SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Trainer (#3800)

Browse Source 
* doc

* [tests] Add sample files for a regression task

* [HUGE] Trainer

* Feedback from @sshleifer

* Feedback from @thomwolf + logging tweak

* [file_utils] when downloading concurrently, get_from_cache will use the cached file for subsequent processes

* [glue] Use default max_seq_length of 128 like before

* [glue] move DataTrainingArguments around

* [ner] Change interface of InputExample, and align run_{tf,pl}

* Re-align the pl scripts a little bit

* ner

* [ner] Add integration test

* Fix language_modeling with API tweak

* [ci] Tweak loss target

* Don't break console output

* amp.initialize: model must be on right device before

* [multiple-choice] update for Trainer

* Re-align to 827d6d6ef0
This commit is contained in:
Julien Chaumond
2020-04-21 20:11:56 -04:00
committed by GitHub
parent eb5601b0a5
commit dd9d483d03
41 changed files with 2682 additions and 2567 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/ner/README.md
View File

@@ -64,7 +64,6 @@ To start training, just run:
```bash
python3 run_ner.py --data_dir ./ \
--model_type bert \
--labels ./labels.txt \
--model_name_or_path $BERT_MODEL \
--output_dir $OUTPUT_DIR \
@@ -125,7 +124,6 @@ To start training, just run:
```bash
python3 run_tf_ner.py --data_dir ./ \
--model_type bert \
--labels ./labels.txt \
--model_name_or_path $BERT_MODEL \
--output_dir $OUTPUT_DIR \

6
examples/ner/run.sh
View File

@@ -4,7 +4,7 @@ curl -L 'https://sites.google.com/site/germeval2014ner/data/NER-de-dev.tsv?attre
| grep -v "^#" | cut -f 2,3 | tr '\t' ' ' > dev.txt.tmp
curl -L 'https://sites.google.com/site/germeval2014ner/data/NER-de-test.tsv?attredirects=0&d=1' \
| grep -v "^#" | cut -f 2,3 | tr '\t' ' ' > test.txt.tmp
wget "https://raw.githubusercontent.com/stefan-it/fine-tuned-berts-seq/master/scripts/preprocess.py"
wget "https://raw.githubusercontent.com/stefan-it/fine-tuned-berts-seq/master/scripts/preprocess.py"
export MAX_LENGTH=128
export BERT_MODEL=bert-base-multilingual-cased
python3 preprocess.py train.txt.tmp $BERT_MODEL $MAX_LENGTH > train.txt
@@ -17,8 +17,8 @@ export NUM_EPOCHS=3
export SAVE_STEPS=750
export SEED=1
python3 run_ner.py --data_dir ./ \
--model_type bert \
python3 run_ner.py \
--data_dir . \
--labels ./labels.txt \
--model_name_or_path $BERT_MODEL \
--output_dir $OUTPUT_DIR \

