Run 4. Outer Step 62. Inner Step 24.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5611289,
-    5611293,
-    5611298,
-    5611303,
-    5611307
+    5611313,
+    5611317,
+    5611322,
+    5611327,
+    5611331
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 23,
+  "inner_step": 24,
   "inner_steps": 0,
   "last_allreduce_block": 5605539,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4da07ae69d9195765bc5aef297b461e12f5606a12f838f0cc9c18d857d30bf56
+oid sha256:871a80febe5fe4189efc41f7354eb862d5fca160bd1ea4500dad9846fbff8cb3
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d1192224237090873af78aa543922fd972cf4898a5c758da874c7b58a62f5ec
+oid sha256:a838db723f89a713f6005068206999fb1137d6012b985d63dd75b7a68f6dea49
 size 4040701744