Run 4. Outer Step 43. Inner Step 16.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5563281,
-    5563285,
-    5563290,
-    5563294,
-    5563298
+    5563303,
+    5563307,
+    5563312,
+    5563316,
+    5563320
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 15,
+  "inner_step": 16,
   "inner_steps": 0,
   "last_allreduce_block": 5560919,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:639c67b357a7b36b150a3f74aa5c175574aedfe72efa66550a949d35af757e31
+oid sha256:ea7079731da245b8e58ac4b6b80f1bac75415e609c45a39c7086867d0a830bcf
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61615c1050aaef236c5ea5e4a9ac658ade524333209e40364c2d5fe2189d750a
+oid sha256:eb3f346b5b626cb7892838ff79fb6176b2cb9995d9a191bd237c0e70e10369c5
 size 4040701744