|
|
--- |
|
|
license: llama2 |
|
|
library_name: peft |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
base_model: codellama/CodeLlama-13b-hf |
|
|
model-index: |
|
|
- name: codellama13B-noautogen-StaproCoder |
|
|
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. --> |
|
|
|
|
|
# codellama13B-noautogen-StaproCoder |
|
|
|
|
|
This model is a fine-tuned version of [codellama/CodeLlama-13b-hf](https://huggingface.co/codellama/CodeLlama-13b-hf) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.3758 |
|
|
|
|
|
## 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: 0.0005 |
|
|
- train_batch_size: 6 |
|
|
- eval_batch_size: 6 |
|
|
- seed: 42 |
|
|
- gradient_accumulation_steps: 4 |
|
|
- total_train_batch_size: 24 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: cosine |
|
|
- lr_scheduler_warmup_ratio: 0.1 |
|
|
- training_steps: 2000 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:-----:|:----:|:---------------:| |
|
|
| 0.417 | 0.05 | 100 | 0.5468 | |
|
|
| 0.5187 | 0.1 | 200 | 0.4993 | |
|
|
| 0.3279 | 0.15 | 300 | 0.4787 | |
|
|
| 0.452 | 0.2 | 400 | 0.4551 | |
|
|
| 0.4738 | 0.25 | 500 | 0.4402 | |
|
|
| 0.4338 | 0.3 | 600 | 0.4263 | |
|
|
| 0.4024 | 0.35 | 700 | 0.4183 | |
|
|
| 0.4268 | 0.4 | 800 | 0.4082 | |
|
|
| 0.3572 | 0.45 | 900 | 0.4014 | |
|
|
| 0.3584 | 0.5 | 1000 | 0.3967 | |
|
|
| 0.359 | 0.55 | 1100 | 0.3913 | |
|
|
| 0.3023 | 0.6 | 1200 | 0.3865 | |
|
|
| 0.2707 | 0.65 | 1300 | 0.3820 | |
|
|
| 0.2918 | 0.7 | 1400 | 0.3790 | |
|
|
| 0.3188 | 0.75 | 1500 | 0.3757 | |
|
|
| 0.167 | 0.8 | 1600 | 0.3741 | |
|
|
| 0.2962 | 0.85 | 1700 | 0.3742 | |
|
|
| 0.2603 | 0.9 | 1800 | 0.3747 | |
|
|
| 0.2544 | 0.95 | 1900 | 0.3755 | |
|
|
| 0.254 | 1.0 | 2000 | 0.3758 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.9.0 |
|
|
- Transformers 4.39.0.dev0 |
|
|
- Pytorch 2.2.1+cu121 |
|
|
- Datasets 2.17.1 |
|
|
- Tokenizers 0.15.2 |
