Run 4. Outer Step 23. Inner Step 24.

config.json

@@ -268,18 +268,22 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5531602,
-    5531604,
-    5531606,
-    5531609,
-    5531612
+    5531615,
+    5531619,
+    5531622,
+    5531624,
+    5531626,
+    5531629,
+    5531631,
+    5531634,
+    5531636
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 23,
+  "inner_step": 24,
   "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 sha256:6b5cd72403a27c09e4d2145cfc76cd9d32a7203745c6e30c1f3620d9bf0dc99b
+oid sha256:44a2931bfd66f4c1bdb4bb6bb6f647a5e95faa994afd22040d7cc5a94d622b1b
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25e8f1acc7c1839369bee6de6e6c13df448e451c54286c48194aec4cdbf64734
+oid sha256:c56ee13ba7b583b9d6208d2f92fd8d5d08beb1595cbbd9b164035ea213350eea
 size 4040701744