Run 4. Outer Step 34. Inner Step 42.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5548266,
-    5548268,
-    5548270,
-    5548272,
-    5548274,
-    5548276,
-    5548278
+    5548281,
+    5548283,
+    5548285,
+    5548287,
+    5548289
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 41,
+  "inner_step": 42,
   "inner_steps": 0,
   "last_allreduce_block": 5546853,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a132578d8545240718d216e01d99f0a1607f6390878895e5cc62681eded2b14
+oid sha256:5a45be846e1e60f6bedd1e16873006cde549f68ec23dd351a31c675ca2ee973b
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1df27434b6befd391ea016ecffe0c6a46471ec443862e66edb14df6b84927cfd
+oid sha256:5fa281f211e526ee1f8fab1bf36a55b9223cbb187f48222b5ca12a20124ceff6
 size 4040701744