Run 2. Outer Step 2. Inner Step 117.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5330503,
-    5330506,
-    5330512,
-    5330515,
-    5330520
+    5330554,
+    5330558,
+    5330562,
+    5330566,
+    5330570
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 110,
+  "inner_step": 117,
   "inner_steps": 0,
   "last_allreduce_block": 5323221,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b45da69e5e7c2a90a09c0d7c886516d2faed0cca4301c8c9d5ee779e9a9a6dbd
+oid sha256:1fa75e0b8e6d0c03acf813da2644fd9b5ad7fb336d9ad77229c48875555f1ce3
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b21ad997d00291af46fb3385476c1551611d1b60737195fc4a31b44f235e36f7
+oid sha256:958310cb9221d13f6559c726d2fa5a78d892f8cee3799e4940b87e877bee47be
 size 4040701744