Run 4. Outer Step 32. Inner Step 17.

config.json

@@ -268,23 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5543129,
-    5543130,
-    5543132,
-    5543134,
-    5543136,
-    5543138,
-    5543140,
-    5543142,
-    5543145,
-    5543147
+    5543149,
+    5543151,
+    5543153,
+    5543155,
+    5543157
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 16,
+  "inner_step": 17,
   "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 sha256:2485b40f1ccc982637df2fb5abe73f58470ae50a84f07a1408688b5514cefe1b
+oid sha256:104beabf5595cc598aea6b3de7272656047894cf7ba1c77fa70e29f558bb42e4
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19aa5bbe5c2e7319e99df44455e01437c2b3a08769801be9255c687672e5f0f0
+oid sha256:886b2c41f5eb0e71889c839a321864ac94d3c20b248643098a6c9361e523b196
 size 4040701744