|
|
--- |
|
|
license: bigcode-openrail-m |
|
|
library_name: peft |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
base_model: WizardLM/WizardCoder-1B-V1.0 |
|
|
model-index: |
|
|
- name: WizardCoder1B-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. --> |
|
|
|
|
|
# WizardCoder1B-StaproCoder |
|
|
|
|
|
This model is a fine-tuned version of [WizardLM/WizardCoder-1B-V1.0](https://huggingface.co/WizardLM/WizardCoder-1B-V1.0) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.2618 |
|
|
|
|
|
## 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: 12 |
|
|
- eval_batch_size: 12 |
|
|
- seed: 42 |
|
|
- gradient_accumulation_steps: 4 |
|
|
- total_train_batch_size: 48 |
|
|
- 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 | |
|
|
|:-------------:|:-----:|:----:|:---------------:| |
|
|
| 0.3982 | 0.05 | 100 | 0.3337 | |
|
|
| 0.3102 | 0.1 | 200 | 0.2979 | |
|
|
| 0.3561 | 0.15 | 300 | 0.2811 | |
|
|
| 0.299 | 0.2 | 400 | 0.2739 | |
|
|
| 0.2599 | 0.25 | 500 | 0.2702 | |
|
|
| 0.2105 | 0.3 | 600 | 0.2671 | |
|
|
| 0.2772 | 0.35 | 700 | 0.2638 | |
|
|
| 0.2038 | 0.4 | 800 | 0.2626 | |
|
|
| 0.2102 | 0.45 | 900 | 0.2627 | |
|
|
| 0.2527 | 0.5 | 1000 | 0.2606 | |
|
|
| 0.2137 | 0.55 | 1100 | 0.2606 | |
|
|
| 0.1793 | 0.6 | 1200 | 0.2622 | |
|
|
| 0.1655 | 0.65 | 1300 | 0.2618 | |
|
|
| 0.228 | 0.7 | 1400 | 0.2616 | |
|
|
| 0.1542 | 0.75 | 1500 | 0.2611 | |
|
|
| 0.194 | 0.8 | 1600 | 0.2614 | |
|
|
| 0.2056 | 0.85 | 1700 | 0.2612 | |
|
|
| 0.2081 | 0.9 | 1800 | 0.2615 | |
|
|
| 0.1824 | 0.95 | 1900 | 0.2618 | |
|
|
| 0.1841 | 1.0 | 2000 | 0.2618 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.9.0 |
|
|
- Transformers 4.39.0.dev0 |
|
|
- Pytorch 2.2.1+cu121 |
|
|
- Datasets 2.17.1 |
|
|
- Tokenizers 0.15.2 |
