Run 2. Outer Step 9. Inner Step 0.

config.json

@@ -267,19 +267,13 @@
     "AutoConfig": "distributed/optimized-gpt2-500m--configuration_gpt_optimized.GPTOptimConfig",
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
-  "block_list": [
-    5355184,
-    5355186,
-    5355187,
-    5355188,
-    5355188
-  ],
+  "block_list": [],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 278,
+  "inner_step": 0,
   "inner_steps": 0,
   "last_allreduce_block": 5351170,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7bd0adb2630f9bbc1a92958896774e8d9dbd92c04aa15ae087488cd834a2897
+oid sha256:57a7560b7d6dcff2f9b986cdf1519151986f63582928104d82fbbcf373d695a7
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afa89fd5a7fd5a6fe1fac75e05196387da9c7c803471ae10efc5f6ff5336e19e
+oid sha256:30a3c2a1f583992135596ada96883cba467a485b6ef53f21ba48c2355f414587
 size 4040701744