|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
""" Finetuning the library models for sequence classification on GLUE (Bert, XLM, XLNet, RoBERTa, Albert, XLM-RoBERTa).""" |
|
|
|
|
|
import argparse |
|
import json |
|
import logging |
|
import os |
|
import random |
|
|
|
import numpy as np |
|
import torch |
|
from torch.utils.data import DataLoader, RandomSampler, SequentialSampler, TensorDataset |
|
from torch.utils.data.distributed import DistributedSampler |
|
from tqdm import tqdm, trange |
|
|
|
from transformers import WEIGHTS_NAME,AdamW,AlbertConfig,AlbertTokenizer,BertConfig,BertTokenizer,DistilBertConfig,DistilBertForSequenceClassification,DistilBertTokenizer,FlaubertConfig, FlaubertForSequenceClassification,FlaubertTokenizer,RobertaConfig,RobertaForSequenceClassification,RobertaTokenizer,XLMConfig,XLMForSequenceClassification,XLMRobertaConfig,XLMRobertaForSequenceClassification,XLMRobertaTokenizer,XLMTokenizer,XLNetConfig,XLNetForSequenceClassification,XLNetTokenizer,get_linear_schedule_with_warmup |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
from pabee.modeling_albert import AlbertForSequenceClassification |
|
from pabee.modeling_bert import BertForSequenceClassification |
|
from transformers import glue_compute_metrics as compute_metrics |
|
from transformers import glue_convert_examples_to_features as convert_examples_to_features |
|
from transformers import glue_output_modes as output_modes |
|
from transformers import glue_processors as processors |
|
|
|
from torch.utils.tensorboard import SummaryWriter |
|
|
|
|
|
logger = logging.getLogger(__name__) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
MODEL_CLASSES = { |
|
"bert": (BertConfig, BertForSequenceClassification, BertTokenizer), |
|
|
|
|
|
|
|
|
|
"albert": (AlbertConfig, AlbertForSequenceClassification, AlbertTokenizer), |
|
|
|
|
|
} |
|
|
|
|
|
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 |
|
|
|
|
|
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 = get_linear_schedule_with_warmup( |
|
optimizer, num_warmup_steps=args.warmup_steps, num_training_steps=t_total |
|
) |
|
|
|
|
|
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") |
|
): |
|
|
|
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.n_gpu > 1: |
|
model = torch.nn.DataParallel(model) |
|
|
|
|
|
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, |
|
) |
|
|
|
|
|
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 |
|
epochs_trained = 0 |
|
steps_trained_in_current_epoch = 0 |
|
|
|
if os.path.exists(args.model_name_or_path): |
|
|
|
global_step = int(args.model_name_or_path.split("-")[-1].split("/")[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) |
|
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): |
|
|
|
|
|
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", "albert"] else None |
|
) |
|
outputs = model(**inputs) |
|
loss = outputs[0] |
|
|
|
if args.n_gpu > 1: |
|
loss = loss.mean() |
|
if args.gradient_accumulation_steps > 1: |
|
loss = loss / args.gradient_accumulation_steps |
|
|
|
|
|
|
|
|
|
else: |
|
loss.backward() |
|
|
|
tr_loss += loss.item() |
|
if (step + 1) % args.gradient_accumulation_steps == 0: |
|
|
|
|
|
|
|
torch.nn.utils.clip_grad_norm_(model.parameters(), args.max_grad_norm) |
|
|
|
optimizer.step() |
|
scheduler.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: |
|
logs = {} |
|
if ( |
|
args.local_rank == -1 and args.evaluate_during_training |
|
): |
|
results = evaluate(args, model, tokenizer) |
|
for key, value in results.items(): |
|
eval_key = "eval_{}".format(key) |
|
logs[eval_key] = value |
|
|
|
loss_scalar = (tr_loss - logging_loss) / args.logging_steps |
|
learning_rate_scalar = scheduler.get_lr()[0] |
|
logs["learning_rate"] = learning_rate_scalar |
|
logs["loss"] = loss_scalar |
|
logging_loss = tr_loss |
|
|
|
for key, value in logs.items(): |
|
tb_writer.add_scalar(key, value, global_step) |
|
print(json.dumps({**logs, **{"step": global_step}})) |
|
|
|
if args.local_rank in [-1, 0] and args.save_steps > 0 and global_step % args.save_steps == 0: |
|
|
|
