Downloads · 30 days
0
Phi0503HMA10
Litzy619/Phi0503HMA10
Phi0503HMA10 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 10, 2024
Parameters
3.9B
8.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors7.9 GB · 95%
Parameter types
How the weights are stored.
BF163.8B · 98%
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. -->
Phi0503HMA10
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: 0.1439
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: 100
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.5505 | 0.09 | 10 | 1.2821 |
| 0.516 | 0.18 | 20 | 0.2954 |
| 0.2842 | 0.27 | 30 | 0.3173 |
| 0.3169 | 0.36 | 40 | 0.4883 |
| 0.4946 | 0.45 | 50 | 0.2295 |
| 0.6098 | 0.54 | 60 | 1.0244 |
| 0.567 | 0.63 | 70 | 0.2381 |
| 0.2346 | 0.73 | 80 | 0.2265 |
| 0.2844 | 0.82 | 90 | 0.2214 |
| 4.2973 | 0.91 | 100 | 2.3953 |
| 1.7624 | 1.0 | 110 | 1.0186 |
| 0.7104 | 1.09 | 120 | 0.4461 |
| 0.3678 | 1.18 | 130 | 0.2999 |
| 0.2858 | 1.27 | 140 | 0.2034 |
| 0.224 | 1.36 | 150 | 0.1894 |
| 0.2127 | 1.45 | 160 | 0.2045 |
| 0.2229 | 1.54 | 170 | 0.1843 |
| 0.1846 | 1.63 | 180 | 0.1824 |
| 0.1745 | 1.72 | 190 | 0.1665 |
| 0.1676 | 1.81 | 200 | 0.1567 |
| 0.1583 | 1.9 | 210 | 0.1572 |
| 0.1475 | 1.99 | 220 | 0.1532 |
| 0.1529 | 2.08 | 230 | 0.1466 |
| 0.1481 | 2.18 | 240 | 0.1453 |
| 0.1474 | 2.27 | 250 | 0.1497 |
| 0.1479 | 2.36 | 260 | 0.1471 |
| 0.1404 | 2.45 | 270 | 0.1438 |
| 0.1457 | 2.54 | 280 | 0.1444 |
| 0.147 | 2.63 | 290 | 0.1451 |
| 0.1451 | 2.72 | 300 | 0.1444 |
| 0.1508 | 2.81 | 310 | 0.1442 |
| 0.1447 | 2.9 | 320 | 0.1439 |
| 0.1425 | 2.99 | 330 | 0.1439 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.14.0
- License
- mit
- Created
- May 10, 2024
- Updated
- May 10, 2024