Run 4. Outer Step 40. Inner Step 40.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5556165,
-    5556169,
-    5556174,
-    5556178,
-    5556182
+    5556186,
+    5556190,
+    5556195,
+    5556199,
+    5556203
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 39,
+  "inner_step": 40,
   "inner_steps": 0,
   "last_allreduce_block": 5552497,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4223e3b57ffaba838956579d69f4e10b1f226fc66dbe8e99194b5b8e2e9ffee4
+oid sha256:d328be4944c448416852c90b53186a6ff335d673ed260b1456e4fb7ba8ac01b1
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51f5a12eb73c3eddf12d6a4c724d5bd313dafa0c60c9024223e8b13edaa8c6fe
+oid sha256:ea0069fd808a3d088cbbb3b746343f2171125928ef2b0d9e4009a43529466bd9
 size 4040701744