Run 4. Outer Step 5. Inner Step 5.

config.json

@@ -268,22 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5487980,
-    5487982,
-    5487985,
-    5487987,
-    5487989,
-    5487991,
-    5487993,
-    5487995,
-    5487998
+    5488001,
+    5488003,
+    5488005,
+    5488007,
+    5488009
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 4,
+  "inner_step": 5,
   "inner_steps": 0,
   "last_allreduce_block": 5487765,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63097410adb97415c7397a1a2d4f1c7d733217857ce92a3e4ff327d526f8d3d4
+oid sha256:12b266f2cfb528e0bd2aa4ad1c36cb6b276bf6c19f77aff0efb1ac821f5b692e
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d525de4e75ffcbddfbb67c26ead2c88c7804a0dd54f7832d0180ecd9c2c3e8c7
+oid sha256:0b562e999c75ebed17168c6f785f087a01f4a1088219d80708ad08681624b350
 size 4040701744