Run 4. Outer Step 27. Inner Step 20.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5536573,
-    5536576,
-    5536578,
-    5536580,
-    5536583,
-    5536585,
-    5536587,
-    5536590
+    5536592,
+    5536595,
+    5536598,
+    5536600,
+    5536603
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 19,
+  "inner_step": 20,
   "inner_steps": 0,
   "last_allreduce_block": 5535854,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e83bbc6c657fbc7e113ac8973758a61b612f016df66d77afadf38e13328fbef
+oid sha256:6bb9dc7ac8ea3783a54d9ace231ddf1e31406448baf9dc5199f485b4355f21ae
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b946ab41a7cc9ab9b52d85efce774e0ade9d63e5fc91722b2c2163350d2e21a
+oid sha256:c1791ee32b652733c34219f8d6fcaa3fd2084ea0e6e68396d8c9c706631f8fd0
 size 4040701744