Downloads · 30 days
7
33% of all-time downloads
phi-3-mini-LoRA
ishidahra/phi-3-mini-LoRA
phi-3-mini-LoRA is a machine learning model from ishidahra. 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
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
- Nov 14, 2024
- Updated
- Nov 14, 2024
- SHA
- a67e1f8f
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-3.5-mini-instruct on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5654
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- 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 |
|---|---|---|---|
| 1.2166 | 0.1809 | 100 | 0.6490 |
| 0.6134 | 0.3618 | 200 | 0.5894 |
| 0.5827 | 0.5427 | 300 | 0.5800 |
| 0.5851 | 0.7237 | 400 | 0.5755 |
| 0.5672 | 0.9046 | 500 | 0.5733 |
| 0.5796 | 1.0855 | 600 | 0.5708 |
| 0.5619 | 1.2664 | 700 | 0.5693 |
| 0.5644 | 1.4473 | 800 | 0.5685 |
| 0.5777 | 1.6282 | 900 | 0.5671 |
| 0.5639 | 1.8091 | 1000 | 0.5670 |
| 0.5647 | 1.9900 | 1100 | 0.5663 |
| 0.5558 | 2.1710 | 1200 | 0.5663 |
| 0.5726 | 2.3519 | 1300 | 0.5657 |
| 0.5602 | 2.5328 | 1400 | 0.5656 |
| 0.5609 | 2.7137 | 1500 | 0.5654 |
| 0.5644 | 2.8946 | 1600 | 0.5654 |
Framework versions
- PEFT 0.10.0
- Transformers 4.41.2
- Pytorch 2.2.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1
- Library
- peft
- License
- mit
- Created
- Nov 14, 2024
- Updated
- Nov 14, 2024