Run 4. Outer Step 12. Inner Step 18.

config.json

@@ -268,20 +268,20 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5508875,
-    5508878,
-    5508882,
-    5508885,
-    5508889,
-    5508892,
-    5508896
+    5508900,
+    5508904,
+    5508908,
+    5508911,
+    5508915,
+    5508918,
+    5508922
   ],
   "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": 5506953,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b508f7526b25ce7f9727f1266c13322f3d81f3d27c81913bc45e85e6c6598c6
+oid sha256:ec529849e9681172d411a9235fd12f3a69e6485bca6e4d92fc8def4f18625003
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4b6937f0ac417f39ed8085cb26865764f59ed7279b94b17cd35fda7d1be6e78
+oid sha256:398bc91b4f76b27e739e24c180089b856a69c3d8ae43781a5b1851f6c56fc476
 size 4040701744