Run 4. Outer Step 58. Inner Step 28.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5603240,
-    5603243,
-    5603245,
-    5603248,
-    5603251,
-    5603253,
-    5603255
+    5603256,
+    5603259,
+    5603261,
+    5603263,
+    5603266
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 27,
+  "inner_step": 28,
   "inner_steps": 0,
   "last_allreduce_block": 5602341,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d533e73595bff3c45366b686344ee435c3b448c46903705b568e1ee5cd609aa6
+oid sha256:82b055bf1498a009c840eb4f7e9eddfb92616eba3bd588a6ae942b1b2971ed86
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82391d915d51fb871fc93e97f70f16abfed93a06716fafc3be50a22704ffe9b7
+oid sha256:5a8bf441d254e86d95a0f2a5ad34b1d8b6fc31d5169c07a1ab6dabc98eb16983
 size 4040701744