Run 4. Outer Step 7. Inner Step 161.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5499127,
-    5499130,
-    5499132,
-    5499134,
-    5499136,
-    5499137,
-    5499140,
-    5499141
+    5499144,
+    5499146,
+    5499148,
+    5499151,
+    5499154
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 160,
+  "inner_step": 161,
   "inner_steps": 0,
   "last_allreduce_block": 5492224,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:355424566345e9327229de13c08e0393b2dcda968f6ee0d8387190e9ff3e98eb
+oid sha256:654272d8ac925f332aafa45227785aa89b0458a4bb3e07b31e71d07f5141d010
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0143e0c433d304f616428f77f449eb3c43dbd41815b18cf2b6384e8f93f786a8
+oid sha256:7ad82a0fcd69a03edaef4dbe09fb0d73e95e1055b494ba64bfd806ac47ebca5a
 size 4040701744