nshtrainer 1.0.0b52__py3-none-any.whl → 1.0.0b54__py3-none-any.whl

nshtrainer/_checkpoint/metadata.py

@@ -11,7 +11,7 @@ import numpy as np
 import torch
 
 from ..util._environment_info import EnvironmentConfig
-from ..util.path import compute_file_checksum, try_symlink_or_copy
+from ..util.path import compute_file_checksum, path_exists, try_symlink_or_copy
 
 if TYPE_CHECKING:
     from ..trainer.trainer import Trainer
@@ -154,7 +154,7 @@ def remove_checkpoint_metadata(checkpoint_path: Path):
 def remove_checkpoint_metadata_link(ckpt_link_path: Path):
     path = _metadata_path(ckpt_link_path)
     # If the metadata does not exist, we can safely ignore this
-    if not path.exists(follow_symlinks=False):
+    if not path_exists(path, follow_symlinks=False):
         # This is EXTREMELY important here
         # Otherwise, we've already deleted the file that the symlink
         # used to point to, so this always returns False

nshtrainer/_checkpoint/saver.py

@@ -7,7 +7,7 @@ from pathlib import Path
 
 from lightning.pytorch import Trainer
 
-from ..util.path import try_symlink_or_copy
+from ..util.path import path_exists, try_symlink_or_copy
 from .metadata import (
     link_checkpoint_metadata,
     remove_checkpoint_metadata,
@@ -29,7 +29,7 @@ def link_checkpoint(
 
     if remove_existing:
         try:
-            if linkpath.exists(follow_symlinks=False):
+            if path_exists(linkpath, follow_symlinks=False):
                 # follow_symlinks=False is EXTREMELY important here
                 # Otherwise, we've already deleted the file that the symlink
                 # used to point to, so this always returns False

nshtrainer/trainer/trainer.py

@@ -457,7 +457,21 @@ class Trainer(LightningTrainer):
     ):
         filepath = Path(filepath)
 
-        super().save_checkpoint(filepath, weights_only, storage_options)
+        if self.model is None:
+            raise AttributeError(
+                "Saving a checkpoint is only possible if a model is attached to the Trainer. Did you call"
+                " `Trainer.save_checkpoint()` before calling `Trainer.{fit,validate,test,predict}`?"
+            )
+        with self.profiler.profile("save_checkpoint"):  # type: ignore
+            checkpoint = self._checkpoint_connector.dump_checkpoint(weights_only)
+            # Update the checkpoint for the trainer hyperparameters
+            checkpoint[self.CHECKPOINT_HYPER_PARAMS_KEY] = self.hparams.model_dump(
+                mode="json"
+            )
+            self.strategy.save_checkpoint(
+                checkpoint, filepath, storage_options=storage_options
+            )
+            self.strategy.barrier("Trainer.save_checkpoint")
 
         # Save the checkpoint metadata
         metadata_path = None

nshtrainer/util/path.py

@@ -1,5 +1,6 @@
 from __future__ import annotations
 
+import errno
 import hashlib
 import logging
 import os
@@ -98,7 +99,7 @@ def try_symlink_or_copy(
     # If the link already exists, remove it
     if remove_existing:
         try:
-            if link_path.exists(follow_symlinks=False):
+            if path_exists(link_path, follow_symlinks=False):
                 # follow_symlinks=False is EXTREMELY important here
                 # Otherwise, we've already deleted the file that the symlink
                 # used to point to, so this always returns False
@@ -132,3 +133,43 @@ def try_symlink_or_copy(
     else:
         log.debug(f"Created symlink or copied {file_path} to {link_path}")
         return True
+
+
+_WINERROR_NOT_READY = 21  # drive exists but is not accessible
+_WINERROR_INVALID_NAME = 123  # fix for bpo-35306
+_WINERROR_CANT_RESOLVE_FILENAME = 1921  # broken symlink pointing to itself
+
+# EBADF - guard against macOS `stat` throwing EBADF
+_IGNORED_ERRNOS = (errno.ENOENT, errno.ENOTDIR, errno.EBADF, errno.ELOOP)
+
+_IGNORED_WINERRORS = (
+    _WINERROR_NOT_READY,
+    _WINERROR_INVALID_NAME,
+    _WINERROR_CANT_RESOLVE_FILENAME,
+)
+
+
+def _ignore_error(exception):
+    return (
+        getattr(exception, "errno", None) in _IGNORED_ERRNOS
+        or getattr(exception, "winerror", None) in _IGNORED_WINERRORS
+    )
+
+
+def path_exists(path: Path, follow_symlinks: bool = True):
+    """
+    Whether this path exists.
+
+    This method normally follows symlinks; to check whether a symlink exists,
+    add the argument follow_symlinks=False.
+    """
+    try:
+        path.stat(follow_symlinks=follow_symlinks)
+    except OSError as e:
+        if not _ignore_error(e):
+            raise
+        return False
+    except ValueError:
+        # Non-encodable path
+        return False
+    return True

{nshtrainer-1.0.0b52.dist-info → nshtrainer-1.0.0b54.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: nshtrainer
-Version: 1.0.0b52
+Version: 1.0.0b54
 Summary: 
 Author: Nima Shoghi
 Author-email: nimashoghi@gmail.com

