Run 4. Outer Step 2. Inner Step 16.

config.json

@@ -268,22 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5480538,
-    5480541,
-    5480544,
-    5480546,
-    5480548,
-    5480551,
-    5480552,
-    5480554,
-    5480556
+    5480559,
+    5480562,
+    5480565,
+    5480566,
+    5480568
   ],
   "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": 5477809,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:903aa08a3b68743993bbd7fbb63f386f6c64d300827f915050e77f732fecbb87
+oid sha256:87c62b3e7eba549e5f402854fc9f196f0aa6ab759b64ddc8a928b784cc39a89f
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f16135c4c4a1316ceb272d13ddf4ef397788ab93381aade03c35f004e71658a
+oid sha256:8f0c4554da331be6d62be40508f5a97b23399b72488cf4107eec80d96d9a06a8
 size 4040701744