from __future__ import absolute_import, division, print_function import argparse import glob import logging import os import random import numpy as np import torch from torch import nn import torch.nn.functional as F from torch.nn import CrossEntropyLoss from torch.utils.data import (DataLoader, RandomSampler, SequentialSampler, TensorDataset) from torch.utils.data.distributed import DistributedSampler from tensorboardX import SummaryWriter from tqdm import tqdm, trange from pytorch_transformers import (WEIGHTS_NAME, BertConfig, BertForTokenClassification, BertForSequenceClassification, BertTokenizer, RobertaConfig, RobertaForSequenceClassification, RobertaTokenizer, XLMConfig, XLMForSequenceClassification, XLMTokenizer, XLNetConfig, XLNetForSequenceClassification, XLNetTokenizer) from pytorch_transformers import AdamW, WarmupLinearSchedule from seqeval.metrics import classification_report from utils_glue import compute_metrics # Prepare GLUE task output_modes = { "ner": "classification", } class Ner(BertForTokenClassification): def forward(self, input_ids, token_type_ids=None, attention_mask=None, labels=None,valid_ids=None,attention_mask_label=None): #sequence_output, _ = self.bert(input_ids, token_type_ids, attention_mask, output_all_encoded_layers=False) sequence_output, _ = self.bert(input_ids, token_type_ids, attention_mask) batch_size,max_len,feat_dim = sequence_output.shape valid_output = torch.zeros(batch_size,max_len,feat_dim,dtype=torch.float32,device='cuda') for i in range(batch_size): jj = -1 for j in range(max_len): if valid_ids[i][j].item() == 1: jj += 1 valid_output[i][jj] = sequence_output[i][j] sequence_output = self.dropout(valid_output) logits = self.classifier(sequence_output) if labels is not None: loss_fct = CrossEntropyLoss(ignore_index=0) # Only keep active parts of the loss attention_mask_label = None if attention_mask_label is not None: active_loss = attention_mask_label.view(-1) == 1 active_logits = logits.view(-1, self.num_labels)[active_loss] active_labels = labels.view(-1)[active_loss] loss = loss_fct(active_logits, active_labels) else: loss = loss_fct(logits.view(-1, self.num_labels), labels.view(-1)) return loss else: return logits class InputExample(object): """A single training/test example for simple sequence classification.""" def __init__(self, guid, text_a, text_b=None, label=None): """Constructs a InputExample. Args: guid: Unique id for the example. text_a: string. The untokenized text of the first sequence. For single sequence tasks, only this sequence must be specified. text_b: (Optional) string. The untokenized text of the second sequence. Only must be specified for sequence pair tasks. label: (Optional) string. The label of the example. This should be specified for train and dev examples, but not for test examples. """ self.guid = guid self.text_a = text_a self.text_b = text_b self.label = label class InputFeatures(object): """A single set of features of data.""" def __init__(self, input_ids, input_mask, segment_ids, label_id, valid_ids=None, label_mask=None): self.input_ids = input_ids self.input_mask = input_mask self.segment_ids = segment_ids self.label_id = label_id self.valid_ids = valid_ids self.label_mask = label_mask def readfile(filename): ''' read file ''' f = open(filename) data = [] sentence = [] label= [] for line in f: if len(line)==0 or line.startswith('-DOCSTART') or line[0]=="\n": if len(sentence) > 0: data.append((sentence,label)) sentence = [] label = [] continue splits = line.split(' ') sentence.append(splits[0]) label.append(splits[-1][:-1]) if len(sentence) >0: data.append((sentence,label)) sentence = [] label = [] return data class DataProcessor(object): """Base class for data converters for sequence classification data sets.""" def get_train_examples(self, data_dir): """Gets a collection of `InputExample`s for