runnable 0.30.4__py3-none-any.whl → 0.30.5__py3-none-any.whl

extensions/nodes/torch.py

@@ -6,7 +6,7 @@ import string
 from datetime import datetime
 from typing import Any, Callable
 
-from pydantic import ConfigDict, Field
+from pydantic import BaseModel, ConfigDict, Field
 
 from extensions.nodes.torch_config import TorchConfig
 from runnable import PythonJob, datastore, defaults
@@ -120,7 +120,8 @@ class TorchNode(DistributedNode, TorchConfig):
         return cls(executable=executable, **node_config, **task_config)
 
     def get_launch_config(self) -> LaunchConfig:
-        config, _, _ = config_from_args(self)
+        easy_model = EasyModel(**self.model_dump(exclude_none=True))
+        config, _, _ = config_from_args(easy_model)
         config.run_id = self._context.run_id
         return config
 
@@ -194,3 +195,9 @@ class TorchNode(DistributedNode, TorchConfig):
         assert (
             map_variable is None or not map_variable
         ), "TorchNode does not support map_variable"
+
+
+class EasyModel(BaseModel):
+    model_config = ConfigDict(extra="allow")
+    logs_specs: str | None = None
+    local_addr: str | None = Field(default=None)

extensions/nodes/torch_config.py

@@ -1,33 +1,39 @@
+from enum import Enum
+
 from pydantic import BaseModel, Field
 
 
+class StartMethod(str, Enum):
+    spawn = "spawn"
+    fork = "fork"
+    forkserver = "forkserver"
+
+
 class TorchConfig(BaseModel):
     nnodes: str = Field(default="1:1")
-    nproc_per_node: int = Field(default=4)
-
-    rdzv_backend: str = Field(default="static")
-    rdzv_endpoint: str = Field(default="")
-    rdzv_id: str | None = Field(default=None)
-    rdzv_conf: str = Field(default="")
-
-    max_restarts: int = Field(default=3)
-    monitor_interval: float = Field(default=0.1)
-    start_method: str = Field(default="spawn")
-    role: str = Field(default="default_role")
-    log_dir: str = Field(default="torch_logs")
-    redirects: str = Field(default="1")
-    tee: str = Field(default="1")
-    master_addr: str = Field(default="localhost")
-    master_port: str = Field(default="29500")
+    nproc_per_node: int = Field(default=1)
+
+    rdzv_backend: str | None = Field(default="static")
+    rdzv_endpoint: str | None = Field(default="")
+    rdzv_id: str | None = Field(default="none")
+    rdzv_conf: str | None = Field(default="")
+
+    max_restarts: int | None = Field(default=None)
+    monitor_interval: float | None = Field(default=0.1)
+    start_method: str | None = Field(default=StartMethod.spawn)
+    role: str | None = Field(default="default")
+    log_dir: str | None = Field(default="torch_logs")
+    redirects: str | None = Field(default="0")
+    tee: str | None = Field(default="0")
+    master_addr: str | None = Field(default="localhost")
+    master_port: str | None = Field(default="29500")
     training_script: str = Field(default="dummy_training_script")
     training_script_args: str = Field(default="")
 
     # Optional fields
-    local_ranks_filter: str = Field(default="")
-    node_rank: int = Field(default=0)
-    local_addr: str | None = Field(default=None)
-    logs_specs: str | None = Field(default=None)
-    standalone: bool = Field(default=False)
-    module: bool = Field(default=False)
-    no_python: bool = Field(default=False)
-    run_path: bool = Field(default=False)
+    local_ranks_filter: str | None = Field(default="0")
+    node_rank: int | None = Field(default=0)
+    standalone: bool | None = Field(default=None)
+    module: bool | None = Field(default=False)
+    no_python: bool | None = Field(default=False)
+    run_path: bool | None = Field(default=False)

{runnable-0.30.4.dist-info → runnable-0.30.5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: runnable
-Version: 0.30.4
+Version: 0.30.5
 Summary: Add your description here
 Author-email: "Vammi, Vijay" <vijay.vammi@astrazeneca.com>
 License-File: LICENSE

{runnable-0.30.4.dist-info → runnable-0.30.5.dist-info}/RECORD

@@ -16,8 +16,8 @@ extensions/job_executor/pyproject.toml,sha256=UIEgiCYHTXcRWSByNMFuKJFKgxTBpQqTqy
 extensions/nodes/README.md,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 extensions/nodes/nodes.py,sha256=s9ub1dqy4qHjRQG6YElCdL7rCOTYNs9RUIrStZ6tEB4,28256
 extensions/nodes/pyproject.toml,sha256=YTu-ETN3JNFSkMzzWeOwn4m-O2nbRH-PmiPBALDCUw4,278
-extensions/nodes/torch.py,sha256=id0_HVkRcqL9_DPOI-b53vaDwRgVfGB-zZS3yrRej9g,6318
-extensions/nodes/torch_config.py,sha256=yDvDADpnLhQsNtfH8qIztLHQ2LhYiOJEWljxpH9GZzs,1222
+extensions/nodes/torch.py,sha256=JyU4fZl06QLW90YVckPenQ6bAXZGNr66eGLnr-dpOsE,6562
+extensions/nodes/torch_config.py,sha256=6J-Oy0TPnAgiyKST8pDZ-OIUWzZqyNs_ej18yuOI9-E,1383
 extensions/pipeline_executor/README.md,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 extensions/pipeline_executor/__init__.py,sha256=wfigTL2T9OHrmE8b2Ydmb8h6hr-oF--Yc2FectC7WaY,24623
 extensions/pipeline_executor/argo.py,sha256=AEGSWVZulBL6EsvbVCaeBeTl2m_t5ymc6RFpMKhivis,37946
@@ -58,8 +58,8 @@ runnable/sdk.py,sha256=NZVQGaL4Zm2hwloRmqEgp8UPbBg9hY1abQGYnOgniPI,35128
 runnable/secrets.py,sha256=4L_dBFxTgr8r_hHUD6RlZEtqaOHDRsFG5PXO5wlvMI0,2324
 runnable/tasks.py,sha256=Qb1IhVxHv68E7vf3M3YCf7MGRHyjmsEEYBpEpiZ4mRI,29062
 runnable/utils.py,sha256=hBr7oGwGL2VgfITlQCTz-a1iwvvf7Mfl-HY8UdENZac,19929
-runnable-0.30.4.dist-info/METADATA,sha256=S-5zecrqE4tU5MW4Fe1-2F-Q_hLU7fAXZ2oo9xVRRUw,10115
-runnable-0.30.4.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-runnable-0.30.4.dist-info/entry_points.txt,sha256=PrjKrlfXPZaV_7hz8orGu4FDnatLqnhPOXljyllszdw,1880
-runnable-0.30.4.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-runnable-0.30.4.dist-info/RECORD,,
+runnable-0.30.5.dist-info/METADATA,sha256=FXkML9uUZiGwloqMjW6rh89cN4H_2XzBrtcMPDG92VU,10115
+runnable-0.30.5.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+runnable-0.30.5.dist-info/entry_points.txt,sha256=PrjKrlfXPZaV_7hz8orGu4FDnatLqnhPOXljyllszdw,1880
+runnable-0.30.5.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+runnable-0.30.5.dist-info/RECORD,,