Run 4. Outer Step 17. Inner Step 19.

config.json

@@ -268,20 +268,20 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5519509,
-    5519512,
-    5519516,
-    5519519,
-    5519523,
-    5519527,
-    5519530
+    5519534,
+    5519538,
+    5519542,
+    5519545,
+    5519549,
+    5519552,
+    5519556
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 17,
+  "inner_step": 19,
   "inner_steps": 0,
   "last_allreduce_block": 5509976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9ced29185dd8862f7a7ba345e255ca95fc8df06797bec39b543f7a548355c83
+oid sha256:42a1bb5be2e9f513de75f62e92a5f81bbf7e005fe43c504a62dd1c021fccd333
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ef3df08992a4e5b9ec20977638355694e358e26d5ccca0c706110ec086b5932
+oid sha256:eb07ae428f36d6463f38ee29456f2afda1f3fc3cf587d327e6dfd0ee0520efbd
 size 4040701744