Run 4. Outer Step 23. Inner Step 0.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5529351,
-    5529357,
-    5529362,
-    5529368,
-    5529373
+    5529379,
+    5529385,
+    5529390,
+    5529396,
+    5529401
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 67,
+  "inner_step": 0,
   "inner_steps": 0,
   "last_allreduce_block": 5506953,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61be43a90fb992ec86b167f99e3290efd567ac2f90a336758b56a613bc697edf
+oid sha256:d861e92a3f2d8a1b9e05c3315b01c3dc6352c87e6f4b853f3c120ddce80536e7
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a214bbf93832087f94bf4a4cd4bfc6311a329efd6369a514556c2eb013045358
+oid sha256:247684af8b4487a83f1105176581f7b911e8632a65d944122a8661fdf5319c51
 size 4040701744