release v0.3.6.9

README.md

@@ -31,9 +31,11 @@ Lightning defers training and validation loop logic to you. It guarantees correc
 
 
 ## Why do I want to use lightning?
-When starting a new project the last thing you want to do is recode a training loop, model loading/saving, distributed training, when to validate, etc... You're likely to spend a long time ironing out all the bugs without even getting to the core of your research.
+When starting a new project the last thing you want to do is recode a training loop, multi-cluster training, 16-bit precision, early-stopping, model loading/saving, when to validate, etc... You're likely to spend a long time ironing out all the bugs without even getting to the core of your research.
 
-With lightning, you guarantee those parts of your code work so you can focus on what the meat of the research: Data and training, validation loop logic. Don't worry about multiple gpus or speeding up your code, lightning will do that for you!
+With lightning, you guarantee those parts of your code work so you can focus on what the meat of the research: The data and the training/validation loop logic. 
+
+Don't worry about training on multiple gpus or speeding up your code, lightning will do that for you!
 
 ## How do I do use it?   
 
@@ -316,6 +318,19 @@ python single_gpu_node_template.py --gpus "0,1"
 python multi_node_cluster_template.py --nb_gpu_nodes 4 --gpus '0,1,2,3,4,5,6,7'
 ```
 
+## Contributing    
+Welcome to the PTL community! We're building the most advanced research platform on the planet to implement the latest, best practices that the amazing PyTorch team rolls out!  
+
+#### Bug fixes:  
+1. Submit a github issue.   
+2. Fix it.  
+3. Submit a PR! 
+
+#### New Features:  
+1. Submit a github issue.   
+2. We'll agree on the feature scope.     
+3. Submit a PR! (with updated docs and tests 🙃).    
+
 ## Bleeding edge
 If you can't wait for the next release, install the most up to date code with:  
 ```bash

pytorch_lightning/__init__.py

@@ -1,3 +1,3 @@
-from .models import Trainer
+from .models.trainer import Trainer
 from .root_module.root_module import LightningModule
 from .root_module.decorators import data_loader

pytorch_lightning/models/__init__.py

@@ -1 +0,0 @@
-from .trainer import Trainer

pytorch_lightning/models/trainer.py

@@ -612,7 +612,7 @@ class Trainer(TrainerIO):
 
         # enable cluster checkpointing
         # also restores training state
-        if self.cluster is not None and self.proc_rank == 0:  # pragma: no cover
+        if self.cluster is not None:  # pragma: no cover
             self.enable_auto_hpc_walltime_manager()
 
         # ---------------------------
@@ -885,4 +885,4 @@ class Trainer(TrainerIO):
         # model checkpointing
         if self.proc_rank == 0 and self.checkpoint_callback is not None:
             print('save callback...')
-            self.checkpoint_callback.on_epoch_end(epoch=self.current_epoch, logs=self.__tng_tqdm_dic)
+            self.checkpoint_callback.on_epoch_end(epoch=self.current_epoch, logs=self.__tng_tqdm_dic)

pytorch_lightning/root_module/model_saving.py

@@ -102,13 +102,16 @@ class TrainerIO(object):
             return
 
         # allow test tube to handle model check pointing automatically
-        self.cluster.set_checkpoint_save_function(
-            self.hpc_save,
-            kwargs={
-                'folderpath': self.checkpoint_callback.filepath,
-                'experiment': self.experiment
-            }
-        )
+        # only if proc 0 so we don't trigger world_size resubmits
+        if self.proc_rank == 0:
+            self.cluster.set_checkpoint_save_function(
+                self.hpc_save,
+                kwargs={
+                    'folderpath': self.checkpoint_callback.filepath,
+                    'experiment': self.experiment
+                }
+            )
+
         self.cluster.set_checkpoint_load_function(
             self.hpc_load,
             kwargs={

setup.py

@@ -7,7 +7,7 @@ from setuptools import setup, find_packages
 # http://blog.ionelmc.ro/2014/05/25/python-packaging/
 setup(
     name="pytorch-lightning",
-    version='0.3.6.7',
+    version='0.3.6.9',
     description="The Keras for ML researchers using PyTorch",
     author="William Falcon",
     author_email="waf2107@columbia.edu",
@@ -19,7 +19,7 @@ setup(
     install_requires=[
         "torch>=1.1.0",
         "tqdm",
-        "test-tube>=0.6.7.4",
+        "test-tube>=0.6.7.6",
     ],
     packages=find_packages(),
     long_description=open("README.md", encoding="utf-8").read(),