Run 4. Outer Step 23. Inner Step 18.

config.json

@@ -268,18 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5531431,
-    5531434,
-    5531437,
-    5531440,
-    5531442
+    5531444,
+    5531446,
+    5531448,
+    5531450,
+    5531453,
+    5531455,
+    5531457,
+    5531459,
+    5531462,
+    5531464
   ],
   "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": 5529444,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfd046d84bcf11dd52fbe0f049571d09ab64e73175c1421b0d622b4659809e1f
+oid sha256:960096c02254776de66b08120c933aaae942be0e16d40beb057c3b71355d77d0
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9279968414e6410d2190923d1619800e1d83010df3be5f5be9a7332870906feb
+oid sha256:e936afdded179525a2e1924a3470d8834b364a80ba9de415b2d364e6859a0d53
 size 4040701744