the train set.""" raise NotImplementedError() def get_dev_examples(self, data_dir): """Gets a collection of `InputExample`s for the dev set.""" raise NotImplementedError() def get_labels(self): """Gets the list of labels for this data set.""" raise NotImplementedError() @classmethod def _read_tsv(cls, input_file, quotechar=None): """Reads a tab separated value file.""" return readfile(input_file) class NerProcessor(DataProcessor): """Processor for the CoNLL-2003 data set.""" def get_train_examples(self, data_dir): """See base class.""" return self._create_examples( self._read_tsv(os.path.join(data_dir, "train.txt")), "train") def get_dev_examples(self, data_dir): """See base class.""" return self._create_examples( self._read_tsv(os.path.join(data_dir, "valid.txt")), "dev") def get_test_examples(self, data_dir): """See base class.""" return self._create_examples( self._read_tsv(os.path.join(data_dir, "test.txt")), "test") def get_labels(self): return ["O", "B-MISC", "I-MISC", "B-PER", "I-PER", "B-ORG", "I-ORG", "B-LOC", "I-LOC", "[CLS]", "[SEP]"] def _create_examples(self,lines,set_type): examples = [] for i,(sentence,label) in enumerate(lines): guid = "%s-%s" % (set_type, i) text_a = ' '.join(sentence) text_b = None label = label examples.append(InputExample(guid=guid,text_a=text_a,text_b=text_b,label=label)) return examples def convert_examples_to_features(examples, label_list, max_seq_length, tokenizer): """Loads a data file into a list of `InputBatch`s.""" label_map = {label : i for i, label in enumerate(label_list,1)} features = [] for (ex_index,example) in enumerate(examples): textlist = example.text_a.split(' ') labellist = example.label tokens = [] labels = [] valid = [] label_mask = [] for i, word in enumerate(textlist): token = tokenizer.tokenize(word) tokens.extend(token) label_1 = labellist[i] for m in range(len(token)): if m == 0: labels.append(label_1) valid.append(1) label_mask.append(1) else: valid.append(0) if len(tokens) >= max_seq_length - 1: tokens = tokens[0:(max_seq_length - 2)] labels = labels[0:(max_seq_length - 2)] valid = valid[0:(max_seq_length - 2)] label_mask = label_mask[0:(max_seq_length - 2)] ntokens = [] segment_ids = [] label_ids = [] ntokens.append("[CLS]") segment_ids.append(0) valid.insert(0,1) label_mask.insert(0,1) label_ids.append(label_map["[CLS]"]) for i, token in enumerate(tokens): ntokens.append(token) segment_ids.append(0) if len(labels) > i: label_ids.append(label_map[labels[i]]) ntokens.append("[SEP]") segment_ids.append(0) valid.append(1) label_mask.append(1) label_ids.append(label_map["[SEP]"]) input_ids = tokenizer.convert_tokens_to_ids(ntokens) input_mask = [1] * len(input_ids) label_mask = [1] * len(label_ids) while len(input_ids) < max_seq_length: input_ids.append(0) input_mask.append(0) segment_ids.append(0) label_ids.append(0) valid.append(1) label_mask.append(0) while len(label_ids) < max_seq_length: label_ids.append(0) label_mask.append(0) assert len(input_ids) == max_seq_length assert len(input_mask) == max_seq_length assert len(segment_ids) == max_seq_length assert len(label_ids) == max_seq_length assert len(valid) == max_seq_length assert len(label_mask) == max_seq_length if ex_index < 5: logger.info("*** Example ***") logger.info("guid: %s" % (example.guid)) logger.info("tokens: %s" % " ".join( [str(x) for x in tokens])) logger.info("input_ids: %s" % " ".join([str(x) for x in input_ids])) logger.info("input_mask: %s" % " ".join([str(x) for x in input_mask])) logger.info( "segment_ids: %s" % " ".join([str(x) for x in segment_ids])) # logger.info("label: %s (id = %d)" % (example.label, label_ids)) features.append( InputFeatures(input_ids=input_ids, input_mask=input_mask, segment_ids=segment_ids, label_id=label_ids, valid_ids=valid, label_mask=label_mask)) return features logger = logging.getLogger(__name__) ALL_MODELS = sum((tuple(conf.pretrained_config_archive_map.keys()) for conf in (BertConfig, XLNetConfig, XLMConfig, RobertaConfig)), ()) MODEL_CLASSES = { 'bert': (BertConfig, BertForSequenceClassification, BertTokenizer), 'xlnet': (XLNetConfig, XLNetForSequenceClassification, XLNetTokenizer), 'xlm': (XLMConfig, XLMForSequenceClassification, XLMTokenizer), 'roberta': (RobertaConfig, RobertaForSequenceClassification, RobertaTokenizer), } def set_seed(args): random.seed(args.seed) np.random.seed(args.seed) torch.manual_seed(args.seed) if args.n_gpu > 0: torch.cuda.manual_seed_all(args.seed) def train(args, train_dataset, model, tokenizer): """ Train the model """ if args.local_rank in [-1, 0]: tb_writer = SummaryWriter() args.train_batch_size = args.per_gpu_train_batch_size * max(1, args.n_gpu) train_sampler = RandomSampler(train_dataset) if args.local_rank == -1 else DistributedSampler(train_dataset) train_dataloader = DataLoader(train_dataset, sampler=train_sampler, batch_size=args.train_batch_size) if args.max_steps > 0: t_total = args.max_steps args.num_train_epochs = args.max_steps // (len(train_dataloader) // args.gradient_accumulation_steps) + 1 else: t_total = len(train_dataloader) // args.gradient_accumulation_steps * args.num_train_epochs # Prepare optimizer and schedule (linear warmup and decay) no_decay = ['bias', 'LayerNorm.weight'] optimizer_grouped_parameters = [ {'params': [p for n, p in model.named_parameters() if not any(nd in n for nd in no_decay)], 'weight_decay': args.weight_decay}, {'params': [p for n, p in model.named_parameters() if any(nd in n for nd in no_decay)], 'weight_decay': 0.0} ] optimizer = AdamW(optimizer_grouped_parameters, lr=args.learning_rate, eps=args.adam_epsilon) scheduler = WarmupLinearSchedule(optimizer, warmup_steps=args.warmup_steps, t_total=t_total) if args.fp16: try: from apex import amp except ImportError: raise ImportError("Please install apex from https://www.github.com/nvidia/apex to use fp16 training.") model, optimizer = amp.initialize(model, optimizer, opt_level=args.fp16_opt_level) # multi-gpu training (should be after apex fp16 initialization) if args.n_gpu > 1: model = torch.nn.DataParallel(model) # Distributed training (should be after apex fp16 initialization) if args.local_rank != -1: model = torch.nn.parallel.DistributedDataParallel(model, device_ids=[args.local_rank], output_device=args.local_rank, find_unused_parameters=True) # Train! logger.info("***** Running training *****") logger.info(" Num examples = %d", len(train_dataset)) logger.info(" Num Epochs = %d", args.num_train_epochs) logger.info(" Instantaneous batch size per GPU = %d", args.per_gpu_train_batch_size) logger.info(" Total train batch size (w. parallel, distributed & accumulation) = %d", args.train_batch_size * args.gradient_accumulation_steps * (torch.distributed.get_world_size() if args.local_rank != -1 else 1)) logger.info(" Gradient Accumulation steps = %d", args.gradient_accumulation_steps) logger.info(" Total optimization steps = %d", t_total) global_step = 0 tr_loss, logging_loss = 0.0, 0.0 model.zero_grad() train_iterator = trange(int(args.num_train_epochs), desc="Epoch", disable=args.local_rank not in [-1, 0]) set_seed(args) # Added here for reproductibility (even between python 2 and 3) for _ in train_iterator: epoch_iterator = tqdm(train_dataloader, desc="Iteration", disable=args.local_rank not in [-1, 0]) for step, batch in enumerate(epoch_iterator): model.train() batch = tuple(t.to(args.device) for t in batch) input_ids, input_mask, segment_ids, label_ids, valid_ids,l_mask = batch inputs = {'input_ids': batch[0], 'attention_mask': batch[1], 'token_type_ids': batch[2] if args.model_type in ['bert', 'xlnet'] else None, # XLM and RoBERTa don't use segment_ids 'labels': batch[3]} #outputs = model(**inputs) outputs = model(input_ids, segment_ids, input_mask, label_ids,valid_ids,l_mask) loss = outputs #[0] # model outputs are always tuple in pytorch-transformers (see doc) if args.n_gpu > 1: loss = loss.mean() # mean() to average on multi-gpu parallel training if args.gradient_accumulation_steps > 1: loss = loss / args.gradient_accumulation_steps if args.fp16: with amp.scale_loss(loss, optimizer) as scaled_loss: scaled_loss.backward() torch.nn.utils.clip_grad_norm_(amp.master_params(optimizer), args.max_grad_norm) else: loss.backward() torch.nn.utils.clip_grad_norm_(model.parameters(), args.max_grad_norm) tr_loss += loss.item() if (step + 1) % args.gradient_accumulation_steps == 0: scheduler.step() # Update learning rate schedule optimizer.step() model.zero_grad() global_step += 1 if args.local_rank in [-1, 0] and args.logging_steps > 0 and global_step % args.logging_steps == 0: # Log metrics if args.local_rank == -1 and args.evaluate_during_training: # Only evaluate when single GPU otherwise metrics may not average well results = evaluate(args, model, tokenizer) for key, value in results.items(): tb_writer.add_scalar('eval_{}'.format(key), value, global_step) tb_writer.add_scalar('lr', scheduler.get_lr()[0], global_step) tb_writer.add_scalar('loss', (tr_loss - logging_loss)/args.logging_steps, global_step) logging_loss = tr_loss if args.local_rank in [-1, 0] and args.save_steps > 0 and global_step % args.save_steps == 0: # Save model checkpoint output_dir = os.path.join(args.output_dir, 'checkpoint-{}'.format(global_step)) if not os.path.exists(output_dir): os.makedirs(output_dir) model_to_save = model.module if hasattr(model, 'module') else model # Take care of distributed/parallel training model_to_save.save_pretrained(output_dir) torch.save(args, os.path.join(output_dir, 'training_args.bin')) logger.info("Saving model checkpoint to %s", output_dir) if args.max_steps > 0 and global_step > args.max_steps: epoch_iterator.close() break if args.max_steps > 0 and global_step > args.max_steps: train_iterator.close() break if args.local_rank in [-1, 0]: tb_writer.close() return global_step, tr_loss / global_step def evaluate(args, model, tokenizer, prefix, label_map): # 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 = load_and_cache_examples(args, eval_task, tokenizer, 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) if args.local_rank == -1 else DistributedSampler(eval_dataset) eval_dataloader = DataLoader(eval_dataset, sampler=eval_sampler, batch_size=args.eval_batch_size) # 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 y_true = [] y_pred = [] for batch in tqdm(eval_dataloader, desc="Evaluating"): model.eval() batch = tuple(t.to(args.device) for t in batch) with torch.no_grad(): input_ids, input_mask, segment_ids, label_ids, valid_ids,l_mask = batch outputs = model(input_ids, segment_ids, input_mask,valid_ids=valid_ids,attention_mask_label=l_mask) logits = outputs #[:2] logits = torch.argmax(F.log_softmax(logits,dim=2),dim=2) logits = logits.detach().cpu().numpy() label_ids = label_ids.to('cpu').numpy() input_mask = input_mask.to('cpu').numpy() for i, label in enumerate(label_ids): temp_1 = [] temp_2 = [] for j,m in enumerate(label): if j == 0: continue elif label_ids[i][j] == len(label_map): y_true.append(temp_1) y_pred.append(temp_2) break else: temp_1.append(label_map[label_ids[i][j]]) temp_2.append(label_map[logits[i][j]]) report = classification_report(y_true, y_pred,digits=4) logger.info("\n%s", report) output_eval_file = os.path.join(args.output_dir, "eval_results.txt") with open(output_eval_file, "w") as writer: logger.info("***** Eval results *****") logger.info("\n%s", report) writer.write(report) def load_and_cache_examples(args, task, tokenizer, evaluate=False): if args.local_rank not in [-1, 0] and not evaluate: torch.distributed.barrier() # Make sure only the first process in distributed training