Run 3. Outer Step 11. Inner Step 232.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5444016,
-    5444020,
-    5444024,
-    5444027,
-    5444031
+    5444059,
+    5444064,
+    5444067,
+    5444071,
+    5444074
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 231,
+  "inner_step": 232,
   "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:b2b99b576297860f30b22f7f7aa5bba5b3e0e9a664d50370eebcb2992a069d22
+oid sha256:e321c09db9a4c6525e6f55b1f437cab04584612de376d0b1555fe62bf26b0134
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8832a7634ab4ba92d6caba36c6c9cff5eb772bb5598702cc19afee59e9ffde7c
+oid sha256:ac1399ceb31ab80b90505128aee527674159df45cbef39b50f5046e7d31ae267
 size 4040701744