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": [
-    5355081,
-    5355083,
-    5355084,
-    5355085,
-    5355085
+    5355111,
+    5355113,
+    5355114,
+    5355115,
+    5355115
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 258,
+  "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:b33b821b78b94075e4aa663b617c382b04f1f711c3fce1ccafb8f1d106a2d7b6
+oid sha256:ebc1569049a737c440250f038385b708b877f3e88c700852b7095795903a984b
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:997239f588b2199bbf4ee8cfe159230ee779f625b43373f026f09b64da8a3a09
+oid sha256:4a983ad694d63b0bb7844df27b01ac702294471021c7fbcc75d171323775db91
 size 4040701744