Run 3. Outer Step 11. Inner Step 26.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5432148,
-    5432150,
-    5432152,
-    5432153,
-    5432155
+    5432181,
+    5432183,
+    5432185,
+    5432186,
+    5432188
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 24,
+  "inner_step": 26,
   "inner_steps": 0,
   "last_allreduce_block": 5422706,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c12a52886dc1968ad341f13b8c84408e19226762d2dc3f6b53de4e4a8199570e
+oid sha256:ab7c38fb57f48260407342560b9643a14d5366c113fbb3b31868ad6f7bce5dd7
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c62ad5e6073ff9feb4ab00d7cf19f9b70fdc33b7da8bd50779c6c99a0fc794f1
+oid sha256:072d888e194d2f9f90e0c262bb3e8cac4c07e6f1de6440078743881fba495b3e
 size 4040701744