Run 4. Outer Step 27. Inner Step 28.

config.json

@@ -268,23 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5536804,
-    5536806,
-    5536808,
-    5536811,
-    5536815,
-    5536816,
-    5536818,
-    5536820,
-    5536822,
-    5536823
+    5536825,
+    5536828,
+    5536831,
+    5536832,
+    5536834
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 27,
+  "inner_step": 28,
   "inner_steps": 0,
   "last_allreduce_block": 5535854,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:757b14622ea19a5dc8708ed38c9c7d51b5e764b79aaa7c0d28be8cc7d7edd61a
+oid sha256:d1d6e88283a133702c7957aeab0589e8ba908d476f75b08d55ce4a351dcc0e61
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d06b6c8926d5d64c5935034a988973baf355d015f3d49813f8a1f4200e4c1147
+oid sha256:a146ef59a564a9efc08f6c7e840ae8ce47997d5368713db5907d41026658b416
 size 4040701744