Downloads · 30 days
0
V0424HMA5
Litzy619/V0424HMA5
V0424HMA5 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. -->
V0424HMA5
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: 0.1467
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 |
|---|---|---|---|
| 1.6866 | 0.09 | 10 | 0.1565 |
| 0.1493 | 0.18 | 20 | 0.1091 |
| 0.109 | 0.27 | 30 | 0.1005 |
| 0.1556 | 0.36 | 40 | 0.1006 |
| 0.0904 | 0.45 | 50 | 0.0750 |
| 0.0874 | 0.54 | 60 | 0.0702 |
| 0.0796 | 0.63 | 70 | 0.0750 |
| 0.1471 | 0.73 | 80 | 0.0761 |
| 0.0894 | 0.82 | 90 | 3.9310 |
| 1.6248 | 0.91 | 100 | 0.2083 |
| 0.3602 | 1.0 | 110 | 0.2208 |
| 0.7484 | 1.09 | 120 | 0.5896 |
| 0.2412 | 1.18 | 130 | 0.1540 |
| 0.1665 | 1.27 | 140 | 0.1771 |
| 0.1688 | 1.36 | 150 | 0.1605 |
| 0.1604 | 1.45 | 160 | 0.1586 |
| 0.1633 | 1.54 | 170 | 0.1550 |
| 0.1616 | 1.63 | 180 | 0.1554 |
| 0.1543 | 1.72 | 190 | 0.1481 |
| 0.149 | 1.81 | 200 | 0.1602 |
| 0.1544 | 1.9 | 210 | 0.1482 |
| 0.1535 | 1.99 | 220 | 0.1489 |
| 0.1529 | 2.08 | 230 | 0.1527 |
| 0.1473 | 2.18 | 240 | 0.1485 |
| 0.1469 | 2.27 | 250 | 0.1484 |
| 0.1489 | 2.36 | 260 | 0.1483 |
| 0.1469 | 2.45 | 270 | 0.1478 |
| 0.1459 | 2.54 | 280 | 0.1466 |
| 0.1461 | 2.63 | 290 | 0.1473 |
| 0.1483 | 2.72 | 300 | 0.1467 |
| 0.1471 | 2.81 | 310 | 0.1468 |
| 0.1475 | 2.9 | 320 | 0.1466 |
| 0.1474 | 2.99 | 330 | 0.1467 |
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