Downloads · 30 days
12
43% of all-time downloads
edos_taskb_llama3b_lora
Anwaarma/edos_taskb_llama3b_lora
edos_taskb_llama3b_lora is a machine learning model from Anwaarma. 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
28
Public
Repo size
990 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.2 GB · 97%
At a glance
- Library
- peft
- License
- llama3.2
- Access
- Public
- Created
- Sep 24, 2025
- Updated
- Sep 24, 2025
- SHA
- c7f127dd
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. -->
edos_taskb_llama3b_lora
This model is a fine-tuned version of meta-llama/Llama-3.2-3B on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9839
- Accuracy: 0.5660
- F1 Macro: 0.5362
- F1 Micro: 0.5660
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: 0.00015
- train_batch_size: 32
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.06
- num_epochs: 15
- label_smoothing_factor: 0.02
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | F1 Micro |
|---|---|---|---|---|---|---|
| 2.2913 | 1.8598 | 100 | 1.0997 | 0.5144 | 0.4213 | 0.5144 |
| 2.005 | 3.7103 | 200 | 1.0233 | 0.5309 | 0.4693 | 0.5309 |
| 1.8166 | 5.5607 | 300 | 0.9849 | 0.5700 | 0.4826 | 0.5700 |
| 1.7241 | 7.4112 | 400 | 0.9637 | 0.5679 | 0.5349 | 0.5679 |
| 1.6516 | 9.2617 | 500 | 0.9544 | 0.5802 | 0.4941 | 0.5802 |
| 1.6584 | 11.1121 | 600 | 0.9481 | 0.5905 | 0.5182 | 0.5905 |
| 1.6708 | 12.9720 | 700 | 0.9471 | 0.5844 | 0.5152 | 0.5844 |
Framework versions
- PEFT 0.17.1
- Transformers 4.56.2
- Pytorch 2.8.0+cu126
- Datasets 4.1.1
- Tokenizers 0.22.0
- Library
- peft
- License
- llama3.2
- Created
- Sep 24, 2025
- Updated
- Sep 24, 2025