758
examples/ner/run_ner.py
View File

@@ -16,656 +16,264 @@
""" Fine-tuning the library models for named entity recognition on CoNLL-2003 (Bert or Roberta). """
import argparse
import glob
import logging
import os
import random
from dataclasses import dataclass, field
from typing import Dict, List, Optional, Tuple
import numpy as np
import torch
from seqeval.metrics import f1_score, precision_score, recall_score
from torch.nn import CrossEntropyLoss
from torch.utils.data import DataLoader, RandomSampler, SequentialSampler, TensorDataset
from torch.utils.data.distributed import DistributedSampler
from tqdm import tqdm, trange
from torch import nn
from transformers import (
MODEL_FOR_TOKEN_CLASSIFICATION_MAPPING,
WEIGHTS_NAME,
AdamW,
AutoConfig,
AutoModelForTokenClassification,
AutoTokenizer,
get_linear_schedule_with_warmup,
EvalPrediction,
HfArgumentParser,
Trainer,
TrainingArguments,
set_seed,
)
from utils_ner import convert_examples_to_features, get_labels, read_examples_from_file
try:
from torch.utils.tensorboard import SummaryWriter
except ImportError:
from tensorboardX import SummaryWriter
from utils_ner import NerDataset, Split, get_labels
logger = logging.getLogger(__name__)
MODEL_CONFIG_CLASSES = list(MODEL_FOR_TOKEN_CLASSIFICATION_MAPPING.keys())
MODEL_TYPES = tuple(conf.model_type for conf in MODEL_CONFIG_CLASSES)
ALL_MODELS = sum((tuple(conf.pretrained_config_archive_map.keys()) for conf in MODEL_CONFIG_CLASSES), ())
@dataclass
class ModelArguments:
"""
Arguments pertaining to which model/config/tokenizer we are going to fine-tune from.
"""
TOKENIZER_ARGS = ["do_lower_case", "strip_accents", "keep_accents", "use_fast"]
model_name_or_path: str = field(
metadata={"help": "Path to pretrained model or model identifier from huggingface.co/models"}
)
config_name: Optional[str] = field(
default=None, metadata={"help": "Pretrained config name or path if not the same as model_name"}
)
tokenizer_name: Optional[str] = field(
default=None, metadata={"help": "Pretrained tokenizer name or path if not the same as model_name"}
)
use_fast: bool = field(default=False, metadata={"help": "Set this flag to use fast tokenization."})
# If you want to tweak more attributes on your tokenizer, you should do it in a distinct script,
# or just modify its tokenizer_config.json.
cache_dir: Optional[str] = field(
default=None, metadata={"help": "Where do you want to store the pretrained models downloaded from s3"}
)
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)
@dataclass
class DataTrainingArguments:
"""
Arguments pertaining to what data we are going to input our model for training and eval.
"""
def train(args, train_dataset, model, tokenizer, labels, pad_token_label_id):
""" 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,
data_dir: str = field(
metadata={"help": "The input data dir. Should contain the .txt files for a CoNLL-2003-formatted task."}
)
labels: Optional[str] = field(
metadata={"help": "Path to a file containing all labels. If not specified, CoNLL-2003 labels are used."}
)
max_seq_length: int = field(
default=128,
metadata={
"help": "The maximum total input sequence length after tokenization. Sequences longer "
"than this will be truncated, sequences shorter will be padded."
},
{"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 = get_linear_schedule_with_warmup(
optimizer, num_warmup_steps=args.warmup_steps, num_training_steps=t_total
)
# Check if saved optimizer or scheduler states exist
if os.path.isfile(os.path.join(args.model_name_or_path, "optimizer.pt")) and os.path.isfile(
os.path.join(args.model_name_or_path, "scheduler.pt")
):
# Load in optimizer and scheduler states
optimizer.load_state_dict(torch.load(os.path.join(args.model_name_or_path, "optimizer.pt")))
scheduler.load_state_dict(torch.load(os.path.join(args.model_name_or_path, "scheduler.pt")))
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),
overwrite_cache: bool = field(
default=False, metadata={"help": "Overwrite the cached training and evaluation sets"}
)
logger.info(" Gradient Accumulation steps = %d", args.gradient_accumulation_steps)
logger.info(" Total optimization steps = %d", t_total)
global_step = 0
epochs_trained = 0
steps_trained_in_current_epoch = 0
# Check if continuing training from a checkpoint
if os.path.exists(args.model_name_or_path):
# set global_step to gobal_step of last saved checkpoint from model path
try:
global_step = int(args.model_name_or_path.split("-")[-1].split("/")[0])
except ValueError:
global_step = 0
epochs_trained = global_step // (len(train_dataloader) // args.gradient_accumulation_steps)
steps_trained_in_current_epoch = global_step % (len(train_dataloader) // args.gradient_accumulation_steps)
logger.info(" Continuing training from checkpoint, will skip to saved global_step")
logger.info(" Continuing training from epoch %d", epochs_trained)
logger.info(" Continuing training from global step %d", global_step)
logger.info(" Will skip the first %d steps in the first epoch", steps_trained_in_current_epoch)
tr_loss, logging_loss = 0.0, 0.0
model.zero_grad()
train_iterator = trange(
epochs_trained, int(args.num_train_epochs), desc="Epoch", disable=args.local_rank not in [-1, 0]
)
set_seed(args) # Added here for reproductibility
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):
# Skip past any already trained steps if resuming training
if steps_trained_in_current_epoch > 0:
steps_trained_in_current_epoch -= 1
continue
model.train()
batch = tuple(t.to(args.device) for t in batch)
inputs = {"input_ids": batch[0], "attention_mask": batch[1], "labels": batch[3]}
if args.model_type != "distilbert":
inputs["token_type_ids"] = (
batch[2] if args.model_type in ["bert", "xlnet"] else None
) # XLM and RoBERTa don"t use segment_ids
outputs = model(**inputs)
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()
else:
loss.backward()
tr_loss += loss.item()
if (step + 1) % args.gradient_accumulation_steps == 0:
if args.fp16:
torch.nn.utils.clip_grad_norm_(amp.master_params(optimizer), args.max_grad_norm)
else:
torch.nn.utils.clip_grad_norm_(model.parameters(), args.max_grad_norm)
optimizer.step()
scheduler.step() # Update learning rate schedule
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, labels, pad_token_label_id, mode="dev")
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)
tokenizer.save_pretrained(output_dir)
torch.save(args, os.path.join(output_dir, "training_args.bin"))
logger.info("Saving model checkpoint to %s", output_dir)
torch.save(optimizer.state_dict(), os.path.join(output_dir, "optimizer.pt"))
torch.save(scheduler.state_dict(), os.path.join(output_dir, "scheduler.pt"))
