Run 4. Outer Step 27. Inner Step 35.

config.json

@@ -268,23 +268,22 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5537002,
-    5537004,
-    5537007,
-    5537009,
-    5537011,
-    5537013,
-    5537015,
-    5537017,
-    5537019,
-    5537021
+    5537024,
+    5537026,
+    5537028,
+    5537030,
+    5537032,
+    5537035,
+    5537037,
+    5537039,
+    5537041
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 34,
+  "inner_step": 35,
   "inner_steps": 0,
   "last_allreduce_block": 5535854,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2a95a9af18ba44f912569637d44393f3c988ed84c42f33dc1b2746265c94164
+oid sha256:c8e8818804cfd4bd7942a1775747a9a0ec37d8a1cf481c1c108855f2f7a45d84
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b03d9a10a369b1cec01e5bf25dde9bf01241c32614c49907b9eee4dfafcbbf6
+oid sha256:425e4d4764f33836f2f13d7c84325e0e96d499d7bbb77af1f1a452e310fefbd7
 size 4040701744