Run 4. Outer Step 63. Inner Step 61.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5613872,
-    5613873,
-    5613874,
-    5613874,
-    5613874
+    5613875,
+    5613875,
+    5613876,
+    5613876,
+    5613876
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 60,
+  "inner_step": 61,
   "inner_steps": 0,
   "last_allreduce_block": 5611658,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73f37466bbbb2d7531bae8e9d367134a8f9d607f57a0a0bb9ac61255c6dd375b
+oid sha256:4d0ad15300b4ba5580da5f6c0ccc41ef1056f652458cb06352697cf98890d7c8
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1abbbaad0545aceb6d7ac66299e8a91a17462116deae1f12034c04ac473b9ca9
+oid sha256:1095b93d57f8dbcd0f2c73017da77e274eb674309356e1c648af7420fc29794c
 size 4040701744