Run 4. Outer Step 22. Inner Step 64.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5529210,
-    5529216,
-    5529222,
-    5529227,
-    5529233
+    5529239,
+    5529245,
+    5529250,
+    5529255,
+    5529261
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 63,
+  "inner_step": 64,
   "inner_steps": 0,
   "last_allreduce_block": 5506953,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:561b349ecc05a6cf4b523af566f374e7ff3b6b2160289799f7671f116e9c15ca
+oid sha256:88b6714c5cffef632a5015554a53d14190d5ae207673330cd2a821f37d7a484e
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58e589eea41ba4cab76509da31ed59049818de8a80cae49d397d7efbd2498bd9
+oid sha256:75cea1a4185cd4aa949f4da5bb7540b26d492880d464f51a423784a6ff8ff823
 size 4040701744