Run 4. Outer Step 22. Inner Step 17.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5527248,
-    5527254,
-    5527260,
-    5527267,
-    5527273
+    5527280,
+    5527286,
+    5527292,
+    5527298,
+    5527304
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 16,
+  "inner_step": 17,
   "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:a8bc9cc6e08608bf017553b3bf1d216dd705aae8d553df8b54423d81ac3857ad
+oid sha256:c773bfa20eaf3932a5254f32248b0136389c5f06e6e26cb9d9ab49bf6bfb8bde
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:695c6090fd3e1d9333f058a3eeb60fecca46ecf5641ec938b0c5ed55daba9e6f
+oid sha256:0d92c3bf72f8d4f719c3031ce3bde1b1f53776151764d5adcc8b150d3985143d
 size 4040701744