Run 3. Outer Step 10. Inner Step 0.

config.json

@@ -268,18 +268,17 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5421896,
-    5421899,
-    5421902,
-    5421910,
-    5421913
+    5421940,
+    5421943,
+    5421947,
+    5421950
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 1031,
+  "inner_step": 0,
   "inner_steps": 0,
   "last_allreduce_block": 5398844,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa75f6a313ebd30c9a5544210566f84308d246e0822286ae2e23fc426fe960d1
+oid sha256:3696f16251e4cf140b2e7efc156ee8e9ef13117a257cd9db0b37053f02f9f6b0
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:faa457f8889957d7152e4a48844d6ead7d9ac7711ee578f30a077ec78ff84e79
+oid sha256:e1d86956a834f241b8448f6c09032d2415839cee8d2803df93472f7f0b43c4b5
 size 4040701744