Run 4. Outer Step 2. Inner Step 11.

config.json

@@ -268,24 +268,26 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5480375,
-    5480378,
-    5480380,
-    5480383,
-    5480385,
-    5480388,
-    5480392,
-    5480394,
-    5480397,
-    5480399,
-    5480401
+    5480402,
+    5480404,
+    5480405,
+    5480406,
+    5480408,
+    5480410,
+    5480412,
+    5480414,
+    5480417,
+    5480420,
+    5480422,
+    5480424,
+    5480426
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 10,
+  "inner_step": 11,
   "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 sha256:42c1e3f988e29e2a1b5ff7f2915aca369e69d824d23afdef11550326083de48f
+oid sha256:a257ed16c9b82c3b3165d77c3e574d8e48a971499c97b3cd6710bf3afc91972a
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6843b4f7c88ddf9b1dd0654618d013abcb57ae1884a009b9f0df7536dc1c9031
+oid sha256:1d59e021d84391912a35c39a1d13a8ce1deddc2c9f1c2538d270717d52b49d64
 size 4040701744