Run 4. Outer Step 33. Inner Step 24.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5544723,
-    5544725,
-    5544728,
-    5544730,
-    5544732,
-    5544734,
-    5544736
+    5544739,
+    5544742,
+    5544744,
+    5544747,
+    5544750
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 23,
+  "inner_step": 24,
   "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:dacf631208f25608c1b9a19eb04bb758199623ace8ed415a88ca7e28a9e63825
+oid sha256:354772bb9d70500b226f1665b550d3eeedd15a2d2d7102ee10ab61e481a6a628
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c9730d6b03581db7668baeeb46dfbf6a26071e8d32710d81d9794d800b7277b
+oid sha256:e1892ed6ba2049c8caa0410bb05c2f7f69caf0d5697fa5d29fffb84efb64da6c
 size 4040701744