Run 4. Outer Step 3. Inner Step 133.

config.json

@@ -268,18 +268,25 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5484682,
-    5484686,
-    5484688,
-    5484690,
-    5484693
+    5484696,
+    5484698,
+    5484700,
+    5484703,
+    5484705,
+    5484706,
+    5484709,
+    5484711,
+    5484712,
+    5484715,
+    5484717,
+    5484719
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 132,
+  "inner_step": 133,
   "inner_steps": 0,
   "last_allreduce_block": 5477809,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2f9fa0f3c4d76ff485a9b6ac346794c94b1457eeff8a0763ce7851bf9afe208
+oid sha256:43e022ab049d7909b48f787bde81b6f807a39cbd520e32481adb48d825f834dc
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84efd8ba2b1355db5abce7cbbe6f3b0d1afb7d8aac3d382b7cc1b0ccd7bb43f6
+oid sha256:a42ae0507743a12b72d7065b9acbe334a14ccacb76203d5c4f48fca4ec057d19
 size 4040701744