starcoder-java2py-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: 0.2013
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: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- training_steps: 150
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
3.6996 | 0.17 | 25 | 0.3575 |
0.2656 | 0.33 | 50 | 0.2185 |
0.2123 | 0.5 | 75 | 0.2070 |
0.2077 | 0.67 | 100 | 0.2030 |
0.2036 | 0.83 | 125 | 0.2016 |
0.2042 | 1.0 | 150 | 0.2013 |
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-java2py-snippet1
Base model
bigcode/starcoder