Run 4. Outer Step 29. Inner Step 36.

config.json

@@ -268,18 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5539610,
-    5539613,
-    5539615,
-    5539618,
-    5539619
+    5539621,
+    5539623,
+    5539624,
+    5539627,
+    5539629,
+    5539631,
+    5539633,
+    5539636,
+    5539638,
+    5539640
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 35,
+  "inner_step": 36,
   "inner_steps": 0,
   "last_allreduce_block": 5538408,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab4fd83d0485fbc1daafca87f373bcbac33409ac0fe8198662f1736328039657
+oid sha256:b6dd28d23ed52f65373b6d5a99142a95762ad31a2889f9c7ecdbb2eb8a67f71f
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e04e21cf304f336545ebb8d02abc929a4755115aa14f211c19d689afa7b8674
+oid sha256:b7b3215798ce8c9f975edd657f70dd48a806ee08fa177546c94e35a95550f64d
 size 4040701744