Run 3. Outer Step 11. Inner Step 237.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5444146,
-    5444149,
-    5444153,
-    5444157,
-    5444161
+    5444189,
+    5444192,
+    5444196,
+    5444200,
+    5444204
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 236,
+  "inner_step": 237,
   "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:f6309d888216b0f4eb20aa29929b1112617d497053116415878db6f5bacb77b7
+oid sha256:301a6937d44473c07da053ac4c5214a8ce47e1245868b3ca955d80c6843ca6e5
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a263eaf37511701ee286645a86c3e55f0acbed28fa6eb4a23f2a4858eaad1c7c
+oid sha256:6ab1c84b7406aa50621625108bd9721d54605c98dc4507daa20dcf55db7f7695
 size 4040701744