Run 4. Outer Step 22. Inner Step 63.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5529182,
-    5529188,
-    5529193,
-    5529198,
-    5529204
+    5529210,
+    5529216,
+    5529222,
+    5529227,
+    5529233
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 62,
+  "inner_step": 63,
   "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 sha256:04fee594acf0aa6975f1eda7211f2ff4dcaec4cbf402ba36a8507d2a382d5e0d
+oid sha256:561b349ecc05a6cf4b523af566f374e7ff3b6b2160289799f7671f116e9c15ca
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c5852e3dee7946c8cbf752e3faa15553b8226b42a7c8775e70daa6582d9ce5d
+oid sha256:58e589eea41ba4cab76509da31ed59049818de8a80cae49d397d7efbd2498bd9
 size 4040701744