Run 4. Outer Step 22. Inner Step 12.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5527028,
-    5527035,
-    5527040,
-    5527047,
-    5527053
+    5527060,
+    5527066,
+    5527072,
+    5527078,
+    5527084
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 11,
+  "inner_step": 12,
   "inner_steps": 0,
   "last_allreduce_block": 5523943,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ad8952aa2ca8f2918a6cbbdca9abc897148296c1a2ab0ee27412d69701319c3
+oid sha256:6bcc9e345dca22422a842e0d5311d7a41b98d39c1f604c201dd72f8218fcdeaa
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe7e8692ca8c19534a4a4e943e6633d54dfae7a354b3179eee210fd3fdd7bacb
+oid sha256:d02ca0b7f7bba5614e744fe7d66fec69f38971121abfc6db930931d58d402923
 size 4040701744