Run 2. Outer Step 1. Inner Step 4.

config.json

@@ -267,13 +267,19 @@
     "AutoConfig": "distributed/optimized-gpt2-500m--configuration_gpt_optimized.GPTOptimConfig",
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
-  "block_list": [],
+  "block_list": [
+    5326837,
+    5326840,
+    5326844,
+    5326848,
+    5326851
+  ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 0,
+  "inner_step": 4,
   "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:b7debebcd6091553c4fc865a538a768e96dd8cc8a2e3e2ec4737f397ffa275db
-size 2944
+oid sha256:59abff5726b119abc35a4a7641129748d449b9d45405f4519e310ba523720a33
+size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72d1f4054db89ccac14b1f1280d753c2392383a6cf8af7ff098a570ffafd3cb9
+oid sha256:1b651263ac00f5dc56b8234b65a66beb8b9ff115e750d61cde7511cb796e6960
 size 4040701744