Run 4. Outer Step 33. Inner Step 2.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5546741,
-    5546745,
-    5546750,
-    5546754,
-    5546759
+    5546764,
+    5546768,
+    5546773,
+    5546777,
+    5546781
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 1,
+  "inner_step": 2,
   "inner_steps": 0,
   "last_allreduce_block": 5543976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d434f5e8e16eb19a539f46334a1c865b04bff511b8b0bd6e6f7682391fdb7a96
+oid sha256:589dabae5df5849a6f785dc9110361aa909f9364300d1a457136cbcb921b3ce0
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2620e5ff56b5bfd800ae59f38dba8964b833e0436ec0d36031aa52cc960eea5a
+oid sha256:c3be40c45ad2306425831ff28533367f20135d497d217a7593bf741f40b6d073
 size 4040701744