mirror of
https://github.com/hpcaitech/ColossalAI.git
synced 2025-09-30 05:55:56 +00:00
[misc] update pre-commit and run all files (#4752)
* [misc] update pre-commit * [misc] run pre-commit * [misc] remove useless configuration files * [misc] ignore cuda for clang-format
This commit is contained in:
@@ -4,7 +4,7 @@ from colossalai.legacy.amp import AMP_TYPE
|
||||
TRAIN_ITERS = 10
|
||||
DECAY_ITERS = 4
|
||||
WARMUP_FRACTION = 0.01
|
||||
GLOBAL_BATCH_SIZE = 32 # dp world size * sentences per GPU
|
||||
GLOBAL_BATCH_SIZE = 32 # dp world size * sentences per GPU
|
||||
EVAL_ITERS = 10
|
||||
EVAL_INTERVAL = 10
|
||||
LR = 0.0001
|
||||
@@ -28,8 +28,8 @@ SEED = 1234
|
||||
NUM_MICRO_BATCHES = 4
|
||||
|
||||
# colossalai config
|
||||
parallel = dict(pipeline=1, tensor=dict(size=2, mode='sequence'))
|
||||
parallel = dict(pipeline=1, tensor=dict(size=2, mode="sequence"))
|
||||
|
||||
fp16 = dict(mode=AMP_TYPE.NAIVE, verbose=True)
|
||||
|
||||
gradient_handler = [dict(type='SequenceParallelGradientHandler')]
|
||||
gradient_handler = [dict(type="SequenceParallelGradientHandler")]
|
||||
|
Reference in New Issue
Block a user