Run 4. Outer Step 12. Inner Step 10.

config.json

@@ -268,20 +268,21 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5508666,
-    5508670,
-    5508674,
-    5508677,
-    5508681,
-    5508684,
-    5508688
+    5508692,
+    5508696,
+    5508699,
+    5508703,
+    5508706,
+    5508709,
+    5508713,
+    5508717
   ],
   "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 sha256:54ecdaa559055c5f06d5a6f5d5ad387321cad24fdc12660ce6215357c8a28e71
+oid sha256:63a1c975e2b5a7055797e5d2e477753ec44a447deac6017ce131f43be44afaef
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7eb8c260ef11a910b6ecf44d675e0f305312d59911b08a9be37365790e8aa79
+oid sha256:a89c7e5a18c3c92a24cdd63b444cb23252d90a214c3e663cbabf423f4c01d35d
 size 4040701744