Run 4. Outer Step 83. Inner Step 26.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5673672,
-    5673689
+    5673707,
+    5673724
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 25,
+  "inner_step": 26,
   "inner_steps": 0,
   "last_allreduce_block": 5672513,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bcd33f9ba542a093cdc9489aff0d939338ca84c2f4d471af93d114e6fb50191
+oid sha256:54dbc242105208b71a34893858ec02ffcbd8262f5cd4837a3cd9d5c47c823d83
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddf37b9f2e7919585a98128c3c406b26d5a48120dee96bd901688417ac9db5b1
+oid sha256:5e3371ce186daf6b8d8727cf3ad668d7779dcf277056d3508ea302dafe94da67
 size 4040701744