Run 4. Outer Step 33. Inner Step 31.

config.json

@@ -268,19 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5544964,
-    5544969,
-    5544974,
-    5544978,
-    5544983,
-    5544988
+    5544994,
+    5544999,
+    5545004,
+    5545009,
+    5545014
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 30,
+  "inner_step": 31,
   "inner_steps": 0,
   "last_allreduce_block": 5543976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f81622669d4892e61873579970acf3a817c04278d99c8ccb05a3a4ec97c80265
+oid sha256:4d0abb71b593d2d9400fa455c0a088f2b61dd88f97c13c2d0aa0743f418b2bcb
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b5a981504bcda03ad7287c78edb9eda853e3d94f97cf2b31b744b21e94ab16b
+oid sha256:668c5e723e9a36babc66e1cb219b9a2f55a8f763c723e8fe9a00040e076e6607
 size 4040701744