Run 4. Outer Step 23. Inner Step 17.

config.json

@@ -268,18 +268,24 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5531399,
-    5531401,
-    5531405,
-    5531408,
-    5531410
+    5531413,
+    5531416,
+    5531419,
+    5531421,
+    5531423,
+    5531426,
+    5531427,
+    5531428,
+    5531429,
+    5531431,
+    5531434
   ],
   "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": 5529444,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d6bb3f2c9b21c939db538f55ccbb8e6e05d8f80913bcf19d3e8fdc0988dd5fe
+oid sha256:0679446667c1e01440a23d789c7d3f8b1f566f10eab5788a477c78959568ca2e
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e67681a71f89144d29f16b80018c9a9554375240a63e5db51428da8cfff65c1
+oid sha256:9dc64340fa64bdd4ea83896b46eb7def7cca66cc9026f9b288ac4589ebfac4a7
 size 4040701744