Downloads · 30 days
3
14% of all-time downloads
CodeLlama-7B-Instruct-AWQ-FaVe-rank32-10epochs
Ferdi/CodeLlama-7B-Instruct-AWQ-FaVe-rank32-10epochs
CodeLlama-7B-Instruct-AWQ-FaVe-rank32-10epochs is a machine learning model from Ferdi. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as llama2.
should probably proofread and complete it, then remove this comment. --
All-time downloads
22
Public
Repo size
67.1 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors67.1 MB · 97%
At a glance
- Library
- peft
- License
- llama2
- Access
- Public
- Created
- Jun 25, 2024
- Updated
- Jun 25, 2024
- SHA
- 111ee526
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. -->
CodeLlama-7B-Instruct-AWQ-FaVe-rank32-10epochs
This model is a fine-tuned version of TheBloke/CodeLlama-7B-Instruct-AWQ on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4062
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: 0.0001
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- 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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.2685 | 10 | 2.3372 |
| 2.2955 | 0.5369 | 20 | 1.6076 |
| 2.2955 | 0.8054 | 30 | 1.0489 |
| 1.1613 | 1.0738 | 40 | 0.8034 |
| 1.1613 | 1.3423 | 50 | 0.6930 |
| 0.6945 | 1.6107 | 60 | 0.6359 |
| 0.6945 | 1.8792 | 70 | 0.6086 |
| 0.5899 | 2.1477 | 80 | 0.5537 |
| 0.5899 | 2.4161 | 90 | 0.5240 |
| 0.4857 | 2.6846 | 100 | 0.4897 |
| 0.4857 | 2.9530 | 110 | 0.4603 |
| 0.4616 | 3.2215 | 120 | 0.4355 |
| 0.4616 | 3.4899 | 130 | 0.4248 |
| 0.3633 | 3.7584 | 140 | 0.4078 |
| 0.3633 | 4.0268 | 150 | 0.3912 |
| 0.3445 | 4.2953 | 160 | 0.3831 |
| 0.3445 | 4.5638 | 170 | 0.3899 |
| 0.254 | 4.8322 | 180 | 0.3664 |
| 0.254 | 5.1007 | 190 | 0.3493 |
| 0.2453 | 5.3691 | 200 | 0.3728 |
| 0.2453 | 5.6376 | 210 | 0.3465 |
| 0.2113 | 5.9060 | 220 | 0.3514 |
| 0.2113 | 6.1745 | 230 | 0.3731 |
| 0.1808 | 6.4430 | 240 | 0.3614 |
| 0.1808 | 6.7114 | 250 | 0.3566 |
| 0.1851 | 6.9799 | 260 | 0.3680 |
| 0.1851 | 7.2483 | 270 | 0.3830 |
| 0.1477 | 7.5168 | 280 | 0.3728 |
| 0.1477 | 7.7852 | 290 | 0.3743 |
| 0.1452 | 8.0537 | 300 | 0.3839 |
| 0.1452 | 8.3221 | 310 | 0.4053 |
| 0.1206 | 8.5906 | 320 | 0.3879 |
| 0.1206 | 8.8591 | 330 | 0.3865 |
| 0.1378 | 9.1275 | 340 | 0.3948 |
| 0.1378 | 9.3960 | 350 | 0.4026 |
| 0.1044 | 9.6644 | 360 | 0.4057 |
| 0.1044 | 9.9329 | 370 | 0.4062 |
Framework versions
- PEFT 0.10.0
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Library
- peft
- License
- llama2
- Created
- Jun 25, 2024
- Updated
- Jun 25, 2024