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

more explicit notation: num_train_step => num_train_optimization_steps

Browse Source
This commit is contained in:
thomwolf
2019-02-05 15:36:33 +01:00
parent 5169069997
commit 1579c53635
6 changed files with 44 additions and 46 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
examples/run_classifier.py
View File

@@ -438,11 +438,13 @@ def main():
tokenizer = BertTokenizer.from_pretrained(args.bert_model, do_lower_case=args.do_lower_case)
train_examples = None
num_train_steps = None
num_train_optimization_steps = None
if args.do_train:
train_examples = processor.get_train_examples(args.data_dir)
num_train_steps =
len(train_examples) // args.train_batch_size // args.gradient_accumulation_steps * args.num_train_epochs
num_train_optimization_steps = int(
len(train_examples) / args.train_batch_size / args.gradient_accumulation_steps) * args.num_train_epochs
if args.local_rank != -1:
num_train_optimization_steps = num_train_optimization_steps // torch.distributed.get_world_size()
# Prepare model
model = BertForSequenceClassification.from_pretrained(args.bert_model,
@@ -468,9 +470,6 @@ def main():
{'params': [p for n, p in param_optimizer if not any(nd in n for nd in no_decay)], 'weight_decay': 0.01},
{'params': [p for n, p in param_optimizer if any(nd in n for nd in no_decay)], 'weight_decay': 0.0}
]
t_total = num_train_steps
if args.local_rank != -1:
t_total = t_total // torch.distributed.get_world_size()
if args.fp16:
try:
from apex.optimizers import FP16_Optimizer
@@ -491,7 +490,7 @@ def main():
optimizer = BertAdam(optimizer_grouped_parameters,
lr=args.learning_rate,
warmup=args.warmup_proportion,
t_total=t_total)
t_total=num_train_optimization_steps)
global_step = 0
nb_tr_steps = 0
@@ -502,7 +501,7 @@ def main():
logger.info("***** Running training *****")
logger.info(" Num examples = %d", len(train_examples))
logger.info(" Batch size = %d", args.train_batch_size)
logger.info(" Num steps = %d", num_train_steps)
logger.info(" Num steps = %d", num_train_optimization_steps)
all_input_ids = torch.tensor([f.input_ids for f in train_features], dtype=torch.long)
all_input_mask = torch.tensor([f.input_mask for f in train_features], dtype=torch.long)
all_segment_ids = torch.tensor([f.segment_ids for f in train_features], dtype=torch.long)
@@ -539,7 +538,7 @@ def main():
if args.fp16:
# modify learning rate with special warm up BERT uses
# if args.fp16 is False, BertAdam is used that handles this automatically
lr_this_step = args.learning_rate * warmup_linear(global_step/t_total, args.warmup_proportion)
lr_this_step = args.learning_rate * warmup_linear(global_step/num_train_optimization_steps, args.warmup_proportion)
for param_group in optimizer.param_groups:
param_group['lr'] = lr_this_step
optimizer.step()