Downloads · 30 days
0
Phi0503HMA14OLD
Litzy619/Phi0503HMA14OLD
Phi0503HMA14OLD 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 8, 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. -->
Phi0503HMA14
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: 0.0738
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 |
|---|---|---|---|
| 4.2233 | 0.09 | 10 | 0.8637 |
| 0.4106 | 0.18 | 20 | 0.2438 |
| 0.2551 | 0.27 | 30 | 0.2755 |
| 0.2371 | 0.36 | 40 | 0.2183 |
| 0.2228 | 0.45 | 50 | 0.2071 |
| 0.1902 | 0.54 | 60 | 0.1768 |
| 0.2067 | 0.63 | 70 | 0.2505 |
| 0.1893 | 0.73 | 80 | 0.1504 |
| 0.1217 | 0.82 | 90 | 0.1161 |
| 0.1036 | 0.91 | 100 | 0.0835 |
| 0.0826 | 1.0 | 110 | 0.0735 |
| 0.064 | 1.09 | 120 | 0.0755 |
| 0.0594 | 1.18 | 130 | 0.0867 |
| 0.073 | 1.27 | 140 | 0.0728 |
| 0.0596 | 1.36 | 150 | 0.0720 |
| 0.0748 | 1.45 | 160 | 0.0685 |
| 0.0675 | 1.54 | 170 | 0.0663 |
| 0.0634 | 1.63 | 180 | 0.0620 |
| 0.0605 | 1.72 | 190 | 0.0593 |
| 0.0632 | 1.81 | 200 | 0.0609 |
| 0.0526 | 1.9 | 210 | 0.0663 |
| 0.0505 | 1.99 | 220 | 0.0689 |
| 0.0313 | 2.08 | 230 | 0.0721 |
| 0.0301 | 2.18 | 240 | 0.0821 |
| 0.0268 | 2.27 | 250 | 0.0789 |
| 0.0212 | 2.36 | 260 | 0.0793 |
| 0.0283 | 2.45 | 270 | 0.0768 |
| 0.0231 | 2.54 | 280 | 0.0750 |
| 0.0218 | 2.63 | 290 | 0.0761 |
| 0.0273 | 2.72 | 300 | 0.0756 |
| 0.0311 | 2.81 | 310 | 0.0743 |
| 0.0245 | 2.9 | 320 | 0.0735 |
| 0.025 | 2.99 | 330 | 0.0738 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.14.0
- License
- mit
- Created
- May 8, 2024
- Updated
- May 8, 2024