Run 4. Outer Step 22. Inner Step 16.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5527186,
-    5527192,
-    5527198,
-    5527204,
-    5527210
+    5527218,
+    5527224,
+    5527230,
+    5527235,
+    5527241
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 15,
+  "inner_step": 16,
   "inner_steps": 0,
   "last_allreduce_block": 5523943,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87b4c0390d4ea047d12417ef9f23b4659211f9627d8553c2ca60695a86013af7
+oid sha256:a8bc9cc6e08608bf017553b3bf1d216dd705aae8d553df8b54423d81ac3857ad
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abaa054f0abc924c88173d604583a079bd66acf8a496dd55dd1b40b2c7ffd100
+oid sha256:695c6090fd3e1d9333f058a3eeb60fecca46ecf5641ec938b0c5ed55daba9e6f
 size 4040701744