Downloads · 30 days
6
29% of all-time downloads
phi-3-mini-LoRA
pzs26401/phi-3-mini-LoRA
phi-3-mini-LoRA is a machine learning model from pzs26401. 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
21
Public
Repo size
17.8 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors17.8 MB · 91%
At a glance
- Library
- peft
- License
- mit
- Access
- Public
- Created
- Jul 31, 2024
- Updated
- Jul 31, 2024
- SHA
- 5ee55d24
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. -->
<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/> <img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>
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: 0.5538
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: 4
- total_train_batch_size: 16
- 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 |
|---|---|---|---|
| 0.9859 | 0.0905 | 100 | 0.7611 |
| 0.6236 | 0.1810 | 200 | 0.5919 |
| 0.5846 | 0.2714 | 300 | 0.5761 |
| 0.5813 | 0.3619 | 400 | 0.5696 |
| 0.5696 | 0.4524 | 500 | 0.5659 |
| 0.5616 | 0.5429 | 600 | 0.5638 |
| 0.5682 | 0.6333 | 700 | 0.5621 |
| 0.5683 | 0.7238 | 800 | 0.5615 |
| 0.5532 | 0.8143 | 900 | 0.5599 |
| 0.5571 | 0.9048 | 1000 | 0.5596 |
| 0.5695 | 0.9952 | 1100 | 0.5586 |
| 0.5547 | 1.0857 | 1200 | 0.5578 |
| 0.5524 | 1.1762 | 1300 | 0.5574 |
| 0.5458 | 1.2667 | 1400 | 0.5568 |
| 0.5447 | 1.3572 | 1500 | 0.5563 |
| 0.5566 | 1.4476 | 1600 | 0.5561 |
| 0.5678 | 1.5381 | 1700 | 0.5557 |
| 0.559 | 1.6286 | 1800 | 0.5553 |
| 0.5528 | 1.7191 | 1900 | 0.5556 |
| 0.5523 | 1.8095 | 2000 | 0.5548 |
| 0.5481 | 1.9000 | 2100 | 0.5550 |
| 0.5545 | 1.9905 | 2200 | 0.5546 |
| 0.5412 | 2.0810 | 2300 | 0.5544 |
| 0.5449 | 2.1715 | 2400 | 0.5543 |
| 0.5657 | 2.2619 | 2500 | 0.5543 |
| 0.5484 | 2.3524 | 2600 | 0.5541 |
| 0.5553 | 2.4429 | 2700 | 0.5540 |
| 0.5398 | 2.5334 | 2800 | 0.5540 |
| 0.5488 | 2.6238 | 2900 | 0.5537 |
| 0.5484 | 2.7143 | 3000 | 0.5538 |
| 0.5512 | 2.8048 | 3100 | 0.5538 |
| 0.5493 | 2.8953 | 3200 | 0.5537 |
| 0.5404 | 2.9857 | 3300 | 0.5538 |
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 31, 2024
- Updated
- Jul 31, 2024