Run 4. Outer Step 23. Inner Step 1.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5529415,
-    5529421,
-    5529426,
-    5529432,
-    5529437
+    5529443,
+    5529448,
+    5529453,
+    5529459,
+    5529464
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 0,
+  "inner_step": 1,
   "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:d861e92a3f2d8a1b9e05c3315b01c3dc6352c87e6f4b853f3c120ddce80536e7
+oid sha256:6f01d0752c1b59433b53b864e169f861b726e3ad9fc220dbc8dafe33d4d7e34d
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:247684af8b4487a83f1105176581f7b911e8632a65d944122a8661fdf5319c51
+oid sha256:15369e8764f69ecf695adee04ec035fa5959c98ba8f81a358294872eb7ecbd7f
 size 4040701744