Run 4. Outer Step 7. Inner Step 68.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5494788,
-    5494793,
-    5494798,
-    5494803,
-    5494808
+    5494814,
+    5494819,
+    5494824,
+    5494829,
+    5494835
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 67,
+  "inner_step": 68,
   "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 sha256:579ca1a5ab7f7ed49a69dda58b50cc355ee0f0a42d95df10aab719a40b1fb0d7
+oid sha256:6aca244962cc24f76909f1e9060b926d12e62339b2f9f7003f062ece684ce8de
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edc84d520bfa070b9760001a70ebefb16c95f6232e4b7dd1ab6d511857a756f2
+oid sha256:93477a77fe96ad1e8ac29b310a42344e1fd3eed224e85214115849f05074f564
 size 4040701744