def main(): parser = argparse.ArgumentParser() # Required parameters parser.add_argument( "--data_dir", default=None, type=str, required=True, help= "The input data dir. Should contain the .tsv files (or other data files) for the task.", ) parser.add_argument( "--model_type", default=None, type=str, required=True, help="Model type selected in the list: " + ", ".join(MODEL_CLASSES.keys()), ) parser.add_argument( "--model_name_or_path", default=None, type=str, required=True, help= "Path to pretrained model or model identifier from huggingface.co/models", ) parser.add_argument( "--task_name", default=None, type=str, required=True, help="The name of the task to train selected in the list: " + ", ".join(hans_processors.keys()), ) parser.add_argument( "--output_dir", default=None, type=str, required=True, help= "The output directory where the model predictions and checkpoints will be written.", ) # Other parameters parser.add_argument( "--config_name", default="", type=str, help="Pretrained config name or path if not the same as model_name") parser.add_argument( "--tokenizer_name", default="", type=str, help="Pretrained tokenizer name or path if not the same as model_name", ) parser.add_argument( "--cache_dir", default="", type=str, help= "Where do you want to store the pre-trained models downloaded from s3", ) parser.add_argument( "--max_seq_length", default=128, type=int, help= "The maximum total input sequence length after tokenization. Sequences longer " "than this will be truncated, sequences shorter will be padded.", ) parser.add_argument("--do_train", action="store_true", help="Whether to run training.") parser.add_argument("--do_eval", action="store_true", help="Whether to run eval on the dev set.") parser.add_argument( "--evaluate_during_training", action="store_true", help="Rul evaluation during training at each logging step.") parser.add_argument( "--do_lower_case", action="store_true", help="Set this flag if you are using an uncased model.") parser.add_argument("--per_gpu_train_batch_size", default=8, type=int, help="Batch size per GPU/CPU for training.") parser.add_argument("--per_gpu_eval_batch_size", default=8, type=int, help="Batch size per GPU/CPU for evaluation.") parser.add_argument( "--gradient_accumulation_steps", type=int, default=1, help= "Number of updates steps to accumulate before performing a backward/update pass.", ) parser.add_argument("--learning_rate", default=5e-5, type=float, help="The initial learning rate for Adam.") parser.add_argument("--weight_decay", default=0.0, type=float, help="Weight decay if we apply some.") parser.add_argument("--adam_epsilon", default=1e-8, type=float, help="Epsilon for Adam optimizer.") parser.add_argument("--max_grad_norm", default=1.0, type=float, help="Max gradient norm.") parser.add_argument("--num_train_epochs", default=3.0, type=float, help="Total number of training epochs to perform.") parser.add_argument( "--max_steps", default=-1, type=int, help= "If > 0: set total number of training steps to perform. Override num_train_epochs.", ) parser.add_argument("--warmup_steps", default=0, type=int, help="Linear warmup over warmup_steps.") parser.add_argument("--logging_steps", type=int, default=50, help="Log every X updates steps.") parser.add_argument("--save_steps", type=int, default=50, help="Save checkpoint every X updates steps.") parser.add_argument( "--eval_all_checkpoints", action="store_true", help= "Evaluate all checkpoints starting with the same prefix as model_name ending and ending with step number", ) parser.add_argument("--no_cuda", action="store_true", help="Avoid using CUDA when available") parser.add_argument("--overwrite_output_dir", action="store_true", help="Overwrite the content of the output directory") parser.add_argument( "--overwrite_cache", action="store_true", help="Overwrite the cached training and evaluation sets") parser.add_argument("--seed", type=int, default=42, help="random seed for initialization") parser.add_argument( "--fp16", action="store_true", help= "Whether to use 16-bit (mixed) precision (through NVIDIA apex) instead of 