Run 4. Outer Step 27. Inner Step 33.

config.json

@@ -268,18 +268,21 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5536935,
-    5536938,
-    5536940,
-    5536942,
-    5536946
+    5536948,
+    5536951,
+    5536953,
+    5536957,
+    5536959,
+    5536962,
+    5536964,
+    5536966
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 32,
+  "inner_step": 33,
   "inner_steps": 0,
   "last_allreduce_block": 5535854,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79ce0b1e28aa33f1188e0fb7eccbbb709d1d38b8a998a307eba9d4c3ed885bf5
+oid sha256:95ee7b31efc227b6ad4f4fa9e365970add4d4bacfadb17869a8af2f615685c1f
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ed7277053297ac63b38ea747bb82ac66f2be6906c037c798382e56132cc5094
+oid sha256:529d2fdddd1e6fae907d33446b62e8d28d2694f51d54d2b7866fda9265183ef4
 size 4040701744