Downloads · 30 days
0
V0424HMA23
Litzy619/V0424HMA23
V0424HMA23 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 28, 2024
Repo size
597 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin597 MB · 100%
At a glance
- License
- mit
- Access
- Public
- Created
- Apr 27, 2024
- Updated
- Apr 28, 2024
- SHA
- e1cd29e8
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. -->
V0424HMA23
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: 0.0677
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: 80
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.7953 | 0.09 | 10 | 0.3102 |
| 0.1851 | 0.18 | 20 | 0.1074 |
| 0.1059 | 0.27 | 30 | 0.0854 |
| 0.0883 | 0.36 | 40 | 0.0786 |
| 0.0853 | 0.45 | 50 | 0.0757 |
| 0.0884 | 0.54 | 60 | 0.0741 |
| 0.0784 | 0.63 | 70 | 0.0724 |
| 0.0726 | 0.73 | 80 | 0.0840 |
| 0.085 | 0.82 | 90 | 0.0728 |
| 0.0871 | 0.91 | 100 | 0.0770 |
| 0.0839 | 1.0 | 110 | 0.0698 |
| 0.064 | 1.09 | 120 | 0.0797 |
| 0.0714 | 1.18 | 130 | 0.0778 |
| 0.0777 | 1.27 | 140 | 0.0738 |
| 0.0712 | 1.36 | 150 | 0.0684 |
| 0.0799 | 1.45 | 160 | 0.0680 |
| 0.0658 | 1.54 | 170 | 0.0653 |
| 0.0631 | 1.63 | 180 | 0.0699 |
| 0.0589 | 1.72 | 190 | 0.0674 |
| 0.0665 | 1.81 | 200 | 0.0637 |
| 0.0578 | 1.9 | 210 | 0.0672 |
| 0.053 | 1.99 | 220 | 0.0650 |
| 0.0368 | 2.08 | 230 | 0.0729 |
| 0.0343 | 2.18 | 240 | 0.0792 |
| 0.0331 | 2.27 | 250 | 0.0727 |
| 0.0339 | 2.36 | 260 | 0.0701 |
| 0.0336 | 2.45 | 270 | 0.0694 |
| 0.0308 | 2.54 | 280 | 0.0691 |
| 0.0307 | 2.63 | 290 | 0.0684 |
| 0.0323 | 2.72 | 300 | 0.0681 |
| 0.0343 | 2.81 | 310 | 0.0679 |
| 0.0316 | 2.9 | 320 | 0.0677 |
| 0.0347 | 2.99 | 330 | 0.0677 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.14.1
- License
- mit
- Created
- Apr 27, 2024
- Updated
- Apr 28, 2024