logger.info("Saving optimizer and scheduler states 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, labels, pad_token_label_id, mode, prefix=""):
eval_dataset = load_and_cache_examples(args, tokenizer, labels, pad_token_label_id, mode=mode)
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)
# multi-gpu evaluate
if args.n_gpu > 1 and not isinstance(model, torch.nn.DataParallel):
model = torch.nn.DataParallel(model)
# Eval!
logger.info("***** Running evaluation %s *****", 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
model.eval()
for batch in tqdm(eval_dataloader, desc="Evaluating"):
batch = tuple(t.to(args.device) for t in batch)
with torch.no_grad():
inputs = {"input_ids": batch[0], "attention_mask": batch[1], "labels": batch[3]}
if args.model_type != "distilbert":
inputs["token_type_ids"] = (
batch[2] if args.model_type in ["bert", "xlnet"] else None
) # XLM and RoBERTa don"t use segment_ids
outputs = model(**inputs)
tmp_eval_loss, logits = outputs[:2]
if args.n_gpu > 1:
tmp_eval_loss = tmp_eval_loss.mean() # mean() to average on multi-gpu parallel evaluating
eval_loss += tmp_eval_loss.item()
nb_eval_steps += 1
if preds is None:
preds = logits.detach().cpu().numpy()
out_label_ids = inputs["labels"].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)
eval_loss = eval_loss / nb_eval_steps
preds = np.argmax(preds, axis=2)
label_map = {i: label for i, label in enumerate(labels)}
out_label_list = [[] for _ in range(out_label_ids.shape[0])]
preds_list = [[] for _ in range(out_label_ids.shape[0])]
for i in range(out_label_ids.shape[0]):
for j in range(out_label_ids.shape[1]):
if out_label_ids[i, j] != pad_token_label_id:
out_label_list[i].append(label_map[out_label_ids[i][j]])
preds_list[i].append(label_map[preds[i][j]])
results = {
"loss": eval_loss,
"precision": precision_score(out_label_list, preds_list),
"recall": recall_score(out_label_list, preds_list),
"f1": f1_score(out_label_list, preds_list),
}
logger.info("***** Eval results %s *****", prefix)
for key in sorted(results.keys()):
logger.info(" %s = %s", key, str(results[key]))
return results, preds_list
def load_and_cache_examples(args, tokenizer, labels, pad_token_label_id, mode):
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
# Load data features from cache or dataset file
cached_features_file = os.path.join(
args.data_dir,
"cached_{}_{}_{}".format(
mode, list(filter(None, args.model_name_or_path.split("/"))).pop(), str(args.max_seq_length)
),
)
if os.path.exists(cached_features_file) and not args.overwrite_cache:
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)
examples = read_examples_from_file(args.data_dir, mode)
features = convert_examples_to_features(
examples,
labels,
args.max_seq_length,
tokenizer,
cls_token_at_end=bool(args.model_type in ["xlnet"]),
# xlnet has a cls token at the end
cls_token=tokenizer.cls_token,
cls_token_segment_id=2 if args.model_type in ["xlnet"] else 0,
sep_token=tokenizer.sep_token,
sep_token_extra=bool(args.model_type in ["roberta"]),
# roberta uses an extra separator b/w pairs of sentences, cf. github.com/pytorch/fairseq/commit/1684e166e3da03f5b600dbb7855cb98ddfcd0805
pad_on_left=bool(args.model_type in ["xlnet"]),
# pad on the left for xlnet
pad_token=tokenizer.pad_token_id,
pad_token_segment_id=tokenizer.pad_token_type_id,
pad_token_label_id=pad_token_label_id,
)
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_ids for f in features], dtype=torch.long)
dataset = TensorDataset(all_input_ids, all_input_mask, all_segment_ids, all_label_ids)
return dataset
def main():
parser = argparse.ArgumentParser()
# 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.
# Required parameters
parser.add_argument(
"--data_dir",
default=None,
type=str,
required=True,
help="The input data dir. Should contain the training files for the CoNLL-2003 NER task.",
)
parser.add_argument(
"--model_type",
default=None,
type=str,
required=True,
help="Model type selected in the list: " + ", ".join(MODEL_TYPES),
)
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(
"--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(
"--labels",
default="",
type=str,
help="Path to a file containing all labels. If not specified, CoNLL-2003 labels are used.",
)
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("--do_predict", action="store_true", help="Whether to run predictions on the test set.")
parser.add_argument(
"--evaluate_during_training",
action="store_true",
help="Whether to run 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(
"--keep_accents", action="store_const", const=True, help="Set this flag if model is trained with accents."
)
parser.add_argument(
"--strip_accents", action="store_const", const=True, help="Set this flag if model is trained without accents."
)
parser.add_argument("--use_fast", action="store_const", const=True, help="Set this flag to use fast tokenization.")
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=500, help="Log every X updates steps.")
parser.add_argument("--save_steps", type=int, default=500, 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()
parser = HfArgumentParser((ModelArguments, DataTrainingArguments, TrainingArguments))
model_args, data_args, training_args = parser.parse_args_into_dataclasses()
if (
os.path.exists(args.output_dir)
and os.listdir(args.output_dir)
and args.do_train
and not args.overwrite_output_dir
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(
"Output directory ({}) already exists and is not empty. Use --overwrite_output_dir to overcome.".format(
args.output_dir
)
f"Output directory ({training_args.output_dir}) already exists and is not empty. Use --overwrite_output_dir to overcome."
)
# 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,
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",
args.local_rank,
device,
args.n_gpu,
bool(args.local_rank != -1),
args.fp16,
training_args.local_rank,
training_args.device,
training_args.n_gpu,
bool(training_args.local_rank != -1),
training_args.fp16,
)
logger.info("Training/evaluation parameters %s", training_args)
# Set seed
set_seed(args)
set_seed(training_args.seed)
# Prepare CONLL-2003 task
labels = get_labels(args.labels)
labels = get_labels(data_args.labels)
label_map: Dict[int, str] = {i: label for i, label in enumerate(labels)}
num_labels = len(labels)
# Use cross entropy ignore index as padding label id so that only real label ids contribute to the loss later
pad_token_label_id = CrossEntropyLoss().ignore_index
# 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
#
# Distributed training:
# The .from_pretrained methods guarantee that only one local process can concurrently
# download model & vocab.
args.model_type = args.model_type.lower()