32-bit", ) parser.add_argument( "--fp16_opt_level", type=str, default="O1", help= "For fp16: Apex AMP optimization level selected in ['O0', 'O1', 'O2', and 'O3']." "See details at https://nvidia.github.io/apex/amp.html", ) parser.add_argument("--local_rank", type=int, default=-1, help="For distributed training: local_rank") parser.add_argument("--server_ip", type=str, default="", help="For distant debugging.") parser.add_argument("--server_port", type=str, default="", help="For distant debugging.") args = parser.parse_args() if (os.path.exists(args.output_dir) and os.listdir(args.output_dir) and args.do_train and not args.overwrite_output_dir): raise ValueError( "Output directory ({}) already exists and is not empty. Use --overwrite_output_dir to overcome." .format(args.output_dir)) # Setup distant debugging if needed if args.server_ip and args.server_port: # Distant debugging - see https://code.visualstudio.com/docs/python/debugging#_attach-to-a-local-script import ptvsd print("Waiting for debugger attach") ptvsd.enable_attach(address=(args.server_ip, args.server_port), redirect_output=True) ptvsd.wait_for_attach() # Setup CUDA, GPU & distributed training if args.local_rank == -1 or args.no_cuda: device = torch.device("cuda" if torch.cuda.is_available() and not args.no_cuda else "cpu") args.n_gpu = 0 if args.no_cuda else torch.cuda.device_count() else: # Initializes the distributed backend which will take care of sychronizing nodes/GPUs torch.cuda.set_device(args.local_rank) device = torch.device("cuda", args.local_rank) torch.distributed.init_process_group(backend="nccl") args.n_gpu = 1 args.device = device # Setup logging logging.basicConfig( format="%(asctime)s - %(levelname)s - %(name)s - %(message)s", datefmt="%m/%d/%Y %H:%M:%S", level=logging.INFO if args.local_rank in [-1, 0] else logging.WARN, ) logger.warning( "Process rank: %s, device: %s, n_gpu: %s, distributed training: %s, 16-bits training: %s", args.local_rank, device, args.n_gpu, bool(args.local_rank != -1), args.fp16, ) # Set seed set_seed(args) # Prepare GLUE task args.task_name = args.task_name.lower() if args.task_name not in hans_processors: raise ValueError("Task not found: %s" % (args.task_name)) processor = hans_processors[args.task_name]() args.output_mode = hans_output_modes[args.task_name] label_list = processor.get_labels() num_labels = len(label_list) # Load pretrained model and tokenizer if args.local_rank not in [-1, 0]: torch.distributed.barrier( ) # Make sure only the first process in distributed training will download model & vocab args.model_type = args.model_type.lower() config_class, model_class, tokenizer_class = MODEL_CLASSES[args.model_type] config = config_class.from_pretrained( args.config_name if args.config_name else args.model_name_or_path, num_labels=num_labels, finetuning_task=args.task_name, cache_dir=args.cache_dir if args.cache_dir else None, ) tokenizer = tokenizer_class.from_pretrained( args.tokenizer_name if args.tokenizer_name else args.model_name_or_path, do_lower_case=args.do_lower_case, cache_dir=args.cache_dir if args.cache_dir else None, ) model = model_class.from_pretrained( args.model_name_or_path, from_tf=bool(".ckpt" in args.model_name_or_path), config=config, cache_dir=args.cache_dir if args.cache_dir else None, ) if args.local_rank == 0: torch.distributed.barrier( ) # Make sure only the first process in distributed training will download model & vocab model.to(args.device) logger.info("Training/evaluation parameters %s", args) # Training if args.do_train: train_dataset = HansDataset(args.data_dir, tokenizer, args.task_name, args.max_seq_length, overwrite_cache=args.overwrite_cache) global_step, tr_loss = train(args, train_dataset, model, tokenizer) logger.info(" global_step = %s, average loss = %s", global_step, tr_loss) # Saving best-practices: if you use defaults names for the model, you can reload it using from_pretrained() if args.do_train and (args.local_rank == -1 or torch.distributed.get_rank() == 0): # Create output directory if needed if not os.path.exists(args.output_dir) and args.local_rank in [-1, 0]: os.makedirs(args.output_dir) logger.info("Saving