Run 3. Outer Step 4. 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": [
-    5373054,
-    5373058,
-    5373063,
-    5373067,
-    5373072
-  ],
+  "block_list": [],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 75,
+  "inner_step": 0,
   "inner_steps": 0,
   "last_allreduce_block": 5363566,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:032bb470e72fe55cb92cb41059ca535ac6fa30ba2f2fc1aa072caa07a1a82c82
+oid sha256:d808873bfe02d86e1d4a7d4936075fcba6bfab08ed64ecc830edc43f9556c603
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18d12f61655b7726b30b663cdb6a74d0dd02d88e8aa377ee44a437c5663dc651
+oid sha256:15324b2f635bc7310338ce9bf66e9183708feb24b47bbd3c9e8e3af7c21747a4
 size 4040701744