Run 3. Outer Step 9. Inner Step 13.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5399385,
-    5399389,
-    5399393,
-    5399397,
-    5399401
+    5399432,
+    5399436,
+    5399440,
+    5399444,
+    5399448
   ],
   "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": 5398844,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fd6ba5e2f6157bc6feba9dd76e4ecf798cde086665b76bb48db3e13bf0b419b
+oid sha256:34fa00484b6e62a5015eaa75cf30cbc8c8b2d85115072fa3be9614099974dc9d
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7597a76f6a7cf2221752796c85edc1063f3e1f578e7af4e298d5fe4bb0e7337a
+oid sha256:d358c927188195e229a9f2ff4139af2a9e39b42640ece8e2c12941c8e31785b2
 size 4040701744