Run 4. Outer Step 23. Inner Step 10.

config.json

@@ -268,22 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5531191,
-    5531193,
-    5531196,
-    5531198,
-    5531200,
-    5531203,
-    5531205,
-    5531207,
-    5531209
+    5531212,
+    5531215,
+    5531217,
+    5531219,
+    5531222,
+    5531224,
+    5531227,
+    5531229,
+    5531231,
+    5531233
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 9,
+  "inner_step": 10,
   "inner_steps": 0,
   "last_allreduce_block": 5529444,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6219780ea195085dfbd0310ad04ae6d2370c6917f349c2455bab257ef7e4dfc8
+oid sha256:783749c65473d0d2aa6dd2e3fc6e2b55dbf0dbed9393185cb83ce86174d1e6a5
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4783cf9c3f9bfb26c48c0d4163be7b7d3cd25431a91fa3e7c02ad50e49781692
+oid sha256:7501eace35fccea321429d08b3952cfc86890498d85218e36454800261a94b29
 size 4040701744