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": [
-    5470136,
-    5470140,
-    5470142,
-    5470144,
-    5470146
+    5470181,
+    5470182,
+    5470184,
+    5470186,
+    5470189
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 68,
+  "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:b53bf226402862fbfa5902871a9cd08f446c460e27bf92957a9976b1c5ed82e8
+oid sha256:cb8f1647bf91221dcc2d1f1c69ddd14d73769b09d94020335976026d59b57127
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0f87920e5ab29a2c2cd22f2323acff5733670fc241c90e9360f1817a30a8792
+oid sha256:b5c3f9dc20562f0d1c8a8a725bba43b1b782fe3e6ce00272eed660bd76144143
 size 4040701744