Run 4. Outer Step 31. Inner Step 35.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5542476,
-    5542479,
-    5542481,
-    5542484,
-    5542486,
-    5542488,
-    5542491,
-    5542494
+    5542497,
+    5542499,
+    5542501,
+    5542504,
+    5542505
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 34,
+  "inner_step": 35,
   "inner_steps": 0,
   "last_allreduce_block": 5541234,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:564805d7f13d8a30c349e5dd0bad33df6ab51d1b9ce589131d4923c63334761e
+oid sha256:5906184cbb2cd4ea5c40da4389f7d5a5d9c8bee8674c2017743d5021e789f7bd
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fb9a717c2b6ffc5f9f67075773b81deadbd54536f9735d6210975346c8726ac
+oid sha256:ec249a986127230ce66f7f6415d71987e4299b07f133adbfc38c2b684ef85333
 size 4040701744