Downloads · 30 days
0
PHI30512HMAB2H
Litzy619/PHI30512HMAB2H
PHI30512HMAB2H 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 13, 2024
Parameters
3.9B
8.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors7.9 GB · 96%
Parameter types
How the weights are stored.
BF163.8B · 99%
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. -->
PHI30512HMAB2H
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: 0.0778
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 |
|---|---|---|---|
| 5.1146 | 0.09 | 10 | 2.3492 |
| 1.1333 | 0.18 | 20 | 0.3905 |
| 0.7088 | 0.27 | 30 | 0.3297 |
| 0.2795 | 0.36 | 40 | 0.2609 |
| 0.2615 | 0.45 | 50 | 0.2361 |
| 0.2203 | 0.54 | 60 | 0.2194 |
| 0.2338 | 0.63 | 70 | 0.2381 |
| 0.2231 | 0.73 | 80 | 0.1473 |
| 0.3939 | 0.82 | 90 | 0.2078 |
| 0.1899 | 0.91 | 100 | 0.1756 |
| 0.1743 | 1.0 | 110 | 0.1207 |
| 0.1234 | 1.09 | 120 | 0.1252 |
| 0.0985 | 1.18 | 130 | 0.0798 |
| 0.1583 | 1.27 | 140 | 0.0846 |
| 0.1099 | 1.36 | 150 | 0.1042 |
| 0.1727 | 1.45 | 160 | 0.1675 |
| 0.1701 | 1.54 | 170 | 0.1622 |
| 0.1069 | 1.63 | 180 | 0.0767 |
| 0.0735 | 1.72 | 190 | 0.0767 |
| 0.12 | 1.81 | 200 | 0.5347 |
| 0.3029 | 1.9 | 210 | 0.0825 |
| 0.0712 | 1.99 | 220 | 0.0767 |
| 0.0669 | 2.08 | 230 | 0.9840 |
| 0.2695 | 2.18 | 240 | 0.5707 |
| 0.385 | 2.27 | 250 | 0.1643 |
| 0.1644 | 2.36 | 260 | 0.1611 |
| 0.1309 | 2.45 | 270 | 0.0754 |
| 0.0609 | 2.54 | 280 | 0.0761 |
| 0.0719 | 2.63 | 290 | 0.0951 |
| 0.0886 | 2.72 | 300 | 0.0872 |
| 0.0838 | 2.81 | 310 | 0.0797 |
| 0.0698 | 2.9 | 320 | 0.0779 |
| 0.0735 | 2.99 | 330 | 0.0778 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.14.0
- License
- mit
- Created
- May 12, 2024
- Updated
- May 13, 2024