Statscoder
This model is a fine-tuned version of bigcode/santacoder on R
and SAS
language repositories in the stack dataset.
Training procedure
The model was finetuned using the code adapted from loubnabnl/santacoder-finetuning. Adapted to handle multiple subsets of datasets and it is here.
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- optimizer: adafactor
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- training_steps: 1600
- seq_length: 1024
- no_fp16
- Downloads last month
- 18
Inference API (serverless) does not yet support model repos that contain custom code.