Run 3. Outer Step 6. Inner Step 271.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5389485,
-    5389488,
-    5389492,
-    5389496,
-    5389499
+    5389530,
+    5389534,
+    5389537,
+    5389541,
+    5389544
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 268,
+  "inner_step": 271,
   "inner_steps": 0,
   "last_allreduce_block": 5378990,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:165dcf58fd1c2c343b01625b9ba03b6d22cb28228009cd9c5b90d13b5e1cb645
+oid sha256:480dbafad045e0fd2c3e1cf6b553ec93c572454acdac2bbf25c4ca1f63f610bb
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24a730acdb0e74075418ec50878319e53be4f73350cb77bb34ffade0ddbda759
+oid sha256:99c7dbcce4a553a5c7bfbeceeeffe31895ab0007c421db07d18de9253e45e356
 size 4040701744