Downloads · 30 days
0
PHI30512HMAB17H
Litzy619/PHI30512HMAB17H
PHI30512HMAB17H 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
Repo size
327 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin327 MB · 100%
At a glance
- License
- mit
- Access
- Public
- Created
- May 13, 2024
- Updated
- May 13, 2024
- SHA
- 4d6d61cf
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. -->
PHI30512HMAB17H
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: 0.0440
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 |
|---|---|---|---|
| 4.1597 | 0.09 | 10 | 0.7808 |
| 0.4185 | 0.18 | 20 | 0.4023 |
| 0.3734 | 0.27 | 30 | 0.2647 |
| 0.2773 | 0.36 | 40 | 0.2336 |
| 0.2505 | 0.45 | 50 | 0.2249 |
| 0.2522 | 0.54 | 60 | 0.2339 |
| 0.2124 | 0.63 | 70 | 0.1910 |
| 0.2256 | 0.73 | 80 | 0.2006 |
| 0.1823 | 0.82 | 90 | 0.1994 |
| 0.1815 | 0.91 | 100 | 0.1664 |
| 0.171 | 1.0 | 110 | 0.1653 |
| 0.1624 | 1.09 | 120 | 0.1640 |
| 0.1636 | 1.18 | 130 | 0.1678 |
| 0.1769 | 1.27 | 140 | 0.1674 |
| 0.169 | 1.36 | 150 | 0.1653 |
| 0.1611 | 1.45 | 160 | 0.1644 |
| 0.1622 | 1.54 | 170 | 0.1564 |
| 0.1644 | 1.63 | 180 | 0.1590 |
| 0.149 | 1.72 | 190 | 0.1235 |
| 0.1722 | 1.81 | 200 | 0.1176 |
| 0.1604 | 1.9 | 210 | 0.1478 |
| 0.1312 | 1.99 | 220 | 0.0832 |
| 0.0895 | 2.08 | 230 | 0.1083 |
| 0.097 | 2.18 | 240 | 0.0659 |
| 0.058 | 2.27 | 250 | 0.0510 |
| 0.0572 | 2.36 | 260 | 0.0477 |
| 0.0554 | 2.45 | 270 | 0.0463 |
| 0.041 | 2.54 | 280 | 0.0462 |
| 0.0603 | 2.63 | 290 | 0.0443 |
| 0.0451 | 2.72 | 300 | 0.0442 |
| 0.0419 | 2.81 | 310 | 0.0446 |
| 0.0517 | 2.9 | 320 | 0.0441 |
| 0.0626 | 2.99 | 330 | 0.0440 |
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