Downloads · 30 days
0
V0415B2
Litzy619/V0415B2
V0415B2 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 17, 2024
Parameters
2.8B
5.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors5.7 GB · 98%
Parameter types
How the weights are stored.
F162.8B · 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. -->
V0415B2
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: 0.0627
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 |
|---|---|---|---|
| 2.7796 | 0.09 | 10 | 2.7689 |
| 2.7682 | 0.18 | 20 | 2.7065 |
| 2.6102 | 0.27 | 30 | 2.3490 |
| 2.084 | 0.36 | 40 | 1.5865 |
| 1.2444 | 0.45 | 50 | 0.6290 |
| 0.3515 | 0.54 | 60 | 0.1070 |
| 0.1138 | 0.63 | 70 | 0.0952 |
| 0.1011 | 0.73 | 80 | 0.0862 |
| 0.0923 | 0.82 | 90 | 0.0828 |
| 0.0889 | 0.91 | 100 | 0.0770 |
| 0.0881 | 1.0 | 110 | 0.0754 |
| 0.0808 | 1.09 | 120 | 0.0727 |
| 0.082 | 1.18 | 130 | 0.0707 |
| 0.0819 | 1.27 | 140 | 0.0689 |
| 0.0743 | 1.36 | 150 | 0.0680 |
| 0.0812 | 1.45 | 160 | 0.0669 |
| 0.0735 | 1.54 | 170 | 0.0655 |
| 0.0763 | 1.63 | 180 | 0.0655 |
| 0.077 | 1.72 | 190 | 0.0650 |
| 0.0754 | 1.81 | 200 | 0.0638 |
| 0.0667 | 1.9 | 210 | 0.0636 |
| 0.0687 | 1.99 | 220 | 0.0646 |
| 0.0653 | 2.08 | 230 | 0.0642 |
| 0.0697 | 2.18 | 240 | 0.0638 |
| 0.0658 | 2.27 | 250 | 0.0632 |
| 0.0696 | 2.36 | 260 | 0.0633 |
| 0.0653 | 2.45 | 270 | 0.0631 |
| 0.0625 | 2.54 | 280 | 0.0629 |
| 0.0615 | 2.63 | 290 | 0.0630 |
| 0.0681 | 2.72 | 300 | 0.0629 |
| 0.0755 | 2.81 | 310 | 0.0628 |
| 0.0641 | 2.9 | 320 | 0.0628 |
| 0.0705 | 2.99 | 330 | 0.0627 |
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 17, 2024