Run 4. Outer Step 62. Inner Step 36.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5644176,
-    5644180,
-    5644184,
-    5644188,
-    5644192
+    5644196,
+    5644201,
+    5644205,
+    5644210,
+    5644214
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 35,
+  "inner_step": 36,
   "inner_steps": 0,
   "last_allreduce_block": 5643114,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36d0110b44eb0a41b0b1ffc4df389f76bc2b788e2ae862e8e537baa2a02633e9
+oid sha256:9e1b4039b3c945a61bc46f9da53cad71f879872aba1836116157375558c52462
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0595963ea6de451fb51d80a35ff5faa7f01cfc98e1441a28cca8a1a08d31066
+oid sha256:7b8f147a7364c559d1ef6c544e43428224ab2dd737e03d2811c254be1d5b4b5a
 size 4040701744