Run 4. Outer Step 21. Inner Step 24.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5526205,
-    5526210,
-    5526216,
-    5526222,
-    5526228
+    5526233,
+    5526239,
+    5526245,
+    5526250,
+    5526256
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 23,
+  "inner_step": 24,
   "inner_steps": 0,
   "last_allreduce_block": 5513324,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc798e76fa7f29fefb8a61f3eca63c3f2a4c1b9f4b874e9a78acf8e1129e8129
+oid sha256:2012a2760167d21596c556f51f548e349ec03617ddcd2b46bb152159d199e9f3
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5757c5d248d1e35f6449faa2f6140e4fb3901ebbd2d34ab1c295e8a8ae6b7f94
+oid sha256:622b315d4df2f61b0f0318d5aecb2ae2d051a1872302243fcae83174ab9614ea
 size 4040701744