Run 4. Outer Step 28. Inner Step 37.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5538264,
-    5538267,
-    5538269,
-    5538270,
-    5538273,
-    5538275,
-    5538277,
-    5538279
+    5538282,
+    5538285,
+    5538287,
+    5538288,
+    5538289
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 36,
+  "inner_step": 37,
   "inner_steps": 0,
   "last_allreduce_block": 5537093,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcd31903348845444e0e6463da832703727c396ceb45979c5234e4bc44ef43c2
+oid sha256:662be9ac4de6f01c14ed09451beb9e26a90499da0fbafb6f2c878489f14e4742
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:531d43f20d08283c7aca28861d1fb44fe1c42950cb43d4a0997cd0e6d9d63d36
+oid sha256:4be568fd09fbc0e917e087838053bd0d964f36020b44320323acce425e14e2b3
 size 4040701744