Run 4. Outer Step 18. Inner Step 12.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5521497,
-    5521500,
-    5521504,
-    5521506,
-    5521511,
-    5521515
+    5521519,
+    5521523,
+    5521527,
+    5521530,
+    5521534,
+    5521538
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 11,
+  "inner_step": 12,
   "inner_steps": 0,
   "last_allreduce_block": 5509976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:519d39565e5f4ddd6e7cf478a37f383c7669c3556cf5e6b0c1ebc5b9b46eeab9
+oid sha256:46d94e178af24a5e667602d46ac0824c5d311d117a4911dd0e8dbf1e63a66661
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67f664fc4aa7413bb6dbd207a253a0b2d9ba3083a2821b8ee4fa0519bc7429b7
+oid sha256:ce14e8026e2dc28dd5f1e5403cffd025abc413bc872aafc8e6b76a0b760edcbb
 size 4040701744