Run 4. Outer Step 29. Inner Step 40.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5539770,
-    5539771,
-    5539774,
-    5539776,
-    5539779,
-    5539781,
-    5539783,
-    5539785
+    5539787,
+    5539790,
+    5539793,
+    5539795,
+    5539798
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 39,
+  "inner_step": 40,
   "inner_steps": 0,
   "last_allreduce_block": 5538408,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eceae8b67f6c3f2b49ae0865eaa71dde5423c7e004a37d419465b2282b7537c7
+oid sha256:a6f605c8b4f46fe2b40057db63184e858209280ee15bb9f694948fabab3373a1
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7e07f210769f3b946e36cea48960414731dedb96a576f38c209d418c601f059
+oid sha256:3a9d611f2f5fe991ea2e948c9d895c1bfb658c6c2416ade3fd726ee1405bfd0d
 size 4040701744