Run 4. Outer Step 23. Inner Step 0.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5529362,
-    5529366,
-    5529370,
-    5529375,
-    5529379
+    5529386,
+    5529390,
+    5529394,
+    5529398,
+    5529403
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 32,
+  "inner_step": 0,
   "inner_steps": 0,
   "last_allreduce_block": 5526620,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bd0ca788e51acf53cd5600092822900727c0cab318f5bdab97401ad6ed00b81
+oid sha256:a53e9d8fe775660d19dc5642528d95232dd50b543a3cb6d9b46cfbb4f0a97563
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b777adaba569b77767ee8625c6b5882b09cc0f6f3aa933410cc37bd18adf7e50
+oid sha256:5d2d0e09e1ee9b9e2f103435b0085a7a78cd3f101a1ff3528c4641833bf9d162
 size 4040701744