Run 3. Outer Step 11. Inner Step 234.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5444059,
-    5444064,
-    5444067,
-    5444071,
-    5444074
+    5444102,
+    5444106,
+    5444109,
+    5444113,
+    5444117
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 232,
+  "inner_step": 234,
   "inner_steps": 0,
   "last_allreduce_block": 5422706,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e321c09db9a4c6525e6f55b1f437cab04584612de376d0b1555fe62bf26b0134
+oid sha256:4f26afc6d39712adef8a95184823f5a2419dc4d0ca21c18467389728de1c062f
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac1399ceb31ab80b90505128aee527674159df45cbef39b50f5046e7d31ae267
+oid sha256:16394953e3dbcbd07823025a2e57476f0c58a613d63bb25ad4b292d5c2c59852
 size 4040701744