Run 4. Outer Step 30. Inner Step 18.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5541185,
-    5541189,
-    5541194,
-    5541199,
-    5541204
+    5541209,
+    5541214,
+    5541219,
+    5541224,
+    5541229
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 17,
+  "inner_step": 18,
   "inner_steps": 0,
   "last_allreduce_block": 5539810,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38513b955ce64eb5a5e78174c7ba422605c220ee03c15f5f1ac3c406c771b62e
+oid sha256:a1ea5fb505c6edc004e9b09b5687a744db2d69b30c99ba44ec79d6c1398f1dfc
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13a238d9131d64f5f44a40a596dfc29d4585f5aecb648296c7eda719ca3bab3b
+oid sha256:dfcad3333e298eb76153120bf3f3374672493a5a6721cb1ccd5cf26a55018829
 size 4040701744