Run 4. Outer Step 21. Inner Step 18.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5525971,
-    5525977,
-    5525982,
-    5525988,
-    5525994
+    5526000,
+    5526006,
+    5526011,
+    5526017,
+    5526023
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 17,
+  "inner_step": 18,
   "inner_steps": 0,
   "last_allreduce_block": 5513324,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a748e980b8c8e1164cc113c572ba9a13cb294e6b72b38c875ecbf634a35ea017
+oid sha256:2f284892571ea86e6d7a50191125c7feed01c4bebb30f0bed9bb538b5cf59983
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9006a54ba0cc153a4ac4f055c04de1124e94053b1d942ef4c5cb6156a6f8bf5
+oid sha256:309e114fc071a24f63ab9332cd56f27136fde485ffb890dc0231e5bf2cd0ada1
 size 4040701744