Run 3. Outer Step 11. Inner Step 229.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5443928,
-    5443932,
-    5443936,
-    5443940,
-    5443943
+    5443972,
+    5443976,
+    5443980,
+    5443983,
+    5443987
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 227,
+  "inner_step": 229,
   "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:c3e828043e6af726860d63a133c1770c898a474565c3c1358f70541f573d1b7c
+oid sha256:c007c664a7ecdbdff7629813cf4c0a34fbbe48c153daf02d4269f89f8b192cc2
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b02a6a620f957c68d155743d4fdc6fd9f3eab3046c5b1588c13b2279ada41324
+oid sha256:a96df44f9e83b2823a6383bab3ed00fa7b62fa487ca09898c7d3f8072c7bde0e
 size 4040701744