Run 4. Outer Step 53. Inner Step 32.

config.json

@@ -268,21 +268,22 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5577261,
-    5577263,
-    5577264,
-    5577265,
-    5577267,
-    5577269,
-    5577271,
-    5577274
+    5577277,
+    5577279,
+    5577282,
+    5577284,
+    5577286,
+    5577288,
+    5577290,
+    5577291,
+    5577292
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 31,
+  "inner_step": 32,
   "inner_steps": 0,
   "last_allreduce_block": 5576204,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01a164a3a393c58750b4537ba77b90318b4ce4e5d48e412fdd5e8421acc69873
+oid sha256:0eb387cbfb9069e1b1f247edf8e2b669a0f49c3ead21304158a0bbc3b6a0d201
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0b223301d8ae35baea46064b31734b1a7bef8b9903982b6683df42e67b3a1c7
+oid sha256:6a718e4b343c0afecb3bdd158ea7aeca91a785e63070d4575679ce01eee47542
 size 4040701744