Run 4. Outer Step 22. Inner Step 66.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5529295,
-    5529301,
-    5529306,
-    5529312,
-    5529317
+    5529323,
+    5529329,
+    5529334,
+    5529339,
+    5529345
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 65,
+  "inner_step": 66,
   "inner_steps": 0,
   "last_allreduce_block": 5506953,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d95c90ecb2a2d7a47511bfa5f3227ff53ff4510e57f84e4ce763dee4a567973d
+oid sha256:c2a8685ac8e4f98ad462f788cb26de4661a5762cc7e860ec278c24871e375479
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acccb385b570574c0e7aaa04af614df12e479839f51c0a55d161051c279887dd
+oid sha256:93a6f564dbdfcf00e698e35b3af8e3f5c660af324340fd7cb851ffbbf860be38
 size 4040701744