Run 2. Outer Step 6. Inner Step 556.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5337470,
-    5337475,
-    5337479,
-    5337483,
-    5337487
+    5337518,
+    5337523,
+    5337527,
+    5337532,
+    5337535
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 549,
+  "inner_step": 556,
   "inner_steps": 0,
   "last_allreduce_block": 5330632,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78a89842b73e823604b9ce17adbbf8d9b7b203f2e771c7d6a2640b9d8b549a82
+oid sha256:169e2aaa25335338ee247fda5b0f686dd9d9688c27a2539a8e433d46c3547151
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ef76485d8fbbd51218e1e513386186ef023ad07a943db882f84ac4e2b182c52
+oid sha256:6d892cdb62c6ebec9158eb31f038cf9acd3ad8bf299f7101c723584506101129
 size 4040701744