{ "model": { "general": { "max_seq_length": 128, "seed": 42, "num_train_epochs": null, "max_steps": 60, "dataset_text_field": "text", "model_name": null, "repository": null }, "peft": { "r": 16, "alpha": 16, "dropout": 0, "bias": "none", "rslora": false, "loftq_config": null }, "sft": { "per_device_train_batch_size": 2, "gradient_accumulation_steps": 4, "learning_rate": 2e-4, "warmup_steps": 5, "logging_steps": 1, "optim": "adamw_8bit", "weight_decay": 0.01, "lr_scheduler_type": "linear", "dataset_num_proc": 2, "packing": false }, "choices": ["unsloth/llama-3-8b-bnb-4bit", "unsloth/Qwen2-7B", "unsloth/gemma-7b-bnb-4bit", "unsloth/mistral-7b-v0.3-bnb-4bit"] } }