config = AutoConfig.from_pretrained(
args.config_name if args.config_name else args.model_name_or_path,
model_args.config_name if model_args.config_name else model_args.model_name_or_path,
num_labels=num_labels,
id2label={str(i): label for i, label in enumerate(labels)},
id2label=label_map,
label2id={label: i for i, label in enumerate(labels)},
cache_dir=args.cache_dir if args.cache_dir else None,
cache_dir=model_args.cache_dir,
)
tokenizer_args = {k: v for k, v in vars(args).items() if v is not None and k in TOKENIZER_ARGS}
logger.info("Tokenizer arguments: %s", tokenizer_args)
tokenizer = AutoTokenizer.from_pretrained(
args.tokenizer_name if args.tokenizer_name else args.model_name_or_path,
cache_dir=args.cache_dir if args.cache_dir else None,
**tokenizer_args,
model_args.tokenizer_name if model_args.tokenizer_name else model_args.model_name_or_path,
cache_dir=model_args.cache_dir,
use_fast=model_args.use_fast,
)
model = AutoModelForTokenClassification.from_pretrained(
args.model_name_or_path,
from_tf=bool(".ckpt" in args.model_name_or_path),
model_args.model_name_or_path,
from_tf=bool(".ckpt" in model_args.model_name_or_path),
config=config,
cache_dir=args.cache_dir if args.cache_dir else None,
cache_dir=model_args.cache_dir,
)
if args.local_rank == 0:
torch.distributed.barrier() # Make sure only the first process in distributed training will download model & vocab
# Get datasets
train_dataset = (
NerDataset(
data_dir=data_args.data_dir,
tokenizer=tokenizer,
labels=labels,
model_type=config.model_type,
max_seq_length=data_args.max_seq_length,
overwrite_cache=data_args.overwrite_cache,
mode=Split.train,
local_rank=training_args.local_rank,
)
if training_args.do_train
else None
)
eval_dataset = (
NerDataset(
data_dir=data_args.data_dir,
tokenizer=tokenizer,
labels=labels,
model_type=config.model_type,
max_seq_length=data_args.max_seq_length,
overwrite_cache=data_args.overwrite_cache,
mode=Split.dev,
local_rank=training_args.local_rank,
)
if training_args.do_eval
else None
)
model.to(args.device)
def align_predictions(predictions: np.ndarray, label_ids: np.ndarray) -> Tuple[List[int], List[int]]:
preds = np.argmax(predictions, axis=2)
logger.info("Training/evaluation parameters %s", args)
batch_size, seq_len = preds.shape
out_label_list = [[] for _ in range(batch_size)]
preds_list = [[] for _ in range(batch_size)]
for i in range(batch_size):
for j in range(seq_len):
if label_ids[i, j] != nn.CrossEntropyLoss().ignore_index:
out_label_list[i].append(label_map[label_ids[i][j]])
preds_list[i].append(label_map[preds[i][j]])
return preds_list, out_label_list
def compute_metrics(p: EvalPrediction) -> Dict:
preds_list, out_label_list = align_predictions(p.predictions, p.label_ids)
return {
"precision": precision_score(out_label_list, preds_list),
"recall": recall_score(out_label_list, preds_list),
"f1": f1_score(out_label_list, preds_list),
}
# Initialize our Trainer
trainer = Trainer(
model=model,
args=training_args,
train_dataset=train_dataset,
eval_dataset=eval_dataset,
compute_metrics=compute_metrics,
)
# Training
if args.do_train:
train_dataset = load_and_cache_examples(args, tokenizer, labels, pad_token_label_id, mode="train")
global_step, tr_loss = train(args, train_dataset, model, tokenizer, labels, pad_token_label_id)
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"))
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
)
# Evaluation
results = {}
if args.do_eval and args.local_rank in [-1, 0]:
tokenizer = AutoTokenizer.from_pretrained(args.output_dir, **tokenizer_args)
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 = AutoModelForTokenClassification.from_pretrained(checkpoint)
model.to(args.device)
result, _ = evaluate(args, model, tokenizer, labels, pad_token_label_id, mode="dev", prefix=global_step)
if global_step:
result = {"{}_{}".format(global_step, k): v for k, v in result.items()}
results.update(result)
output_eval_file = os.path.join(args.output_dir, "eval_results.txt")
with open(output_eval_file, "w") as writer:
for key in sorted(results.keys()):
writer.write("{} = {}\n".format(key, str(results[key])))
if training_args.do_eval and training_args.local_rank in [-1, 0]:
logger.info("*** Evaluate ***")
if args.do_predict and args.local_rank in [-1, 0]:
tokenizer = AutoTokenizer.from_pretrained(args.output_dir, **tokenizer_args)
model = AutoModelForTokenClassification.from_pretrained(args.output_dir)
model.to(args.device)
result, predictions = evaluate(args, model, tokenizer, labels, pad_token_label_id, mode="test")
# Save results
output_test_results_file = os.path.join(args.output_dir, "test_results.txt")
result = trainer.evaluate()
output_eval_file = os.path.join(training_args.output_dir, "eval_results.txt")
with open(output_eval_file, "w") as writer:
logger.info("***** Eval results *****")
for key, value in result.items():
logger.info(" %s = %s", key, value)
writer.write("%s = %s\n" % (key, value))
results.update(result)
# Predict
if training_args.do_predict and training_args.local_rank in [-1, 0]:
test_dataset = NerDataset(
data_dir=data_args.data_dir,
tokenizer=tokenizer,
labels=labels,
model_type=config.model_type,
max_seq_length=data_args.max_seq_length,
overwrite_cache=data_args.overwrite_cache,
mode=Split.test,
local_rank=training_args.local_rank,
)
predictions, label_ids, metrics = trainer.predict(test_dataset)
preds_list, _ = align_predictions(predictions, label_ids)
output_test_results_file = os.path.join(training_args.output_dir, "test_results.txt")
with open(output_test_results_file, "w") as writer:
for key in sorted(result.keys()):
writer.write("{} = {}\n".format(key, str(result[key])))
for key, value in metrics.items():
logger.info(" %s = %s", key, value)
writer.write("%s = %s\n" % (key, value))
# Save predictions
output_test_predictions_file = os.path.join(args.output_dir, "test_predictions.txt")
output_test_predictions_file = os.path.join(training_args.output_dir, "test_predictions.txt")
with open(output_test_predictions_file, "w") as writer:
with open(os.path.join(args.data_dir, "test.txt"), "r") as f:
with open(os.path.join(data_args.data_dir, "test.txt"), "r") as f:
example_id = 0
for line in f:
if line.startswith("-DOCSTART-") or line == "" or line == "\n":
writer.write(line)
if not predictions[example_id]:
if not preds_list[example_id]:
example_id += 1
elif predictions[example_id]:
output_line = line.split()[0] + " " + predictions[example_id].pop(0) + "\n"
elif preds_list[example_id]:
output_line = line.split()[0] + " " + preds_list[example_id].pop(0) + "\n"
writer.write(output_line)
else:
logger.warning("Maximum sequence length exceeded: No prediction for '%s'.", line.split()[0])

