Run 4. Outer Step 47. Inner Step 34.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5568889,
-    5568891,
-    5568893,
-    5568896,
-    5568899,
-    5568901,
-    5568904
+    5568908,
+    5568910,
+    5568913,
+    5568915,
+    5568917
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 33,
+  "inner_step": 34,
   "inner_steps": 0,
   "last_allreduce_block": 5567600,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9f2f621710e3470f7937ea2165a652b27907baab4fbddc3be7a68de7927c661
+oid sha256:2e3efb4ebaf5f08c67ab19db15aa6b0980d189b2484b6fac5f6eb24ea3590857
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:426d87e5633a533cd38d2a2f3878bbeaf6e5841aad470d8225e1db6fe0a9790d
+oid sha256:b761730103040e176ca115bbebac09fc852a600f8331fbb43a19704457a1879f
 size 4040701744