Run 4. Outer Step 12. Inner Step 30.

config.json

@@ -268,20 +268,20 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5509163,
-    5509167,
-    5509171,
-    5509174,
-    5509178,
-    5509181,
-    5509185
+    5509189,
+    5509193,
+    5509196,
+    5509200,
+    5509204,
+    5509208,
+    5509212
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 29,
+  "inner_step": 30,
   "inner_steps": 0,
   "last_allreduce_block": 5506953,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73d8df7481e41916796e6093495d5d2d1613db90f79531235296c9a472873d1b
+oid sha256:2932d70da1252995fe34e2128ed668f01e989683a04805eb7caefa5f7c951aeb
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df50bb68cdd5eb37a0c124ab337e42a6dbeeac7ef1d819054db9a3401b685cda
+oid sha256:8c171da3cbf407fedded559259aa563b7d57f903bf6325b3bccf3433d686648d
 size 4040701744