| { |
| "model": "facebook/llm-compiler-7b", |
| "project_name": "LlmCompiler-Stm32", |
| "data_path": "Cal-mfbc5446/Dataset10", |
| "train_split": "train", |
| "valid_split": null, |
| "add_eos_token": true, |
| "block_size": 1024, |
| "model_max_length": 4096, |
| "padding": "right", |
| "trainer": "sft", |
| "use_flash_attention_2": false, |
| "log": "tensorboard", |
| "disable_gradient_checkpointing": false, |
| "logging_steps": 50, |
| "eval_strategy": "epoch", |
| "save_total_limit": 1, |
| "auto_find_batch_size": false, |
| "mixed_precision": "fp16", |
| "lr": 2e-05, |
| "epochs": 3, |
| "batch_size": 1, |
| "warmup_ratio": 0.1, |
| "gradient_accumulation": 32, |
| "optimizer": "adamw_torch", |
| "scheduler": "cosine", |
| "weight_decay": 0.01, |
| "max_grad_norm": 1.0, |
| "seed": 42, |
| "chat_template": "tokenizer", |
| "quantization": "int4", |
| "target_modules": "all-linear", |
| "merge_adapter": false, |
| "peft": true, |
| "lora_r": 16, |
| "lora_alpha": 32, |
| "lora_dropout": 0.05, |
| "model_ref": null, |
| "dpo_beta": 0.1, |
| "max_prompt_length": 128, |
| "max_completion_length": null, |
| "prompt_text_column": "prompt", |
| "text_column": "messages", |
| "rejected_text_column": "rejected_text", |
| "push_to_hub": true, |
| "username": "Cal-mfbc5446", |
| "unsloth": false, |
| "distributed_backend": "none" |
| } |
