Run 4. Outer Step 33. Inner Step 25.

config.json

@@ -268,18 +268,24 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5544723,
-    5544725,
-    5544726,
-    5544731,
-    5544733
+    5544736,
+    5544738,
+    5544741,
+    5544743,
+    5544745,
+    5544747,
+    5544748,
+    5544750,
+    5544752,
+    5544755,
+    5544758
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 24,
+  "inner_step": 25,
   "inner_steps": 0,
   "last_allreduce_block": 5543976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc0590b68fcf74d2658d4af274439a96fb6bfb00f6833153b286a5648fcb8a1a
+oid sha256:8c571937a5f0bfcdf0fa5db866eec936abf9bc0c47d21bde4322fea427bbd741
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:868588e67b5ff5965d51ebfc8e0a70ff8cd168b0d175b60bc5fee73e37044080
+oid sha256:7fa9696d62994bbe52b95b4195b65c7b46727a5b16194feb46f11f678981dea8
 size 4040701744