Run 4. Outer Step 23. Inner Step 18.

config.json

@@ -268,22 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5531437,
-    5531439,
-    5531441,
-    5531444,
-    5531447,
-    5531450,
-    5531452,
-    5531454,
-    5531457
+    5531460,
+    5531462,
+    5531464,
+    5531467,
+    5531469
   ],
   "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": 5529444,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0679446667c1e01440a23d789c7d3f8b1f566f10eab5788a477c78959568ca2e
+oid sha256:726b35443d7212da549bb3f5c2001a107d69e64b55d7d9d8981efbbfa7c009ad
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9dc64340fa64bdd4ea83896b46eb7def7cca66cc9026f9b288ac4589ebfac4a7
+oid sha256:b857cddf932f86daa2f30a52532a1a2b7398d3f9d076512a3b36bf4c3467f348
 size 4040701744