Run 4. Outer Step 29. Inner Step 22.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5539752,
-    5539754,
-    5539756,
-    5539758,
-    5539760,
-    5539762,
-    5539764,
-    5539766
+    5539769,
+    5539772,
+    5539774,
+    5539777,
+    5539779
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 21,
+  "inner_step": 22,
   "inner_steps": 0,
   "last_allreduce_block": 5538408,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c65375d8c09ffc27cea5f27077142012e8bf8906e693009f39f1eeeeccb1aa0d
+oid sha256:73e58bc8066a02159b3b52f839bb1cc85f4f21146fb9936b569fc5157e845145
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fecb99eebbb8dbd9a3f23a406406f83199b8f4fa6c9acb648a8af5e592708c12
+oid sha256:31ee543259986d118c542e2724fc3f94ade959683af8593a62d5c85f8e560965
 size 4040701744