Run 4. Outer Step 12. Inner Step 16.

config.json

@@ -268,20 +268,20 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5508823,
-    5508827,
-    5508831,
-    5508834,
-    5508838,
-    5508841,
-    5508844
+    5508848,
+    5508852,
+    5508855,
+    5508859,
+    5508859,
+    5508867,
+    5508870
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 15,
+  "inner_step": 16,
   "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 sha256:4aab6f26b7b8d7935e161d6c3c50b0d6df393a2bcfbe4776a5407dc4bf9c6b6f
+oid sha256:1be0ff75ee6c2280290f41327bdd79d6913df0dc878641cf004c7daea8de9863
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f022e91dcfea568d9cd3b592d04505ffa7f502d4288ebc38fd0679ac37878d8
+oid sha256:995d890f1cedb4a9a1491297d6c31566d119984a141b7192f5f2f90fee3e75a0
 size 4040701744