Run 4. Outer Step 31. Inner Step 36.

config.json

@@ -268,23 +268,21 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5542230,
-    5542233,
-    5542236,
-    5542238,
-    5542241,
-    5542244,
-    5542246,
-    5542248,
-    5542248,
-    5542249
+    5542250,
+    5542252,
+    5542254,
+    5542256,
+    5542258,
+    5542262,
+    5542264,
+    5542265
   ],
   "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": 5529444,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96fa6b413f004ecb796acb190979f9aa1ef3759d67b49399bbfda093fa0ab42f
+oid sha256:3ebbc1438e6b43848ffe2d91edca75593b5a3fb14954923e0aaa893da15fec9e
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c7e8325138371d1ccd998393f84b711d5edd65d8bd6c93637a187f96125ec83
+oid sha256:e412ec9714cc4654e87703f4c1ddfd56b95a12f0488830441d872703c05aef7f
 size 4040701744