Run 3. Outer Step 12. Inner Step 121.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5470107,
-    5470109,
-    5470111,
-    5470112,
-    5470114
+    5470146,
+    5470148,
+    5470150,
+    5470151,
+    5470153
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 119,
+  "inner_step": 121,
   "inner_steps": 0,
   "last_allreduce_block": 5450451,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da625aa28bbb140a83d6b085065677022e6140df2eedf2981c15b50e3bd9d5e9
+oid sha256:6fedeb4acc5c4d804bc57500998fd6d45b59a4f8ee4d68d1e5aacf43af93b598
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6710434cd57854ddbc7623142117b081d9addb26de26f944e173d9461486df4
+oid sha256:b911675ba465d0be050d86b1c6b113cd0213af18afd860c35f97f21984dcc8df
 size 4040701744