Run 4. Outer Step 23. Inner Step 11.

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5531212,
-    5531215,
-    5531217,
-    5531219,
-    5531222,
-    5531224,
-    5531227,
-    5531229,
-    5531231,
-    5531233
+    5531235,
+    5531238,
+    5531241,
+    5531243,
+    5531246,
+    5531248,
+    5531251,
+    5531253,
+    5531255,
+    5531258
   ],
   "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": 5529444,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:783749c65473d0d2aa6dd2e3fc6e2b55dbf0dbed9393185cb83ce86174d1e6a5
+oid sha256:3c0d541fc995035a3d8557b252176b2e9c28b35be60f956b90b8ab94e441dade
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7501eace35fccea321429d08b3952cfc86890498d85218e36454800261a94b29
+oid sha256:cbab9f36f128eda58a331d28e7e1c91bfc64515983373216dde9aa83bbf972b0
 size 4040701744