Downloads · 30 days
0
Phi0503HMA18OLD
Litzy619/Phi0503HMA18OLD
Phi0503HMA18OLD is a machine learning model from Litzy619. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
Access
Public
Updated May 10, 2024
Parameters
3.9B
16.7 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors7.9 GB · 95%
Parameter types
How the weights are stored.
BF163.8B · 98%
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. -->
Phi0503HMA18
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: 0.0803
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: 0.0003
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine_with_restarts
- lr_scheduler_warmup_steps: 60
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.9264 | 0.09 | 10 | 0.4060 |
| 0.5196 | 0.18 | 20 | 2.6047 |
| 0.5297 | 0.27 | 30 | 0.2263 |
| 0.2143 | 0.36 | 40 | 0.1990 |
| 0.2823 | 0.45 | 50 | 0.2488 |
| 0.2513 | 0.54 | 60 | 0.1911 |
| 0.1606 | 0.63 | 70 | 0.1463 |
| 0.1446 | 0.73 | 80 | 0.1406 |
| 0.1202 | 0.82 | 90 | 0.1288 |
| 0.1229 | 0.91 | 100 | 0.1081 |
| 0.1123 | 1.0 | 110 | 0.1439 |
| 0.123 | 1.09 | 120 | 0.1062 |
| 0.0765 | 1.18 | 130 | 0.0812 |
| 0.0736 | 1.27 | 140 | 0.0723 |
| 0.0629 | 1.36 | 150 | 0.0730 |
| 0.0554 | 1.45 | 160 | 0.0738 |
| 0.0532 | 1.54 | 170 | 0.0671 |
| 0.0595 | 1.63 | 180 | 0.0657 |
| 0.0594 | 1.72 | 190 | 0.0681 |
| 0.0613 | 1.81 | 200 | 0.0624 |
| 0.0488 | 1.9 | 210 | 0.0623 |
| 0.0576 | 1.99 | 220 | 0.0607 |
| 0.0284 | 2.08 | 230 | 0.0712 |
| 0.0171 | 2.18 | 240 | 0.1021 |
| 0.0287 | 2.27 | 250 | 0.0831 |
| 0.0209 | 2.36 | 260 | 0.0753 |
| 0.0229 | 2.45 | 270 | 0.0752 |
| 0.0209 | 2.54 | 280 | 0.0759 |
| 0.0206 | 2.63 | 290 | 0.0773 |
| 0.0199 | 2.72 | 300 | 0.0788 |
| 0.0162 | 2.81 | 310 | 0.0796 |
| 0.0181 | 2.9 | 320 | 0.0802 |
| 0.0213 | 2.99 | 330 | 0.0803 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.14.0
- License
- mit
- Created
- May 9, 2024
- Updated
- May 10, 2024