2
examples/ner/run_pl.sh
View File

@@ -11,7 +11,7 @@ curl -L 'https://sites.google.com/site/germeval2014ner/data/NER-de-dev.tsv?attre
| grep -v "^#" | cut -f 2,3 | tr '\t' ' ' > dev.txt.tmp
curl -L 'https://sites.google.com/site/germeval2014ner/data/NER-de-test.tsv?attredirects=0&d=1' \
| grep -v "^#" | cut -f 2,3 | tr '\t' ' ' > test.txt.tmp
wget "https://raw.githubusercontent.com/stefan-it/fine-tuned-berts-seq/master/scripts/preprocess.py"
wget "https://raw.githubusercontent.com/stefan-it/fine-tuned-berts-seq/master/scripts/preprocess.py"
export MAX_LENGTH=128
export BERT_MODEL=bert-base-multilingual-cased
python3 preprocess.py train.txt.tmp $BERT_MODEL $MAX_LENGTH > train.txt

32
examples/ner/run_pl_ner.py
View File

@@ -27,7 +27,7 @@ class NERTransformer(BaseTransformer):
self.labels = get_labels(hparams.labels)
num_labels = len(self.labels)
self.pad_token_label_id = CrossEntropyLoss().ignore_index
super(NERTransformer, self).__init__(hparams, num_labels, self.mode)
super().__init__(hparams, num_labels, self.mode)
def forward(self, **inputs):
return self.model(**inputs)
@@ -35,10 +35,10 @@ class NERTransformer(BaseTransformer):
def training_step(self, batch, batch_num):
"Compute loss and log."
inputs = {"input_ids": batch[0], "attention_mask": batch[1], "labels": batch[3]}
if self.hparams.model_type != "distilbert":
if self.config.model_type != "distilbert":
inputs["token_type_ids"] = (
batch[2] if self.hparams.model_type in ["bert", "xlnet"] else None
) # XLM and RoBERTa don"t use segment_ids
batch[2] if self.config.model_type in ["bert", "xlnet"] else None
) # XLM and RoBERTa don"t use token_type_ids
outputs = self(**inputs)
loss = outputs[0]
@@ -58,12 +58,12 @@ class NERTransformer(BaseTransformer):
self.labels,
args.max_seq_length,
self.tokenizer,
cls_token_at_end=bool(args.model_type in ["xlnet"]),
cls_token_at_end=bool(self.config.model_type in ["xlnet"]),
cls_token=self.tokenizer.cls_token,
cls_token_segment_id=2 if args.model_type in ["xlnet"] else 0,
cls_token_segment_id=2 if self.config.model_type in ["xlnet"] else 0,
sep_token=self.tokenizer.sep_token,
sep_token_extra=bool(args.model_type in ["roberta"]),
pad_on_left=bool(args.model_type in ["xlnet"]),
sep_token_extra=bool(self.config.model_type in ["roberta"]),
pad_on_left=bool(self.config.model_type in ["xlnet"]),
pad_token=self.tokenizer.pad_token_id,
pad_token_segment_id=self.tokenizer.pad_token_type_id,
pad_token_label_id=self.pad_token_label_id,
@@ -77,21 +77,25 @@ class NERTransformer(BaseTransformer):
logger.info("Loading features from cached file %s", cached_features_file)
features = torch.load(cached_features_file)
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_attention_mask = torch.tensor([f.attention_mask for f in features], dtype=torch.long)
if features[0].token_type_ids is not None:
all_token_type_ids = torch.tensor([f.token_type_ids for f in features], dtype=torch.long)
else:
all_token_type_ids = torch.tensor([0 for f in features], dtype=torch.long)
# HACK(we will not use this anymore soon)
all_label_ids = torch.tensor([f.label_ids for f in features], dtype=torch.long)
return DataLoader(
TensorDataset(all_input_ids, all_input_mask, all_segment_ids, all_label_ids), batch_size=batch_size
TensorDataset(all_input_ids, all_attention_mask, all_token_type_ids, all_label_ids), batch_size=batch_size
)
def validation_step(self, batch, batch_nb):
"Compute validation"
inputs = {"input_ids": batch[0], "attention_mask": batch[1], "labels": batch[3]}
if self.hparams.model_type != "distilbert":
if self.config.model_type != "distilbert":
inputs["token_type_ids"] = (
batch[2] if self.hparams.model_type in ["bert", "xlnet"] else None
) # XLM and RoBERTa don"t use segment_ids
batch[2] if self.config.model_type in ["bert", "xlnet"] else None
) # XLM and RoBERTa don"t use token_type_ids
outputs = self(**inputs)
tmp_eval_loss, logits = outputs[:2]
preds = logits.detach().cpu().numpy()

