Downloads · 30 days
0
V0508HMA15HPHI3B1
Litzy619/V0508HMA15HPHI3B1
V0508HMA15HPHI3B1 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 9, 2024
Parameters
3.9B
8.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors8.1 GB · 92%
Parameter types
How the weights are stored.
BF163.8B · 97%
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. -->
V0508HMA15HPHI3B1
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: 0.0759
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 |
|---|---|---|---|
| 4.0539 | 0.09 | 10 | 0.4056 |
| 0.2678 | 0.18 | 20 | 0.2377 |
| 0.3002 | 0.27 | 30 | 0.2459 |
| 0.2402 | 0.36 | 40 | 0.2783 |
| 0.2519 | 0.45 | 50 | 0.2303 |
| 0.2249 | 0.54 | 60 | 0.2132 |
| 0.2258 | 0.63 | 70 | 0.2016 |
| 0.21 | 0.73 | 80 | 0.1504 |
| 0.1338 | 0.82 | 90 | 0.1060 |
| 0.1138 | 0.91 | 100 | 0.0950 |
| 0.0903 | 1.0 | 110 | 0.0831 |
| 0.0717 | 1.09 | 120 | 0.0837 |
| 0.0936 | 1.18 | 130 | 0.1182 |
| 0.1048 | 1.27 | 140 | 0.0978 |
| 0.0863 | 1.36 | 150 | 0.0781 |
| 0.0892 | 1.45 | 160 | 0.0815 |
| 0.0731 | 1.54 | 170 | 0.0752 |
| 0.0702 | 1.63 | 180 | 0.0796 |
| 0.0714 | 1.72 | 190 | 0.0733 |
| 0.0709 | 1.81 | 200 | 0.0745 |
| 0.065 | 1.9 | 210 | 0.0868 |
| 0.0647 | 1.99 | 220 | 0.0789 |
| 0.0361 | 2.08 | 230 | 0.0826 |
| 0.0325 | 2.18 | 240 | 0.0823 |
| 0.0264 | 2.27 | 250 | 0.0894 |
| 0.0284 | 2.36 | 260 | 0.0787 |
| 0.0343 | 2.45 | 270 | 0.0776 |
| 0.0258 | 2.54 | 280 | 0.0808 |
| 0.0274 | 2.63 | 290 | 0.0791 |
| 0.0315 | 2.72 | 300 | 0.0775 |
| 0.0315 | 2.81 | 310 | 0.0768 |
| 0.0232 | 2.9 | 320 | 0.0760 |
| 0.0297 | 2.99 | 330 | 0.0759 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.18.0
- Tokenizers 0.14.1
- License
- mit
- Created
- May 8, 2024
- Updated
- May 9, 2024