Downloads · 30 days
0
V0508HMA15HPHI3V1
Litzy619/V0508HMA15HPHI3V1
V0508HMA15HPHI3V1 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 9, 2024
Parameters
3.9B
8.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors8.1 GB · 92%
Parameter types
How the weights are stored.
BF163.8B · 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. -->
V0508HMA15HPHI3V1
This model is a fine-tuned version of microsoft/Phi-3-mini-4k-instruct 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: 100
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.8946 | 0.09 | 10 | 0.3617 |
| 0.2808 | 0.18 | 20 | 0.2431 |
| 0.2803 | 0.27 | 30 | 0.2445 |
| 0.2404 | 0.36 | 40 | 0.2344 |
| 0.2139 | 0.45 | 50 | 0.1702 |
| 0.167 | 0.54 | 60 | 0.1360 |
| 0.1183 | 0.63 | 70 | 0.1183 |
| 0.1029 | 0.73 | 80 | 0.0853 |
| 0.0959 | 0.82 | 90 | 0.0814 |
| 0.0967 | 0.91 | 100 | 0.0840 |
| 0.0998 | 1.0 | 110 | 0.0904 |
| 0.0722 | 1.09 | 120 | 0.0687 |
| 0.0585 | 1.18 | 130 | 0.0754 |
| 0.0666 | 1.27 | 140 | 0.0703 |
| 0.0647 | 1.36 | 150 | 0.0717 |
| 0.064 | 1.45 | 160 | 0.0915 |
| 0.068 | 1.54 | 170 | 0.0718 |
| 0.0644 | 1.63 | 180 | 0.0707 |
| 0.0581 | 1.72 | 190 | 0.0655 |
| 0.0654 | 1.81 | 200 | 0.0628 |
| 0.0546 | 1.9 | 210 | 0.0732 |
| 0.0534 | 1.99 | 220 | 0.0658 |
| 0.0333 | 2.08 | 230 | 0.0743 |
| 0.0281 | 2.18 | 240 | 0.0819 |
| 0.0274 | 2.27 | 250 | 0.0715 |
| 0.027 | 2.36 | 260 | 0.0686 |
| 0.035 | 2.45 | 270 | 0.0652 |
| 0.0225 | 2.54 | 280 | 0.0686 |
| 0.0244 | 2.63 | 290 | 0.0704 |
| 0.0307 | 2.72 | 300 | 0.0683 |
| 0.0338 | 2.81 | 310 | 0.0661 |
| 0.0252 | 2.9 | 320 | 0.0654 |
| 0.0265 | 2.99 | 330 | 0.0654 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.18.0
- Tokenizers 0.14.1
- License
- mit
- Created
- May 8, 2024
- Updated
- May 9, 2024