Downloads · 30 days
0
Phi0503HMA26
Litzy619/Phi0503HMA26
Phi0503HMA26 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 12, 2024
Parameters
3.9B
16.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors7.9 GB · 96%
Parameter types
How the weights are stored.
BF163.8B · 99%
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. -->
Phi0503HMA26
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: 0.0635
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: 80
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.4865 | 0.09 | 10 | 0.8844 |
| 0.3885 | 0.18 | 20 | 0.2386 |
| 0.2667 | 0.27 | 30 | 0.2422 |
| 0.2338 | 0.36 | 40 | 0.2291 |
| 0.2321 | 0.45 | 50 | 0.2215 |
| 0.226 | 0.54 | 60 | 0.2156 |
| 0.2283 | 0.63 | 70 | 0.2006 |
| 0.2115 | 0.73 | 80 | 0.2034 |
| 0.1803 | 0.82 | 90 | 0.1707 |
| 0.1687 | 0.91 | 100 | 0.2004 |
| 0.1851 | 1.0 | 110 | 0.1699 |
| 0.1641 | 1.09 | 120 | 0.1648 |
| 0.1642 | 1.18 | 130 | 0.1666 |
| 0.1748 | 1.27 | 140 | 0.1629 |
| 0.1665 | 1.36 | 150 | 0.1627 |
| 0.134 | 1.45 | 160 | 0.1023 |
| 0.1085 | 1.54 | 170 | 0.0887 |
| 0.0876 | 1.63 | 180 | 0.0784 |
| 0.0749 | 1.72 | 190 | 0.0729 |
| 0.0673 | 1.81 | 200 | 0.0721 |
| 0.0687 | 1.9 | 210 | 0.0764 |
| 0.0648 | 1.99 | 220 | 0.0698 |
| 0.0477 | 2.08 | 230 | 0.0734 |
| 0.0522 | 2.18 | 240 | 0.0681 |
| 0.0437 | 2.27 | 250 | 0.0679 |
| 0.0437 | 2.36 | 260 | 0.0661 |
| 0.0497 | 2.45 | 270 | 0.0651 |
| 0.0437 | 2.54 | 280 | 0.0651 |
| 0.0433 | 2.63 | 290 | 0.0651 |
| 0.0464 | 2.72 | 300 | 0.0649 |
| 0.0558 | 2.81 | 310 | 0.0640 |
| 0.0455 | 2.9 | 320 | 0.0635 |
| 0.0469 | 2.99 | 330 | 0.0635 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.14.0
- License
- mit
- Created
- May 11, 2024
- Updated
- May 12, 2024