Downloads · 30 days
0
Phi0503HMA24
Litzy619/Phi0503HMA24
Phi0503HMA24 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. -->
Phi0503HMA24
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: 0.0726
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 |
|---|---|---|---|
| 3.9527 | 0.09 | 10 | 0.4517 |
| 0.2973 | 0.18 | 20 | 0.2376 |
| 0.2492 | 0.27 | 30 | 0.3797 |
| 0.2204 | 0.36 | 40 | 0.1632 |
| 0.1199 | 0.45 | 50 | 0.1100 |
| 0.1216 | 0.54 | 60 | 0.0921 |
| 0.0821 | 0.63 | 70 | 0.0914 |
| 0.1329 | 0.73 | 80 | 0.3868 |
| 0.3425 | 0.82 | 90 | 0.1646 |
| 0.1313 | 0.91 | 100 | 0.0851 |
| 0.0883 | 1.0 | 110 | 0.0778 |
| 0.0649 | 1.09 | 120 | 0.0842 |
| 0.078 | 1.18 | 130 | 0.0862 |
| 0.0702 | 1.27 | 140 | 0.0741 |
| 0.075 | 1.36 | 150 | 0.0816 |
| 0.0812 | 1.45 | 160 | 0.0697 |
| 0.0612 | 1.54 | 170 | 0.0692 |
| 0.0611 | 1.63 | 180 | 0.0714 |
| 0.0578 | 1.72 | 190 | 0.0709 |
| 0.068 | 1.81 | 200 | 0.0684 |
| 0.0604 | 1.9 | 210 | 0.0715 |
| 0.0592 | 1.99 | 220 | 0.0698 |
| 0.0325 | 2.08 | 230 | 0.0825 |
| 0.0302 | 2.18 | 240 | 0.0940 |
| 0.0252 | 2.27 | 250 | 0.0822 |
| 0.0231 | 2.36 | 260 | 0.0770 |
| 0.0318 | 2.45 | 270 | 0.0715 |
| 0.0235 | 2.54 | 280 | 0.0717 |
| 0.0236 | 2.63 | 290 | 0.0746 |
| 0.0324 | 2.72 | 300 | 0.0733 |
| 0.0283 | 2.81 | 310 | 0.0720 |
| 0.0248 | 2.9 | 320 | 0.0721 |
| 0.0266 | 2.99 | 330 | 0.0726 |
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