Run 4. Outer Step 3. Inner Step 140.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5484792,
-    5484794,
-    5484796,
-    5484801,
-    5484803,
-    5484806,
-    5484808,
-    5484810
+    5484813,
+    5484815,
+    5484818,
+    5484821,
+    5484824
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 139,
+  "inner_step": 140,
   "inner_steps": 0,
   "last_allreduce_block": 5480541,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d6422e2bf3aa1b8c6515a643aea01d6ce6f0ea5f07571d58d721c16143d7da4
+oid sha256:f42818c2fb17441da1a1dfab1ea51899ccc6a2762ed26db6b30831d8d40c61d8
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb704421513f8ba03d34a6b2627c4f4dee98574f124c26ea767a06fd76ab1aa8
+oid sha256:6af268b986765b66ec17205321f261664e8ef688ada76c190af9fa090557b3c6
 size 4040701744