| {"max_seq_length": 1000, "language": "python", "dataset_size": 100, "epochs": 1, "per_device_train_batch_size": 8, "gradient_accumulation_steps": 16, "learning_rate": 1.41e-05, "lora_r": 64, "lora_alpha": 16, "lora_dropout": 0.1, "dataset_name": "stojchet/csn_java_python_subset", "base_model": "deepseek-ai/deepseek-coder-1.3b-base", "dataset_ref_field": "whole_func_string", "config_path": "configs", "config_name": "sft_small"} |