Downloads · 30 days
0
V0424HMA18
Litzy619/V0424HMA18
V0424HMA18 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 27, 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. -->
V0424HMA18
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: 0.0654
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 |
|---|---|---|---|
| 1.5282 | 0.09 | 10 | 0.1426 |
| 0.1466 | 0.18 | 20 | 0.1074 |
| 0.1005 | 0.27 | 30 | 0.0848 |
| 0.0927 | 0.36 | 40 | 0.0819 |
| 0.0835 | 0.45 | 50 | 0.0793 |
| 0.0912 | 0.54 | 60 | 0.0793 |
| 0.0807 | 0.63 | 70 | 0.0805 |
| 0.083 | 0.73 | 80 | 0.0868 |
| 0.0842 | 0.82 | 90 | 0.0750 |
| 0.0855 | 0.91 | 100 | 0.0692 |
| 0.0837 | 1.0 | 110 | 0.0701 |
| 0.068 | 1.09 | 120 | 0.0679 |
| 0.0664 | 1.18 | 130 | 0.0789 |
| 0.0691 | 1.27 | 140 | 0.0657 |
| 0.0609 | 1.36 | 150 | 0.0667 |
| 0.0674 | 1.45 | 160 | 0.0714 |
| 0.065 | 1.54 | 170 | 0.0710 |
| 0.0649 | 1.63 | 180 | 0.0660 |
| 0.052 | 1.72 | 190 | 0.0653 |
| 0.0658 | 1.81 | 200 | 0.0637 |
| 0.0528 | 1.9 | 210 | 0.0677 |
| 0.056 | 1.99 | 220 | 0.0602 |
| 0.0355 | 2.08 | 230 | 0.0702 |
| 0.0367 | 2.18 | 240 | 0.0769 |
| 0.0329 | 2.27 | 250 | 0.0683 |
| 0.0282 | 2.36 | 260 | 0.0696 |
| 0.0343 | 2.45 | 270 | 0.0711 |
| 0.0312 | 2.54 | 280 | 0.0675 |
| 0.0283 | 2.63 | 290 | 0.0665 |
| 0.0327 | 2.72 | 300 | 0.0659 |
| 0.0321 | 2.81 | 310 | 0.0658 |
| 0.0311 | 2.9 | 320 | 0.0655 |
| 0.0329 | 2.99 | 330 | 0.0654 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.14.1
- License
- mit
- Created
- Apr 26, 2024
- Updated
- Apr 27, 2024