trl/trainer/bco_trainer.py [401:498]: - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - ) ref_model_init_kwargs["torch_dtype"] = torch_dtype if isinstance(model, str): model = AutoModelForCausalLM.from_pretrained(model, **model_init_kwargs) if isinstance(ref_model, str): ref_model = AutoModelForCausalLM.from_pretrained(ref_model, **ref_model_init_kwargs) # Initialize this variable to False. This helps tracking the case when `peft_module_casting_to_bf16` # has been called in order to properly call autocast if needed. self._peft_has_been_casted_to_bf16 = False if not is_peft_available() and peft_config is not None: raise ValueError( "PEFT is not installed and you passed a `peft_config` in the trainer's kwargs, please install it with `pip install peft` to use the PEFT models" ) elif is_peft_available() and peft_config is not None: # if model is a peft model and we have a peft_config, we merge and unload it first if isinstance(model, PeftModel): model = model.merge_and_unload() if getattr(model, "is_loaded_in_8bit", False) or getattr(model, "is_loaded_in_4bit", False): _support_gc_kwargs = hasattr( args, "gradient_checkpointing_kwargs" ) and "gradient_checkpointing_kwargs" in list( inspect.signature(prepare_model_for_kbit_training).parameters ) prepare_model_kwargs = {"use_gradient_checkpointing": args.gradient_checkpointing} if _support_gc_kwargs: prepare_model_kwargs["gradient_checkpointing_kwargs"] = args.gradient_checkpointing_kwargs model = prepare_model_for_kbit_training(model, **prepare_model_kwargs) elif args.gradient_checkpointing: # For backward compatibility with older versions of transformers if hasattr(model, "enable_input_require_grads"): model.enable_input_require_grads() else: def make_inputs_require_grad(module, input, output): output.requires_grad_(True) model.get_input_embeddings().register_forward_hook(make_inputs_require_grad) # get peft model with the given config model = get_peft_model(model, peft_config) if args.bf16 and getattr(model, "is_loaded_in_4bit", False): peft_module_casting_to_bf16(model) # If args.bf16 we need to explicitly call `generate` with torch amp autocast context manager self._peft_has_been_casted_to_bf16 = True # For models that use gradient_checkpointing, we need to attach a hook that enables input # to explicitly have `requires_grad=True`, otherwise training will either silently # fail or completely fail. elif args.gradient_checkpointing: # For backward compatibility with older versions of transformers if hasattr(model, "enable_input_require_grads"): model.enable_input_require_grads() else: def make_inputs_require_grad(module, input, output): output.requires_grad_(True) model.get_input_embeddings().register_forward_hook(make_inputs_require_grad) if args.generate_during_eval and not (is_wandb_available() or is_comet_available()): raise ValueError( "`generate_during_eval=True` requires Weights and Biases or Comet to be installed." " Please install `wandb` or `comet-ml` to resolve." ) if model is not None: self.is_encoder_decoder = model.config.is_encoder_decoder elif args.is_encoder_decoder is None: raise ValueError("When no model is provided, you need to pass the parameter is_encoder_decoder.") else: self.is_encoder_decoder = args.is_encoder_decoder self.is_peft_model = is_peft_available() and isinstance(model, PeftModel) self.model_adapter_name = model_adapter_name self.ref_adapter_name = ref_adapter_name if ref_model: self.ref_model = ref_model elif self.is_peft_model or args.precompute_ref_log_probs: # The `model` with adapters turned off will be used as the reference model self.ref_model = None else: self.ref_model = create_reference_model(model) if processing_class is None: raise ValueError( "max_length or a processing_class must be specified when using the default DPODataCollatorWithPadding" ) if args.max_length is None: warnings.warn( - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - trl/trainer/kto_trainer.py [386:483]: - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - ) ref_model_init_kwargs["torch_dtype"] = torch_dtype if isinstance(model, str): model = AutoModelForCausalLM.from_pretrained(model, **model_init_kwargs) if isinstance(ref_model, str): ref_model = AutoModelForCausalLM.from_pretrained(ref_model, **ref_model_init_kwargs) # Initialize this variable to False. This helps tracking the case when `peft_module_casting_to_bf16` # has been called in order to properly call autocast if needed. self._peft_has_been_casted_to_bf16 = False if not is_peft_available() and peft_config is not None: raise ValueError( "PEFT is not installed and you passed a `peft_config` in the trainer's kwargs, please install it with `pip install peft` to use the PEFT models" ) elif is_peft_available() and peft_config is not None: # if model is a peft model and we have a peft_config, we merge and unload it first if isinstance(model, PeftModel): model = model.merge_and_unload() if getattr(model, "is_loaded_in_8bit", False) or getattr(model, "is_loaded_in_4bit", False): _support_gc_kwargs = hasattr( args, "gradient_checkpointing_kwargs" ) and "gradient_checkpointing_kwargs" in list( inspect.signature(prepare_model_for_kbit_training).parameters ) prepare_model_kwargs = {"use_gradient_checkpointing": args.gradient_checkpointing} if _support_gc_kwargs: prepare_model_kwargs["gradient_checkpointing_kwargs"] = args.gradient_checkpointing_kwargs model = prepare_model_for_kbit_training(model, **prepare_model_kwargs) elif args.gradient_checkpointing: # For backward compatibility with older versions of transformers if hasattr(model, "enable_input_require_grads"): model.enable_input_require_grads() else: def make_inputs_require_grad(module, input, output): output.requires_grad_(True) model.get_input_embeddings().register_forward_hook(make_inputs_require_grad) # get peft model with the given config model = get_peft_model(model, peft_config) if args.bf16 and getattr(model, "is_loaded_in_4bit", False): peft_module_casting_to_bf16(model) # If args.bf16 we need to explicitly call `generate` with torch amp autocast context manager self._peft_has_been_casted_to_bf16 = True # For models that use gradient_checkpointing, we need to attach a hook that enables input # to explicitly have `requires_grad=True`, otherwise training will either silently # fail or completely fail. elif args.gradient_checkpointing: # For backward compatibility with older versions of transformers if hasattr(model, "enable_input_require_grads"): model.enable_input_require_grads() else: def make_inputs_require_grad(module, input, output): output.requires_grad_(True) model.get_input_embeddings().register_forward_hook(make_inputs_require_grad) if args.generate_during_eval and not (is_wandb_available() or is_comet_available()): raise ValueError( "`generate_during_eval=True` requires Weights and Biases or Comet to be installed." " Please install `wandb` or `comet-ml` to resolve." ) if model is not None: self.is_encoder_decoder = model.config.is_encoder_decoder elif args.is_encoder_decoder is None: raise ValueError("When no model is provided, you need to pass the parameter is_encoder_decoder.") else: self.is_encoder_decoder = args.is_encoder_decoder self.is_peft_model = is_peft_available() and isinstance(model, PeftModel) self.model_adapter_name = model_adapter_name self.ref_adapter_name = ref_adapter_name if ref_model: self.ref_model = ref_model elif self.is_peft_model or args.precompute_ref_log_probs: # The `model` with adapters turned off will be used as the reference model self.ref_model = None else: self.ref_model = create_reference_model(model) if processing_class is None: raise ValueError( "max_length or a processing_class must be specified when using the default DPODataCollatorWithPadding" ) if args.max_length is None: warnings.warn( - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -