Run 4. Outer Step 21. Inner Step 29.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5526407,
-    5526413,
-    5526418,
-    5526424,
-    5526429
+    5526435,
+    5526440,
+    5526446,
+    5526452,
+    5526457
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 28,
+  "inner_step": 29,
   "inner_steps": 0,
   "last_allreduce_block": 5513324,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:801896c7536635820cc3a93f935b7264cab61aa6f06551178171b8ac44e61ed3
+oid sha256:57670b85bd402c84c5193cda847208c70f888cfda0f16146d176413c64e5bcd5
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:913695c72e7db39322144d7fd914bdb61f96a320f62b880517a1f48e053a966f
+oid sha256:307a163d0cd24a44f4b39c92676591b9945f3abf1278416f67a72f996e2f836c
 size 4040701744