wassname/ray
1
0
Fork 0
mirror of https://github.com/wassname/ray.git synced 2026-08-10 12:30:14 +08:00
Code Issues Packages Projects Releases Wiki Activity

[tune] Change the log syncing behavior (#4450)

Browse Source 
* Change the log syncing behavior

* fix up abstractions for syncer

* Finished checkpoint syncing

* Code

* Set of changes to get things running

* Fixes for log syncing

* Fix parts

* Lint and other fixes

* fix some test

* Remove extra parsing functionality

* some test fixes

* Fix up cloud syncing

* Another thing to do

* Fix up tests and local sync

Changes LogSync into a mixin, and adds tests for different
functionalities.

* Fix up tests, start on local migration

* fix distributed migrations

* comments

* formatting

* Better checkpoint directory handling

* fix tests

* fix tests

* fix click

* comments

* formatting comments

* formatting and comments

* sync function deprecations

* syncfunction

* Add documentation for Syncing and Uploading

* nit

* BaseSyncer as base for Mixin in edge case

* more docs

* clean up assertions

* validate

* nit

* Update test_cluster.py

* betterdoc

* Update tune-usage.rst

* cleanup

* nit
This commit is contained in:
Kristian Hartikainen
2019-07-02 20:46:00 -07:00
committed by Richard Liaw
parent 71d4637b75
commit 9e0192bc0b
14 changed files with 718 additions and 466 deletions
Download Patch File Download Diff File Expand all files Collapse all files
python/ray/tune/experiment.py
+15 -12
View File
@@ -52,7 +52,6 @@ class Experiment(object):
>>> },
>>> num_samples=10,
>>> local_dir="~/ray_results",
>>> upload_dir="s3://your_bucket/path",
>>> checkpoint_freq=10,
>>> max_failures=2)
"""
@@ -68,7 +67,7 @@ class Experiment(object):
upload_dir=None,
trial_name_creator=None,
loggers=None,
sync_function=None,
sync_to_driver=None,
checkpoint_freq=0,
checkpoint_at_end=False,
keep_checkpoints_num=None,
@@ -78,18 +77,16 @@ class Experiment(object):
restore=None,
repeat=None,
trial_resources=None,
custom_loggers=None):
if sync_function:
assert upload_dir, "Need `upload_dir` if sync_function given."
custom_loggers=None,
sync_function=None):
if repeat:
_raise_deprecation_note("repeat", "num_samples", soft=False)
if trial_resources:
_raise_deprecation_note(
"trial_resources", "resources_per_trial", soft=False)
if custom_loggers:
_raise_deprecation_note("custom_loggers", "loggers", soft=False)
if sync_function:
_raise_deprecation_note(
"sync_function", "sync_to_driver", soft=False)
run_identifier = Experiment._register_if_needed(run)
spec = {
"run": run_identifier,
@@ -98,10 +95,10 @@ class Experiment(object):
"resources_per_trial": resources_per_trial,
"num_samples": num_samples,
"local_dir": os.path.expanduser(local_dir or DEFAULT_RESULTS_DIR),
"upload_dir": upload_dir or "", # argparse converts None to "null"
"upload_dir": upload_dir,
"trial_name_creator": trial_name_creator,
"loggers": loggers,
"sync_function": sync_function,
"sync_to_driver": sync_to_driver,
"checkpoint_freq": checkpoint_freq,
"checkpoint_at_end": checkpoint_at_end,
"keep_checkpoints_num": keep_checkpoints_num,
@@ -182,7 +179,13 @@ class Experiment(object):
@property
def checkpoint_dir(self):
return os.path.join(self.spec["local_dir"], self.name)
if self.local_dir:
return os.path.join(self.local_dir, self.name)
@property
def remote_checkpoint_dir(self):
if self.spec["upload_dir"]:
return os.path.join(self.spec["upload_dir"], self.name)
def convert_to_experiment_list(experiments):