Run 4. Outer Step 90. Inner Step 21.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5682726,
-    5682756
+    5682788,
+    5682819
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 19,
+  "inner_step": 21,
   "inner_steps": 0,
   "last_allreduce_block": 5676357,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcd54363b47fff6962620a0582181035731d05b342ca5135d42a2327802c60f9
+oid sha256:e456bc1ed8b534e080e0e87ef0116260ece4abd59832eb96af9b1fd17ec59386
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:251497297725509af250fb3ded33c073c82f72ea7f5b1d7d03066a8b696d40f3
+oid sha256:166d019cb719392b5f0662d9b17d1770d31a9c3ddebe247114d8cd557c8d4d71
 size 4040701744