Run 4. Outer Step 40. Inner Step 0.

config.json

@@ -268,18 +268,17 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5555035,
-    5555038,
-    5555042,
-    5555046,
-    5555050
+    5555055,
+    5555059,
+    5555062,
+    5555066
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 43,
+  "inner_step": 0,
   "inner_steps": 0,
   "last_allreduce_block": 5552497,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d15e99209120f74317b9302f655fe495c07fb7257e9e83a953eca3897df5576
+oid sha256:efdc58b652ef747373e6dca8dd3b66481cd08f7a6de0f297daeae1819101295d
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ec286975855d2056c10f6d1c34fb3484a9eefe5ff6eefd59a12acb775b76737
+oid sha256:3a66c7f8796ead9bff1fff0e1d9c66d922573e0b095829de904f8fee2dc6bf2b
 size 4040701744