Training in progress, step 500

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj",
-    "up_proj",
-    "down_proj",
     "gate_proj",
+    "v_proj",
+    "o_proj",
     "k_proj",
-    "o_proj"
+    "down_proj",
+    "up_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:088a356538d85505a6d61a6da067e191928a6890eaaf86623a8e92f7069ff567
+oid sha256:2a319813dec1eb33d84460d7a6b0203722a9068bb538ad8c6e0666533704442f
 size 1342238560

language_service.8096406fb6d8.root.log.INFO.20240805-122034.4270

@@ -51,3 +51,10 @@ I0805 12:27:14.300485      65 ls.go:1241] cancel was requested for: 52, needs to
 I0805 12:27:14.477490      65 ls.go:1241] cancel was requested for: 54, needs to be canceled: false
 I0805 12:27:14.810338      65 ls.go:1241] cancel was requested for: 56, needs to be canceled: false
 I0805 12:27:15.618393      65 ls.go:1241] cancel was requested for: 57, needs to be canceled: false
+I0805 12:32:32.426373      65 ls.go:1241] cancel was requested for: 72, needs to be canceled: false
+I0805 12:32:38.016865      65 ls.go:1241] cancel was requested for: 73, needs to be canceled: false
+I0805 12:32:38.481001      65 ls.go:1241] cancel was requested for: 74, needs to be canceled: false
+I0805 12:32:39.175366      65 ls.go:1241] cancel was requested for: 75, needs to be canceled: false
+I0805 12:32:53.967976      65 ls.go:1241] cancel was requested for: 78, needs to be canceled: false
+I0805 12:35:13.458373      65 ls.go:1241] cancel was requested for: 79, needs to be canceled: false
+I0805 12:48:54.185585      65 ls.go:1241] cancel was requested for: 80, needs to be canceled: false

language_service.INFO

@@ -51,3 +51,10 @@ I0805 12:27:14.300485      65 ls.go:1241] cancel was requested for: 52, needs to
 I0805 12:27:14.477490      65 ls.go:1241] cancel was requested for: 54, needs to be canceled: false
 I0805 12:27:14.810338      65 ls.go:1241] cancel was requested for: 56, needs to be canceled: false
 I0805 12:27:15.618393      65 ls.go:1241] cancel was requested for: 57, needs to be canceled: false
+I0805 12:32:32.426373      65 ls.go:1241] cancel was requested for: 72, needs to be canceled: false
+I0805 12:32:38.016865      65 ls.go:1241] cancel was requested for: 73, needs to be canceled: false
+I0805 12:32:38.481001      65 ls.go:1241] cancel was requested for: 74, needs to be canceled: false
+I0805 12:32:39.175366      65 ls.go:1241] cancel was requested for: 75, needs to be canceled: false
+I0805 12:32:53.967976      65 ls.go:1241] cancel was requested for: 78, needs to be canceled: false
+I0805 12:35:13.458373      65 ls.go:1241] cancel was requested for: 79, needs to be canceled: false
+I0805 12:48:54.185585      65 ls.go:1241] cancel was requested for: 80, needs to be canceled: false

runs/Aug05_12-31-46_8096406fb6d8/events.out.tfevents.1722861112.8096406fb6d8.7300.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48c09a95160e4e1709131b44b04c67d31562180005d2968bddc96ee3658e3ae8
+size 6160

tmp4ugedcwg/_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

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1225af208199bd0cd564a8f76fd75f267da12e9be92fad9fc87d683cd1f1c63b
+oid sha256:4d31a2b1b9cd6270e505123447098c3a9936da8c8b084de21f4a20859c486d6a
 size 5432