metadata
license: bigcode-openrail-m
base_model: bigcode/starcoder
tags:
- generated_from_trainer
model-index:
- name: starcoder-finetuned-cpp2py
results: []
starcoder-finetuned-cpp2py
This model is a fine-tuned version of bigcode/starcoder on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3484
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: 2e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- training_steps: 1000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.892 | 0.1 | 100 | 0.4126 |
| 0.4991 | 0.2 | 200 | 0.3559 |
| 0.4578 | 0.3 | 300 | 0.3554 |
| 0.4463 | 0.4 | 400 | 0.3514 |
| 0.4381 | 0.5 | 500 | 0.3522 |
| 0.4365 | 0.6 | 600 | 0.3496 |
| 0.4322 | 0.7 | 700 | 0.3498 |
| 0.4332 | 0.8 | 800 | 0.3485 |
| 0.4297 | 0.9 | 900 | 0.3492 |
| 0.432 | 1.0 | 1000 | 0.3484 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3