Run 4. Outer Step 27. Inner Step 36.

config.json

@@ -268,23 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5537030,
-    5537032,
-    5537034,
-    5537037,
-    5537039,
-    5537041,
-    5537044,
-    5537046,
-    5537047,
-    5537049
+    5537050,
+    5537052,
+    5537054,
+    5537057,
+    5537060
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 35,
+  "inner_step": 36,
   "inner_steps": 0,
   "last_allreduce_block": 5535854,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2c7538749c51d43fee6e996e2125cf1b2dd1f932b99922208a8226528b599bb
+oid sha256:1154cb2520202f333dd04fb93db7d6b82c0a2ad6c0499df900e115f272872f30
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c26b3e0d2d78958782736d36c236e38e5b292436ca901ac506d233b9e2b09a8b
+oid sha256:f1d6fb3b2a16b5ae5bd770c2ea3a018839d9e0813e6fc3d7131b118666e65763
 size 4040701744