Run 4. Outer Step 4. Inner Step 9.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5486638,
-    5486640,
-    5486643,
-    5486646,
-    5486649,
-    5486650,
-    5486652,
-    5486654
+    5486657,
+    5486660,
+    5486663,
+    5486666,
+    5486670
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 8,
+  "inner_step": 9,
   "inner_steps": 0,
   "last_allreduce_block": 5485540,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5dc5cd414549c26ac227cad0a6630502745d81d51e6ac8d54779bec61e0cf08
+oid sha256:85253c423201444d603bc3503c588c1482ed7e0c2075fbc72fc5453796465c86
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01c4aa3b9c575ba673e85ffa61241eb0139a56e5868846a6c291b03434a5d9ff
+oid sha256:01685e1efa70f230ae4fa46c79fa3f4efc9fa2e960cc34dd3f18a630225bb414
 size 4040701744