Run 4. Outer Step 11. Inner Step 23.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5507621,
-    5507625,
-    5507629,
-    5507632,
-    5507636,
-    5507640
+    5507644,
+    5507648,
+    5507651,
+    5507655,
+    5507658,
+    5507662
   ],
   "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": 5506953,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ff5840fcb13b12129a1d3b877bd6458b9f4d56622d69a5293fa977f4b7bf97a
+oid sha256:7fc606fd13313bd58f6e0531b539762b7aba3ce0f8c29936401f6dfb07290cdd
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:705773920dcf7d39744237ee6fadc01b468c742dfd0ac3815058163afca83f8a
+oid sha256:5f82162127b60f9d5b4f47459fdbc00674fb6303a6c551d47270dd89b7d126af
 size 4040701744