Run 4. Outer Step 12. Inner Step 38.

config.json

@@ -268,19 +268,20 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5509644,
-    5509648,
-    5509653,
-    5509657,
-    5509661,
-    5509665
+    5509670,
+    5509674,
+    5509677,
+    5509681,
+    5509685,
+    5509690,
+    5509693
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 37,
+  "inner_step": 38,
   "inner_steps": 0,
   "last_allreduce_block": 5508496,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7450c2db3fa131a3ddc4c72753b73494feae4bab90a23ffb275a3210c53ba711
+oid sha256:6f297c9e1b9b261f83d2059d0526d9f862c0e9fdafe995ed66184dd0137843b6
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:900bfb17a3a8d22717539f5533464f08b3c8bad0aba12ba433a7243270b04243
+oid sha256:f4c9bf4ecca4f1c07994b5341e9365c2b17c72c1de8b834ed91a3b2d0bc12b68
 size 4040701744