Run 4. Outer Step 22. Inner Step 10.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5527011,
-    5527018,
-    5527025,
-    5527032,
-    5527038
+    5527046,
+    5527053,
+    5527060,
+    5527067,
+    5527073
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 9,
+  "inner_step": 10,
   "inner_steps": 0,
   "last_allreduce_block": 5506953,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc43867bb8ba0b7c91000dc48c18e0254dbed0483382b190fb46b1e202bdab4e
+oid sha256:7004b7a2d11a116a1abc5f682f2911d2cef2e6a6d447ed1971ca91fe7cdeecc7
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59f4dcb34fa0254e0cea20b47d485bd0d7de449104d2339de7f47b73e513dc73
+oid sha256:10592f2d50c6577d1ca1e172036f44058ecb49d9e1e5b795d0c751f484ff13a7
 size 4040701744