Run 4. Outer Step 10. Inner Step 111.

config.json

@@ -268,18 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5506713,
-    5506717,
-    5506721,
-    5506729,
-    5506733
+    5506737,
+    5506741,
+    5506746,
+    5506749,
+    5506753,
+    5506756
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 110,
+  "inner_step": 111,
   "inner_steps": 0,
   "last_allreduce_block": 5492224,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9840ed47d33a9a031b33f7d50a30a71a22c57de36955aa4ddc3b1190f3794f00
+oid sha256:a695203d18c9dce6c48f3674e43dcd6b3cc17c7e6826403f00b562693b7e4a8b
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51b366466ba7ab576e43934d2ecca9c3d916cbb099e025b4dd3255def1fc97a5
+oid sha256:4545044376b63bae744d2c915fc8a61b46522d7dfd4eda66b04a5d2edbade523
 size 4040701744