Downloads · 30 days
3
18% of all-time downloads
phi-3-mini-LoRA
TomSchut/phi-3-mini-LoRA
phi-3-mini-LoRA is a machine learning model from TomSchut. 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
17
Public
Repo size
36.2 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors35.7 MB · 94%
At a glance
- Library
- peft
- License
- mit
- Access
- Public
- Created
- Aug 14, 2024
- Updated
- Aug 14, 2024
- SHA
- 9c16fa9c
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: 0.3153
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 |
|---|---|---|---|
| 2.564 | 0.1763 | 100 | 0.5477 |
| 0.3761 | 0.3526 | 200 | 0.3389 |
| 0.3323 | 0.5289 | 300 | 0.3310 |
| 0.3286 | 0.7052 | 400 | 0.3266 |
| 0.3229 | 0.8814 | 500 | 0.3234 |
| 0.3229 | 1.0577 | 600 | 0.3213 |
| 0.3201 | 1.2340 | 700 | 0.3211 |
| 0.3165 | 1.4103 | 800 | 0.3212 |
| 0.3189 | 1.5866 | 900 | 0.3189 |
| 0.3181 | 1.7629 | 1000 | 0.3185 |
| 0.3166 | 1.9392 | 1100 | 0.3180 |
| 0.3152 | 2.1155 | 1200 | 0.3172 |
| 0.3153 | 2.2918 | 1300 | 0.3169 |
| 0.3148 | 2.4680 | 1400 | 0.3168 |
| 0.3131 | 2.6443 | 1500 | 0.3158 |
| 0.3139 | 2.8206 | 1600 | 0.3155 |
| 0.3134 | 2.9969 | 1700 | 0.3153 |
Framework versions
- PEFT 0.12.0
- Transformers 4.44.0
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1
- Library
- peft
- License
- mit
- Created
- Aug 14, 2024
- Updated
- Aug 14, 2024