Run 4. Outer Step 32. Inner Step 16.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5543102,
-    5543105,
-    5543107,
-    5543109,
-    5543112,
-    5543114,
-    5543116,
-    5543118
+    5543120,
+    5543122,
+    5543123,
+    5543125,
+    5543127
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 15,
+  "inner_step": 16,
   "inner_steps": 0,
   "last_allreduce_block": 5529444,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82699045943a6f9eac11dad80b876edd875303e3d37db7999512f07572d683d1
+oid sha256:2485b40f1ccc982637df2fb5abe73f58470ae50a84f07a1408688b5514cefe1b
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6b2f9d7fd517b2ad663a8deb180457fee48c30b56a422c3cd9b60a76aab19bc
+oid sha256:19aa5bbe5c2e7319e99df44455e01437c2b3a08769801be9255c687672e5f0f0
 size 4040701744