Run 4. Outer Step 25. Inner Step 36.

config.json

@@ -268,23 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5534464,
-    5534466,
-    5534468,
-    5534471,
-    5534473,
-    5534475,
-    5534477,
-    5534480,
-    5534483,
-    5534485
+    5534489,
+    5534491,
+    5534493,
+    5534495,
+    5534498
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 35,
+  "inner_step": 36,
   "inner_steps": 0,
   "last_allreduce_block": 5533305,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98d6b621e661602f5ffdbda065a9bc9437cc58e9ad6f86012e8195414d0ce561
+oid sha256:b6b0d02a4605f25534af916b418fbaa9aa0dc8a08aa4dfcf792c7f293483847e
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a06e4f9f00d8297b61589b340c7de0862316948acfdf14071514e3512dcddf7c
+oid sha256:6d466025bfc2edbcb5bc1f1878c61168c3ae41ac45381476185e910ff173714b
 size 4040701744