{"max_seq_length": 1000, "language": "python", "dataset_size": 7500, "epochs": 4, "per_device_train_batch_size": 8, "gradient_accumulation_steps": 64, "learning_rate": 1e-06, "no_lora": true, "lora_r": 64, "lora_alpha": 16, "lora_dropout": 0.15, "weight_decay": 0.15, "dataset_name": "stojchet/dpo-final_base_dataset", "base_model": "deepseek-ai/deepseek-coder-1.3b-base"}