Downloads · 30 days
0
V0415MA1plus
Litzy619/V0415MA1plus
V0415MA1plus 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 16, 2024
Parameters
2.8B
6.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors5.8 GB · 96%
Parameter types
How the weights are stored.
F162.8B · 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. -->
V0415MA1plus
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: 0.0713
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 |
|---|---|---|---|
| 1.7976 | 0.09 | 10 | 0.1879 |
| 0.142 | 0.18 | 20 | 0.1048 |
| 0.0998 | 0.27 | 30 | 0.0795 |
| 0.0848 | 0.36 | 40 | 0.0713 |
| 0.0727 | 0.45 | 50 | 0.0728 |
| 0.0834 | 0.54 | 60 | 0.0712 |
| 0.0738 | 0.63 | 70 | 0.0660 |
| 0.0741 | 0.73 | 80 | 0.0674 |
| 0.0723 | 0.82 | 90 | 0.0675 |
| 0.0776 | 0.91 | 100 | 0.0679 |
| 0.0708 | 1.0 | 110 | 0.0669 |
| 0.0515 | 1.09 | 120 | 0.0636 |
| 0.0559 | 1.18 | 130 | 0.0680 |
| 0.0549 | 1.27 | 140 | 0.0672 |
| 0.0514 | 1.36 | 150 | 0.0601 |
| 0.059 | 1.45 | 160 | 0.0615 |
| 0.0494 | 1.54 | 170 | 0.0683 |
| 0.0555 | 1.63 | 180 | 0.0612 |
| 0.048 | 1.72 | 190 | 0.0601 |
| 0.058 | 1.81 | 200 | 0.0586 |
| 0.0491 | 1.9 | 210 | 0.0578 |
| 0.0423 | 1.99 | 220 | 0.0620 |
| 0.0243 | 2.08 | 230 | 0.0616 |
| 0.0238 | 2.18 | 240 | 0.0724 |
| 0.0207 | 2.27 | 250 | 0.0787 |
| 0.0203 | 2.36 | 260 | 0.0800 |
| 0.0238 | 2.45 | 270 | 0.0760 |
| 0.0216 | 2.54 | 280 | 0.0746 |
| 0.0214 | 2.63 | 290 | 0.0730 |
| 0.0246 | 2.72 | 300 | 0.0722 |
| 0.0246 | 2.81 | 310 | 0.0716 |
| 0.0237 | 2.9 | 320 | 0.0714 |
| 0.0267 | 2.99 | 330 | 0.0713 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.14.1
- License
- mit
- Created
- Apr 16, 2024
- Updated
- Apr 16, 2024