Run 4. Outer Step 53. Inner Step 28.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5577145,
-    5577147,
-    5577149,
-    5577151,
-    5577153,
-    5577155,
-    5577157,
-    5577159
+    5577162,
+    5577164,
+    5577166,
+    5577168,
+    5577171
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 27,
+  "inner_step": 28,
   "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:afd8d6e9c5f8be015a1c9837b90aa3e0692e89ded484221bb26abb26f439162d
+oid sha256:151667ef4c4c1eedd68ec7a96763d1f055992fef5c46d888e1179847df73800e
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40b16abb88c2f80a39ad214d0b6feea09e581d30b812cf01dd63f2cabbae6a7f
+oid sha256:0b30cebbc365e1e5712a9665ba065b9a58723d02e472eb7ad759906863b6c1d8
 size 4040701744