Training in progress, step 1500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:993993994e36595cd7f80d49a58f162b982803b16013a68f6b9882723c0980d4
+oid sha256:6f12b6e2abc11cb1f20e15a6264a2af2a535109117ca4b55e2d22c10765bfaad
 size 2422994960

runs/Sep06_22-17-44_ab8ef642973f/events.out.tfevents.1725662209.ab8ef642973f.24.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66421ee09245d60daf05a2f2d9b388381630fc7a1b3fd2a5d147af0c3a370c46
+size 8996

tmp9a0e0bhj/_remote_module_non_scriptable.py

@@ -0,0 +1,81 @@
+from typing import *
+
+import torch
+import torch.distributed.rpc as rpc
+from torch import Tensor
+from torch._jit_internal import Future
+from torch.distributed.rpc import RRef
+from typing import Tuple  # pyre-ignore: unused import
+
+
+module_interface_cls = None
+
+
+def forward_async(self, *args, **kwargs):
+    args = (self.module_rref, self.device, self.is_device_map_set, *args)
+    kwargs = {**kwargs}
+    return rpc.rpc_async(
+        self.module_rref.owner(),
+        _remote_forward,
+        args,
+        kwargs,
+    )
+
+
+def forward(self, *args, **kwargs):
+    args = (self.module_rref, self.device, self.is_device_map_set, *args)
+    kwargs = {**kwargs}
+    ret_fut = rpc.rpc_async(
+        self.module_rref.owner(),
+        _remote_forward,
+        args,
+        kwargs,
+    )
+    return ret_fut.wait()
+
+
+_generated_methods = [
+    forward_async,
+    forward,
+]
+
+
+
+
+def _remote_forward(
+    module_rref: RRef[module_interface_cls], device: str, is_device_map_set: bool, *args, **kwargs):
+    module = module_rref.local_value()
+    device = torch.device(device)
+
+    if device.type != "cuda":
+        return module.forward(*args, **kwargs)
+
+    # If the module is on a cuda device,
+    # move any CPU tensor in args or kwargs to the same cuda device.
+    # Since torch script does not support generator expression,
+    # have to use concatenation instead of
+    # ``tuple(i.to(device) if isinstance(i, Tensor) else i for i in *args)``.
+    args = (*args,)
+    out_args: Tuple[()] = ()
+    for arg in args:
+        arg = (arg.to(device),) if isinstance(arg, Tensor) else (arg,)
+        out_args = out_args + arg
+
+    kwargs = {**kwargs}
+    for k, v in kwargs.items():
+        if isinstance(v, Tensor):
+            kwargs[k] = kwargs[k].to(device)
+
+    if is_device_map_set:
+        return module.forward(*out_args, **kwargs)
+
+    # If the device map is empty, then only CPU tensors are allowed to send over wire,
+    # so have to move any GPU tensor to CPU in the output.
+    # Since torch script does not support generator expression,
+    # have to use concatenation instead of
+    # ``tuple(i.cpu() if isinstance(i, Tensor) else i for i in module.forward(*out_args, **kwargs))``.
+    ret: Tuple[()] = ()
+    for i in module.forward(*out_args, **kwargs):
+        i = (i.cpu(),) if isinstance(i, Tensor) else (i,)
+        ret = ret + i
+    return ret

tmpt9boyj22.json

@@ -0,0 +1,12 @@
+{
+  "shell_port": 39393,
+  "iopub_port": 38105,
+  "stdin_port": 53859,
+  "control_port": 49187,
+  "hb_port": 50903,
+  "ip": "127.0.0.1",
+  "key": "3427a58e-8280834fd4423ed4ea84f59c",
+  "transport": "tcp",
+  "signature_scheme": "hmac-sha256",
+  "kernel_name": "python3"
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:306b30570f912eecde8991d8d3337d7e0e054002ec7bcdf9df74086c94fc68ef
+oid sha256:7f501f4a8d41da95a51590cf69469dc2e61588d6776c76ae63c115808cbb6dc4
 size 4856