Run 2. Outer Step 3. 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": [
-    5330551,
-    5330556,
-    5330560,
-    5330564,
-    5330568
-  ],
+  "block_list": [],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 131,
+  "inner_step": 0,
   "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:f730ed94a9145c99e8432df833d6d042ed30096892fef58e5673ef52e12d419c
+oid sha256:c7c29f115224ff3d6030c4329a6b0caa92698ca604f6aa237b0e97db3ae4e03a
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7229db1b8f7363cd23d5a34588768c54edefd0ddd15a890ec1c998d97ec7086
+oid sha256:f116e2c25f57c39ac087d792698fe4e2b8c09eaed86cad254ee90072a84333f2
 size 4040701744