Run 4. Outer Step 23. Inner Step 12.

config.json

@@ -268,23 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5531260,
-    5531263,
-    5531265,
-    5531268,
-    5531271,
-    5531273,
-    5531275,
-    5531278,
-    5531279,
-    5531282
+    5531284,
+    5531287,
+    5531289,
+    5531292,
+    5531294
   ],
   "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": 5529444,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c0d541fc995035a3d8557b252176b2e9c28b35be60f956b90b8ab94e441dade
+oid sha256:66f9742fee20f771d0a627126c009390c5e040e691c2608637692e6f4211353a
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbab9f36f128eda58a331d28e7e1c91bfc64515983373216dde9aa83bbf972b0
+oid sha256:68cc79a0b7f575760fb72e0ebfdecad39bf7165166bb4240cdbf9fd21ca95ff0
 size 4040701744