Run 4. Outer Step 42. Inner Step 16.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5560112,
-    5560115,
-    5560118,
-    5560121,
-    5560124,
-    5560126,
-    5560128
+    5560130,
+    5560133,
+    5560135,
+    5560137,
+    5560139
   ],
   "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": 5559633,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ddd3664f12034e7b029026e56de9a7dbc7f2cca935cf89127466fd7d54420d7
+oid sha256:372d0516d33dcd90d4b01bc7c3f5ee72ae924ca344a3fd2597c7ff25fbe20221
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8682460ae98d5f6f30e738d261c5baf25db6fbc919bea096b25bdd85b57ead22
+oid sha256:e2bf5f0c576dfcf52582c6ed18405dafa8fddb7f5b247525828e0065d53310ed
 size 4040701744