Run 4. Outer Step 27. Inner Step 34.

config.json

@@ -268,23 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5536967,
-    5536969,
-    5536971,
-    5536973,
-    5536976,
-    5536979,
-    5536981,
-    5536984,
-    5536986,
-    5536988
+    5536990,
+    5536993,
+    5536995,
+    5536996,
+    5537000
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 33,
+  "inner_step": 34,
   "inner_steps": 0,
   "last_allreduce_block": 5535854,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95ee7b31efc227b6ad4f4fa9e365970add4d4bacfadb17869a8af2f615685c1f
+oid sha256:38011ad6990bfbee0e2f1a1e8a36abd56243833cb4dc9e0a5dd2898dbb278fb2
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:529d2fdddd1e6fae907d33446b62e8d28d2694f51d54d2b7866fda9265183ef4
+oid sha256:8b03d9a10a369b1cec01e5bf25dde9bf01241c32614c49907b9eee4dfafcbbf6
 size 4040701744