Run 4. Outer Step 33. Inner Step 23.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5544690,
-    5544692,
-    5544695,
-    5544697,
-    5544699,
-    5544701,
-    5544704,
-    5544706
+    5544709,
+    5544712,
+    5544714,
+    5544718,
+    5544720
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 22,
+  "inner_step": 23,
   "inner_steps": 0,
   "last_allreduce_block": 5543976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7032bbe17c7cdea09f8031973216b609af5dce5a7bca686c2c5fb84292751f73
+oid sha256:dacf631208f25608c1b9a19eb04bb758199623ace8ed415a88ca7e28a9e63825
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ec202fc0c6de6950e34f15896d57890b8037efbf9e837f5da2ea31e0e3241cc
+oid sha256:4c9730d6b03581db7668baeeb46dfbf6a26071e8d32710d81d9794d800b7277b
 size 4040701744