Run 4. Outer Step 12. Inner Step 20.

config.json

@@ -268,20 +268,21 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5508900,
-    5508904,
-    5508908,
-    5508911,
-    5508915,
-    5508918,
-    5508922
+    5508926,
+    5508930,
+    5508933,
+    5508937,
+    5508940,
+    5508944,
+    5508947,
+    5508951
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 18,
+  "inner_step": 19,
   "inner_steps": 0,
   "last_allreduce_block": 5506953,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec529849e9681172d411a9235fd12f3a69e6485bca6e4d92fc8def4f18625003
+oid sha256:f74163be5726a68e23632a676a1cd691727f4bdf49f333abc3f9576e911fc9c2
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:398bc91b4f76b27e739e24c180089b856a69c3d8ae43781a5b1851f6c56fc476
+oid sha256:77eb53c87dd1dfc0fdb3e2aa5af9c821b918ddd511b3793342ee84a1a4f3b650
 size 4040701744