Run 4. Outer Step 18. Inner Step 0.

config.json

@@ -268,19 +268,20 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5520960,
-    5520964,
-    5520967,
-    5520971,
-    5520975,
-    5520979
+    5520982,
+    5520986,
+    5520990,
+    5520994,
+    5520998,
+    5521001,
+    5521006
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 70,
+  "inner_step": 0,
   "inner_steps": 0,
   "last_allreduce_block": 5509976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14ba97af7b68962e9b373e391044f70387a27c0858262e62536efb4f24b9faec
+oid sha256:026d9b8041d0600bcbf1927b2236891dcc091f0994bf6d96cc86092286cf7e8c
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6073aaaad1d4d250ec3d828df5144759e0ee310a982ef88a6116c9d084ea213d
+oid sha256:19be2872f794ee09527fac35636314a781b38e3cf8bf87a02964f83bfd135784
 size 4040701744