Run 4. Outer Step 23. Inner Step 23.

config.json

@@ -268,23 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5531579,
-    5531582,
-    5531585,
-    5531587,
-    5531589,
-    5531591,
-    5531593,
-    5531596,
-    5531598,
-    5531600
+    5531602,
+    5531604,
+    5531606,
+    5531609,
+    5531612
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 22,
+  "inner_step": 23,
   "inner_steps": 0,
   "last_allreduce_block": 5529444,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13bd911bbe41366872ff2dc7d8f97fff2bff632064a41d9a6f042ba1c504bf6b
+oid sha256:6b5cd72403a27c09e4d2145cfc76cd9d32a7203745c6e30c1f3620d9bf0dc99b
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0363fbd452715eed3ecf0d6a3ae674a7a0972300b184190f79cb385ff7ded6d7
+oid sha256:25e8f1acc7c1839369bee6de6e6c13df448e451c54286c48194aec4cdbf64734
 size 4040701744