Downloads · 30 days
0
Phi0503HMA22
Litzy619/Phi0503HMA22
Phi0503HMA22 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 11, 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. -->
Phi0503HMA22
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: 0.0803
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 |
|---|---|---|---|
| 4.2194 | 0.09 | 10 | 0.6300 |
| 0.3395 | 0.18 | 20 | 0.2247 |
| 0.2461 | 0.27 | 30 | 0.2248 |
| 0.2061 | 0.36 | 40 | 0.1918 |
| 0.2198 | 0.45 | 50 | 0.1831 |
| 0.1993 | 0.54 | 60 | 0.1771 |
| 0.1676 | 0.63 | 70 | 0.2615 |
| 0.1316 | 0.73 | 80 | 0.0854 |
| 0.0974 | 0.82 | 90 | 0.0932 |
| 0.0916 | 0.91 | 100 | 0.0787 |
| 0.0794 | 1.0 | 110 | 0.0806 |
| 0.0658 | 1.09 | 120 | 0.0709 |
| 0.0619 | 1.18 | 130 | 0.0891 |
| 0.0724 | 1.27 | 140 | 0.0779 |
| 0.0667 | 1.36 | 150 | 0.0794 |
| 0.0752 | 1.45 | 160 | 0.0705 |
| 0.067 | 1.54 | 170 | 0.0698 |
| 0.0627 | 1.63 | 180 | 0.0712 |
| 0.0604 | 1.72 | 190 | 0.0663 |
| 0.0635 | 1.81 | 200 | 0.0655 |
| 0.0567 | 1.9 | 210 | 0.0668 |
| 0.0553 | 1.99 | 220 | 0.0694 |
| 0.0276 | 2.08 | 230 | 0.0814 |
| 0.0285 | 2.18 | 240 | 0.0992 |
| 0.0254 | 2.27 | 250 | 0.0970 |
| 0.0213 | 2.36 | 260 | 0.0887 |
| 0.0274 | 2.45 | 270 | 0.0850 |
| 0.0203 | 2.54 | 280 | 0.0866 |
| 0.0185 | 2.63 | 290 | 0.0885 |
| 0.0295 | 2.72 | 300 | 0.0845 |
| 0.0314 | 2.81 | 310 | 0.0816 |
| 0.0253 | 2.9 | 320 | 0.0805 |
| 0.0245 | 2.99 | 330 | 0.0803 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.14.0
- License
- mit
- Created
- May 11, 2024
- Updated
- May 11, 2024