Downloads · 30 days
0
Phi0503HMA1
Litzy619/Phi0503HMA1
Phi0503HMA1 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 4, 2024
Parameters
3.9B
8.4 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. -->
Phi0503HMA1
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: 0.1635
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 |
|---|---|---|---|
| 4.5767 | 0.09 | 10 | 1.3277 |
| 0.528 | 0.18 | 20 | 0.2431 |
| 0.272 | 0.27 | 30 | 0.2412 |
| 0.4937 | 0.36 | 40 | 1.1132 |
| 0.3726 | 0.45 | 50 | 0.2147 |
| 0.2214 | 0.54 | 60 | 0.2026 |
| 0.3024 | 0.63 | 70 | 0.1963 |
| 0.2358 | 0.73 | 80 | 0.2236 |
| 0.1673 | 0.82 | 90 | 0.1289 |
| 0.1417 | 0.91 | 100 | 0.3550 |
| 0.6614 | 1.0 | 110 | 0.2344 |
| 0.2316 | 1.09 | 120 | 0.1982 |
| 0.3203 | 1.18 | 130 | 0.1760 |
| 0.2092 | 1.27 | 140 | 0.1681 |
| 0.1788 | 1.36 | 150 | 0.1693 |
| 0.8967 | 1.45 | 160 | 1.4252 |
| 0.7768 | 1.54 | 170 | 0.1814 |
| 0.1745 | 1.63 | 180 | 0.1690 |
| 0.1651 | 1.72 | 190 | 0.1664 |
| 0.1648 | 1.81 | 200 | 0.1655 |
| 0.1678 | 1.9 | 210 | 0.1649 |
| 0.164 | 1.99 | 220 | 0.1642 |
| 0.1646 | 2.08 | 230 | 0.1630 |
| 0.1609 | 2.18 | 240 | 0.1630 |
| 0.1601 | 2.27 | 250 | 0.1636 |
| 0.1634 | 2.36 | 260 | 0.1642 |
| 0.1616 | 2.45 | 270 | 0.1640 |
| 0.1619 | 2.54 | 280 | 0.1642 |
| 0.1624 | 2.63 | 290 | 0.1642 |
| 0.1634 | 2.72 | 300 | 0.1638 |
| 0.1634 | 2.81 | 310 | 0.1635 |
| 0.1619 | 2.9 | 320 | 0.1635 |
| 0.1665 | 2.99 | 330 | 0.1635 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.14.1
- License
- mit
- Created
- May 3, 2024
- Updated
- May 4, 2024