|
|
--- |
|
|
license: llama2 |
|
|
library_name: peft |
|
|
tags: |
|
|
- trl |
|
|
- sft |
|
|
- generated_from_trainer |
|
|
base_model: TheBloke/CodeLlama-7B-Instruct-AWQ |
|
|
model-index: |
|
|
- name: CodeLlama-7B-Instruct-AWQ-FaVe-rank32-10epochs |
|
|
results: [] |
|
|
--- |
|
|
|
|
|
<!-- 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](https://huggingface.co/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 |
