Downloads · 30 days
0
Phi0503HMA15OLD
Litzy619/Phi0503HMA15OLD
Phi0503HMA15OLD 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. -->
Phi0503HMA15
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: 0.0780
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 |
|---|---|---|---|
| 4.2792 | 0.09 | 10 | 0.9013 |
| 0.4134 | 0.18 | 20 | 0.2556 |
| 0.2515 | 0.27 | 30 | 0.2349 |
| 0.216 | 0.36 | 40 | 0.2240 |
| 0.2069 | 0.45 | 50 | 0.1794 |
| 0.2172 | 0.54 | 60 | 0.1495 |
| 0.1601 | 0.63 | 70 | 0.1533 |
| 0.1399 | 0.73 | 80 | 0.1102 |
| 0.0989 | 0.82 | 90 | 0.0797 |
| 0.0842 | 0.91 | 100 | 0.1293 |
| 0.0738 | 1.0 | 110 | 0.0729 |
| 0.0594 | 1.09 | 120 | 0.0661 |
| 0.0593 | 1.18 | 130 | 0.0793 |
| 0.0656 | 1.27 | 140 | 0.0695 |
| 0.0607 | 1.36 | 150 | 0.0707 |
| 0.0674 | 1.45 | 160 | 0.0698 |
| 0.0647 | 1.54 | 170 | 0.0688 |
| 0.0622 | 1.63 | 180 | 0.0681 |
| 0.0539 | 1.72 | 190 | 0.0616 |
| 0.0579 | 1.81 | 200 | 0.0621 |
| 0.0503 | 1.9 | 210 | 0.0643 |
| 0.052 | 1.99 | 220 | 0.0657 |
| 0.0267 | 2.08 | 230 | 0.0803 |
| 0.027 | 2.18 | 240 | 0.0948 |
| 0.0216 | 2.27 | 250 | 0.0921 |
| 0.0199 | 2.36 | 260 | 0.0846 |
| 0.0273 | 2.45 | 270 | 0.0769 |
| 0.0167 | 2.54 | 280 | 0.0791 |
| 0.0213 | 2.63 | 290 | 0.0813 |
| 0.027 | 2.72 | 300 | 0.0788 |
| 0.023 | 2.81 | 310 | 0.0778 |
| 0.0204 | 2.9 | 320 | 0.0779 |
| 0.0212 | 2.99 | 330 | 0.0780 |
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