79
examples/ner/run_tf_ner.py
View File

@@ -9,6 +9,7 @@ import re
import numpy as np
import tensorflow as tf
from absl import app, flags, logging
from fastprogress import master_bar, progress_bar
from seqeval import metrics
from transformers import (
@@ -17,34 +18,23 @@ from transformers import (
AutoConfig,
AutoTokenizer,
GradientAccumulator,
PreTrainedTokenizer,
TFAutoModelForTokenClassification,
create_optimizer,
)
from utils_ner import convert_examples_to_features, get_labels, read_examples_from_file
try:
from fastprogress import master_bar, progress_bar
except ImportError:
from fastprogress.fastprogress import master_bar, progress_bar
MODEL_CONFIG_CLASSES = list(TF_MODEL_FOR_TOKEN_CLASSIFICATION_MAPPING.keys())
MODEL_TYPES = tuple(conf.model_type for conf in MODEL_CONFIG_CLASSES)
ALL_MODELS = sum((tuple(conf.pretrained_config_archive_map.keys()) for conf in MODEL_CONFIG_CLASSES), (),)
flags.DEFINE_string(
"data_dir", None, "The input data dir. Should contain the .conll files (or other data files) " "for the task."
"data_dir", None, "The input data dir. Should contain the .conll files (or other data files) for the task."
)
flags.DEFINE_string("model_type", None, "Model type selected in the list: " + ", ".join(MODEL_TYPES))
flags.DEFINE_string(
"model_name_or_path",
None,
"Path to pre-trained model or shortcut name selected in the list: " + ", ".join(ALL_MODELS),
"model_name_or_path", None, "Path to pretrained model or model identifier from huggingface.co/models",
)
flags.DEFINE_string("output_dir", None, "The output directory where the model checkpoints will be written.")
@@ -53,11 +43,11 @@ flags.DEFINE_string(
"labels", "", "Path to a file containing all labels. If not specified, CoNLL-2003 labels are used."
)
flags.DEFINE_string("config_name", "", "Pretrained config name or path if not the same as model_name")
flags.DEFINE_string("config_name", None, "Pretrained config name or path if not the same as model_name")
flags.DEFINE_string("tokenizer_name", "", "Pretrained tokenizer name or path if not the same as model_name")
flags.DEFINE_string("tokenizer_name", None, "Pretrained tokenizer name or path if not the same as model_name")
flags.DEFINE_string("cache_dir", "", "Where do you want to store the pre-trained models downloaded from s3")
flags.DEFINE_string("cache_dir", None, "Where do you want to store the pre-trained models downloaded from s3")
flags.DEFINE_integer(
"max_seq_length",
@@ -123,7 +113,7 @@ flags.DEFINE_boolean(
"Evaluate all checkpoints starting with the same prefix as model_name ending and ending with step number",
)
flags.DEFINE_boolean("no_cuda", False, "Avoid using CUDA when available")
flags.DEFINE_boolean("no_cuda", False, "Avoid using CUDA even if it is available")
flags.DEFINE_boolean("overwrite_output_dir", False, "Overwrite the content of the output directory")
@@ -198,12 +188,10 @@ def train(
@tf.function
def train_step(train_features, train_labels):
def step_fn(train_features, train_labels):
inputs = {"attention_mask": train_features["input_mask"], "training": True}
inputs = {"attention_mask": train_features["attention_mask"], "training": True}
if args["model_type"] != "distilbert":
inputs["token_type_ids"] = (
train_features["segment_ids"] if args["model_type"] in ["bert", "xlnet"] else None
)
if "token_type_ids" in train_features:
inputs["token_type_ids"] = train_features["token_type_ids"]
with tf.GradientTape() as tape:
logits = model(train_features["input_ids"], **inputs)[0]
@@ -320,12 +308,10 @@ def evaluate(args, strategy, model, tokenizer, labels, pad_token_label_id, mode)
logging.info(" Batch size = %d", eval_batch_size)
for eval_features, eval_labels in eval_iterator:
inputs = {"attention_mask": eval_features["input_mask"], "training": False}
inputs = {"attention_mask": eval_features["attention_mask"], "training": False}
if args["model_type"] != "distilbert":
inputs["token_type_ids"] = (
eval_features["segment_ids"] if args["model_type"] in ["bert", "xlnet"] else None
)
if "token_type_ids" in eval_features:
inputs["token_type_ids"] = eval_features["token_type_ids"]
with strategy.scope():
logits = model(eval_features["input_ids"], **inputs)[0]
@@ -356,20 +342,23 @@ def evaluate(args, strategy, model, tokenizer, labels, pad_token_label_id, mode)
return y_true, y_pred, loss.numpy()
