Downloads · 30 days
0
V0424HMA6
Litzy619/V0424HMA6
V0424HMA6 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 24, 2024
Parameters
2.9B
6.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors5.9 GB · 91%
Parameter types
How the weights are stored.
F162.8B · 97%
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. -->
V0424HMA6
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: 0.1480
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 |
|---|---|---|---|
| 1.6303 | 0.09 | 10 | 0.1548 |
| 0.1532 | 0.18 | 20 | 0.1184 |
| 0.1168 | 0.27 | 30 | 0.0949 |
| 0.2198 | 0.36 | 40 | 0.0971 |
| 0.0993 | 0.45 | 50 | 0.0863 |
| 0.0947 | 0.54 | 60 | 0.0737 |
| 0.0782 | 0.63 | 70 | 0.0718 |
| 0.086 | 0.73 | 80 | 0.0760 |
| 0.0877 | 0.82 | 90 | 0.0852 |
| 0.1259 | 0.91 | 100 | 0.0977 |
| 0.4521 | 1.0 | 110 | 0.4505 |
| 2.192 | 1.09 | 120 | 0.3481 |
| 0.98 | 1.18 | 130 | 0.3816 |
| 0.2241 | 1.27 | 140 | 0.1646 |
| 0.2434 | 1.36 | 150 | 0.3400 |
| 0.5348 | 1.45 | 160 | 0.1840 |
| 0.1717 | 1.54 | 170 | 0.1585 |
| 0.1724 | 1.63 | 180 | 0.1613 |
| 0.1633 | 1.72 | 190 | 0.1531 |
| 0.1621 | 1.81 | 200 | 0.1668 |
| 0.1661 | 1.9 | 210 | 0.1782 |
| 0.1755 | 1.99 | 220 | 0.1592 |
| 0.1634 | 2.08 | 230 | 0.1635 |
| 0.1579 | 2.18 | 240 | 0.1507 |
| 0.1506 | 2.27 | 250 | 0.1524 |
| 0.1537 | 2.36 | 260 | 0.1487 |
| 0.1479 | 2.45 | 270 | 0.1506 |
| 0.1492 | 2.54 | 280 | 0.1469 |
| 0.1482 | 2.63 | 290 | 0.1489 |
| 0.1511 | 2.72 | 300 | 0.1479 |
| 0.1486 | 2.81 | 310 | 0.1476 |
| 0.149 | 2.9 | 320 | 0.1478 |
| 0.1495 | 2.99 | 330 | 0.1480 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.18.0
- Tokenizers 0.14.1
- License
- mit
- Created
- Apr 24, 2024
- Updated
- Apr 24, 2024