Run 3. Outer Step 1. Inner Step 15.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5366717,
-    5366723,
-    5366729,
-    5366736,
-    5366742
+    5366770,
+    5366776,
+    5366783,
+    5366789,
+    5366795
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 14,
+  "inner_step": 15,
   "inner_steps": 0,
   "last_allreduce_block": 5366095,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f2167e8f98896afa739c7effb8613fbe626ee1c58f9ece7428321a042e2dd33
+oid sha256:a26abd299ab0b24e3bec01e993cb154a0b9d99e7e27a65ec466e1e69bb9ff9a1
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddbae9373511f45b62c878846a94dcac2a77435bbb91916a523e0f420297942d
+oid sha256:e75ac39e4191a59eb9d68e21f6bd4c06dad93933cfc4bb3e8d40b8e5ce49801d
 size 4040701744