def load_cache(cached_file, max_seq_length):
def load_cache(cached_file, tokenizer: PreTrainedTokenizer, max_seq_length):
name_to_features = {
"input_ids": tf.io.FixedLenFeature([max_seq_length], tf.int64),
"input_mask": tf.io.FixedLenFeature([max_seq_length], tf.int64),
"segment_ids": tf.io.FixedLenFeature([max_seq_length], tf.int64),
"attention_mask": tf.io.FixedLenFeature([max_seq_length], tf.int64),
"label_ids": tf.io.FixedLenFeature([max_seq_length], tf.int64),
}
# TODO Find a cleaner way to do this.
if "token_type_ids" in tokenizer.model_input_names:
name_to_features["token_type_ids"] = tf.io.FixedLenFeature([max_seq_length], tf.int64)
def _decode_record(record):
example = tf.io.parse_single_example(record, name_to_features)
features = {}
features["input_ids"] = example["input_ids"]
features["input_mask"] = example["input_mask"]
features["segment_ids"] = example["segment_ids"]
features["attention_mask"] = example["attention_mask"]
if "token_type_ids" in example:
features["token_type_ids"] = example["token_type_ids"]
return features, example["label_ids"]
@@ -393,8 +382,9 @@ def save_cache(features, cached_features_file):
record_feature = collections.OrderedDict()
record_feature["input_ids"] = create_int_feature(feature.input_ids)
record_feature["input_mask"] = create_int_feature(feature.input_mask)
record_feature["segment_ids"] = create_int_feature(feature.segment_ids)
record_feature["attention_mask"] = create_int_feature(feature.attention_mask)
if feature.token_type_ids is not None:
record_feature["token_type_ids"] = create_int_feature(feature.token_type_ids)
record_feature["label_ids"] = create_int_feature(feature.label_ids)
tf_example = tf.train.Example(features=tf.train.Features(feature=record_feature))
@@ -410,13 +400,11 @@ def load_and_cache_examples(args, tokenizer, labels, pad_token_label_id, batch_s
# Load data features from cache or dataset file
cached_features_file = os.path.join(
args["data_dir"],
"cached_{}_{}_{}.tf_record".format(
mode, list(filter(None, args["model_name_or_path"].split("/"))).pop(), str(args["max_seq_length"])
),
"cached_{}_{}_{}.tf_record".format(mode, tokenizer.__class__.__name__, str(args["max_seq_length"])),
)
if os.path.exists(cached_features_file) and not args["overwrite_cache"]:
logging.info("Loading features from cached file %s", cached_features_file)
dataset, size = load_cache(cached_features_file, args["max_seq_length"])
dataset, size = load_cache(cached_features_file, tokenizer, args["max_seq_length"])
else:
logging.info("Creating features from dataset file at %s", args["data_dir"])
examples = read_examples_from_file(args["data_dir"], mode)
@@ -440,7 +428,7 @@ def load_and_cache_examples(args, tokenizer, labels, pad_token_label_id, batch_s
)
logging.info("Saving features into cached file %s", cached_features_file)
save_cache(features, cached_features_file)
dataset, size = load_cache(cached_features_file, args["max_seq_length"])
dataset, size = load_cache(cached_features_file, tokenizer, args["max_seq_length"])
if mode == "train":
dataset = dataset.repeat()
@@ -500,17 +488,18 @@ def main(_):
config = AutoConfig.from_pretrained(
args["config_name"] if args["config_name"] else args["model_name_or_path"],
num_labels=num_labels,
cache_dir=args["cache_dir"] if args["cache_dir"] else None,
cache_dir=args["cache_dir"],
)
logging.info("Training/evaluation parameters %s", args)
args["model_type"] = config.model_type
# Training
if args["do_train"]:
tokenizer = AutoTokenizer.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,
cache_dir=args["cache_dir"],
)
with strategy.scope():
@@ -518,7 +507,7 @@ def main(_):
args["model_name_or_path"],
from_pt=bool(".bin" in args["model_name_or_path"]),
config=config,
cache_dir=args["cache_dir"] if args["cache_dir"] else None,
cache_dir=args["cache_dir"],
)
train_batch_size = args["per_device_train_batch_size"] * args["n_device"]
@@ -538,8 +527,7 @@ def main(_):
pad_token_label_id,
)
if not os.path.exists(args["output_dir"]):
os.makedirs(args["output_dir"])
os.makedirs(args["output_dir"], exist_ok=True)
logging.info("Saving model to %s", args["output_dir"])
@@ -637,5 +625,4 @@ if __name__ == "__main__":
flags.mark_flag_as_required("data_dir")
flags.mark_flag_as_required("output_dir")
flags.mark_flag_as_required("model_name_or_path")
flags.mark_flag_as_required("model_type")
app.run(main)

