Downloads · 30 days
0
V0424HMA4
Litzy619/V0424HMA4
V0424HMA4 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. -->
V0424HMA4
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: 0.1475
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 |
|---|---|---|---|
| 1.7259 | 0.09 | 10 | 0.1501 |
| 0.1625 | 0.18 | 20 | 0.1179 |
| 0.1147 | 0.27 | 30 | 0.0946 |
| 0.1 | 0.36 | 40 | 0.0843 |
| 0.0845 | 0.45 | 50 | 0.0766 |
| 0.0932 | 0.54 | 60 | 0.0825 |
| 0.0859 | 0.63 | 70 | 0.0738 |
| 0.0804 | 0.73 | 80 | 0.0825 |
| 0.0886 | 0.82 | 90 | 0.0815 |
| 0.305 | 0.91 | 100 | 0.1126 |
| 0.1279 | 1.0 | 110 | 0.1019 |
| 0.6008 | 1.09 | 120 | 0.2538 |
| 1.0009 | 1.18 | 130 | 0.2666 |
| 0.2339 | 1.27 | 140 | 0.1617 |
| 0.2166 | 1.36 | 150 | 0.1888 |
| 0.1717 | 1.45 | 160 | 0.1619 |
| 0.166 | 1.54 | 170 | 0.1569 |
| 0.1608 | 1.63 | 180 | 0.1716 |
| 0.155 | 1.72 | 190 | 0.1543 |
| 0.1524 | 1.81 | 200 | 0.1611 |
| 0.1564 | 1.9 | 210 | 0.1490 |
| 0.1544 | 1.99 | 220 | 0.1514 |
| 0.1581 | 2.08 | 230 | 0.1557 |
| 0.1521 | 2.18 | 240 | 0.1514 |
| 0.1517 | 2.27 | 250 | 0.1486 |
| 0.1534 | 2.36 | 260 | 0.1484 |
| 0.1499 | 2.45 | 270 | 0.1484 |
| 0.1484 | 2.54 | 280 | 0.1466 |
| 0.1475 | 2.63 | 290 | 0.1485 |
| 0.15 | 2.72 | 300 | 0.1467 |
| 0.1495 | 2.81 | 310 | 0.1470 |
| 0.1488 | 2.9 | 320 | 0.1471 |
| 0.1482 | 2.99 | 330 | 0.1475 |
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