| --- |
| license: bigcode-openrail-m |
| library_name: peft |
| tags: |
| - generated_from_trainer |
| base_model: bigcode/starcoderbase-1b |
| model-index: |
| - name: code_example |
| 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. --> |
|
|
| # code_example |
| |
| 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: 1.0596 |
| |
| ## 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: 16 |
| - eval_batch_size: 16 |
| - seed: 42 |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| - lr_scheduler_type: cosine |
| - lr_scheduler_warmup_steps: 30 |
| - training_steps: 2000 |
|
|
| ### Training results |
|
|
| | Training Loss | Epoch | Step | Validation Loss | |
| |:-------------:|:-----:|:----:|:---------------:| |
| | 0.9662 | 0.05 | 100 | 0.9184 | |
| | 0.9899 | 0.1 | 200 | 0.9461 | |
| | 0.6517 | 0.15 | 300 | 0.9698 | |
| | 0.8963 | 0.2 | 400 | 0.9823 | |
| | 0.9498 | 0.25 | 500 | 0.9727 | |
| | 0.5741 | 0.3 | 600 | 1.0098 | |
| | 0.7985 | 0.35 | 700 | 1.0212 | |
| | 0.8268 | 0.4 | 800 | 1.0123 | |
| | 0.5209 | 0.45 | 900 | 1.0178 | |
| | 0.7512 | 0.5 | 1000 | 1.0302 | |
| | 0.7718 | 0.55 | 1100 | 1.0342 | |
| | 0.4746 | 0.6 | 1200 | 1.0492 | |
| | 0.6964 | 0.65 | 1300 | 1.0394 | |
| | 0.6844 | 0.7 | 1400 | 1.0471 | |
| | 0.5396 | 0.75 | 1500 | 1.0495 | |
| | 0.6569 | 0.8 | 1600 | 1.0553 | |
| | 0.6005 | 0.85 | 1700 | 1.0609 | |
| | 0.6015 | 0.9 | 1800 | 1.0632 | |
| | 0.5552 | 0.95 | 1900 | 1.0620 | |
| | 0.5883 | 1.0 | 2000 | 1.0596 | |
|
|
|
|
| ### Framework versions |
|
|
| - PEFT 0.8.2 |
| - Transformers 4.37.2 |
| - Pytorch 2.1.0+cu121 |
| - Datasets 2.17.1 |
| - Tokenizers 0.15.2 |