process the dataset, and the others will use the cache processor = NerProcessor() output_mode = output_modes[task] # Load data features from cache or dataset file cached_features_file = os.path.join(args.data_dir, 'cached_{}_{}_{}_{}'.format( 'dev' if evaluate else 'train', list(filter(None, args.model_name_or_path.split('/'))).pop(), str(args.max_seq_length), str(task))) if os.path.exists(cached_features_file): logger.info("Loading features from cached file %s", cached_features_file) features = torch.load(cached_features_file) else: logger.info("Creating features from dataset file at %s", args.data_dir) label_list = processor.get_labels() if task in ['mnli', 'mnli-mm'] and args.model_type in ['roberta']: # HACK(label indices are swapped in RoBERTa pretrained model) label_list[1], label_list[2] = label_list[2], label_list[1] examples = processor.get_dev_examples(args.data_dir) if evaluate else processor.get_train_examples(args.data_dir) # Changed features = convert_examples_to_features(examples, label_list, args.max_seq_length, tokenizer) if args.local_rank in [-1, 0]: logger.info("Saving features into cached file %s", cached_features_file) torch.save(features, cached_features_file) if args.local_rank == 0 and not evaluate: torch.distributed.barrier() # Make sure only the first process in distributed training process the dataset, and the others will use the cache # Convert to Tensors and build dataset all_input_ids = torch.tensor([f.input_ids for f in features], dtype=torch.long) all_input_mask = torch.tensor([f.input_mask for f in features], dtype=torch.long) all_segment_ids = torch.tensor([f.segment_ids for f in features], dtype=torch.long) all_label_ids = torch.tensor([f.label_id for f in features], dtype=torch.long) all_valid_ids = torch.tensor([f.valid_ids for f in features], dtype=torch.long) all_lmask_ids = torch.tensor([f.label_mask for f in features], dtype=torch.long) dataset = TensorDataset(all_input_ids, all_input_mask, all_segment_ids, all_label_ids,all_valid_ids,all_lmask_ids) #dataset = TensorDataset(all_input_ids, all_input_mask, all_segment_ids, all_label_ids) return dataset 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 pre-trained model or shortcut name selected in the list: " + ", ".join(ALL_MODELS)) parser.add_argument("--task_name", default="ner", type=str, required=True, help="The name of the task to train selected in the list: ner") 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 deay 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 = 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) processors = {'ner': NerProcessor} processor = processors[args.task_name]() args.output_mode = output_modes[args.task_name] label_list = processor.get_labels() num_labels = len(label_list) + 1 # 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) 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) model = model_class.from_pretrained(args.model_name_or_path, from_tf=bool('.ckpt' in args.model_name_or_path), config=config) model = Ner.from_pretrained(args.model_name_or_path, num_labels=num_labels) 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 = load_and_cache_examples(args, args.task_name, tokenizer, evaluate=False) 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, do_lower_case=args.do_lower_case) 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("pytorch_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 "" model = model_class.from_pretrained(checkpoint) model = Ner.from_pretrained(checkpoint, num_labels=num_labels) model.to(args.device) label_map = {i : label for i, label in enumerate(label_list,1)} result = evaluate(args, model, tokenizer, prefix=global_step, label_map=label_map) #result = dict((k + '_{}'.format(global_step), v) for k, v in result.items()) #results.update(result) return results if __name__ == "__main__": main()