Run 4. Outer Step 31. Inner Step 37.

config.json

@@ -268,22 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5542269,
-    5542272,
-    5542274,
-    5542276,
-    5542278,
-    5542280,
-    5542282,
-    5542285,
-    5542287
+    5542290,
+    5542292,
+    5542295,
+    5542297,
+    5542299
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 36,
+  "inner_step": 37,
   "inner_steps": 0,
   "last_allreduce_block": 5529444,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ebbc1438e6b43848ffe2d91edca75593b5a3fb14954923e0aaa893da15fec9e
+oid sha256:74cedabbf61dec26c4dec965f52172b5ed3297e3bc616d54c40b213aaba0ebad
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e412ec9714cc4654e87703f4c1ddfd56b95a12f0488830441d872703c05aef7f
+oid sha256:a3cc5a257d29e1f9f636c2d614206f8278694fdcc7bbe9baaef10afc5ebf243c
 size 4040701744