Run 4. Outer Step 22. Inner Step 10.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5527007,
-    5527014,
-    5527021,
-    5527028,
-    5527035
+    5527043,
+    5527050,
+    5527056,
+    5527063,
+    5527069
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 9,
+  "inner_step": 10,
   "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 sha256:621fa689dbe622783999df2cb8bd4b26f83f5faf4244423411f70c9995ff62c1
+oid sha256:390cc6e640a95d6ee2b744c3fcb7da2d7d71976cbe5bb0a33687dc42c9da4a12
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eace81fcb44526d8c0bec8035e14035239e81f3009765c80c5e6627445b4f69b
+oid sha256:ee21b0f9643898caf77120ba2b69cccddd207983758ed2623331d376699a6e9f
 size 4040701744