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 |
|
) |
|
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, prefix="", patience=0): |
|
|
|
if args.model_type == 'albert': |
|
model.albert.set_regression_threshold(args.regression_threshold) |
|
if args.do_train: |
|
model.albert.set_mode('last') |
|
elif args.eval_mode == 'patience': |
|
model.albert.set_mode('patience') |
|
model.albert.set_patience(patience) |
|
elif args.eval_mode == 'confi': |
|
model.albert.set_mode('confi') |
|
model.albert.set_confi_threshold(patience) |
|
model.albert.reset_stats() |
|
elif args.model_type == 'bert': |
|
model.bert.set_regression_threshold(args.regression_threshold) |
|
if args.do_train: |
|
model.bert.set_mode('last') |
|
elif args.eval_mode == 'patience': |
|
model.bert.set_mode('patience') |
|
model.bert.set_patience(patience) |
|
elif args.eval_mode == 'confi': |
|
model.bert.set_mode('confi') |
|
model.bert.set_confi_threshold(patience) |
|
model.bert.reset_stats() |
|
else: |
|
raise NotImplementedError() |
|
|
|
|
|
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) |
|
|
|
eval_sampler = SequentialSampler(eval_dataset) |
|
eval_dataloader = DataLoader(eval_dataset, sampler=eval_sampler, batch_size=args.eval_batch_size) |
|
|
|
|
|
if args.n_gpu > 1 and not isinstance(model, torch.nn.DataParallel): |
|
model = torch.nn.DataParallel(model) |
|
|
|
|
|
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() |
|
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", "albert"] else None |
|
) |
|
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() |
|
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 |
|
if args.output_mode == "classification": |
|
preds = np.argmax(preds, axis=1) |
|
elif args.output_mode == "regression": |
|
preds = np.squeeze(preds) |
|
result = compute_metrics(eval_task, preds, out_label_ids) |
|
results.update(result) |
|
|
|
output_eval_file = os.path.join(eval_output_dir, prefix, "eval_results.txt") |
|
with open(output_eval_file, "w") as writer: |
|
logger.info("***** Eval results {} *****".format(prefix)) |
|
for key in sorted(result.keys()): |
|
logger.info(" %s = %s", key, str(result[key])) |
|
print(" %s = %s" % (key, str(result[key]))) |
|
writer.write("%s = %s\n" % (key, str(result[key]))) |
|
|
|
if args.eval_all_checkpoints and patience != 0: |
|
if args.model_type == 'albert': |
|
model.albert.log_stats() |
|
elif args.model_type == 'bert': |
|
model.bert.log_stats() |
|
else: |
|
raise NotImplementedError() |
|
|
|
return results |
|
|
|
|
|
def load_and_cache_examples(args, task, tokenizer, evaluate=False): |
|
if args.local_rank not in [-1, 0] and not evaluate: |
|
torch.distributed.barrier() |
|
|
|
processor = processors[task]() |
|
output_mode = output_modes[task] |
|
|
|
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) 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) |
|
label_list = processor.get_labels() |
|
if task in ["mnli", "mnli-mm"] and args.model_type in ["roberta", "xlmroberta"]: |
|
|
|
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) |
|
) |
|
|
|
features = convert_examples_to_features( |
|
examples, |
|
tokenizer, |
|
label_list=label_list, |
|
max_length=args.max_seq_length, |
|
output_mode=output_mode, |
|
|
|
|
|
|
|
) |
|
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() |
|
|
|
|
|
all_input_ids = torch.tensor([f.input_ids for f in features], dtype=torch.long) |
|
all_attention_mask = torch.tensor([f.attention_mask for f in features], dtype=torch.long) |
|
all_token_type_ids = torch.tensor([f.token_type_ids for f in features], dtype=torch.long) |
|
if output_mode == "classification": |
|
all_labels = torch.tensor([f.label for f in features], dtype=torch.long) |
|
elif output_mode == "regression": |
|
all_labels = torch.tensor([f.label for f in features], dtype=torch.float) |
|
|
|
dataset = TensorDataset(all_input_ids, all_attention_mask, all_token_type_ids, all_labels) |
|
return dataset |
|
|
|
|
|
def main(): |
|
parser = argparse.ArgumentParser() |
|
|
|
|
|
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: " |
|
) |
|
parser.add_argument( |
|
