Run 4. Outer Step 25. Inner Step 40.

config.json

@@ -268,18 +268,24 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5534576,
-    5534579,
-    5534582,
-    5534584,
-    5534586
+    5534588,
+    5534590,
+    5534593,
+    5534595,
+    5534598,
+    5534600,
+    5534602,
+    5534603,
+    5534605,
+    5534607,
+    5534610
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 39,
+  "inner_step": 40,
   "inner_steps": 0,
   "last_allreduce_block": 5533305,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbfb1a7500b9056f91ad69debfe3d9a8e6971c3111015ad2448abce7e88a8a6d
+oid sha256:e104383e2151a8f50b7785d805f09ee59a1bfb1b4da5a6296f40674d25449bdb
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57e6715db4f31d108bd0f896da244aa2476a819f66b38e4ed7c886542eb71a6e
+oid sha256:7056db13bfb244b3262e66733fa9d5a71e01b2679b1bae49ae7784ba131c9af3
 size 4040701744