Run 2. Outer Step 7. Inner Step 185.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5348273,
-    5348277,
-    5348280,
-    5348283,
-    5348288
+    5348330,
+    5348333,
+    5348336,
+    5348341,
+    5348345
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 177,
+  "inner_step": 185,
   "inner_steps": 0,
   "last_allreduce_block": 5339896,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08149e18a38391eb65f82cb872907ed8021cf61a04f335b45759ff857184ea06
+oid sha256:5d2a625d085a21e4b0a6911e5332f8e2beb810dd1ab8c2ddbd50bf35dd286fbc
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0107b760e6ff7b4815ffe3b8f2151fc1311f17e61e03d0544bee06180b7c8cc
+oid sha256:3bbd4862b5c62d61e094b0975862901d5632a2fbbdf30351fc12489daa527ccb
 size 4040701744