Run 3. Outer Step 10. Inner Step 33.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5422668,
-    5422671,
-    5422674,
-    5422677,
-    5422681
+    5422709,
+    5422712,
+    5422715,
+    5422718,
+    5422721
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 31,
+  "inner_step": 33,
   "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 sha256:61a5152d6c6c02e1d5bab21a9748581a21c4a208d8f3990f94ea8c0f422c4c86
+oid sha256:db075bf0553d79d4981aa818f9f67e772855671350322cb0a2e87098b9c25862
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4ad11171c5af24864c09639e4ba8e42da808c872c8207f87745b323cb30cb35
+oid sha256:cb54b581eafed88596a7cfa93eff601da3bbc9f61953f2cefb2f34b9ccf906b4
 size 4040701744