Run 3. Outer Step 9. Inner Step 1024.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5421689,
-    5421693,
-    5421696,
-    5421699,
-    5421702
+    5421729,
+    5421733,
+    5421736,
+    5421740,
+    5421743
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 1022,
+  "inner_step": 1024,
   "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 sha256:499d3dac6cd91c84bf14d4b92eb1ab16a6e379b42760d7ccc5c9ff4c035cdfd9
+oid sha256:40f75804a32e5e643087938a7e43f72548940d146ec0f097037ba119fa2357a9
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44746cbc78378b6f468ec8b9d08cb481dea09ba5385c1dda5ae61ac1cf391762
+oid sha256:43dc920657d46698a2ae3d6334cec75adbff8179f659767dae4bae8b15a59fd7
 size 4040701744