Run 4. Outer Step 7. Inner Step 65.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5494681,
-    5494686,
-    5494691,
-    5494696,
-    5494702
+    5494708,
+    5494713,
+    5494718,
+    5494723,
+    5494729
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 64,
+  "inner_step": 65,
   "inner_steps": 0,
   "last_allreduce_block": 5492224,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e029ef9ea77a09e5d1297e08ce1e158df6c66275af51f465b9e4754fbb5d7f70
+oid sha256:c30ca41aa14d31ae56f6096e6c37c116753734e292d8381f4c64e0be8f0ef88f
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a095ecd373fd7d309feec0b109cb113bf21c7372b04a08516fba06b0393b2ad
+oid sha256:a72c7196e41f3251d16ae2b40716510f3ad95f5564ef17f87707e6c81b0ab050
 size 4040701744