Run 3. Outer Step 11. Inner Step 23.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5432067,
-    5432069,
-    5432070,
-    5432070,
-    5432072
+    5432100,
+    5432101,
+    5432103,
+    5432105,
+    5432106
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 22,
+  "inner_step": 23,
   "inner_steps": 0,
   "last_allreduce_block": 5422706,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d26aba47b0db4cfd34f95bc72c42dd95115b0325888931a563a6f3f4603d9fdc
+oid sha256:731d47f4a68f9f0334d03b873c3daba7ce2548acc72b721a65930a001f4ba38f
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72e207aa833a02364af39840f2b363a9a4efa4659b2a58e86de170d43c131e41
+oid sha256:88cf88930e00fdd5984b65f8ffa740435ee1abcd8a33aa28399dd68b12e91c44
 size 4040701744