Downloads · 30 days
0
V0422MADP4B
Litzy619/V0422MADP4B
V0422MADP4B 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 Apr 23, 2024
Parameters
2.9B
6.6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors6 GB · 90%
Parameter types
How the weights are stored.
F162.8B · 96%
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. -->
V0422MADP4B
This model is a fine-tuned version of microsoft/phi-2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1556
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 |
|---|---|---|---|
| 5.7814 | 0.09 | 10 | 2.3299 |
| 3.5184 | 0.18 | 20 | 1.4709 |
| 0.9285 | 0.27 | 30 | 0.5274 |
| 0.2707 | 0.36 | 40 | 0.2098 |
| 0.1787 | 0.45 | 50 | 0.1532 |
| 0.167 | 0.54 | 60 | 0.1670 |
| 0.1677 | 0.63 | 70 | 0.1730 |
| 0.168 | 0.73 | 80 | 0.1649 |
| 0.1621 | 0.82 | 90 | 0.1719 |
| 0.1634 | 0.91 | 100 | 0.1898 |
| 0.1698 | 1.0 | 110 | 0.1689 |
| 0.1692 | 1.09 | 120 | 0.1730 |
| 0.1633 | 1.18 | 130 | 0.1680 |
| 0.1659 | 1.27 | 140 | 0.1974 |
| 0.1953 | 1.36 | 150 | 0.1618 |
| 0.1599 | 1.45 | 160 | 0.1535 |
| 0.1666 | 1.54 | 170 | 0.1564 |
| 0.1621 | 1.63 | 180 | 0.1572 |
| 0.1794 | 1.72 | 190 | 0.2161 |
| 0.2005 | 1.81 | 200 | 0.2021 |
| 0.1798 | 1.9 | 210 | 0.2139 |
| 0.1747 | 1.99 | 220 | 0.1848 |
| 0.1773 | 2.08 | 230 | 0.1753 |
| 0.1617 | 2.18 | 240 | 0.1605 |
| 0.1657 | 2.27 | 250 | 0.1646 |
| 0.1584 | 2.36 | 260 | 0.1595 |
| 0.1643 | 2.45 | 270 | 0.1582 |
| 0.1582 | 2.54 | 280 | 0.1594 |
| 0.1583 | 2.63 | 290 | 0.1583 |
| 0.1597 | 2.72 | 300 | 0.1560 |
| 0.157 | 2.81 | 310 | 0.1557 |
| 0.1625 | 2.9 | 320 | 0.1558 |
| 0.1633 | 2.99 | 330 | 0.1556 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.2.2+cu121
- Datasets 2.18.0
- Tokenizers 0.14.1
- License
- mit
- Created
- Apr 22, 2024
- Updated
- Apr 23, 2024