Run 4. Outer Step 52. Inner Step 35.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5576059,
-    5576061,
-    5576064,
-    5576066,
-    5576068,
-    5576070,
-    5576072,
-    5576073
+    5576076,
+    5576078,
+    5576079,
+    5576081,
+    5576083
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 34,
+  "inner_step": 35,
   "inner_steps": 0,
   "last_allreduce_block": 5574901,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2552ecdb486d19cb096066ce27bba252b8557564940d2893817e020ceb4a3978
+oid sha256:f5a35cc516ad57d34e1f49259b115d1dc2521920dea443da870feaeea0170f96
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13ed88a2f3f293b143639b85e05f92050c62cee6d4ea58c1e25d2483653d74fd
+oid sha256:45109e8bb40cccb547cf238c1b2d05e445ec88c55583334e61955c4416abc3b7
 size 4040701744