Run 4. Outer Step 35. Inner Step 12.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5548533,
-    5548539,
-    5548543,
-    5548548,
-    5548553
+    5548559,
+    5548563,
+    5548567,
+    5548572,
+    5548577
   ],
   "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": 5546853,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de2ca978233825caa3df4bb0bc838af7f04d561bba21a9adf0499fd2db86e523
+oid sha256:26bbd791d90679a9a581de8b1fd3b3a6710d4eb465e5b4324556e9dde6c186d2
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4476beb277a98fc312fad892de94b394d2d244f3342ded2beed49f07c12659bb
+oid sha256:37f8b171220c71366c76d245c6c08362675903b1e0facceae5bb02fab88b4749
 size 4040701744