Run 4. Outer Step 17. Inner Step 33.

config.json

@@ -268,20 +268,20 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5519877,
-    5519880,
-    5519884,
-    5519888,
-    5519892,
-    5519895,
-    5519899
+    5519903,
+    5519907,
+    5519910,
+    5519914,
+    5519917,
+    5519921,
+    5519924
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 32,
+  "inner_step": 33,
   "inner_steps": 0,
   "last_allreduce_block": 5509976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfdd703c13cfdcf13683e97a5e40318f9a64ec936bb6d1c160745cef68ac7a0a
+oid sha256:cf6b38a1fcc79088caea133107d79dcf861038021f84e060ff82234a542d530e
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca577b8aa8d7ea8a9bf9fd9f0f97d55eda2034963a06452eac98b91ba6d5e258
+oid sha256:8cfc29b20cabeb19c79f013c12eccf69447c1700f30b67f5864a427e456c31e1
 size 4040701744