Run 4. Outer Step 20. Inner Step 12.

config.json

@@ -268,24 +268,26 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5525155,
-    5525158,
-    5525161,
-    5525163,
-    5525165,
-    5525167,
-    5525169,
-    5525171,
-    5525173,
-    5525176,
-    5525179
+    5525183,
+    5525185,
+    5525186,
+    5525188,
+    5525190,
+    5525192,
+    5525194,
+    5525196,
+    5525199,
+    5525201,
+    5525202,
+    5525205,
+    5525207
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 11,
+  "inner_step": 12,
   "inner_steps": 0,
   "last_allreduce_block": 5523943,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:395874e19aacbc5318ec33a1cd4b8dd01ed5c615a13fd4b8e8c7f2ed1aad9497
+oid sha256:193e297d6f94ad091a212fb15d93bb5666e4d52513b80b23b04436f6ef5f49d7
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e62d700ec045ebe03a94da59f77e61cd37a8b102f5c2ec0a8f2e219b6fb63b5
+oid sha256:09aec599e3f3361da96a615809a439a82372312e024b338d9a671c00d5b43579
 size 4040701744