Outer Step 0. Inner Step 13. Batch Size 168

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5130105,
-    5130111,
-    5130116,
-    5130124,
-    5130134,
-    5130141,
-    5130162,
-    5130169,
-    5130178,
-    5130187
+    5130229,
+    5130237,
+    5130246,
+    5130253,
+    5130266,
+    5130274,
+    5130281,
+    5130289,
+    5130300,
+    5130318
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 5,
+  "inner_step": 13,
   "inner_steps": 0,
   "last_allreduce_block": 5072405,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb5e9dbd8e188b70ea47571033add485a13d99c4cbb1e424cd20c6a914795869
+oid sha256:50237a8764ed66ffe376f488660ff552d7626839dd285cbbe93becad7fec1911
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cefca2de66af0d105137a32800a1e8854dec1be7e51f1a3b62fa43b59d5d547e
+oid sha256:d08349266c51de2e802515ed68edcd5feae1e6c270d6c1e7e203a2a3d518984f
 size 4040701744