Run 4. Outer Step 37. Inner Step 18.

config.json

@@ -268,19 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5551675,
-    5551678,
-    5551680,
-    5551684,
-    5551687,
-    5551689
+    5551692,
+    5551694,
+    5551696,
+    5551700,
+    5551703
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 17,
+  "inner_step": 18,
   "inner_steps": 0,
   "last_allreduce_block": 5550793,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9a94a58bcbb90b50e5fff879da8ec9b5a19fc6e5e47105cf637bfd407d67d0a
+oid sha256:a818c648b3486354221822784ebd3dc6b9054ea2428d9f357677783a138760be
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dd1fe4c5624bf195ba5a4d051370b7ac9559886783e58a5462c0e0bc24c0684
+oid sha256:0de1533c1e0c8fe2473673a6cbe289ebbe59075fc889f05c9091f9f5490d5535
 size 4040701744