Run 4. Outer Step 12. Inner Step 9.

config.json

@@ -268,20 +268,20 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5508640,
-    5508644,
-    5508648,
-    5508651,
-    5508655,
-    5508658,
-    5508662
+    5508666,
+    5508670,
+    5508674,
+    5508677,
+    5508681,
+    5508684,
+    5508688
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 8,
+  "inner_step": 9,
   "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 sha256:1b1e936b4090c7ed9255e26158d5975be3b603db337eaf07981c2add97c41c73
+oid sha256:54ecdaa559055c5f06d5a6f5d5ad387321cad24fdc12660ce6215357c8a28e71
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6624c6c86202642ab5de89a6b20832cec07c24ae0e6906ea68dc73f6d5549f0b
+oid sha256:b7eb8c260ef11a910b6ecf44d675e0f305312d59911b08a9be37365790e8aa79
 size 4040701744