Outer Step 0. Inner Step 164. Batch Size 404

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5141740,
-    5141751,
-    5141760,
-    5141768,
-    5141775,
-    5141781,
-    5141789,
-    5141796,
-    5141802,
-    5141812
+    5141834,
+    5141840,
+    5141848,
+    5141855,
+    5141861,
+    5141869,
+    5141878,
+    5141885,
+    5141893,
+    5141897
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 157,
+  "inner_step": 164,
   "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 sha256:2ef6fefca58c0cf9cbed11b17995e192de529f09a27607bf242b44d1f8b3f073
+oid sha256:72c6bb6641ec1d3b429c74b422b65be9464580a1755a52bfe818a2d6b9ca141b
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59134d3ef25da687a7b726221aab67ca6d9f63f39d96b2f742c312c9c386b5f8
+oid sha256:60f7482680010eb92334750a968b980824d8d1537168d5a84367795ca2f80be9
 size 4040701744