riaz.somc/transformers
1
0
Fork 0
mirror of https://github.com/huggingface/transformers.git synced 2025-08-02 11:11:05 +06:00
Code Issues Actions 3 Packages Projects Releases Wiki Activity

remove duplicate accumulate gradient step arguments

Browse Source
This commit is contained in:
thomwolf 2018-11-09 09:19:45 +01:00
parent 0c24db9d5f
commit 34bdc8b54f
2 changed files with 8 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
run_classifier.py
View File

@ -392,10 +392,6 @@ def main():
default=False, default=False,
action='store_true', action='store_true',
help="Whether not to use CUDA when available") help="Whether not to use CUDA when available")
parser.add_argument("--accumulate_gradients",
type=int,
default=1,
help="Number of steps to accumulate gradient on (divide the batch_size and accumulate)")
parser.add_argument("--local_rank", parser.add_argument("--local_rank",
type=int, type=int,
default=-1, default=-1,
@ -426,11 +422,11 @@ def main():
torch.distributed.init_process_group(backend='nccl') torch.distributed.init_process_group(backend='nccl')
logger.info("device %s n_gpu %d distributed training %r", device, n_gpu, bool(args.local_rank != -1)) logger.info("device %s n_gpu %d distributed training %r", device, n_gpu, bool(args.local_rank != -1))
if args.accumulate_gradients < 1: if args.gradient_accumulation_steps < 1:
raise ValueError("Invalid accumulate_gradients parameter: {}, should be >= 1".format( raise ValueError("Invalid gradient_accumulation_steps parameter: {}, should be >= 1".format(
args.accumulate_gradients)) args.gradient_accumulation_steps))
args.train_batch_size = int(args.train_batch_size / args.accumulate_gradients) args.train_batch_size = int(args.train_batch_size / args.gradient_accumulation_steps)
random.seed(args.seed) random.seed(args.seed)
np.random.seed(args.seed) np.random.seed(args.seed)

12
run_squad.py
View File

@ -731,10 +731,6 @@ def main():
type=int, type=int,
default=-1, default=-1,
help="local_rank for distributed training on gpus") help="local_rank for distributed training on gpus")
parser.add_argument("--accumulate_gradients",
type=int,
default=1,
help="Number of steps to accumulate gradient on (divide the batch_size and accumulate)")
parser.add_argument('--seed', parser.add_argument('--seed',
type=int, type=int,
default=42, default=42,
@ -756,11 +752,11 @@ def main():
torch.distributed.init_process_group(backend='nccl') torch.distributed.init_process_group(backend='nccl')
logger.info("device %s n_gpu %d distributed training %r", device, n_gpu, bool(args.local_rank != -1)) logger.info("device %s n_gpu %d distributed training %r", device, n_gpu, bool(args.local_rank != -1))
if args.accumulate_gradients < 1: if args.gradient_accumulation_steps < 1:
raise ValueError("Invalid accumulate_gradients parameter: {}, should be >= 1".format( raise ValueError("Invalid gradient_accumulation_steps parameter: {}, should be >= 1".format(
args.accumulate_gradients)) args.gradient_accumulation_steps))
args.train_batch_size = int(args.train_batch_size / args.accumulate_gradients) args.train_batch_size = int(args.train_batch_size / args.gradient_accumulation_steps)
random.seed(args.seed) random.seed(args.seed)
np.random.seed(args.seed) np.random.seed(args.seed)