Run 4. Outer Step 53. Inner Step 32.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5577265,
-    5577268,
-    5577270,
-    5577272,
-    5577274,
-    5577276,
-    5577278,
-    5577280
+    5577282,
+    5577284,
+    5577287,
+    5577290,
+    5577293
   ],
   "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:f1ce07f120d73002bd466ba0ad07ed942ab2100b3bcd64cef9c83b15156a6721
+oid sha256:3dc299b6486ad569666b274f423bad89427f0aa3d415cd6a1ef73ad87662159b
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e13a3ae685f8d4bea658659228deed13a9d71b3de21c789cb886388c4f4b59a
+oid sha256:a3646a82adf7f63f9212d4a345dc1edfbbb067886827d56f1b886810047f1a1a
 size 4040701744