Run 4. Outer Step 21. Inner Step 25.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5526414,
-    5526421,
-    5526427,
-    5526434,
-    5526441
+    5526448,
+    5526455,
+    5526462,
+    5526468,
+    5526475
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 24,
+  "inner_step": 25,
   "inner_steps": 0,
   "last_allreduce_block": 5523943,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fd05ab758cb6ff5d899a1b1893dc2a3a4871fdac09a7dcb68e37cb20b1ed173
+oid sha256:4fadfa9a8c6773c75176681038cf2ee74a3b62399113de114c147f16a6d7aa42
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56a8add87dcea43e3a8284c97b9b255fed5cff1f39a473f32bd71c065f34cb35
+oid sha256:8ababe390c3ab7d9aca52f4ba0f0cefae6bc5acc0485029ebfdc17d292fdf467
 size 4040701744