starcoder-finetuned-code2code
This model is a fine-tuned version of bigcode/starcoder on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3667
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: 0.0001
- 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: 600
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.7191 | 0.17 | 100 | 0.4499 |
0.4506 | 0.33 | 200 | 0.3985 |
0.3988 | 0.5 | 300 | 0.3807 |
0.3684 | 0.67 | 400 | 0.3709 |
0.3499 | 0.83 | 500 | 0.3670 |
0.3438 | 1.0 | 600 | 0.3667 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3
Model tree for jlpan/starcoder-finetuned-code2code
Base model
bigcode/starcoder