metadata
license: bigcode-openrail-m
base_model: bigcode/starcoder
tags:
- generated_from_trainer
model-index:
- name: starcoder-c2py-snippet1
results: []
library_name: peft
starcoder-c2py-snippet1
This model is a fine-tuned version of bigcode/starcoder on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2014
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: 9e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- training_steps: 100
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 8.2651 | 0.1 | 10 | 4.2201 |
| 0.9761 | 0.2 | 20 | 0.5205 |
| 0.3183 | 0.3 | 30 | 0.2766 |
| 0.1887 | 1.04 | 40 | 0.2384 |
| 0.1867 | 1.14 | 50 | 0.2171 |
| 0.1732 | 1.24 | 60 | 0.2072 |
| 0.156 | 1.34 | 70 | 0.2034 |
| 0.1415 | 2.08 | 80 | 0.2022 |
| 0.1614 | 2.17 | 90 | 0.2016 |
| 0.1568 | 2.27 | 100 | 0.2014 |
Framework versions
- PEFT 0.5.0.dev0
- PEFT 0.5.0.dev0
- Transformers 4.32.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3