Run 3. Outer Step 9. Inner Step 1026.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5421729,
-    5421733,
-    5421736,
-    5421740,
-    5421743
+    5421773,
+    5421776,
+    5421779,
+    5421782,
+    5421786
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 1024,
+  "inner_step": 1026,
   "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 sha256:40f75804a32e5e643087938a7e43f72548940d146ec0f097037ba119fa2357a9
+oid sha256:df1e5143663d63c5a3bc158b28f5eca50aed72ffab6641fc49cbcb9dc86a1986
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43dc920657d46698a2ae3d6334cec75adbff8179f659767dae4bae8b15a59fd7
+oid sha256:f4807d1a4bb0918110583205deec5a36b204484bc2e6bbb922cd1c624c6303cc
 size 4040701744