33
examples/ner/test_ner_examples.py Normal file
View File

@@ -0,0 +1,33 @@
import logging
import sys
import unittest
from unittest.mock import patch
import run_ner
logging.basicConfig(level=logging.DEBUG)
logger = logging.getLogger()
class ExamplesTests(unittest.TestCase):
def test_run_ner(self):
stream_handler = logging.StreamHandler(sys.stdout)
logger.addHandler(stream_handler)
testargs = """
--model_name distilbert-base-german-cased
--output_dir ./examples/tests_samples/temp_dir
--overwrite_output_dir
--data_dir ./examples/tests_samples/GermEval
--labels ./examples/tests_samples/GermEval/labels.txt
--max_seq_length 128
--num_train_epochs 6
--logging_steps 1
--do_train
--do_eval
""".split()
with patch.object(sys, "argv", ["run.py"] + testargs):
result = run_ner.main()
self.assertLess(result["loss"], 1.5)

160
examples/ner/utils_ner.py
View File

@@ -18,40 +18,126 @@
import logging
import os
from dataclasses import dataclass
from enum import Enum
from typing import List, Optional, Union
import torch
from torch import nn
from torch.utils.data.dataset import Dataset
from transformers import PreTrainedTokenizer, torch_distributed_zero_first
logger = logging.getLogger(__name__)
class InputExample(object):
"""A single training/test example for token classification."""
@dataclass
class InputExample:
"""
A single training/test example for token classification.
def __init__(self, guid, words, labels):
"""Constructs a InputExample.
Args:
guid: Unique id for the example.
words: list. The words of the sequence.
labels: (Optional) list. The labels for each word of the sequence. This should be
specified for train and dev examples, but not for test examples.
"""
Args:
guid: Unique id for the example.
words: list. The words of the sequence.
labels: (Optional) list. The labels for each word of the sequence. This should be
specified for train and dev examples, but not for test examples.
"""
self.guid = guid
self.words = words
self.labels = labels
guid: str
words: List[str]
labels: Optional[List[str]]
class InputFeatures(object):
"""A single set of features of data."""
@dataclass
class InputFeatures:
"""
A single set of features of data.
Property names are the same names as the corresponding inputs to a model.
"""
def __init__(self, input_ids, input_mask, segment_ids, label_ids):
self.input_ids = input_ids
self.input_mask = input_mask
self.segment_ids = segment_ids
self.label_ids = label_ids
input_ids: List[int]
attention_mask: List[int]
token_type_ids: Optional[List[int]] = None
label_ids: Optional[List[int]] = None
def read_examples_from_file(data_dir, mode):
file_path = os.path.join(data_dir, "{}.txt".format(mode))
class Split(Enum):
train = "train"
dev = "dev"
test = "test"
class NerDataset(Dataset):
"""
This will be superseded by a framework-agnostic approach
soon.
"""
features: List[InputFeatures]
pad_token_label_id: int = nn.CrossEntropyLoss().ignore_index
# Use cross entropy ignore_index as padding label id so that only
# real label ids contribute to the loss later.
def __init__(
self,
data_dir: str,
tokenizer: PreTrainedTokenizer,
labels: List[str],
model_type: str,
max_seq_length: Optional[int] = None,
overwrite_cache=False,
mode: Split = Split.train,
local_rank=-1,
):
# Load data features from cache or dataset file
cached_features_file = os.path.join(
data_dir, "cached_{}_{}_{}".format(mode.value, tokenizer.__class__.__name__, str(max_seq_length)),
)
with torch_distributed_zero_first(local_rank):
# Make sure only the first process in distributed training processes the dataset,
# and the others will use the cache.
if os.path.exists(cached_features_file) and not overwrite_cache:
logger.info(f"Loading features from cached file {cached_features_file}")
self.features = torch.load(cached_features_file)
else:
logger.info(f"Creating features from dataset file at {data_dir}")
examples = read_examples_from_file(data_dir, mode)
# TODO clean up all this to leverage built-in features of tokenizers
self.features = convert_examples_to_features(
examples,
labels,
max_seq_length,
tokenizer,
cls_token_at_end=bool(model_type in ["xlnet"]),
# xlnet has a cls token at the end
cls_token=tokenizer.cls_token,
cls_token_segment_id=2 if model_type in ["xlnet"] else 0,
sep_token=tokenizer.sep_token,
sep_token_extra=bool(model_type in ["roberta"]),
# roberta uses an extra separator b/w pairs of sentences, cf. github.com/pytorch/fairseq/commit/1684e166e3da03f5b600dbb7855cb98ddfcd0805
pad_on_left=bool(tokenizer.padding_side == "left"),
pad_token=tokenizer.pad_token_id,
pad_token_segment_id=tokenizer.pad_token_type_id,
pad_token_label_id=self.pad_token_label_id,
)
if local_rank in [-1, 0]:
logger.info(f"Saving features into cached file {cached_features_file}")
torch.save(self.features, cached_features_file)
def __len__(self):
return len(self.features)
def __getitem__(self, i) -> InputFeatures:
return self.features[i]
def read_examples_from_file(data_dir, mode: Union[Split, str]) -> List[InputExample]:
if isinstance(mode, Split):
mode = mode.value
file_path = os.path.join(data_dir, f"{mode}.txt")
guid_index = 1
examples = []
with open(file_path, encoding="utf-8") as f:
@@ -60,7 +146,7 @@ def read_examples_from_file(data_dir, mode):
for line in f:
if line.startswith("-DOCSTART-") or line == "" or line == "\n":
if words:
examples.append(InputExample(guid="{}-{}".format(mode, guid_index), words=words, labels=labels))
examples.append(InputExample(guid=f"{mode}-{guid_index}", words=words, labels=labels))
guid_index += 1
words = []
labels = []
@@ -73,15 +159,15 @@ def read_examples_from_file(data_dir, mode):
# Examples could have no label for mode = "test"
labels.append("O")
if words:
examples.append(InputExample(guid="{}-{}".format(mode, guid_index), words=words, labels=labels))
examples.append(InputExample(guid=f"{mode}-{guid_index}", words=words, labels=labels))
return examples
def convert_examples_to_features(
examples,
label_list,
max_seq_length,
tokenizer,
examples: List[InputExample],
label_list: List[str],
max_seq_length: int,
tokenizer: PreTrainedTokenizer,
cls_token_at_end=False,
cls_token="[CLS]",
cls_token_segment_id=1,
@@ -93,19 +179,20 @@ def convert_examples_to_features(
pad_token_label_id=-100,
sequence_a_segment_id=0,
mask_padding_with_zero=True,
):
""" Loads a data file into a list of `InputBatch`s
) -> List[InputFeatures]:
""" Loads a data file into a list of `InputFeatures`
`cls_token_at_end` define the location of the CLS token:
- False (Default, BERT/XLM pattern): [CLS] + A + [SEP] + B + [SEP]
- True (XLNet/GPT pattern): A + [SEP] + B + [SEP] + [CLS]
`cls_token_segment_id` define the segment id associated to the CLS token (0 for BERT, 2 for XLNet)
"""
# TODO clean up all this to leverage built-in features of tokenizers
label_map = {label: i for i, label in enumerate(label_list)}
features = []
for (ex_index, example) in enumerate(examples):
if ex_index % 10000 == 0:
if ex_index % 10_000 == 0:
logger.info("Writing example %d of %d", ex_index, len(examples))
tokens = []
@@ -120,7 +207,7 @@ def convert_examples_to_features(
label_ids.extend([label_map[label]] + [pad_token_label_id] * (len(word_tokens) - 1))
# Account for [CLS] and [SEP] with "- 2" and with "- 3" for RoBERTa.
special_tokens_count = tokenizer.num_added_tokens()
special_tokens_count = tokenizer.num_special_tokens_to_add()
if len(tokens) > max_seq_length - special_tokens_count:
tokens = tokens[: (max_seq_length - special_tokens_count)]
label_ids = label_ids[: (max_seq_length - special_tokens_count)]
@@ -193,13 +280,18 @@ def convert_examples_to_features(
logger.info("segment_ids: %s", " ".join([str(x) for x in segment_ids]))
logger.info("label_ids: %s", " ".join([str(x) for x in label_ids]))
if "token_type_ids" not in tokenizer.model_input_names:
segment_ids = None
features.append(
InputFeatures(input_ids=input_ids, input_mask=input_mask, segment_ids=segment_ids, label_ids=label_ids)
InputFeatures(
input_ids=input_ids, attention_mask=input_mask, token_type_ids=segment_ids, label_ids=label_ids
)
)
return features
def get_labels(path):
def get_labels(path: str) -> List[str]:
if path:
with open(path, "r") as f:
labels = f.read().splitlines()