Run 4. Outer Step 58. Inner Step 63.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5604150,
-    5604154,
-    5604159,
-    5604163,
-    5604168
+    5604172,
+    5604177,
+    5604181,
+    5604185,
+    5604189
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 62,
+  "inner_step": 63,
   "inner_steps": 0,
   "last_allreduce_block": 5576204,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3737ea0b5868f4dc5f93360bed9f2272b86fc99c82e1ed7fd1cb045315a7b504
+oid sha256:bcee43412abf966052976711334620537b3cce167bc6b1dfcbd9ccbb58647359
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3de4413ff7223c64b6d8c3d2f5cea7709fcbc2f46c1a5754cd0b08399f74c29
+oid sha256:eb514e93ee849a47e12cdd09d7d608a5d43fc16d9abfee3ccdddde49fe7fa8df
 size 4040701744