Downloads · 30 days
0
llama-3-8b-local
Rafaelrosendo1/llama-3-8b-local
llama-3-8b-local is a machine learning model from Rafaelrosendo1. 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 llama2.
should probably proofread and complete it, then remove this comment. --
Access
Public
Updated Apr 25, 2024
Repo size
321 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin160 MB · 50%
At a glance
- License
- llama2
- Access
- Public
- Created
- Apr 25, 2024
- Updated
- Apr 25, 2024
- SHA
- af2ebc8d
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. -->
llama-3-8b-local
This model is a fine-tuned version of meta-llama/Llama-2-7b-hf on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.4659
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: 0.0002
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.8928 | 0.03 | 25 | 1.7769 |
| 1.7131 | 0.05 | 50 | 1.7402 |
| 1.7496 | 0.08 | 75 | 1.7192 |
| 1.689 | 0.1 | 100 | 1.7037 |
| 1.717 | 0.13 | 125 | 1.6896 |
| 1.7199 | 0.15 | 150 | 1.6779 |
| 1.7089 | 0.18 | 175 | 1.6697 |
| 1.7245 | 0.21 | 200 | 1.6561 |
| 1.7614 | 0.23 | 225 | 1.6454 |
| 1.6727 | 0.26 | 250 | 1.6346 |
| 1.7209 | 0.28 | 275 | 1.6233 |
| 1.7111 | 0.31 | 300 | 1.6171 |
| 1.7534 | 0.34 | 325 | 1.6063 |
| 1.6882 | 0.36 | 350 | 1.5964 |
| 1.6095 | 0.39 | 375 | 1.5892 |
| 1.6543 | 0.41 | 400 | 1.5815 |
| 1.5767 | 0.44 | 425 | 1.5750 |
| 1.6283 | 0.46 | 450 | 1.5630 |
| 1.637 | 0.49 | 475 | 1.5568 |
| 1.6754 | 0.52 | 500 | 1.5498 |
| 1.5772 | 0.54 | 525 | 1.5408 |
| 1.6307 | 0.57 | 550 | 1.5337 |
| 1.6931 | 0.59 | 575 | 1.5301 |
| 1.5761 | 0.62 | 600 | 1.5207 |
| 1.5813 | 0.64 | 625 | 1.5162 |
| 1.5495 | 0.67 | 650 | 1.5087 |
| 1.5888 | 0.7 | 675 | 1.5012 |
| 1.624 | 0.72 | 700 | 1.4997 |
| 1.552 | 0.75 | 725 | 1.4921 |
| 1.6675 | 0.77 | 750 | 1.4884 |
| 1.6556 | 0.8 | 775 | 1.4849 |
| 1.6342 | 0.83 | 800 | 1.4828 |
| 1.6684 | 0.85 | 825 | 1.4781 |
| 1.7 | 0.88 | 850 | 1.4744 |
| 1.6327 | 0.9 | 875 | 1.4715 |
| 1.6484 | 0.93 | 900 | 1.4690 |
| 1.509 | 0.95 | 925 | 1.4668 |
| 1.5963 | 0.98 | 950 | 1.4659 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.1.2+cu121
- Datasets 2.12.0
- Tokenizers 0.14.1
- License
- llama2
- Created
- Apr 25, 2024
- Updated
- Apr 25, 2024