Downloads · 30 days
0
Phi0503HMA10OLD
Litzy619/Phi0503HMA10OLD
Phi0503HMA10OLD 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 7, 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. -->
Phi0503HMA10
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: 0.0671
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 |
|---|---|---|---|
| 4.3726 | 0.09 | 10 | 1.2275 |
| 0.6273 | 0.18 | 20 | 0.3121 |
| 0.5505 | 0.27 | 30 | 0.2639 |
| 0.2708 | 0.36 | 40 | 0.2764 |
| 0.2706 | 0.45 | 50 | 0.2277 |
| 0.229 | 0.54 | 60 | 0.2141 |
| 0.2219 | 0.63 | 70 | 0.1942 |
| 0.2033 | 0.73 | 80 | 0.1793 |
| 0.1404 | 0.82 | 90 | 0.1439 |
| 0.1517 | 0.91 | 100 | 0.1780 |
| 0.1616 | 1.0 | 110 | 0.1160 |
| 0.2341 | 1.09 | 120 | 0.1881 |
| 0.7248 | 1.18 | 130 | 0.7271 |
| 1.6046 | 1.27 | 140 | 0.6889 |
| 0.7782 | 1.36 | 150 | 0.3543 |
| 0.3641 | 1.45 | 160 | 0.3444 |
| 0.2674 | 1.54 | 170 | 0.2626 |
| 0.2036 | 1.63 | 180 | 0.1684 |
| 0.1562 | 1.72 | 190 | 0.1432 |
| 0.1498 | 1.81 | 200 | 0.1364 |
| 0.1399 | 1.9 | 210 | 0.1320 |
| 0.1269 | 1.99 | 220 | 0.1328 |
| 0.1282 | 2.08 | 230 | 0.1050 |
| 0.1048 | 2.18 | 240 | 0.0906 |
| 0.0932 | 2.27 | 250 | 0.0730 |
| 0.0792 | 2.36 | 260 | 0.0679 |
| 0.0737 | 2.45 | 270 | 0.0693 |
| 0.0772 | 2.54 | 280 | 0.0679 |
| 0.0794 | 2.63 | 290 | 0.0698 |
| 0.0743 | 2.72 | 300 | 0.0672 |
| 0.0766 | 2.81 | 310 | 0.0670 |
| 0.0751 | 2.9 | 320 | 0.0674 |
| 0.0655 | 2.99 | 330 | 0.0671 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.14.0
- License
- mit
- Created
- May 7, 2024
- Updated
- May 7, 2024