Run 4. Outer Step 17. Inner Step 17.

config.json

@@ -268,20 +268,20 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5519483,
-    5519487,
-    5519491,
-    5519494,
-    5519498,
-    5519501,
-    5519505
+    5519509,
+    5519512,
+    5519516,
+    5519519,
+    5519523,
+    5519527,
+    5519530
   ],
   "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": 5509976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40be0b0833b0c18ddb811b4246a336aa05c41ab25477fc71a59faa8263f6700a
+oid sha256:c9ced29185dd8862f7a7ba345e255ca95fc8df06797bec39b543f7a548355c83
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26bf6ca27dd20c0928adc0ad22d1e8af0099677c3f1498294d5de0e826420667
+oid sha256:2ef3df08992a4e5b9ec20977638355694e358e26d5ccca0c706110ec086b5932
 size 4040701744