Run 2. Outer Step 10. Inner Step 271.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5355150,
-    5355152,
-    5355153,
-    5355154,
-    5355155
+    5355182,
+    5355184,
+    5355186,
+    5355187,
+    5355188
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 264,
+  "inner_step": 271,
   "inner_steps": 0,
   "last_allreduce_block": 5351170,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60b11ae20ff8da2b89efb9df1a8755f3aa47b77651825ddba5648a29f124c373
+oid sha256:9b250cc3be267448a6b159a75a73567449909258887ee65c44437b0114111eda
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06660d7e950ff82ed1e7b3385648e706768c9b033aa95fe55451bcdc15929b73
+oid sha256:6626475e9fe9c0bffd6c375566587d9bc2c62b6e7cb90bd61d1971f616089d78
 size 4040701744