Downloads · 30 days
6
21% of all-time downloads
phi-3-mini-LoRA
fullmetaldr/phi-3-mini-LoRA
phi-3-mini-LoRA is a machine learning model from fullmetaldr. 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 mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
28
Public
Repo size
18.3 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors17.8 MB · 88%
At a glance
- Library
- peft
- License
- mit
- Access
- Public
- Created
- Jul 18, 2024
- Updated
- Jul 18, 2024
- SHA
- f3ca0441
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. -->
phi-3-mini-LoRA
This model is a fine-tuned version of microsoft/Phi-3-mini-4k-instruct on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5562
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.8876 | 0.1810 | 100 | 0.6187 |
| 0.5945 | 0.3619 | 200 | 0.5746 |
| 0.57 | 0.5429 | 300 | 0.5678 |
| 0.5714 | 0.7238 | 400 | 0.5638 |
| 0.558 | 0.9048 | 500 | 0.5623 |
| 0.5654 | 1.0857 | 600 | 0.5608 |
| 0.5526 | 1.2667 | 700 | 0.5597 |
| 0.5538 | 1.4476 | 800 | 0.5588 |
| 0.5667 | 1.6286 | 900 | 0.5579 |
| 0.5557 | 1.8095 | 1000 | 0.5574 |
| 0.5546 | 1.9905 | 1100 | 0.5570 |
| 0.5469 | 2.1715 | 1200 | 0.5566 |
| 0.5611 | 2.3524 | 1300 | 0.5566 |
| 0.5511 | 2.5334 | 1400 | 0.5563 |
| 0.5523 | 2.7143 | 1500 | 0.5562 |
| 0.5541 | 2.8953 | 1600 | 0.5562 |
Framework versions
- PEFT 0.11.1
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Library
- peft
- License
- mit
- Created
- Jul 18, 2024
- Updated
- Jul 18, 2024