model checkpoint to %s", args.output_dir) # Save a trained model, configuration and tokenizer using `save_pretrained()`. # They can then be reloaded using `from_pretrained()` model_to_save = (model.module if hasattr(model, "module") else model ) # Take care of distributed/parallel training model_to_save.save_pretrained(args.output_dir) tokenizer.save_pretrained(args.output_dir) # Good practice: save your training arguments together with the trained model torch.save(args, os.path.join(args.output_dir, "training_args.bin")) # Load a trained model and vocabulary that you have fine-tuned model = model_class.from_pretrained(args.output_dir) tokenizer = tokenizer_class.from_pretrained(args.output_dir) model.to(args.device) # Evaluation results = {} if args.do_eval and args.local_rank in [-1, 0]: tokenizer = tokenizer_class.from_pretrained( args.output_dir, do_lower_case=args.do_lower_case) checkpoints = [args.output_dir] if args.eval_all_checkpoints: checkpoints = list( os.path.dirname(c) for c in sorted( glob.glob(args.output_dir + "/**/" + WEIGHTS_NAME, recursive=True))) logging.getLogger("transformers.modeling_utils").setLevel( logging.WARN) # Reduce logging logger.info("Evaluate the following checkpoints: %s", checkpoints) for checkpoint in checkpoints: global_step = checkpoint.split( "-")[-1] if len(checkpoints) > 1 else "" prefix = checkpoint.split( "/")[-1] if checkpoint.find("checkpoint") != -1 else "" model = model_class.from_pretrained(checkpoint) model.to(args.device) result = evaluate(args, model, tokenizer, label_list, prefix=prefix) result = dict( (k + "_{}".format(global_step), v) for k, v in result.items()) results.update(result) return results
def main(): # See all possible arguments in src/transformers/training_args.py # or by passing the --help flag to this script. # We now keep distinct sets of args, for a cleaner separation of concerns. parser = HfArgumentParser( (ModelArguments, DataTrainingArguments, TrainingArguments)) model_args, data_args, training_args = parser.parse_args_into_dataclasses() if (os.path.exists(training_args.output_dir) and os.listdir(training_args.output_dir) and training_args.do_train and not training_args.overwrite_output_dir): raise ValueError( f"Output directory ({training_args.output_dir}) already exists and is not empty. Use --overwrite_output_dir to overcome." ) # Setup logging logging.basicConfig( format="%(asctime)s - %(levelname)s - %(name)s - %(message)s", datefmt="%m/%d/%Y %H:%M:%S", level=logging.INFO if training_args.local_rank in [-1, 0] else logging.WARN, ) logger.warning( "Process rank: %s, device: %s, n_gpu: %s, distributed training: %s, 16-bits training: %s", training_args.local_rank, training_args.device, training_args.n_gpu, bool(training_args.local_rank != -1), training_args.fp16, ) # Set the verbosity to info of the Transformers logger (on main process only): if is_main_process(training_args.local_rank): transformers.utils.logging.set_verbosity_info() transformers.utils.logging.enable_default_handler() transformers.utils.logging.enable_explicit_format() logger.info("Training/evaluation parameters %s", training_args) # Set seed set_seed(training_args.seed) try: num_labels = hans_tasks_num_labels[data_args.task_name] except KeyError: raise ValueError("Task not found: %s" % (data_args.task_name)) # Load pretrained model and tokenizer # # Distributed training: # The .from_pretrained methods guarantee that only one local process can concurrently # download model & vocab. config = AutoConfig.from_pretrained( model_args.config_name if model_args.config_name else model_args.model_name_or_path, num_labels=num_labels, finetuning_task=data_args.task_name, cache_dir=model_args.cache_dir, ) tokenizer = AutoTokenizer.from_pretrained( model_args.tokenizer_name if model_args.tokenizer_name else model_args.model_name_or_path, cache_dir=model_args.cache_dir, ) model = AutoModelForSequenceClassification.from_pretrained( model_args.model_name_or_path, from_tf=bool(".ckpt" in model_args.model_name_or_path), config=config, cache_dir=model_args.cache_dir, ) # Get datasets train_dataset = (HansDataset( data_dir=data_args.data_dir, tokenizer=tokenizer, task=data_args.task_name, max_seq_length=data_args.max_seq_length, overwrite_cache=data_args.overwrite_cache, ) if training_args.do_train else None) eval_dataset = (HansDataset( data_dir=data_args.data_dir, tokenizer=tokenizer, task=data_args.task_name, max_seq_length=data_args.max_seq_length, overwrite_cache=data_args.overwrite_cache, evaluate=True, ) if training_args.do_eval else None) # Initialize our Trainer trainer = Trainer( model=model, args=training_args, train_dataset=train_dataset, eval_dataset=eval_dataset, data_collator=hans_data_collator, ) # Training if training_args.do_train: trainer.train(model_path=model_args.model_name_or_path if os.path. isdir(model_args.model_name_or_path) else None) trainer.save_model() # For convenience, we also re-save the tokenizer to the same directory, # so that you can share your model easily on huggingface.co/models =) if trainer.is_world_master(): tokenizer.save_pretrained(training_args.output_dir) # Evaluation if training_args.do_eval: logger.info("*** Evaluate ***") output = trainer.predict(eval_dataset) preds = output.predictions preds = np.argmax(preds, axis=1) pair_ids = [ex.pairID for ex in eval_dataset] output_eval_file = os.path.join(training_args.output_dir, "hans_predictions.txt") label_list = eval_dataset.get_labels() if trainer.is_world_master(): with open(output_eval_file, "w") as writer: writer.write("pairID,gold_label\n") for pid, pred in zip(pair_ids, preds): writer.write("ex" + str(pid) + "," + label_list[int(pred)] + "\n") trainer._log(output.metrics)
def evaluate(args, model, tokenizer, label_list, prefix=""): # Loop to handle MNLI double evaluation (matched, mis-matched) eval_task_names = ("mnli", "mnli-mm") if args.task_name == "mnli" else ( args.task_name, ) eval_outputs_dirs = (args.output_dir, args.output_dir + "-MM") if args.task_name == "mnli" else ( args.output_dir, ) results = {} for eval_task, eval_output_dir in zip(eval_task_names, eval_outputs_dirs): eval_dataset = HansDataset( args.data_dir, tokenizer, args.task_name, args.max_seq_length, overwrite_cache=args.overwrite_cache, evaluate=True, ) if not os.path.exists(eval_output_dir) and args.local_rank in [-1, 0]: os.makedirs(eval_output_dir) args.eval_batch_size = args.per_gpu_eval_batch_size * max( 1, args.n_gpu) # Note that DistributedSampler samples randomly eval_sampler = SequentialSampler(eval_dataset) eval_dataloader = DataLoader( eval_dataset, sampler=eval_sampler, batch_size=args.eval_batch_size, collate_fn=default_data_collator, ) # multi-gpu eval if args.n_gpu > 1 and not isinstance(model, torch.nn.DataParallel): model = torch.nn.DataParallel(model) # Eval! logger.info("***** Running evaluation {} *****".format(prefix)) logger.info(" Num examples = %d", len(eval_dataset)) logger.info(" Batch size = %d", args.eval_batch_size) eval_loss = 0.0 nb_eval_steps = 0 preds = None out_label_ids = None for batch in tqdm(eval_dataloader, desc="Evaluating"): model.eval() inputs = { k: t.to(args.device) for k, t in batch.items() if k != "pairID" } pair_ids = batch.pop("pairID", None) with torch.no_grad(): outputs = model(**inputs) tmp_eval_loss, logits = outputs[:2] eval_loss += tmp_eval_loss.mean().item() nb_eval_steps += 1 if preds is None: preds = logits.detach().cpu().numpy() out_label_ids = inputs["labels"].detach().cpu().numpy() pair_ids = pair_ids.detach().cpu().numpy() else: preds = np.append(preds, logits.detach().cpu().numpy(), axis=0) out_label_ids = np.append( out_label_ids, inputs["labels"].detach().cpu().numpy(), axis=0) pair_ids = np.append(pair_ids, pair_ids.detach().cpu().numpy(), axis=0) eval_loss = eval_loss / nb_eval_steps if args.output_mode == "classification": preds = np.argmax(preds, axis=1) elif args.output_mode == "regression": preds = np.squeeze(preds) output_eval_file = os.path.join(eval_output_dir, "hans_predictions.txt") with open(output_eval_file, "w") as writer: writer.write("pairID,gld_label\n") for pid, pred in zip(pair_ids, preds): writer.write("ex" + str(pid) + "," + label_list[int(pred)] + "\n") return results