Run 4. Outer Step 21. Inner Step 26.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5526390,
-    5526396,
-    5526402,
-    5526408,
-    5526414
+    5526422,
+    5526428,
+    5526434,
+    5526441,
+    5526447
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 25,
+  "inner_step": 26,
   "inner_steps": 0,
   "last_allreduce_block": 5523943,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81d2a275bad1df13f57c23a6ee531e5160dd116a360c80fa0b7dc24e899241e6
+oid sha256:7508b105aa9c205ba7a3982f195e0a9d7f34c390fad384312e8f342c2210b0da
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:260ffde445693766e813b7d760d68c8480d161512c259ac888121e987aed54fa
+oid sha256:5354cd9c7840a9ff2aabfc3bf065e69fe735b7b898cae70e3fb15792ac106b64
 size 4040701744