Run 4. Outer Step 55. Inner Step 3.

config.json

@@ -268,16 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5632801,
-    5632835,
-    5632894
+    5632927,
+    5632957
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 0,
+  "inner_step": 3,
   "inner_steps": 0,
   "last_allreduce_block": 5553805,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7485d6afb7104f3fc1e72926c8bdc8fd60984bd1819988cc0b4d550635d772c9
+oid sha256:b894b60d81baef6539dbc7e8cdd324b9f6598f2755325b602b26700a21529ff4
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb2d4c3ef3ffa9f347c402fedde569f6f05a20ac13b6ea2ee1d9e194494271cd
+oid sha256:585798f73c464e5c9c2d10c45535409f57a43b1d5373e8cefec47caaf3ee550f
 size 4040701744