Run 4. Outer Step 40. Inner Step 30.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5556191,
-    5556195,
-    5556200,
-    5556204,
-    5556208
+    5556213,
+    5556217,
+    5556221,
+    5556225,
+    5556229
   ],
   "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": 5555115,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f69d09396603667d7f53d5a47339ecb2eeff062613c807e7fa6b70a0766e8f8
+oid sha256:09bf2e1e5fab2e187165e4225d22089e17f049630f49ed155e1c90bd1b58a6d6
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af023d160b762e6da20f66edbbd6debb5f1f1e3297a25f3b28d2c08df9366c99
+oid sha256:7d8a756ca73b0f7faf7b9f3c332090360a75a1dfbcb3a101d5bb9d8db8631931
 size 4040701744