Run 4. Outer Step 23. Inner Step 14.

config.json

@@ -268,24 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5531318,
-    5531321,
-    5531323,
-    5531325,
-    5531327,
-    5531331,
-    5531332,
-    5531334,
-    5531336,
-    5531338,
-    5531339
+    5531341,
+    5531343,
+    5531346,
+    5531348,
+    5531351
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 13,
+  "inner_step": 14,
   "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 sha256:4cb5aa16022ee110b252527bd642b8c3a80651e53d6383576580017e839b6274
+oid sha256:f2169b4c109fd524d10e7eb57f864d968fd0fc2dbfe7b0a4038cc765ef9f38ff
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bea4a0f9e3d8d900ad95a3dd3a6444a54f5c7b666b246e0c2253a04223a55b7
+oid sha256:c783223b48c378df5739b47fbda52dcccc09a3515da755a0825bf4fe20c84f94
 size 4040701744