Run 4. Outer Step 30. Inner Step 11.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5540855,
-    5540859,
-    5540863,
-    5540868,
-    5540872
+    5540876,
+    5540881,
+    5540885,
+    5540889,
+    5540894
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 10,
+  "inner_step": 11,
   "inner_steps": 0,
   "last_allreduce_block": 5539810,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92b62ea56a91d8448cbf4c7823d9331afe779f66ba03ee00d7ceb06444d77455
+oid sha256:42fc981006ceca97c2fc35042f14014fd6d2076e2319e883287f3e763e9963ba
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca8d955b86fdf16bcb9d394a64ab53b8800880be1067ca1e774266ce99edee65
+oid sha256:8e2366bfd5eed22dfcd85f9a0d0c60db9b9ffca9ca9d04cb8ac5de3c4b9e87c9
 size 4040701744