Downloads · 30 days
0
V0417MADP9
Litzy619/V0417MADP9
V0417MADP9 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 Apr 19, 2024
Parameters
2.9B
6.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors5.9 GB · 91%
Parameter types
How the weights are stored.
F162.8B · 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. -->
V0417MADP9
This model is a fine-tuned version of microsoft/phi-2 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: 60
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 5.3125 | 0.09 | 10 | 2.0178 |
| 3.6162 | 0.18 | 20 | 0.7351 |
| 1.6265 | 0.27 | 30 | 0.1559 |
| 0.7777 | 0.36 | 40 | 0.1366 |
| 0.1862 | 0.45 | 50 | 0.1302 |
| 0.1458 | 0.54 | 60 | 0.1170 |
| 0.1323 | 0.63 | 70 | 0.1083 |
| 0.1224 | 0.73 | 80 | 0.1041 |
| 0.1123 | 0.82 | 90 | 0.1013 |
| 0.1056 | 0.91 | 100 | 0.0898 |
| 0.1065 | 1.0 | 110 | 0.0886 |
| 0.0999 | 1.09 | 120 | 0.0858 |
| 0.1017 | 1.18 | 130 | 0.0830 |
| 0.1028 | 1.27 | 140 | 0.0838 |
| 0.1295 | 1.36 | 150 | 0.1006 |
| 0.1121 | 1.45 | 160 | 0.0873 |
| 0.1014 | 1.54 | 170 | 0.0844 |
| 0.0944 | 1.63 | 180 | 0.0777 |
| 0.0873 | 1.72 | 190 | 0.0776 |
| 0.0924 | 1.81 | 200 | 0.0747 |
| 0.0847 | 1.9 | 210 | 0.0727 |
| 0.0796 | 1.99 | 220 | 0.0727 |
| 0.075 | 2.08 | 230 | 0.0707 |
| 0.0789 | 2.18 | 240 | 0.0702 |
| 0.077 | 2.27 | 250 | 0.0710 |
| 0.0784 | 2.36 | 260 | 0.0692 |
| 0.0784 | 2.45 | 270 | 0.0689 |
| 0.072 | 2.54 | 280 | 0.0685 |
| 0.0697 | 2.63 | 290 | 0.0677 |
| 0.0735 | 2.72 | 300 | 0.0675 |
| 0.0751 | 2.81 | 310 | 0.0674 |
| 0.071 | 2.9 | 320 | 0.0672 |
| 0.0779 | 2.99 | 330 | 0.0671 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.2.2+cu121
- Datasets 2.18.0
- Tokenizers 0.14.1
- License
- mit
- Created
- Apr 18, 2024
- Updated
- Apr 19, 2024