Run 4. Outer Step 58. Inner Step 27.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5603212,
-    5603214,
-    5603217,
-    5603219,
-    5603221,
-    5603224,
-    5603227
+    5603230,
+    5603232,
+    5603233,
+    5603235,
+    5603237
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 26,
+  "inner_step": 27,
   "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:d5857f9e7e8dbd47e78fb09d9083bb0ad2fdae5b01fb2a28ad81e70de5fd2964
+oid sha256:d533e73595bff3c45366b686344ee435c3b448c46903705b568e1ee5cd609aa6
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a9ec35199e58d795077702e80ae891fdea0711767257fefc94e5e2464fcbdf7
+oid sha256:82391d915d51fb871fc93e97f70f16abfed93a06716fafc3be50a22704ffe9b7
 size 4040701744