Run 4. Outer Step 11. Inner Step 26.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5507705,
-    5507709,
-    5507713,
-    5507716,
-    5507720,
-    5507724
+    5507728,
+    5507732,
+    5507735,
+    5507739,
+    5507743,
+    5507746
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 25,
+  "inner_step": 26,
   "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:bfe7e175080977c6b35d3e8649aac70be509f1128e760ce73e92fe97b2b57018
+oid sha256:fc31e2e956541fe2934a90d182d96ec3d835918fd3f395c08f6cf7b4f8ab6bea
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb02a0d4706e3ad79022738a0f0e98e807f2300ed8b6cc1d0e2504cf91cafb30
+oid sha256:054ea6199b08fd23407948183eb95129c4375c1c34cf7a6c46495b29e2cb0140
 size 4040701744