Run 4. Outer Step 4. Inner Step 10.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5486686,
-    5486689,
-    5486690,
-    5486694,
-    5486697,
-    5486700,
-    5486703
+    5486706,
+    5486708,
+    5486711,
+    5486713,
+    5486715
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 9,
+  "inner_step": 10,
   "inner_steps": 0,
   "last_allreduce_block": 5485540,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73532076f095037232d71e042ef576e4a43ab6db076a079eeb3060439cb1fe5c
+oid sha256:a725e00d077db4133fc75bef370fbf2d6904b9e9f1ced371dceabd6291006eef
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12f9996ddb4d5fc39b50630c59397028237f79728754085c139415fe2726052b
+oid sha256:63ab880a594022f8c389d938da406acbe492114765bc7b5eee86d04c9f211083
 size 4040701744