Run 4. Outer Step 0. Inner Step 0.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    4530545,
-    4530549,
-    4530552,
-    4530555,
-    4530559
+    4530585,
+    4530610,
+    4530613,
+    4530616,
+    4530618
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 1,
+  "inner_step": 0,
   "inner_steps": 0,
   "last_allreduce_block": 4016775,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32e2366af216224ce33229771f4f7e9d5e3953191ea55dc9c315ffd8709eed93
-size 8081781962
+oid sha256:311243687e2e4ff1007d2cd7dd8d4b3decea3af58dc4facbf00ba7c06abc57f4
+size 2880

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90effe238df7380cc918399b9eb560a3c324b22d1962e3c45f837683b795e645
+oid sha256:cc48b2b7e0d5442f7e1e7179cf741ecdc55c22ff1248eccdd360b5a867831bae
 size 4040701744