Run 4. Outer Step 61. Inner Step 40.

config.json

@@ -268,20 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5609907,
-    5609911,
-    5609915,
-    5609919,
-    5609923,
-    5609927,
-    5609932
+    5609936,
+    5609940,
+    5609944,
+    5609949,
+    5609953,
+    5609956
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 39,
+  "inner_step": 40,
   "inner_steps": 0,
   "last_allreduce_block": 5602341,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9019dfa1efb6c13ba17c9169082c36918d6dc128c679fc8d854c2af118323198
+oid sha256:5cac73efdafe57105da23b5ff12e9d34c576db384a4e99a094942160c8341385
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:649f3577816df8c0c30fe02743bec490f64b932ffce83951cc08565ff53eacc0
+oid sha256:aec320f882406f3c0676d605d0a21ba9dffa5cb2e99f2511176e3108ab553238
 size 4040701744