Run 4. Outer Step 15. Inner Step 63.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5514820,
-    5514824,
-    5514827,
-    5514831,
-    5514835,
-    5514838
+    5514843,
+    5514847,
+    5514850,
+    5514854,
+    5514858,
+    5514862
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 62,
+  "inner_step": 63,
   "inner_steps": 0,
   "last_allreduce_block": 5511564,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91a629939f2aa36848bec4c080841b31982e9103ed15fe8c0ecd3a505f8dd2de
+oid sha256:12d4552fe87bb5091c0038a3f9252a9f2ef59311a5319c26ddfaac87629c461b
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d34123ed4affa35e19c179d292e689ea57fd950a7fb83daa7ac78a41f7962972
+oid sha256:977adbd1ed3b76eda107953b402d120c5ada23e497681f46fa95076134b23038
 size 4040701744