Merge branch 'master' into patch-1

Author: lantiga

docs/source-pytorch/tuning/profiler_intermediate.rst

@@ -55,7 +55,7 @@ The profiler will generate an output like this:
     Self CPU time total: 1.681ms
 
 .. note::
-    When using the PyTorch Profiler, wall clock time will not not be representative of the true wall clock time.
+    When using the PyTorch Profiler, wall clock time will not be representative of the true wall clock time.
     This is due to forcing profiled operations to be measured synchronously, when many CUDA ops happen asynchronously.
     It is recommended to use this Profiler to find bottlenecks/breakdowns, however for end to end wall clock time use
     the ``SimpleProfiler``.
@@ -142,7 +142,7 @@ This profiler will record ``training_step``, ``validation_step``, ``test_step``,
 The output above shows the profiling for the action ``training_step``.
 
 .. note::
-    When using the PyTorch Profiler, wall clock time will not not be representative of the true wall clock time.
+    When using the PyTorch Profiler, wall clock time will not be representative of the true wall clock time.
     This is due to forcing profiled operations to be measured synchronously, when many CUDA ops happen asynchronously.
     It is recommended to use this Profiler to find bottlenecks/breakdowns, however for end to end wall clock time use
     the ``SimpleProfiler``.

src/lightning/fabric/strategies/deepspeed.py

@@ -144,7 +144,7 @@ def __init__(
             nvme_path: Filesystem path for NVMe device for optimizer/parameter state offloading.
 
             optimizer_buffer_count: Number of buffers in buffer pool for optimizer state offloading
-                when ``offload_optimizer_device`` is set to to ``nvme``.
+                when ``offload_optimizer_device`` is set to ``nvme``.
                 This should be at least the number of states maintained per parameter by the optimizer.
                 For example, Adam optimizer has 4 states (parameter, gradient, momentum, and variance).
 

src/lightning/pytorch/core/module.py

@@ -979,7 +979,7 @@ def configure_optimizers(self) -> OptimizerLRScheduler:
                 # `scheduler.step()`. 1 corresponds to updating the learning
                 # rate after every epoch/step.
                 "frequency": 1,
-                # Metric to to monitor for schedulers like `ReduceLROnPlateau`
+                # Metric to monitor for schedulers like `ReduceLROnPlateau`
                 "monitor": "val_loss",
                 # If set to `True`, will enforce that the value specified 'monitor'
                 # is available when the scheduler is updated, thus stopping

src/lightning/pytorch/strategies/deepspeed.py

@@ -166,7 +166,7 @@ def __init__(
             nvme_path: Filesystem path for NVMe device for optimizer/parameter state offloading.
 
             optimizer_buffer_count: Number of buffers in buffer pool for optimizer state offloading
-                when ``offload_optimizer_device`` is set to to ``nvme``.
+                when ``offload_optimizer_device`` is set to ``nvme``.
                 This should be at least the number of states maintained per parameter by the optimizer.
                 For example, Adam optimizer has 4 states (parameter, gradient, momentum, and variance).