Outer Step 1. Inner Step 2238. Batch Size 36

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5182828,
-    5182832,
-    5182836,
-    5182841,
-    5182845,
-    5182851,
-    5182856,
-    5182860,
-    5182865,
-    5182869
+    5182948,
+    5182953,
+    5182957,
+    5182962,
+    5182967,
+    5182972,
+    5182976,
+    5182981,
+    5182986,
+    5182990
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 2232,
+  "inner_step": 2238,
   "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:ee1fea45cfd5194d948ab3c8f65d06be823e8a25dd714d76b3f15c8b11640fc9
+oid sha256:8e83e819ef85c96484fbf55d2294df5d8d598516445c33346c1344d2872e910b
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d6354655821f0517f7f6716ad455a8997b2c5421836932ecbbdf434e5835eda
+oid sha256:506d44b7114a3ea44684176561061b94b722314594123349a142cac151c7d275
 size 4040701744