Run 4. Outer Step 20. Inner Step 27.

config.json

@@ -268,28 +268,27 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5525362,
-    5525365,
-    5525366,
-    5525368,
-    5525370,
-    5525371,
-    5525373,
-    5525374,
-    5525376,
-    5525377,
-    5525378,
-    5525380,
-    5525382,
-    5525383,
-    5525385
+    5525386,
+    5525388,
+    5525390,
+    5525391,
+    5525393,
+    5525394,
+    5525396,
+    5525397,
+    5525399,
+    5525400,
+    5525401,
+    5525403,
+    5525404,
+    5525407
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 26,
+  "inner_step": 27,
   "inner_steps": 0,
   "last_allreduce_block": 5523943,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e219ec3ac03f16d8de031842fe7794f9e1efce2dfb6e02c31a54969acff87cd5
+oid sha256:9f93899c987ab034866b43232b47e14a0456993aa5fa8545bb9c906e8b7772e9
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82106756061d7b601ad52113a139e306aaa253048cf38f0e6488bb65f6252be8
+oid sha256:4f46c0ebbcdf5c7174dc68e482bbad3eaece4cd63a5d6804d5efd6bef26aa41f
 size 4040701744