Downloads · 30 days
0
Phi0503HMA19
Litzy619/Phi0503HMA19
Phi0503HMA19 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
16.7 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. -->
Phi0503HMA19
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: 0.0771
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: 60
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.0653 | 0.09 | 10 | 0.4649 |
| 0.2835 | 0.18 | 20 | 0.2213 |
| 0.2868 | 0.27 | 30 | 0.2329 |
| 0.2284 | 0.36 | 40 | 0.2334 |
| 0.2317 | 0.45 | 50 | 0.2268 |
| 0.219 | 0.54 | 60 | 0.2073 |
| 0.211 | 0.63 | 70 | 0.1848 |
| 0.1692 | 0.73 | 80 | 0.1167 |
| 0.1311 | 0.82 | 90 | 0.1255 |
| 0.1138 | 0.91 | 100 | 0.0954 |
| 0.0918 | 1.0 | 110 | 0.0852 |
| 0.0756 | 1.09 | 120 | 0.1067 |
| 0.0746 | 1.18 | 130 | 0.0875 |
| 0.0826 | 1.27 | 140 | 0.0751 |
| 0.0723 | 1.36 | 150 | 0.0737 |
| 0.0739 | 1.45 | 160 | 0.0685 |
| 0.0674 | 1.54 | 170 | 0.0687 |
| 0.0667 | 1.63 | 180 | 0.0673 |
| 0.0599 | 1.72 | 190 | 0.0692 |
| 0.0675 | 1.81 | 200 | 0.0677 |
| 0.0565 | 1.9 | 210 | 0.0731 |
| 0.0551 | 1.99 | 220 | 0.0714 |
| 0.0316 | 2.08 | 230 | 0.0762 |
| 0.0331 | 2.18 | 240 | 0.0865 |
| 0.0233 | 2.27 | 250 | 0.0880 |
| 0.0205 | 2.36 | 260 | 0.0863 |
| 0.0316 | 2.45 | 270 | 0.0802 |
| 0.0201 | 2.54 | 280 | 0.0790 |
| 0.0221 | 2.63 | 290 | 0.0803 |
| 0.0303 | 2.72 | 300 | 0.0800 |
| 0.0302 | 2.81 | 310 | 0.0781 |
| 0.027 | 2.9 | 320 | 0.0772 |
| 0.0268 | 2.99 | 330 | 0.0771 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.14.0
- License
- mit
- Created
- May 9, 2024
- Updated
- May 10, 2024