Run 4. Outer Step 33. Inner Step 16.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5544472,
-    5544475,
-    5544478,
-    5544481,
-    5544483,
-    5544485,
-    5544487
+    5544489,
+    5544492,
+    5544495,
+    5544498,
+    5544499
   ],
   "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": 5543976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ecefa3122f2f0e8d27c70645725429f70223e0b9e21ef7e208e1273dfe35cd6
+oid sha256:10eebb89c38ffc9ce94e126bad6575bc0c461024041e3b54a15362f9b14cdd1e
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc98ea6e20e733486d7a3f99a536d8e3d70c8a076f77d57daecfe2925e4188cd
+oid sha256:f410b3441e2a69e86c578cbf818a5bd0adbff71763423ce7953679087b9c3dd7
 size 4040701744