Run 4. Outer Step 2. Inner Step 17.

config.json

@@ -268,22 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5480573,
-    5480577,
-    5480580,
-    5480581,
-    5480583,
-    5480585,
-    5480587,
-    5480590,
-    5480592
+    5480595,
+    5480596,
+    5480600,
+    5480602,
+    5480604
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 16,
+  "inner_step": 17,
   "inner_steps": 0,
   "last_allreduce_block": 5477809,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0f846e2c8b23dba72daf1ec4a35ea32258d3bb6e698b252a8d05b72378a6016
+oid sha256:acb2bf55a9f185cf73b13f14001d4ba823f4b2d9ded661508a0bc512b445ee59
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:454ea44cd20a8e1b934b2757fc13a94a4c3ee74165a29c524c048379ecceb468
+oid sha256:7c518bd48411607ec241ce7ba993a8e421906c0b17ce1a0e5b5334512eddb88e
 size 4040701744