Run 4. Outer Step 20. Inner Step 13.

config.json

@@ -268,26 +268,24 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5525183,
-    5525185,
-    5525186,
-    5525188,
-    5525190,
-    5525192,
-    5525194,
-    5525196,
-    5525199,
-    5525201,
-    5525202,
-    5525205,
-    5525207
+    5525210,
+    5525212,
+    5525214,
+    5525216,
+    5525219,
+    5525222,
+    5525225,
+    5525227,
+    5525229,
+    5525233,
+    5525235
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 12,
+  "inner_step": 13,
   "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 sha256:193e297d6f94ad091a212fb15d93bb5666e4d52513b80b23b04436f6ef5f49d7
+oid sha256:fc39e117cc47ed02d33836ad4779e4b99af4b1cabb6612b245dc020eb2d4a294
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09aec599e3f3361da96a615809a439a82372312e024b338d9a671c00d5b43579
+oid sha256:0aedae576caf766e732848dc141d1c26578142f2dce2cba0e23e190d4256e18a
 size 4040701744