metadata
license: bigcode-openrail-m
base_model: bigcode/starcoder
tags:
- generated_from_trainer
model-index:
- name: starcoder-finetuned-test_newSnippet
results: []
starcoder-finetuned-test_newSnippet
This model is a fine-tuned version of bigcode/starcoder on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1728
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: 8e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 80
- training_steps: 800
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.5787 | 0.06 | 50 | 0.3535 |
| 0.236 | 0.12 | 100 | 0.1948 |
| 0.1862 | 1.01 | 150 | 0.1847 |
| 0.1866 | 1.07 | 200 | 0.1808 |
| 0.1838 | 1.13 | 250 | 0.1794 |
| 0.1718 | 2.02 | 300 | 0.1772 |
| 0.1796 | 2.08 | 350 | 0.1761 |
| 0.178 | 2.14 | 400 | 0.1762 |
| 0.1666 | 3.03 | 450 | 0.1743 |
| 0.1772 | 3.09 | 500 | 0.1739 |
| 0.1739 | 3.15 | 550 | 0.1746 |
| 0.1652 | 4.04 | 600 | 0.1731 |
| 0.1755 | 4.1 | 650 | 0.1731 |
| 0.1706 | 4.16 | 700 | 0.1735 |
| 0.1668 | 5.04 | 750 | 0.1728 |
| 0.1747 | 5.11 | 800 | 0.1728 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3