Downloads · 30 days
0
PHI30515HMA2H
Litzy619/PHI30515HMA2H
PHI30515HMA2H 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 19, 2024
Parameters
3.9B
16.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors7.9 GB · 96%
Parameter types
How the weights are stored.
BF163.8B · 99%
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. -->
PHI30515HMA2H
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: 0.0643
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: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 32
- 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 |
|---|---|---|---|
| 7.2249 | 0.09 | 10 | 2.2001 |
| 1.4719 | 0.18 | 20 | 0.3359 |
| 0.3692 | 0.27 | 30 | 0.2930 |
| 0.7802 | 0.36 | 40 | 0.2417 |
| 0.3078 | 0.45 | 50 | 0.2185 |
| 0.4702 | 0.54 | 60 | 0.2195 |
| 0.272 | 0.63 | 70 | 0.1992 |
| 0.2656 | 0.73 | 80 | 0.1711 |
| 0.1386 | 0.82 | 90 | 0.1117 |
| 0.2291 | 0.91 | 100 | 0.1116 |
| 0.1424 | 1.0 | 110 | 0.0853 |
| 0.099 | 1.09 | 120 | 0.1146 |
| 0.1629 | 1.18 | 130 | 0.1753 |
| 0.6955 | 1.27 | 140 | 0.1667 |
| 0.226 | 1.36 | 150 | 0.1119 |
| 0.1085 | 1.45 | 160 | 0.0805 |
| 0.1083 | 1.54 | 170 | 0.0743 |
| 0.2197 | 1.63 | 180 | 0.9735 |
| 0.4915 | 1.72 | 190 | 0.0757 |
| 0.0954 | 1.81 | 200 | 0.0794 |
| 0.0696 | 1.9 | 210 | 0.0698 |
| 0.068 | 1.99 | 220 | 0.0711 |
| 0.0602 | 2.08 | 230 | 0.0702 |
| 0.0896 | 2.18 | 240 | 0.0871 |
| 0.0724 | 2.27 | 250 | 0.0720 |
| 0.0679 | 2.36 | 260 | 0.0688 |
| 0.0764 | 2.45 | 270 | 0.0683 |
| 0.0642 | 2.54 | 280 | 0.0665 |
| 0.058 | 2.63 | 290 | 0.0659 |
| 0.0554 | 2.72 | 300 | 0.0665 |
| 0.0699 | 2.81 | 310 | 0.0654 |
| 0.0752 | 2.9 | 320 | 0.0645 |
| 0.0654 | 2.99 | 330 | 0.0643 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.14.0
- License
- mit
- Created
- May 16, 2024
- Updated
- May 19, 2024