Run 3. Outer Step 12. Inner Step 69.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5470083,
-    5470088,
-    5470092,
-    5470096,
-    5470100
+    5470137,
+    5470142,
+    5470147,
+    5470153,
+    5470157
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 67,
+  "inner_step": 69,
   "inner_steps": 0,
   "last_allreduce_block": 5450451,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5576e1ac1cdd6beffe6619a65dea5e578e09973e5b886513dd98021720721f19
+oid sha256:ec9b2d1886d00de1420dba3c929564011b27d8151ddbffae026b29c70b530d08
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e26c514618a3d5b76e57ed7c9bea90ffb7cff45283744db78ef01da98a6f3ff5
+oid sha256:0558083e33fa9d769b29209d80aabf643f78cfb4dcc5cf1f4c6f3b3fbc5460a3
 size 4040701744