Downloads · 30 days
0
V0503HMA14H
Litzy619/V0503HMA14H
V0503HMA14H 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 8, 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. -->
V0503HMA14H
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: 0.0604
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 |
|---|---|---|---|
| 1.9666 | 0.09 | 10 | 0.7654 |
| 0.3003 | 0.18 | 20 | 0.1215 |
| 0.115 | 0.27 | 30 | 0.0890 |
| 0.0973 | 0.36 | 40 | 0.0837 |
| 0.0889 | 0.45 | 50 | 0.0764 |
| 0.0865 | 0.54 | 60 | 0.0747 |
| 0.0773 | 0.63 | 70 | 0.0710 |
| 0.121 | 0.73 | 80 | 0.0776 |
| 0.0879 | 0.82 | 90 | 0.0853 |
| 0.0929 | 0.91 | 100 | 0.0799 |
| 0.086 | 1.0 | 110 | 0.0671 |
| 0.0772 | 1.09 | 120 | 0.0857 |
| 0.0727 | 1.18 | 130 | 0.0801 |
| 0.0697 | 1.27 | 140 | 0.0718 |
| 0.0832 | 1.36 | 150 | 0.0756 |
| 0.0834 | 1.45 | 160 | 0.0843 |
| 0.0758 | 1.54 | 170 | 0.0686 |
| 0.0797 | 1.63 | 180 | 0.0793 |
| 0.0725 | 1.72 | 190 | 0.0714 |
| 0.0671 | 1.81 | 200 | 0.0723 |
| 0.0595 | 1.9 | 210 | 0.0679 |
| 0.0583 | 1.99 | 220 | 0.0603 |
| 0.0408 | 2.08 | 230 | 0.0663 |
| 0.0383 | 2.18 | 240 | 0.0653 |
| 0.0365 | 2.27 | 250 | 0.0647 |
| 0.0343 | 2.36 | 260 | 0.0657 |
| 0.0326 | 2.45 | 270 | 0.0657 |
| 0.0324 | 2.54 | 280 | 0.0641 |
| 0.0291 | 2.63 | 290 | 0.0624 |
| 0.0327 | 2.72 | 300 | 0.0611 |
| 0.0344 | 2.81 | 310 | 0.0608 |
| 0.0331 | 2.9 | 320 | 0.0604 |
| 0.0311 | 2.99 | 330 | 0.0604 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.18.0
- Tokenizers 0.14.1
- License
- mit
- Created
- May 5, 2024
- Updated
- May 8, 2024