Run 4. Outer Step 33. Inner Step 23.

config.json

@@ -268,18 +268,20 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5544721,
-    5544724,
-    5544727,
-    5544730,
-    5544732
+    5544736,
+    5544739,
+    5544741,
+    5544743,
+    5544746,
+    5544749,
+    5544751
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 22,
+  "inner_step": 23,
   "inner_steps": 0,
   "last_allreduce_block": 5543976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbd05cec6344f443b36646094dbb2fc72730feb178188f56c885e3e88307dce3
+oid sha256:baa1499bbebe5a6681c77b8b04a0f7eafb5d56428274abaf7e4d2f788dde730a
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:600c502c5997779df246f21c69f209dd4c3f2e284db33e81fe38df823d8085ac
+oid sha256:15d192494591c2c6f282174c60b4653c1f56eef2f81a4fb6ae31e808edc2f9ca
 size 4040701744