Downloads · 30 days
0
PHI30512HMAB25H
Litzy619/PHI30512HMAB25H
PHI30512HMAB25H 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. -->
PHI30512HMAB25H
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: 0.0648
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 |
|---|---|---|---|
| 4.8258 | 0.09 | 10 | 1.2738 |
| 0.6051 | 0.18 | 20 | 0.2854 |
| 0.2802 | 0.27 | 30 | 0.3012 |
| 0.2748 | 0.36 | 40 | 0.2442 |
| 0.2649 | 0.45 | 50 | 0.2520 |
| 0.3586 | 0.54 | 60 | 0.2373 |
| 0.2836 | 0.63 | 70 | 0.2159 |
| 0.2169 | 0.73 | 80 | 0.2030 |
| 0.2442 | 0.82 | 90 | 0.1807 |
| 0.1802 | 0.91 | 100 | 0.1371 |
| 0.123 | 1.0 | 110 | 0.0948 |
| 0.0921 | 1.09 | 120 | 0.0793 |
| 0.0776 | 1.18 | 130 | 0.0916 |
| 0.0914 | 1.27 | 140 | 0.0796 |
| 0.0757 | 1.36 | 150 | 0.0795 |
| 0.0761 | 1.45 | 160 | 0.0762 |
| 0.0695 | 1.54 | 170 | 0.0733 |
| 0.0741 | 1.63 | 180 | 0.0658 |
| 0.07 | 1.72 | 190 | 0.0649 |
| 0.0708 | 1.81 | 200 | 0.0671 |
| 0.0604 | 1.9 | 210 | 0.0779 |
| 0.0665 | 1.99 | 220 | 0.0678 |
| 0.0413 | 2.08 | 230 | 0.0775 |
| 0.0339 | 2.18 | 240 | 0.0797 |
| 0.0361 | 2.27 | 250 | 0.0675 |
| 0.0368 | 2.36 | 260 | 0.0661 |
| 0.044 | 2.45 | 270 | 0.0670 |
| 0.0327 | 2.54 | 280 | 0.0665 |
| 0.0304 | 2.63 | 290 | 0.0685 |
| 0.0417 | 2.72 | 300 | 0.0679 |
| 0.0434 | 2.81 | 310 | 0.0654 |
| 0.039 | 2.9 | 320 | 0.0647 |
| 0.0342 | 2.99 | 330 | 0.0648 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.14.0
- License
- mit
- Created
- May 13, 2024
- Updated
- May 13, 2024