|
--- |
|
base_model: ise-uiuc/Magicoder-S-DS-6.7B |
|
datasets: |
|
- generator |
|
library_name: peft |
|
license: other |
|
tags: |
|
- trl |
|
- sft |
|
- generated_from_trainer |
|
model-index: |
|
- name: finetune_starcoder2 |
|
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. --> |
|
|
|
# finetune_starcoder2 |
|
|
|
This model is a fine-tuned version of [ise-uiuc/Magicoder-S-DS-6.7B](https://huggingface.co/ise-uiuc/Magicoder-S-DS-6.7B) on the generator dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3220 |
|
|
|
## 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: 0.0003 |
|
- train_batch_size: 1 |
|
- eval_batch_size: 5 |
|
- seed: 0 |
|
- gradient_accumulation_steps: 8 |
|
- total_train_batch_size: 8 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_steps: 100 |
|
- training_steps: 2000 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 0.8634 | 0.5340 | 50 | 0.6751 | |
|
| 0.6619 | 1.0681 | 100 | 0.4653 | |
|
| 0.5147 | 1.6021 | 150 | 0.4231 | |
|
| 0.4761 | 2.1362 | 200 | 0.3912 | |
|
| 0.4348 | 2.6702 | 250 | 0.3663 | |
|
| 0.4123 | 3.2043 | 300 | 0.3515 | |
|
| 0.3893 | 3.7383 | 350 | 0.3407 | |
|
| 0.3769 | 4.2724 | 400 | 0.3329 | |
|
| 0.3719 | 4.8064 | 450 | 0.3266 | |
|
| 0.3578 | 5.3405 | 500 | 0.3220 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.11.1 |
|
- Transformers 4.42.4 |
|
- Pytorch 2.3.1+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