{nshtrainer-1.0.0b52.dist-info → nshtrainer-1.0.0b54.dist-info}/RECORD

@@ -1,8 +1,8 @@
 nshtrainer/.nshconfig.generated.json,sha256=yZd6cn1RhvNNJUgiUTRYut8ofZYvbulnpPG-rZIRhi4,106
 nshtrainer/__init__.py,sha256=g_moPnfQxSxFZX5NB9ILQQOJrt4RTRuiFt9N0STIpxM,874
 nshtrainer/_callback.py,sha256=ZDppiJ4d65tRXTEWYPZLH_F1xFizdz1pkWJe_sQ5uII,12564
-nshtrainer/_checkpoint/metadata.py,sha256=ojSEmq0udFwdzIC5vkbF0yEdhMaJ2iBrZCSFNDkeeGY,5578
-nshtrainer/_checkpoint/saver.py,sha256=65UDrz3KuhkgVfco-RkWuoa1wzTZoXxunlC769yJaMc,1639
+nshtrainer/_checkpoint/metadata.py,sha256=Hh5a7OkdknUEbkEwX6vS88-XLEeuVDoR6a3en2uLzQE,5597
+nshtrainer/_checkpoint/saver.py,sha256=utcrYKSosd04N9m2GIylufO5DO05D90qVU3mvadfApU,1658
 nshtrainer/_directory.py,sha256=TJR9ccyuzRlAVfVjGyeQ3E2AFAcz-XbBCxWfiXo2SlY,3191
 nshtrainer/_experimental/__init__.py,sha256=U4S_2y3zgLZVfMenHRaJFBW8yqh2mUBuI291LGQVOJ8,35
 nshtrainer/_hf_hub.py,sha256=4OsCbIITnZk_YLyoMrVyZ0SIN04FBxlC0ig2Et8UAdo,14287
@@ -142,18 +142,18 @@ nshtrainer/trainer/plugin/layer_sync.py,sha256=h-ydZwXepnsw5-paLgiDatqPyQ_8C0QEv
 nshtrainer/trainer/plugin/precision.py,sha256=I0QsB1bVxmsFmBOkgrAfGONsuYae_lD9Bz0PfJEQvH4,5598
 nshtrainer/trainer/signal_connector.py,sha256=GhfGcSzfaTNhnj2QFkBDq5aT7FqbLMA7eC8SYQs8_8w,10828
 nshtrainer/trainer/strategy.py,sha256=VPTn5z3zvXTydY8IJchjhjcOfpvtoejnvUkq5E4WTus,1368
-nshtrainer/trainer/trainer.py,sha256=QEK-0bcw1y5Cconi99PYFXr0MElUGgGYMZ_SlcJUQ1k,20364
+nshtrainer/trainer/trainer.py,sha256=Lo3vUo3ooTAjaX2fUYPFSMv5FP7sWfVov0QbA-T5hZ8,21113
 nshtrainer/util/_environment_info.py,sha256=MT8mBe6ZolRfKiwU-les1P-lPNPqXpHQcfADrh_A3uY,24629
 nshtrainer/util/bf16.py,sha256=9QhHZCkYSfYpIcxwAMoXyuh2yTSHBzT-EdLQB297jEs,762
 nshtrainer/util/config/__init__.py,sha256=Z39JJufSb61Lhn2GfVcv3eFW_eorOrN9-9llDWlnZZM,272
 nshtrainer/util/config/dtype.py,sha256=Fn_MhhQoHPyFAnFPSwvcvLiGR3yWFIszMba02CJiC4g,2213
 nshtrainer/util/config/duration.py,sha256=mM-UfU_HvhXwW33TYEDg0x58n80tnle2e6VaWtxZTjk,764
 nshtrainer/util/environment.py,sha256=s-B5nY0cKYXdFMdNYumvC_xxacMATiI4DvV2gUDu20k,4195
-nshtrainer/util/path.py,sha256=wADa_qFiekiX0PENf9jI-9_abICB0vJFXav8pNLR7lw,3976
+nshtrainer/util/path.py,sha256=PuJzYfY-2jnkTg7t8ucF-neq2ouBOVKsyQkCkrndDfE,5087
 nshtrainer/util/seed.py,sha256=diMV8iwBKN7Xxt5pELmui-gyqyT80_CZzomrWhNss0k,316
 nshtrainer/util/slurm.py,sha256=HflkP5iI_r4UHMyPjw9R4dD5AHsJUpcfJw5PLvGYBRM,1603
 nshtrainer/util/typed.py,sha256=Xt5fUU6zwLKSTLUdenovnKK0N8qUq89Kddz2_XeykVQ,164
 nshtrainer/util/typing_utils.py,sha256=MjY-CUX9R5Tzat-BlFnQjwl1PQ_W2yZQoXhkYHlJ_VA,442
-nshtrainer-1.0.0b52.dist-info/METADATA,sha256=1epCQrU5xMrNSvGY6x-6L6HHKCwlzNsK2jAdb0dVbN0,988
-nshtrainer-1.0.0b52.dist-info/WHEEL,sha256=XbeZDeTWKc1w7CSIyre5aMDU_-PohRwTQceYnisIYYY,88
-nshtrainer-1.0.0b52.dist-info/RECORD,,
+nshtrainer-1.0.0b54.dist-info/METADATA,sha256=oSfrN2tgKgkZJwGbZVNbLULQcVMxh_wb02u7Hrujfn4,988
+nshtrainer-1.0.0b54.dist-info/WHEEL,sha256=XbeZDeTWKc1w7CSIyre5aMDU_-PohRwTQceYnisIYYY,88
+nshtrainer-1.0.0b54.dist-info/RECORD,,