Outer Step 0. Inner Step 190. Batch Size 32

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5156425,
-    5156431,
-    5156436,
-    5156441,
-    5156446,
-    5156451,
-    5156455,
-    5156460,
-    5156466,
-    5156471
+    5156506,
+    5156510,
+    5156513,
+    5156519,
+    5156523,
+    5156527,
+    5156531,
+    5156535,
+    5156539,
+    5156544
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 181,
+  "inner_step": 190,
   "inner_steps": 0,
   "last_allreduce_block": 4016775,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10a8789f48c3acc1b55f5bd460f43737604b2fcac4ec44627c2bd61f1c05a451
+oid sha256:6dddf9da8a20444bc22d99e7a7cbb8fce8b5eae80d406b750ce58e15d6ffe773
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60099e719aebce19b47ca65c79592079f95169a0ba8b9e194886bd5d9d7ab1d6
+oid sha256:a1a01047d6173bf0d003bbe596802400467a6a58f12b698c97d329b18f272440
 size 4040701744