Downloads · 30 days
0
PHI30512HMAB24H
Litzy619/PHI30512HMAB24H
PHI30512HMAB24H 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 13, 2024
Parameters
3.9B
8.2 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. -->
PHI30512HMAB24H
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: 0.1648
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 |
|---|---|---|---|
| 4.7682 | 0.09 | 10 | 1.1976 |
| 0.5956 | 0.18 | 20 | 0.2488 |
| 0.3055 | 0.27 | 30 | 0.2493 |
| 0.2386 | 0.36 | 40 | 0.2397 |
| 0.2408 | 0.45 | 50 | 0.2257 |
| 0.2121 | 0.54 | 60 | 1.7294 |
| 0.7562 | 0.63 | 70 | 0.1616 |
| 0.1541 | 0.73 | 80 | 0.1300 |
| 0.2129 | 0.82 | 90 | 0.4410 |
| 4.0055 | 0.91 | 100 | 0.2221 |
| 0.1856 | 1.0 | 110 | 0.2544 |
| 1.5657 | 1.09 | 120 | 6.5436 |
| 4.5499 | 1.18 | 130 | 2.2041 |
| 2.0579 | 1.27 | 140 | 1.1273 |
| 1.0437 | 1.36 | 150 | 0.8327 |
| 0.7015 | 1.45 | 160 | 0.4925 |
| 0.5356 | 1.54 | 170 | 0.4550 |
| 0.3779 | 1.63 | 180 | 0.3327 |
| 0.3294 | 1.72 | 190 | 0.2671 |
| 0.2727 | 1.81 | 200 | 0.2339 |
| 0.2032 | 1.9 | 210 | 0.1869 |
| 0.1883 | 1.99 | 220 | 0.1860 |
| 0.1833 | 2.08 | 230 | 0.1784 |
| 0.1791 | 2.18 | 240 | 0.1742 |
| 0.1737 | 2.27 | 250 | 0.1759 |
| 0.175 | 2.36 | 260 | 0.1742 |
| 0.1724 | 2.45 | 270 | 0.1769 |
| 0.1716 | 2.54 | 280 | 0.1694 |
| 0.1721 | 2.63 | 290 | 0.1694 |
| 0.1693 | 2.72 | 300 | 0.1669 |
| 0.1706 | 2.81 | 310 | 0.1668 |
| 0.1638 | 2.9 | 320 | 0.1649 |
| 0.167 | 2.99 | 330 | 0.1648 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.14.0
- License
- mit
- Created
- May 13, 2024
- Updated
- May 13, 2024