import DataArguments, ModelArguments, apply_chat_template, get_datasets, get_tokenizer data_args = DataArguments(chat_template=None, dataset_mixer={'HuggingFaceH4/no_robots': 1.0}, dataset_splits=['train_sft', 'test_sft'], max_train_samples=None, max_eval_samples=None, preprocessing_num_workers=12, truncation_side=None) model_args = ModelArguments(base_model_revision=None, model_name_or_path='mistralai/Mistral-7B-v0.1', model_revision='main', model_code_revision=None, torch_dtype='auto', trust_remote_code=True, use_flash_attention_2=True, use_peft=True, lora_r=64, lora_alpha=16, lora_dropout=0.1, lora_target_modules=['q_proj', 'k_proj', 'v_proj', 'o_proj'], lora_modules_to_save=None, load_in_8bit=False, load_in_4bit=True, bnb_4bit_quant_type='nf4', use_bnb_nested_quant=False) ############### # Load datasets ############### raw_datasets = get_datasets(data_args, splits=data_args.dataset_splits) logger.info( f"Training on the following datasets and their proportions: {[split + ' : ' + str(dset.num_rows) for split, dset in raw_datasets.items()]}" ) ################ # Load tokenizer ################ tokenizer = get_tokenizer(model_args, data_args) ##################### # Apply chat template ##################### raw_datasets = raw_datasets.map(apply_chat_template, fn_kwargs={"tokenizer": tokenizer, "task": "sft"}) train_dataset = raw_datasets["train"] eval_dataset = raw_datasets["test"]