Run 3. Outer Step 9. Inner Step 1028.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5421773,
-    5421776,
-    5421779,
-    5421782,
-    5421786
+    5421814,
+    5421817,
+    5421820,
+    5421824,
+    5421827
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 1026,
+  "inner_step": 1028,
   "inner_steps": 0,
   "last_allreduce_block": 5398844,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df1e5143663d63c5a3bc158b28f5eca50aed72ffab6641fc49cbcb9dc86a1986
+oid sha256:5950156f65690a2f74c7eaa0d28dae49545632ae088128eb917a27ba2f10c489
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4807d1a4bb0918110583205deec5a36b204484bc2e6bbb922cd1c624c6303cc
+oid sha256:9075c44370122b8ae3ba6e357a952e2fe652c3adb336963dc66eeb153bbc6a72
 size 4040701744