|
|
--- |
|
|
library_name: peft |
|
|
license: bigcode-openrail-m |
|
|
base_model: bigcode/starcoderbase-1b |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: peft-starcoder-lora-a100 |
|
|
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. --> |
|
|
|
|
|
# peft-starcoder-lora-a100 |
|
|
|
|
|
This model is a fine-tuned version of [bigcode/starcoderbase-1b](https://huggingface.co/bigcode/starcoderbase-1b) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.9646 |
|
|
|
|
|
## 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: 2 |
|
|
- eval_batch_size: 2 |
|
|
- seed: 42 |
|
|
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
|
- lr_scheduler_type: cosine |
|
|
- lr_scheduler_warmup_steps: 30 |
|
|
- training_steps: 1000 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:-----:|:----:|:---------------:| |
|
|
| 1.153 | 0.1 | 100 | 0.9261 | |
|
|
| 1.1271 | 0.2 | 200 | 0.9381 | |
|
|
| 0.906 | 0.3 | 300 | 0.9582 | |
|
|
| 1.028 | 0.4 | 400 | 0.9719 | |
|
|
| 1.0547 | 0.5 | 500 | 0.9610 | |
|
|
| 1.0747 | 0.6 | 600 | 0.9606 | |
|
|
| 0.7872 | 0.7 | 700 | 0.9623 | |
|
|
| 0.7992 | 0.8 | 800 | 0.9618 | |
|
|
| 0.872 | 0.9 | 900 | 0.9631 | |
|
|
| 1.0033 | 1.0 | 1000 | 0.9646 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.14.0 |
|
|
- Transformers 4.47.1 |
|
|
- Pytorch 2.5.1+cu124 |
|
|
- Datasets 3.2.0 |
|
|
- Tokenizers 0.21.0 |
