Run 4. Outer Step 22. Inner Step 0.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5526521,
-    5526527,
-    5526532,
-    5526538,
-    5526543
+    5526549,
+    5526555,
+    5526561,
+    5526566,
+    5526572
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 32,
+  "inner_step": 0,
   "inner_steps": 0,
   "last_allreduce_block": 5513324,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed68614c74103c6b5fd831541acd129bccea63dbdae9074cdaf4b3e98ec18e75
+oid sha256:2a9d96ac1f7fc8e1203be6ea8e9b2b2d5662f6114d0caefe8eaabff31b11d49c
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b65f3b76903593a1d878ac1e897e69866165300c21b4db25aa5ac09ed49e8885
+oid sha256:7aec539754bc0dff9b72c457da0c3bdce156729e01db9a78c0c953b6a547c5d7
 size 4040701744