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

update examples

Browse Source
This commit is contained in:
thomwolf
2019-07-11 15:37:34 +02:00
parent ec07cf5a66
commit b21d84b027
5 changed files with 9 additions and 1124 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
examples/run_glue.py
View File

@@ -74,8 +74,8 @@ def train(args, train_dataset, model, tokenizer):
{'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)
schedule = WarmupLinearSchedule(optimizer, warmup_steps=args.warmup_steps, t_total=t_total)
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
@@ -300,6 +300,8 @@ def main():
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,
@@ -358,7 +360,9 @@ def main():
args.device = device
# Setup logging
logging.basicConfig(level = logging.INFO if args.local_rank in [-1, 0] else logging.WARN)
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)