Run 4. Outer Step 18. Inner Step 13.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5521519,
-    5521523,
-    5521527,
-    5521530,
-    5521534,
-    5521538
+    5521542,
+    5521546,
+    5521549,
+    5521553,
+    5521556,
+    5521560
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 12,
+  "inner_step": 13,
   "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 sha256:46d94e178af24a5e667602d46ac0824c5d311d117a4911dd0e8dbf1e63a66661
+oid sha256:098a3dbb3d367fdd4813320feb29cbee193d20d7af095ff6155be62851c87e6c
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce14e8026e2dc28dd5f1e5403cffd025abc413bc872aafc8e6b76a0b760edcbb
+oid sha256:ac667a96365eec2f5571798d2cb36372b961ae8a118e83147b89b2d4798e6a65
 size 4040701744