Run 3. Outer Step 11. Inner Step 24.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5432112,
-    5432114,
-    5432115,
-    5432117,
-    5432118
+    5432148,
+    5432150,
+    5432152,
+    5432153,
+    5432155
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 23,
+  "inner_step": 24,
   "inner_steps": 0,
   "last_allreduce_block": 5422706,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ca3ef1bd70df94fbb72464915ca58eeef1a09908c79cfb1b9ca4c016089e3c0
+oid sha256:c12a52886dc1968ad341f13b8c84408e19226762d2dc3f6b53de4e4a8199570e
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4593c97c37504d633d964e91165d419b9789cf166fcd1ef4083b031e79c58150
+oid sha256:c62ad5e6073ff9feb4ab00d7cf19f9b70fdc33b7da8bd50779c6c99a0fc794f1
 size 4040701744