0.9311 |
| 0.0081 | 6.0 | 1692 | 0.3638 | 0.9351 | 0.9427 | 0.9379 | 0.9377 |
| 0.0004 | 7.0 | 1974 | 0.3558 | 0.9311 | 0.9378 | 0.9342 | 0.9335 |
| 0.0002 | 8.0 | 2256 | 0.3595 | 0.9301 | 0.9373 | 0.9338 | 0.9328 |
Framework versions
- PEFT 0.21.0
- Transformers 5.17.0
- Pytorch 2.11.0+cu128
- Datasets 5.0.1
- Tokenizers 0.23.1
Built with Llama. Licensed under the Llama 3.2 Community License.
- Library
- peft
- License
- llama3.2
- Created
- Sep 17, 2026
- Updated
- Sep 17, 2026