Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[AMP] Refine found_inf of loss_scaler #37770

Merged
merged 1 commit into from
Dec 2, 2021
Merged

[AMP] Refine found_inf of loss_scaler #37770

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 12 additions & 5 deletions python/paddle/fluid/dygraph/amp/loss_scaler.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -127,6 +127,10 @@ def __init__(self,
self._use_dynamic_loss_scaling = use_dynamic_loss_scaling

self._found_inf = to_variable(np.array([0]).astype(np.bool))
self._temp_found_inf_fp16 = to_variable(
np.array([0]).astype(np.bool))
self._temp_found_inf_fp32 = to_variable(
np.array([0]).astype(np.bool))
self._scale = to_variable(
np.array([self._init_loss_scaling]).astype(np.float32))
self._cache_founf_inf = None
Expand Down Expand Up @@ -282,17 +286,20 @@ def _unscale(self, optimizer):
) and (param._grad_ivar().dtype == core.VarDesc.VarType.FP32
)
]
temp_found_inf_fp16 = to_variable(np.array([0]).astype(np.bool))
temp_found_inf_fp32 = to_variable(np.array([0]).astype(np.bool))
if len(param_grads_fp16):
_C_ops.check_finite_and_unscale(param_grads_fp16, self._scale,
param_grads_fp16,
temp_found_inf_fp16)
self._temp_found_inf_fp16)
if len(param_grads_fp32):
_C_ops.check_finite_and_unscale(param_grads_fp32, self._scale,
param_grads_fp32,
temp_found_inf_fp32)
self._found_inf = temp_found_inf_fp16 or temp_found_inf_fp32
self._temp_found_inf_fp32)
if len(param_grads_fp16) and len(param_grads_fp32):
self._found_inf = self._temp_found_inf_fp16 or self._temp_found_inf_fp32
elif len(param_grads_fp16):
self._found_inf = self._temp_found_inf_fp16
else:
self._found_inf = self._temp_found_inf_fp32

optimizer_state["state"] = OptimizerState.UNSCALED

Expand Down