Run 4. Outer Step 2. Inner Step 12.

config.json

@@ -268,26 +268,25 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5480402,
-    5480404,
-    5480405,
-    5480406,
-    5480408,
-    5480410,
-    5480412,
-    5480414,
-    5480417,
-    5480420,
-    5480422,
-    5480424,
-    5480426
+    5480428,
+    5480430,
+    5480433,
+    5480434,
+    5480436,
+    5480437,
+    5480440,
+    5480443,
+    5480446,
+    5480448,
+    5480450,
+    5480452
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 11,
+  "inner_step": 12,
   "inner_steps": 0,
   "last_allreduce_block": 5477809,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a257ed16c9b82c3b3165d77c3e574d8e48a971499c97b3cd6710bf3afc91972a
+oid sha256:075499803a1c2d22764ff97dc8acaf3cf2ceea01535c9a437f917fbb21b420f7
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d59e021d84391912a35c39a1d13a8ce1deddc2c9f1c2538d270717d52b49d64
+oid sha256:08c9d8e00c2120cd861117ca7d05cc278ef1b907cca265124e53a8529d65a07d
 size 4040701744