Downloads · 30 days
0
V0309O4
Litzy619/V0309O4
V0309O4 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 Mar 10, 2024
Parameters
2.9B
6.6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors6 GB · 90%
Parameter types
How the weights are stored.
F162.8B · 96%
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. -->
V0309O4
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: 0.0667
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: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 32
- 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: 20
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.1847 | 0.09 | 10 | 1.3549 |
| 0.6355 | 0.17 | 20 | 0.1145 |
| 0.1343 | 0.26 | 30 | 0.0832 |
| 0.1143 | 0.34 | 40 | 0.0792 |
| 0.1074 | 0.43 | 50 | 0.0765 |
| 0.0964 | 0.51 | 60 | 0.0726 |
| 0.0886 | 0.6 | 70 | 0.0719 |
| 0.0942 | 0.68 | 80 | 0.0704 |
| 0.0827 | 0.77 | 90 | 0.0704 |
| 0.0819 | 0.85 | 100 | 0.0649 |
| 0.0831 | 0.94 | 110 | 0.0640 |
| 0.0824 | 1.02 | 120 | 0.0615 |
| 0.0778 | 1.11 | 130 | 0.0694 |
| 0.0743 | 1.19 | 140 | 0.0591 |
| 0.0728 | 1.28 | 150 | 0.0610 |
| 0.0735 | 1.37 | 160 | 0.0647 |
| 0.0712 | 1.45 | 170 | 0.0660 |
| 0.0693 | 1.54 | 180 | 0.0694 |
| 0.0716 | 1.62 | 190 | 0.0682 |
| 0.0664 | 1.71 | 200 | 0.0691 |
| 0.0705 | 1.79 | 210 | 0.0664 |
| 0.0624 | 1.88 | 220 | 0.0678 |
| 0.0632 | 1.96 | 230 | 0.0682 |
| 0.0638 | 2.05 | 240 | 0.0690 |
| 0.055 | 2.13 | 250 | 0.0692 |
| 0.0584 | 2.22 | 260 | 0.0710 |
| 0.0539 | 2.3 | 270 | 0.0694 |
| 0.0588 | 2.39 | 280 | 0.0668 |
| 0.0608 | 2.47 | 290 | 0.0661 |
| 0.0589 | 2.56 | 300 | 0.0665 |
| 0.0633 | 2.65 | 310 | 0.0660 |
| 0.0539 | 2.73 | 320 | 0.0662 |
| 0.0538 | 2.82 | 330 | 0.0665 |
| 0.0529 | 2.9 | 340 | 0.0665 |
| 0.0561 | 2.99 | 350 | 0.0667 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.14.1
- License
- mit
- Created
- Mar 10, 2024
- Updated
- Mar 10, 2024