Run 4. Outer Step 68. Inner Step 36.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5654584,
-    5654590,
-    5654594,
-    5654600,
-    5654605
+    5654610,
+    5654614,
+    5654619,
+    5654623,
+    5654627
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 35,
+  "inner_step": 36,
   "inner_steps": 0,
   "last_allreduce_block": 5653456,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d347b2d3341c6c943a1063c38fcbf9ce36ce23a74c4a431578606d9798fcb33
+oid sha256:bb11c13ceaa8c4d4729b4e6d38f7251c94e34a730927cbf5729c10e805161ab9
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99053ba1320dcc5631d22d14afccde33ffc2c1c1a1ab92fbae93f581a62f3f33
+oid sha256:a0d36b50fb491793dc4ec52601e8feac8743682a4db9eac740ce0c46be41733b
 size 4040701744