Run 4. Outer Step 19. Inner Step 26.

config.json

@@ -268,20 +268,21 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5523194,
-    5523198,
-    5523201,
-    5523205,
-    5523209,
-    5523213,
-    5523216
+    5523220,
+    5523224,
+    5523228,
+    5523231,
+    5523234,
+    5523238,
+    5523242,
+    5523245
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 25,
+  "inner_step": 26,
   "inner_steps": 0,
   "last_allreduce_block": 5522512,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee9c97639d6b8ccef34c58e58096b16eb8dc0efa184b2e555b48781524b07082
+oid sha256:e93e871977bf0a6f153a485d0b38b3f9954771b04bc0df90ea5b9d8466dc2549
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c651777fbcb1a6ca7e838a7e058908a45b28de897beb93c4803a51d4c71df27
+oid sha256:58e26330743cee941d42e876d140a5fbed3f8008bdb781b57d9d1e23dee96e77
 size 4040701744