Run 4. Outer Step 33. Inner Step 25.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5544752,
-    5544754,
-    5544757,
-    5544759,
-    5544762,
-    5544765,
-    5544767
+    5544770,
+    5544773,
+    5544775,
+    5544779,
+    5544780
   ],
   "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 sha256:354772bb9d70500b226f1665b550d3eeedd15a2d2d7102ee10ab61e481a6a628
+oid sha256:f7d8b16e68892b99e3afcdc6da9f303729431d0581f29fa0d37d12da63410ca0
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1892ed6ba2049c8caa0410bb05c2f7f69caf0d5697fa5d29fffb84efb64da6c
+oid sha256:24036ae121f3ce747eb69027a317fe2f960a5475d190ea3fed11c748d64450ca
 size 4040701744