Run 4. Outer Step 3. Inner Step 177.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5485430,
-    5485434,
-    5485438,
-    5485441,
-    5485446
+    5485450,
+    5485454,
+    5485458,
+    5485461,
+    5485465
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 176,
+  "inner_step": 177,
   "inner_steps": 0,
   "last_allreduce_block": 5480541,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4eafdcae5096041debe2d359dfd5064fca2f8468b7abaa431b90f96bee588e55
+oid sha256:6f98296264bf10e50b4f036fcd476940f235d7381966392da17d748bd07f2135
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d43eb4cb9ad76260e6eb6f00def4710b9eef5d1c448e713fc62f93a3d8f545c8
+oid sha256:56b01f0d79a9a076a6dfd2248edc79ca1cfc43202675bf8eb9ad6e5294ebe1ab
 size 4040701744