Run 4. Outer Step 40. Inner Step 48.

config.json

@@ -268,23 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5556519,
-    5556521,
-    5556522,
-    5556524,
-    5556526,
-    5556528,
-    5556529,
-    5556531,
-    5556533,
-    5556535
+    5556537,
+    5556539,
+    5556540,
+    5556544,
+    5556546
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 47,
+  "inner_step": 48,
   "inner_steps": 0,
   "last_allreduce_block": 5555115,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a60f89d18ae62e63b6e8f6609e168c689eee663fb69e64d6a6027d9084de7300
+oid sha256:e912d8d948057d98f5c2116ede3f72c329f9d9a7ca0eb6d200ba2a7997eb4427
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d84b77aecb42a304e3eb1a094db934eaafefa8ec3188c21f7c4324d7fe94ce69
+oid sha256:1f71fc7b58e984436a1b3ae68fd1d13e0b28154ff1789d3685100653c5bb4116
 size 4040701744