"--task_name", |
|
default=None, |
|
type=str, |
|
required=True, |
|
help="The name of the task to train selected in the list: " + ", ".join(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.", |
|
) |
|
parser.add_argument( |
|
"--patience", |
|
default='0', |
|
type=str, |
|
required=False, |
|
) |
|
parser.add_argument( |
|
"--regression_threshold", |
|
default=0, |
|
type=float, |
|
required=False, |
|
) |
|
|
|
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="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( |
|
"--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.") |
|
|
|
parser.add_argument("--eval_mode",type=str,default="patience",help='the evaluation mode for the multi-exit BERT patience|confi') |
|
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 |
|
) |
|
) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
if args.local_rank == -1 or args.no_cuda: |
|
print(f'CUDA STATUS: {torch.cuda.is_available()}') |
|
device = torch.device("cuda" if torch.cuda.is_available() and not args.no_cuda else "cpu") |
|
args.n_gpu = torch.cuda.device_count() |
|
else: |
|
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 |
|
|
|
|
|
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(args) |
|
|
|
|
|
args.task_name = args.task_name.lower() |
|
if args.task_name not in processors: |
|
raise ValueError("Task not found: %s" % (args.task_name)) |
|
processor = processors[args.task_name]() |
|
args.output_mode = output_modes[args.task_name] |
|
label_list = processor.get_labels() |
|
num_labels = len(label_list) |
|
print(f'num labels: {num_labels}') |
|
|
|
|
|
if args.local_rank not in [-1, 0]: |
|
torch.distributed.barrier() |
|
|
|
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() |
|
|
|
model.to(args.device) |
|
|
|
print('Total Model Parameters:', sum(param.numel() for param in model.parameters())) |
|
output_layers_param_num = sum(param.numel() for param in model.classifiers.parameters()) |
|
print('Output Layers Parameters:', output_layers_param_num) |
|
single_output_layer_param_num = sum(param.numel() for param in model.classifiers[0].parameters()) |
|
print('Added Output Layers Parameters:', output_layers_param_num - single_output_layer_param_num) |
|
|
|
logger.info("Training/evaluation parameters %s", args) |
|
|
|
|
|
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) |
|
|
|
|
|
if args.do_train and (args.local_rank == -1 or torch.distributed.get_rank() == 0): |
|
|
|
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) |
|
|
|
|
|
model_to_save = ( |
|
model.module if hasattr(model, "module") else model |
|
) |
|
model_to_save.save_pretrained(args.output_dir) |
|
tokenizer.save_pretrained(args.output_dir) |
|
|
|
|
|
torch.save(args, os.path.join(args.output_dir, "training_args.bin")) |
|
|
|
|
|
model = model_class.from_pretrained(args.output_dir) |
|
tokenizer = tokenizer_class.from_pretrained(args.output_dir) |
|
model.to(args.device) |
|
|
|
|
|
results = {} |
|
if args.do_eval and args.local_rank in [-1, 0]: |
|
if args.eval_mode == 'patience': |
|
patience_list = [int(x) for x in args.patience.split(',')] |
|
elif args.eval_mode == 'confi': |
|
patience_list = [float(x) for x in args.patience.split(',')] |
|
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) |
|
logger.info("Evaluate the following checkpoints: %s", checkpoints) |
|
|
|
for checkpoint in checkpoints: |
|
if '600' not in checkpoint: |
|
continue |
|
|
|
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) |
|
|
|
print(f'Evaluation for checkpoint {prefix}') |
|
for patience in patience_list: |
|
print(f'------ Patience Threshold: {patience} ------') |
|
result = evaluate(args, model, tokenizer, prefix=prefix, patience=patience) |
|
result = dict((k + "_{}".format(global_step), v) for k, v in result.items()) |
|
results.update(result) |
|
if args.model_type == 'albert': |
|
print(f'Exits Distribution: {model.albert.exits_count_list}') |
|
elif args.model_type == 'bert': |
|
print(f'Exits Distribution: {model.bert.exits_count_list}') |
|
|
|
|
|
return results |
|
|
|
|
|
if __name__ == "__main__": |
|
main() |
|
|