Run 4. Outer Step 26. Inner Step 36.

config.json

@@ -268,22 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5535752,
-    5535754,
-    5535757,
-    5535759,
-    5535761,
-    5535763,
-    5535765,
-    5535768,
-    5535770
+    5535772,
+    5535774,
+    5535777,
+    5535780,
+    5535782
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 35,
+  "inner_step": 36,
   "inner_steps": 0,
   "last_allreduce_block": 5534554,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6aa3aea31fb6a7829369f44198e99dd2e711268f1c39fadf68347210dcf7d7f
+oid sha256:2ac379b83e0cafb62c5a07db70fdef48279f9ba80c92a3b1e5661149a43ce7d2
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:022493d0d40677169cb9ccd1f449840ed8fa5fe3406635a11d4b185fb77f0934
+oid sha256:8e541e36c227f14f5437749910342fb3160cf4dadb00658b15b67c505b852084
 size 4040701744