Run 2. Outer Step 10. Inner Step 264.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5355115,
-    5355117,
-    5355118,
-    5355119,
-    5355121
+    5355150,
+    5355152,
+    5355153,
+    5355154,
+    5355155
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 257,
+  "inner_step": 264,
   "inner_steps": 0,
   "last_allreduce_block": 5351170,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95b921d8c69081cbc323e3efadd1ae39ca4e07e925cd36d88cc9706034e8469d
+oid sha256:60b11ae20ff8da2b89efb9df1a8755f3aa47b77651825ddba5648a29f124c373
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cb5475b414677accdefaa63b99dfb4a85de8190b8534d3be459a49fdba14250
+oid sha256:06660d7e950ff82ed1e7b3385648e706768c9b033aa95fe55451bcdc15929b73
 size 4040701744