<!-- 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. -->
starcoder_lora_finetuned_cpp2py2_translationdataset_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: 0.1823
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: 50
- training_steps: 500
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.7711 | 0.1 | 50 | 0.2755 |
| 0.2238 | 0.2 | 100 | 0.1994 |
| 0.1911 | 1.01 | 150 | 0.1908 |
| 0.1932 | 1.11 | 200 | 0.1873 |
| 0.1905 | 1.21 | 250 | 0.1862 |
| 0.1785 | 2.03 | 300 | 0.1838 |
| 0.187 | 2.13 | 350 | 0.1833 |
| 0.186 | 2.23 | 400 | 0.1834 |
| 0.1745 | 3.04 | 450 | 0.1823 |
| 0.1861 | 3.14 | 500 | 0.1823 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.4
- Tokenizers 0.13.3
